CN118130487B - Welding detection method and system based on scaffold - Google Patents
Welding detection method and system based on scaffold Download PDFInfo
- Publication number
- CN118130487B CN118130487B CN202410547601.8A CN202410547601A CN118130487B CN 118130487 B CN118130487 B CN 118130487B CN 202410547601 A CN202410547601 A CN 202410547601A CN 118130487 B CN118130487 B CN 118130487B
- Authority
- CN
- China
- Prior art keywords
- scaffold
- detection
- detected
- ultrasonic
- evaluation index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 492
- 238000003466 welding Methods 0.000 title claims abstract description 226
- 238000011156 evaluation Methods 0.000 claims abstract description 200
- 239000006247 magnetic powder Substances 0.000 claims abstract description 168
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 72
- 230000005855 radiation Effects 0.000 claims description 47
- 230000006870 function Effects 0.000 claims description 23
- 230000005540 biological transmission Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 20
- 238000012795 verification Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 18
- 238000010801 machine learning Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 12
- 230000035699 permeability Effects 0.000 claims description 12
- 239000000523 sample Substances 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 10
- 238000010521 absorption reaction Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 239000006249 magnetic particle Substances 0.000 claims description 5
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 230000001678 irradiating effect Effects 0.000 claims description 3
- 229930014626 natural product Natural products 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 230000007547 defect Effects 0.000 description 21
- 239000000463 material Substances 0.000 description 13
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000001066 destructive effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004519 grease Substances 0.000 description 1
- 230000005415 magnetization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/06—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and measuring the absorption
- G01N23/18—Investigating the presence of flaws defects or foreign matter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/83—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields
- G01N27/84—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields by applying magnetic powder or magnetic ink
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
- G01N2291/0234—Metals, e.g. steel
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/028—Material parameters
- G01N2291/0289—Internal structure, e.g. defects, grain size, texture
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/26—Scanned objects
- G01N2291/267—Welds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Signal Processing (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a scaffold-based welding detection method and system, belongs to the technical field of welding detection, and solves the problem of low scaffold welding detection efficiency in the prior art. The invention comprises a welding image acquisition module, a fault prediction module, a magnetic powder detection module, an ultrasonic detection module, a ray detection module, an analysis evaluation module and a positioning feedback module. According to the invention, the welding image of the scaffold to be predicted is obtained, the preset feature extraction is carried out, then the welding condition of the scaffold to be detected is predicted to obtain the first scaffold to be detected, then one or more of magnetic powder detection, ultrasonic detection and ray detection are sequentially carried out on the first scaffold to be detected, the corresponding magnetic powder detection evaluation index, ultrasonic detection evaluation index and ray detection evaluation index are obtained at the same time, finally the fault condition of the first scaffold to be detected is analyzed by combining the corresponding threshold value, and the fault position is obtained for feedback, so that the effect of improving the welding detection efficiency of the scaffold is achieved.
Description
Technical Field
The invention relates to the technical field of welding detection, in particular to a scaffold-based welding detection method and system.
Background
With the advent of large modern large building systems in China, the great development and popularization of scaffolds is urgent. The scaffold can form single-row and double-row scaffolds with different scaffold sizes, shapes and bearing capacities according to specific construction requirements, the scaffold comprises a support frame, a support column, a material lifting frame, a climbing scaffold, an overhanging frame and other construction equipment, and when the joint is designed, the joint has reliable self-locking capacity due to spiral friction force and self-gravity action of an upper bowl buckle. Welding quality detection refers to detection of welding results, and aims to ensure the integrity, reliability, safety and usability of a welding structure. In addition to the requirements for welding technology and welding process, weld quality inspection is also an important part of weld quality management.
The existing welding detection system usually relates to detection in three aspects, wherein the first method adopts a traditional image algorithm and a deep learning algorithm to detect welding defects; the second method adopts destructive experiments on the welded structure and judges the welding quality according to the results of the destructive experiments; the third type of detection is usually performed on the welded workpiece by using a manual detection method, which judges whether the processed material is qualified or not through experience of a detection engineer, and destructive detection is performed on the processed material by performing spot check on the processed material, so that the detection on the processed material is realized.
For example, bulletin numbers: the welding detection information processing system of the patent publication of CN113393207B includes: the system comprises a client entrusting detection module, a test detection module, a detection result release module and a database module; the client entrusting detection module is used for displaying welding detection capability to clients, receiving information of detection items entrusted by the clients and eliminating unreasonable detection items; the test detection module is used for carrying out flow division and task allocation on detection items entrusted by clients, carrying out data recommendation according to specific contents of the detection tasks, and generating detection results of the detection items according to detection results of the detection tasks; the detection result issuing module is used for providing the detection result of the entrusted detection item for the client; the database module is used for storing data in the welding detection process.
For example, bulletin numbers: the welding detection system and method based on edge calculation disclosed in the patent publication of CN113780900B comprises the following steps: the welding machine comprises at least one edge server, a welding machine table and a welding detection model, wherein each edge server is used for receiving welding information of the welding machine table, preprocessing the welding information to form welding processing information, inputting the welding processing information to the welding detection model to obtain a detection result, and judging welding quality of the welding machine table according to the detection result; and the data server is coupled with the edge servers and is used for processing and storing the detection results uploaded by each edge server and the welding information to form display information and visualizing the detection results according to the display information.
However, in the process of implementing the technical scheme of the embodiment of the application, the application discovers that the above technology has at least the following technical problems:
In the prior art, the traditional welding detection technology cannot reflect welding quality in the welding process of the scaffold in real time, consumes time and materials, is high in labor cost, and has the problem of low welding detection efficiency of the scaffold.
Disclosure of Invention
The embodiment of the application solves the problem of low welding detection efficiency of the scaffold in the prior art by providing the welding detection method and the welding detection system based on the scaffold, and realizes the improvement of the welding detection efficiency of the scaffold.
The embodiment of the application provides a welding detection method based on a scaffold, which comprises the following steps of: s1, preprocessing an obtained initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted; s2, extracting preset features of a welding image of the scaffold to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, if the prediction result is faulty, marking the faulty scaffold to be a first scaffold to be detected, otherwise, putting into practical application; s3, performing magnetic powder detection on the first scaffold to be detected to obtain a magnetic powder detection evaluation index, comparing the magnetic powder detection evaluation index with a corresponding threshold value, executing S4 if the magnetic powder detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the magnetic powder detection evaluation index is used for describing the magnetic powder detection fault degree of the first scaffold to be detected; s4, carrying out ultrasonic detection on the first scaffold to be detected to obtain an ultrasonic detection evaluation index, comparing the ultrasonic detection evaluation index with a corresponding threshold value, executing S5 if the ultrasonic detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the ultrasonic detection evaluation index is used for describing the ultrasonic detection fault degree of the first scaffold to be detected; s5, performing ray detection on the first scaffold to be detected to obtain a ray detection evaluation index, comparing the ray detection evaluation index with a corresponding threshold value, executing S6 if the ray detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the ray detection evaluation index is used for describing the ray detection fault degree of the first scaffold to be detected; s6, combining the acquired magnetic powder detection evaluation index and ultrasonic detection evaluation index to obtain a fault detection index, and analyzing the fault condition of the first scaffold to be detected according to the fault detection index, wherein the fault detection index represents comprehensive evaluation of magnetic powder detection, ultrasonic detection and radiation detection results; s7, obtaining the corresponding fault position according to the analysis and comparison result, and feeding back to the client.
Further, the specific method for obtaining the fault detection index is as follows: acquiring a magnetic powder detection index, an ultrasonic detection index and a radial detection index of a first scaffold to be detected, and acquiring a corresponding threshold value and a reference deviation; and calculating a fault detection index of the first scaffold to be detected according to the acquired data, wherein the fault detection index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Represents a natural constant of the natural product,The number of the first scaffold to be detected is indicated,,For the total number of scaffolds to be tested,Is the firstA failure detection index of a first scaffold to be detected,Is the firstMagnetic powder detection evaluation indexes of the first scaffold to be detected,For the threshold value of the magnetic particle inspection evaluation index,For the reference deviation of the magnetic powder test evaluation index,Is the firstUltrasonic detection evaluation indexes of the first scaffold to be detected,The threshold value of the index is evaluated for ultrasonic detection,For the ultrasonic detection the reference deviation of the evaluation index,Is the firstThe radiographic inspection evaluation index of the first scaffold to be inspected,The threshold value of the index is evaluated for the radiation detection,The reference deviation of the index is evaluated for the radiation detection,And evaluating the reference relative deviation of the index for magnetic powder detection.
Further, the specific method for obtaining the prediction result comprises the following steps: step one, obtaining preset characteristics in a welding image of a scaffold to be predicted; step two, constructing a preset feature data set, wherein the preset feature data set is a preset feature data set in a scaffold welding image to be predicted, and the preset feature data set is divided into a training feature set and a verification feature set according to a preset proportion, and the preset feature data is used for describing the properties of preset features; step three, a training machine model is obtained, wherein the training machine model is a converged model obtained by carrying out model training on a preset machine learning model by using a training feature set, and the preset machine learning model is a model selected according to the characteristics of preset feature data; step four, acquiring a verification machine model, wherein the verification machine model is a model obtained by performing model verification on a training machine model by using a verification feature set; fifthly, predicting the welding condition of the scaffold to be detected by using a verification machine model to obtain a prediction result; and step six, judging whether the welding condition of the scaffold to be detected has faults or not according to the prediction result, if the prediction result is that the scaffold to be detected has faults, continuing to detect the fault position, and if the scaffold to be detected has no faults, putting the scaffold to practical application.
Further, the specific method for magnetic powder detection is as follows: performing magnetic powder detection by adding a magnetic field to the welding part of the first scaffold to be detected, obtaining the magnetic powder distribution condition of the welding part of the first scaffold to be detected, and performing comparative analysis on the magnetic powder distribution condition and the reference magnetic powder distribution condition to obtain a first analysis result of the welding part; and comparing the first analysis result of the welding part with a magnetic powder detection reference threshold, if the magnetic powder detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, and otherwise, the corresponding welding part has no fault.
Further, the specific method for ultrasonic detection is as follows: ultrasonic detection is carried out by transmitting ultrasonic waves to a welding part of the first scaffold to be detected, and corresponding reflected sound waves are received; acquiring the sound wave reflection condition of the welding part of the first scaffold to be detected according to the received reflected sound wave, and comparing and analyzing the sound wave reflection condition with the reference sound wave reflection condition to obtain a second analysis result of the welding part; and comparing the second analysis result of the welding part with an ultrasonic detection reference threshold, if the ultrasonic detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, otherwise, the corresponding welding part has no fault.
Further, the specific method for detecting the rays is as follows: radiation detection is carried out by irradiating rays to the welding part of the first scaffold to be detected, a transmission image of the welding part of the first scaffold to be detected is obtained, and the radiation absorption condition is recorded according to the image; comparing and analyzing the ray absorption condition with the reference ray absorption condition to obtain a third analysis result of the welding part; and comparing the third analysis result of the welding part with a ray detection reference threshold, if the ray detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, otherwise, the corresponding welding part has no fault.
Further, the specific acquisition method of the magnetic powder detection evaluation index is as follows: acquiring magnetic field basic data in magnetic powder detection and property basic data of a welding part of a first scaffold to be detected, wherein the magnetic field basic data comprise magnetic field intensity, magnetic powder coverage time and magnetic powder coverage area, and the property basic data comprise magnetic permeability and roughness; according to the obtained magnetic field basic data and the obtained property basic data, calculating a magnetic powder detection evaluation index of the first scaffold to be detected by combining magnetic field weights, wherein the magnetic field weights are used for describing the influence degree of the magnetic field basic data and the property basic data on the magnetic powder detection evaluation index, the magnetic field weights comprise a first magnetic field weight, a second magnetic field weight, a third magnetic field weight, a fourth magnetic field weight and a fifth magnetic field weight, and the magnetic powder detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Represent the firstThe number of the welding parts in the first scaffold to be detected,,Is the firstThe total number of welding sites in the first scaffold to be tested,Is the firstFirst scaffold to be detectedThe magnetic field strength of the individual welding sites,Is the firstFirst scaffold to be detectedThe reference magnetic field strength of the individual weld sites,Is the firstFirst scaffold to be detectedThe magnetic permeability of the individual welded portions,Is the firstThe reference permeability of the first scaffold to be detected,Is the firstFirst scaffold to be detectedThe magnetic powder covering time of each welding part,In order to refer to the magnetic powder coverage time,Is the firstFirst scaffold to be detectedThe magnetic powder coverage area of each welding part,Is the firstFirst scaffold to be detectedThe reference magnetic powder coverage area of each welding part,Is the firstFirst scaffold to be detectedThe roughness of the individual welded portions is such that,Is the firstThe reference roughness of the first scaffold to be detected,For the first magnetic field weight,For the second magnetic field weight,For the third magnetic field weight,For the fourth magnetic field weight,Is the fifth magnetic field weight.
Further, the specific method for obtaining the ultrasonic detection evaluation index is as follows: acquiring ultrasonic basic data and reflected sound wave signal data in ultrasonic detection, wherein the ultrasonic basic data comprises ultrasonic probe frequency, beam angle and gain, and the reflected sound wave signal data comprises sound wave amplitude and sound wave time; according to the obtained ultrasonic basic data and reflected sound wave signal data, calculating an ultrasonic detection evaluation index of a first scaffold to be detected by combining an ultrasonic weight and a reflected sound wave weight, wherein the ultrasonic weight is used for describing the influence degree of the ultrasonic basic data on the ultrasonic detection evaluation index, the reflected sound wave weight is used for describing the influence degree of the reflected sound wave signal data on the ultrasonic detection evaluation index, the ultrasonic weight comprises a first ultrasonic weight, a second ultrasonic weight and a third ultrasonic weight, the reflected sound wave weight comprises a first reflected sound wave weight and a second reflected sound wave weight, and the ultrasonic detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Is the firstFirst scaffold to be detectedThe ultrasonic probe frequency of each welding site,Is the firstFirst scaffold to be detectedThe reference ultrasonic probe frequency of each weld site,Is the firstFirst scaffold to be detectedThe beam angle of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference beam angles of the individual weld sites,Is the firstFirst scaffold to be detectedThe gain of the individual welded locations is such that,Is the firstFirst scaffold to be detectedThe reference gain of the individual weld sites,In order to refer to the gain deviation,Is the firstFirst scaffold to be detectedThe sound wave amplitude of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference sound wave amplitude of the individual weld sites,For the reference acoustic wave amplitude deviation,Is the firstFirst scaffold to be detectedThe sonic time of each weld site,Is the firstFirst scaffold to be detectedThe reference sonic times of the individual weld sites,For the first ultrasonic weight to be applied,For the second ultrasonic weight to be applied,For the third ultrasonic weight, the first ultrasonic weight,For the first reflected sound wave weight,Is the second reflected sound wave weight.
Further, the specific acquisition method of the ray detection evaluation index is as follows: acquiring radiation basic data in radiation detection and transmission image data of a transmission image, wherein the radiation basic data comprises radiation source energy, radiation exposure time and radiation intensity, and the transmission image data comprises image contrast and image brightness; according to the obtained ray basic data and transmission image data, acquiring a ray detection evaluation index of a first scaffold to be detected by combining a ray weight, wherein the ray weight is used for describing the influence degree of the ray basic data and the transmission image data on the ray detection evaluation index, the ray weight comprises a first ray weight, a second ray weight, a third ray weight, a fourth ray weight and a fifth ray weight, and the ray detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Is the firstFirst scaffold to be detectedThe energy of the radiation source at the welding site,Is the firstFirst scaffold to be detectedThe reference source energy of the individual weld sites,For reference to the source energy deviation,Is the firstFirst scaffold to be detectedThe radiation exposure time of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference radiation exposure time of the individual weld sites,For the reference radiation exposure time deviation,Is the firstFirst scaffold to be detectedThe intensity of the radiation at the individual weld sites,Is the firstFirst scaffold to be detectedThe reference ray intensities of the individual weld sites,For the reference ray intensity deviation to be present,Is the firstFirst scaffold to be detectedThe image contrast of the individual weld sites is,Is the firstFirst scaffold to be detectedThe contrast of the reference image of the individual weld sites,For the reference image contrast deviation,Is the firstFirst scaffold to be detectedThe brightness of the image of the individual welded locations,Is the firstFirst scaffold to be detectedThe reference image brightness of the individual weld sites,For the reference image brightness deviation,For the first ray weight to be given,For the second ray weight,For the third ray weight,For the fourth ray weight,And the fifth ray weight.
The embodiment of the application provides a welding detection system based on a scaffold, which comprises a welding image acquisition module, a fault prediction module, a magnetic powder detection module, an ultrasonic detection module, a ray detection module, an analysis evaluation module and a positioning feedback module; the welding image acquisition module is used for preprocessing the acquired initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted; the fault prediction module is used for carrying out preset feature extraction on the welding image of the scaffold to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, if the prediction result is faulty, marking the scaffold to be detected with the fault as a first scaffold to be detected, otherwise, putting the scaffold to be detected into practical application; the magnetic powder detection module is used for carrying out magnetic powder detection on the first scaffold to be detected to obtain a magnetic powder detection evaluation index, comparing the magnetic powder detection evaluation index with a corresponding threshold value, executing the function of the ultrasonic detection module if the magnetic powder detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and the magnetic powder detection evaluation index is used for describing the magnetic powder detection fault degree of the first scaffold to be detected; the ultrasonic detection module is used for carrying out ultrasonic detection on the first scaffold to be detected to obtain an ultrasonic detection evaluation index, comparing the ultrasonic detection evaluation index with a corresponding threshold value, executing the function of the ray detection module if the ultrasonic detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and describing the ultrasonic detection fault degree of the first scaffold to be detected; the ray detection module is used for carrying out ray detection on the first scaffold to be detected to obtain a ray detection evaluation index, comparing the ray detection evaluation index with a corresponding threshold value, executing the function of the analysis evaluation module if the ray detection evaluation index is smaller than the corresponding threshold value, and executing the function of the positioning feedback module if the ray detection evaluation index is smaller than the corresponding threshold value, wherein the ray detection evaluation index is used for describing the ray detection fault degree of the first scaffold to be detected; the analysis evaluation module is used for obtaining a fault detection index by combining the obtained magnetic powder detection evaluation index and the ultrasonic detection evaluation index, analyzing the fault condition of the first scaffold to be detected according to the fault detection index, wherein the fault detection index represents comprehensive evaluation of the magnetic powder detection, the ultrasonic detection and the radiation detection; the positioning feedback module is used for acquiring the corresponding fault position and feeding back to the client.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. The method comprises the steps of obtaining a welding image of a scaffold to be predicted, extracting preset features, predicting the welding condition of the scaffold to be detected to obtain a first scaffold to be detected, sequentially carrying out one or more of magnetic powder detection, ultrasonic detection and ray detection on the first scaffold to be detected, carrying out numerical evaluation on the detection fault degree, analyzing the fault condition of the first scaffold to be detected according to the result of the numerical evaluation, obtaining a fault position according to the analysis result and feeding back to a customer, so that the numerical evaluation of the fault degree of the scaffold is realized, the improvement of the welding detection efficiency of the scaffold is realized, and the problem of low welding detection efficiency of the scaffold in the prior art is effectively solved.
2. According to the magnetic field basic data and the property basic data of the welding part of the first scaffold to be detected in the magnetic powder detection, the magnetic powder detection evaluation index of the first scaffold to be detected is calculated according to the obtained magnetic field basic data and the property basic data and combined with the magnetic field weight, finally the magnetic powder detection fault degree of the first scaffold to be detected is evaluated through the calculated magnetic powder detection evaluation index, and the fault degree of the first scaffold to be detected is comprehensively analyzed by combining the corresponding results of the ray detection and the ultrasonic detection, so that the numerical evaluation of the magnetic powder detection fault condition is realized, and further the more accurate evaluation of the magnetic powder detection fault condition of the first scaffold to be detected is realized.
3. According to the method, ultrasonic basic data and reflected sound wave signal data in ultrasonic detection are obtained, then ultrasonic detection evaluation indexes of the first scaffold to be detected are calculated according to the obtained ultrasonic basic data and reflected sound wave signal data and combined with ultrasonic weights and reflected sound wave weights, finally the ultrasonic detection fault degree of the first scaffold to be detected is evaluated through the calculated ultrasonic detection evaluation indexes, and the fault degree of the first scaffold to be detected is comprehensively analyzed by combining the results corresponding to magnetic powder detection and ray detection, so that the numerical evaluation of the ultrasonic detection fault condition is realized, and further the more accurate evaluation of the ultrasonic detection fault condition of the first scaffold to be detected is realized.
Drawings
Fig. 1 is a flowchart of a scaffold-based welding detection method according to an embodiment of the present application;
FIG. 2 is a flowchart of obtaining a prediction result according to an embodiment of the present application;
Fig. 3 is a schematic structural diagram of a scaffold-based welding detection system according to an embodiment of the present application.
Detailed Description
The embodiment of the application solves the problem of low welding detection efficiency of a scaffold in the prior art by providing a scaffold-based welding detection method and a scaffold-based welding detection system, pre-processing an obtained initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted, extracting preset characteristics of the scaffold welding image to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, obtaining a first scaffold to be detected by the prediction result, carrying out one or more of magnetic powder detection, ultrasonic detection and ray detection on the first scaffold to be detected, carrying out numerical evaluation on the fault degree, analyzing the fault condition of the first scaffold to be detected according to the result of the numerical evaluation, finally obtaining a corresponding fault position according to the analysis result, and feeding back to a client, thereby realizing the improvement of the welding detection efficiency of the scaffold.
The technical scheme in the embodiment of the application aims to solve the problem of low welding detection efficiency of the scaffold, and the overall thought is as follows:
The method comprises the steps of obtaining a welding image of a scaffold to be predicted, extracting preset features, predicting the welding condition of the scaffold to be detected to obtain a first scaffold to be detected, sequentially performing one or more of magnetic powder detection, ultrasonic detection and ray detection on the first scaffold to be detected, simultaneously obtaining a corresponding magnetic powder detection evaluation index, an ultrasonic detection evaluation index and a corresponding ray detection evaluation index, analyzing the fault condition of the first scaffold to be detected according to the obtained data, obtaining a fault position according to the analysis and comparison result, and feeding back the fault position to a customer, so that the effect of improving the welding detection efficiency of the scaffold is achieved.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
As shown in fig. 1, a flowchart of a scaffold-based welding detection method according to an embodiment of the present application is provided, and the method includes the following steps:
S1, preprocessing an obtained initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted;
s2, extracting preset features of a welding image of the scaffold to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, if the prediction result is faulty, marking the faulty scaffold to be a first scaffold to be detected, otherwise, putting into practical application;
S3, performing magnetic powder detection on the first scaffold to be detected to obtain a magnetic powder detection evaluation index, comparing the magnetic powder detection evaluation index with a corresponding threshold value, executing S4 if the magnetic powder detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the magnetic powder detection evaluation index is used for describing the magnetic powder detection fault degree of the first scaffold to be detected;
S4, carrying out ultrasonic detection on the first scaffold to be detected to obtain an ultrasonic detection evaluation index, comparing the ultrasonic detection evaluation index with a corresponding threshold value, executing S5 if the ultrasonic detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the ultrasonic detection evaluation index is used for describing the ultrasonic detection fault degree of the first scaffold to be detected;
s5, performing ray detection on the first scaffold to be detected to obtain a ray detection evaluation index, comparing the ray detection evaluation index with a corresponding threshold value, executing S6 if the ray detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the ray detection evaluation index is used for describing the ray detection fault degree of the first scaffold to be detected;
S6, combining the acquired magnetic powder detection evaluation index and ultrasonic detection evaluation index to obtain a fault detection index, analyzing the fault condition of the first scaffold to be detected according to the fault detection index, wherein the fault detection index represents comprehensive evaluation of magnetic powder detection, ultrasonic detection and radiation detection results;
S7, obtaining the corresponding fault position according to the analysis and comparison result, and feeding back to the client.
In the embodiment, the magnetic powder detection evaluation index, the ultrasonic detection evaluation index and the radiation detection evaluation index which are obtained by combining the magnetic powder detection, the ultrasonic detection and the radiation detection are used for carrying out accurate numerical positioning on the faults of the welding part of the scaffold; the specific steps of pretreatment are as follows: acquiring a first scaffold welding image to be predicted, wherein the first scaffold welding image to be predicted represents an image obtained by denoising an initial scaffold welding image to be predicted; acquiring a second scaffold welding image to be predicted, wherein the second scaffold welding image to be predicted represents an image obtained after image enhancement processing is carried out on the first scaffold welding image to be predicted; acquiring a third scaffold welding image to be predicted, wherein the third scaffold welding image to be predicted represents an image obtained after edge enhancement treatment is carried out on the second scaffold welding image to be predicted; acquiring a fourth scaffold welding image to be predicted, wherein the fourth scaffold welding image to be predicted represents an image obtained by carrying out local contrast enhancement processing on the third scaffold welding image to be predicted; acquiring a scaffold welding image to be predicted, wherein the scaffold welding image to be predicted represents an image obtained after the fifth scaffold welding image to be predicted is subjected to grey-scale treatment; the improvement of scaffold welding detection efficiency is realized.
Further, the specific acquisition method of the fault detection index is as follows: acquiring a magnetic powder detection index, an ultrasonic detection index and a radial detection index of a first scaffold to be detected, and acquiring a corresponding threshold value and a reference deviation; calculating a fault detection index of the first scaffold to be detected according to the acquired data, wherein the fault detection index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Represents a natural constant of the natural product,The number of the first scaffold to be detected is indicated,,For the total number of scaffolds to be tested,Is the firstA failure detection index of a first scaffold to be detected,Is the firstMagnetic powder detection evaluation indexes of the first scaffold to be detected,For the threshold value of the magnetic particle inspection evaluation index,For the reference deviation of the magnetic powder test evaluation index,Is the firstUltrasonic detection evaluation indexes of the first scaffold to be detected,The threshold value of the index is evaluated for ultrasonic detection,For the ultrasonic detection the reference deviation of the evaluation index,Is the firstThe radiographic inspection evaluation index of the first scaffold to be inspected,The threshold value of the index is evaluated for the radiation detection,The reference deviation of the index is evaluated for the radiation detection,And evaluating the reference relative deviation of the index for magnetic powder detection.
In this embodiment, the first scaffold fault condition to be detected is numerically-calculated.
Further, as shown in fig. 2, a flowchart of obtaining a prediction result provided in an embodiment of the present application is shown, where a specific method for obtaining the prediction result is: step one, acquiring preset characteristics: acquiring preset characteristics in a welding image of a scaffold to be predicted; step two, constructing a preset characteristic data set: the method comprises the steps that a preset feature data set is a preset feature data set in a scaffold welding image to be predicted, the preset feature data set is divided into a training feature set and a verification feature set according to a preset proportion, and the preset feature data is used for describing the properties of preset features; step three, obtaining a training machine model: training a machine model to obtain a converged model by training a preset machine learning model by using a training feature set, wherein the preset machine learning model is a model selected according to the characteristics of preset feature data; step four, acquiring a verification machine model: the verification machine model is a model obtained by performing model verification on the training machine model by using a verification feature set; fifthly, predicting welding conditions: predicting the welding condition of the scaffold to be detected by using a verification machine model to obtain a prediction result; step six, judging welding faults: judging whether the welding condition of the scaffold to be detected has faults or not according to the prediction result, if the prediction result is that the scaffold to be detected has faults, continuing to detect the fault position, and if the scaffold to be detected has no faults, putting the scaffold to practical application.
In this embodiment, using a training set training model, model parameters are adjusted by an optimization algorithm to minimize the loss function; evaluating the performance of the model by using the verification set, and adjusting the model super-parameters to improve the performance; accurate prediction of fault conditions of welding images of scaffolds to be predicted is achieved.
Further, the magnetic powder detection method specifically comprises the following steps: performing magnetic powder detection by adding a magnetic field to the welding part of the first scaffold to be detected, obtaining the magnetic powder distribution condition of the welding part of the first scaffold to be detected, and performing comparative analysis on the magnetic powder distribution condition and the reference magnetic powder distribution condition to obtain a first analysis result of the welding part; and comparing the first analysis result of the welding part with a magnetic powder detection reference threshold, if the magnetic powder detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, and otherwise, the corresponding welding part has no fault.
In the embodiment, the magnetic powder detection (MAGNETIC PARTICLE TESTING, MT) is a nondestructive detection method commonly used for detecting cracks, fatigue, welding defects and the like on the surface and the near surface, and the method has strong detection capability on the surface defects and can effectively detect the defects of the cracks and the air holes; the accuracy and the reliability of magnetic powder detection are improved.
Further, the specific method of ultrasonic detection is as follows: ultrasonic detection is carried out by transmitting ultrasonic waves to a welding part of the first scaffold to be detected, and corresponding reflected sound waves are received; acquiring the sound wave reflection condition of the welding part of the first scaffold to be detected according to the received reflected sound wave, and comparing and analyzing the sound wave reflection condition with the reference sound wave reflection condition to obtain a second analysis result of the welding part; and comparing the second analysis result of the welding part with an ultrasonic detection reference threshold, if the ultrasonic detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, otherwise, the corresponding welding part has no fault.
In the embodiment, ultrasonic detection (Ultrasonic Testing, UT) is a common nondestructive detection method for detecting defects, foreign matters and structural changes in materials, and has high sensitivity and precision, can detect larger defects, is harmless to human bodies, has relatively low cost, and is suitable for large-scale application; the accuracy and the reliability of ultrasonic detection are improved.
Further, the specific method of ray detection is as follows: radiation detection is carried out by irradiating rays to the welding part of the first scaffold to be detected, a transmission image of the welding part of the first scaffold to be detected is obtained, and the radiation absorption condition is recorded according to the image; comparing and analyzing the ray absorption condition with the reference ray absorption condition to obtain a third analysis result of the welding part; and comparing the third analysis result of the welding part with a ray detection reference threshold, if the ray detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, otherwise, the corresponding welding part has no fault.
In this embodiment, the radiation detection (Radiographic Testing, RT) is a common nondestructive detection method, which uses X-rays or gamma-rays to penetrate through the detected material, and captures the transmitted radiation image through the detector, so as to detect the defect, foreign matter and structural change in the material, and the method has higher precision and sensitivity, and can detect smaller defects; the accuracy and the reliability of the ray detection are improved.
Further, the specific acquisition method of the magnetic powder detection evaluation index is as follows: acquiring magnetic field basic data in magnetic powder detection and property basic data of a welding part of a first scaffold to be detected, wherein the magnetic field basic data comprise magnetic field intensity, magnetic powder coverage time and magnetic powder coverage area, and the property basic data comprise magnetic permeability and roughness; according to the obtained magnetic field basic data and the obtained property basic data, calculating a magnetic powder detection evaluation index of the first scaffold to be detected by combining magnetic field weights, wherein the magnetic field weights are used for describing the influence degree of the magnetic field basic data and the property basic data on the magnetic powder detection evaluation index, and the magnetic field weights comprise a first magnetic field weight, a second magnetic field weight, a third magnetic field weight, a fourth magnetic field weight and a fifth magnetic field weight, and the magnetic powder detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Represent the firstThe number of the welding parts in the first scaffold to be detected,,Is the firstThe total number of welding sites in the first scaffold to be tested,Is the firstFirst scaffold to be detectedThe magnetic field strength of the individual welding sites,Is the firstFirst scaffold to be detectedThe reference magnetic field strength of the individual weld sites,Is the firstFirst scaffold to be detectedThe magnetic permeability of the individual welded portions,Is the firstThe reference permeability of the first scaffold to be detected,Is the firstFirst scaffold to be detectedThe magnetic powder covering time of each welding part,In order to refer to the magnetic powder coverage time,Is the firstFirst scaffold to be detectedThe magnetic powder coverage area of each welding part,Is the firstFirst scaffold to be detectedThe reference magnetic powder coverage area of each welding part,Is the firstFirst scaffold to be detectedThe roughness of the individual welded portions is such that,Is the firstThe reference roughness of the first scaffold to be detected,For the first magnetic field weight,For the second magnetic field weight,For the third magnetic field weight,For the fourth magnetic field weight,Is the fifth magnetic field weight.
In this embodiment, the first magnetic field weight is a weight factor of a magnetic field strength ratio with respect to a magnetic powder detection evaluation index, the second magnetic field weight is a weight factor of a magnetic permeability ratio with respect to a magnetic powder detection evaluation index, the third magnetic field weight is a weight factor of a magnetic powder coverage time ratio with respect to a magnetic powder detection evaluation index, the fourth magnetic field weight is a weight factor of a magnetic powder coverage area ratio with respect to a magnetic powder detection evaluation index, and the fifth magnetic field weight is a weight factor of a roughness ratio with respect to a magnetic powder detection evaluation index; before magnetic powder detection, the surface of a welding part of a first scaffold to be detected needs to be ensured to be clean, and no grease or impurities and normal operation of magnetic powder detection equipment and fluorescent detection equipment are caused; in the detection process, redundant magnetic powder needs to be removed, so that only residual magnetic powder at potential defect positions is ensured; the magnetic powder detection can intuitively display the shape, position, size and severity of the defect, can roughly determine the property of the defect, has high detection sensitivity, and has the minimum detectable width of 0.1 micron due to the amplifying effect of magnetic marks formed by the magnetic powder collected on the defect, the magnetic powder detection is almost not limited by the size and the geometric shape of a part, and various magnetization methods are comprehensively adopted to detect each welding part of the scaffold and digitize the magnetic powder detection result; the magnetic field strength refers to the strength or density of a magnetic field, and can influence the deposition degree of magnetic powder on the surface of an object to be detected; the magnetic powder coverage area refers to the surface area covered by the magnetic powder, and determines the size and shape of magnetic powder spots formed at faults or defects; the magnetic powder covering time refers to the time covered by the magnetic powder; the permeability and roughness of the detection location can affect the distribution of the magnetic field over its surface. Higher permeability and lower surface roughness may result in a more concentrated concentration of the magnetic field at that location, which may involve other parameters in addition to those parameters, particularly as may be practical; on the basis of the method, the numerical accurate detection of the fault condition of the welding part of the first scaffold to be detected can be realized by combining ultrasonic detection and ray detection; the magnetic powder detection fault condition of the first scaffold to be detected is accurately estimated.
Further, the specific acquisition method of the ultrasonic detection evaluation index is as follows: acquiring ultrasonic basic data and reflected sound wave signal data in ultrasonic detection, wherein the ultrasonic basic data comprises ultrasonic probe frequency, beam angle and gain, and the reflected sound wave signal data comprises sound wave amplitude and sound wave time; according to the obtained ultrasonic basic data and the obtained reflected sound wave signal data, calculating an ultrasonic detection evaluation index of the first scaffold to be detected by combining the ultrasonic weight and the reflected sound wave weight, wherein the ultrasonic weight is used for describing the influence degree of the ultrasonic basic data on the ultrasonic detection evaluation index, the reflected sound wave weight is used for describing the influence degree of the reflected sound wave signal data on the ultrasonic detection evaluation index, the ultrasonic weight comprises a first ultrasonic weight, a second ultrasonic weight and a third ultrasonic weight, the reflected sound wave weight comprises a first reflected sound wave weight and a second reflected sound wave weight, and the ultrasonic detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Is the firstFirst scaffold to be detectedThe ultrasonic probe frequency of each welding site,Is the firstFirst scaffold to be detectedThe reference ultrasonic probe frequency of each weld site,Is the firstFirst scaffold to be detectedThe beam angle of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference beam angles of the individual weld sites,Is the firstFirst scaffold to be detectedThe gain of the individual welded locations is such that,Is the firstFirst scaffold to be detectedThe reference gain of the individual weld sites,In order to refer to the gain deviation,Is the firstFirst scaffold to be detectedThe sound wave amplitude of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference sound wave amplitude of the individual weld sites,For the reference acoustic wave amplitude deviation,Is the firstFirst scaffold to be detectedThe sonic time of each weld site,Is the firstFirst scaffold to be detectedThe reference sonic times of the individual weld sites,For the first ultrasonic weight to be applied,For the second ultrasonic weight to be applied,For the third ultrasonic weight, the first ultrasonic weight,For the first reflected sound wave weight,Is the second reflected sound wave weight.
In this embodiment, the first ultrasonic weight is a weight factor of the frequency ratio of the ultrasonic probe relative to the ultrasonic detection evaluation index, the second ultrasonic weight is a weight factor of the beam angle ratio relative to the ultrasonic detection evaluation index, the third ultrasonic weight is a weight factor of the absolute deviation of the gain relative to the ultrasonic detection evaluation index, the first reflected sound wave weight is a weight factor of the absolute deviation of the sound wave amplitude relative to the ultrasonic detection evaluation index, and the second reflected sound wave weight is a weight factor of the sound wave time ratio relative to the ultrasonic detection evaluation index; the ultrasonic detection evaluation index is also affected by the sound velocity of the sound wave; before ultrasonic inspection, it is necessary to ensure that the surface of the welded part of the first scaffold to be inspected is clean and to properly coat the couplant to ensure good contact for ultrasonic propagation; in the acoustic wave detection, the ultrasonic basic data are kept consistent; the ultrasonic detection can reach millimeter-level precision, can accurately detect some tiny defects, has high detection sensitivity to the defects in the material, can detect tiny cracks and defects, can not influence detected objects, can realize detection of remote objects by properly adjusting the frequency and power of a probe, and digitizes ultrasonic detection results; the ultrasonic probe frequency (Transducer Frequency) determines the penetration depth and resolution of the ultrasonic waves, and generally, high frequency ultrasonic waves can provide higher resolution, are suitable for detecting fine defects on the surface or near-surface, and low frequency ultrasonic waves are suitable for detecting deep or larger defects; the beam angle refers to the divergence angle of the ultrasonic beam, and affects the propagation range of the ultrasonic wave in the detected object; gain refers to the degree of amplification of an ultrasonic signal, which can be used to adjust the intensity of the signal to accommodate detection requirements of different depths and materials; the amplitude of the reflected sound wave reflects the reflection or scattering inside the object to be detected, which is related to the size and shape of the detected fault; the time of reflecting the sound wave is the time from the transmission to the reception of the ultrasonic wave, and is related to the thickness of the object to be detected and the sound velocity. By measuring the sound wave time, the position of the defect and the change condition of the sound velocity can be determined, and other parameters can be related to the parameters, and the parameters can be specifically adjusted according to the actual conditions; on the basis of the method, the numerical accurate detection of the fault condition of the welding part of the first scaffold to be detected can be realized by combining magnetic powder detection and radial detection; the accurate assessment of the ultrasonic detection fault condition of the first scaffold to be detected is realized.
Further, the specific acquisition method of the ray detection evaluation index is as follows: acquiring ray basic data in ray detection and transmission image data of a transmission image, wherein the ray basic data comprises ray source energy, ray exposure time and ray intensity, and the transmission image data comprises image contrast and image brightness; according to the obtained ray basic data and transmission image data, and by combining the ray weights, obtaining a ray detection evaluation index of a first scaffold to be detected, wherein the ray weights are used for describing the influence degree of the ray basic data and the transmission image data on the ray detection evaluation index, and the ray weights comprise a first ray weight, a second ray weight, a third ray weight, a fourth ray weight and a fifth ray weight, and the ray detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Is the firstFirst scaffold to be detectedThe energy of the radiation source at the welding site,Is the firstFirst scaffold to be detectedThe reference source energy of the individual weld sites,For reference to the source energy deviation,Is the firstFirst scaffold to be detectedThe radiation exposure time of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference radiation exposure time of the individual weld sites,For the reference radiation exposure time deviation,Is the firstFirst scaffold to be detectedThe intensity of the radiation at the individual weld sites,Is the firstFirst scaffold to be detectedThe reference ray intensities of the individual weld sites,For the reference ray intensity deviation to be present,Is the firstFirst scaffold to be detectedThe image contrast of the individual weld sites is,Is the firstFirst scaffold to be detectedThe contrast of the reference image of the individual weld sites,For the reference image contrast deviation,Is the firstFirst scaffold to be detectedThe brightness of the image of the individual welded locations,Is the firstFirst scaffold to be detectedThe reference image brightness of the individual weld sites,For the reference image brightness deviation,For the first ray weight to be given,For the second ray weight,For the third ray weight,For the fourth ray weight,And the fifth ray weight.
In this embodiment, the first ray weight is a weight factor of an absolute deviation of energy of a ray source with respect to a ray detection evaluation index, the second ray weight is a weight factor of an absolute deviation of a ray exposure time with respect to a ray detection evaluation index, the third ray weight is a weight factor of an absolute deviation of a ray intensity with respect to a ray detection evaluation index, the fourth ray weight is a weight factor of an absolute deviation of an image contrast with respect to a ray detection evaluation index, and the fifth ray weight is a weight factor of an absolute deviation of an image brightness with respect to a ray detection evaluation index; before radiation detection, it is necessary to ensure that the surface of the first object to be detected is clean, to remove impurities that may affect the transmission of radiation and to ensure that safety measures are complied with in order to prevent radiation leakage; the ray detection can detect fine defects inside the object, can quickly and accurately find defects which cannot be detected on some surfaces, has a detection speed which is relatively high compared with other nondestructive detection methods, and generally only needs a period of minutes to hours; in radiation detection, the source energy directly affects its ability to penetrate the material, with higher energy radiation generally being able to penetrate thicker materials; the radiation exposure time affects the length of time that the radiation passes through the object, which is closely related to the intensity and quality of the signal; image contrast and image brightness influence the analysis of the result of the radiation detection, and besides the parameters, other parameters can be involved, and the parameters can be specifically adjusted according to actual conditions; on the basis of the method, the numerical accurate detection of the fault condition of the welding part of the first scaffold to be detected can be realized by combining magnetic powder detection and ultrasonic detection; the accurate assessment of the radiation detection fault condition of the first scaffold to be detected is realized.
Further, as shown in fig. 3, a structural schematic diagram of a scaffold-based welding detection system provided by the embodiment of the application is shown, and the scaffold-based welding detection system provided by the embodiment of the application comprises a welding image acquisition module, a fault prediction module, a magnetic powder detection module, an ultrasonic detection module, a radiation detection module, an analysis evaluation module and a positioning feedback module; the welding image acquisition module is used for preprocessing the acquired initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted; the failure prediction module is used for carrying out preset feature extraction on the welding image of the scaffold to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, if the prediction result is that the failure exists, recording the scaffold to be detected with the failure as a first scaffold to be detected, otherwise, putting the scaffold to be detected into practical application; the magnetic powder detection module is used for carrying out magnetic powder detection on the first scaffold to be detected to obtain a magnetic powder detection evaluation index, comparing the magnetic powder detection evaluation index with a corresponding threshold value, executing the function of the ultrasonic detection module if the magnetic powder detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and the magnetic powder detection evaluation index is used for describing the magnetic powder detection fault degree of the first scaffold to be detected; the ultrasonic detection module is used for carrying out ultrasonic detection on the first scaffold to be detected to obtain an ultrasonic detection evaluation index, comparing the ultrasonic detection evaluation index with a corresponding threshold value, executing the function of the ray detection module if the ultrasonic detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and describing the ultrasonic detection fault degree of the first scaffold to be detected; the ray detection module is used for carrying out ray detection on the first scaffold to be detected to obtain a ray detection evaluation index, comparing the ray detection evaluation index with a corresponding threshold value, executing the function of the analysis evaluation module if the ray detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and describing the ray detection failure degree of the first scaffold to be detected; the analysis evaluation module is used for obtaining a fault detection index by combining the obtained magnetic powder detection evaluation index and the ultrasonic detection evaluation index, analyzing the fault condition of the first scaffold to be detected according to the fault detection index, and comprehensively evaluating the magnetic powder detection, ultrasonic detection and radiation detection results by the fault detection index; the positioning feedback module is used for acquiring the corresponding fault position and feeding back to the client.
In this embodiment, the systemization of welding detection of the scaffold is achieved.
The technical scheme provided by the embodiment of the application at least has the following technical effects or advantages: relative to the bulletin number: according to the welding detection information processing system disclosed by the patent publication CN113393207B, the magnetic field basic data in magnetic powder detection and the property basic data of the welding part of the first scaffold to be detected are obtained, then the magnetic powder detection evaluation index of the first scaffold to be detected is calculated according to the obtained magnetic field basic data and the property basic data and combined with the magnetic field weight, finally the magnetic powder detection fault degree of the first scaffold to be detected is evaluated through the calculated magnetic powder detection evaluation index, and the fault degree of the first scaffold to be detected is comprehensively analyzed by combining the corresponding results of the ray detection and the ultrasonic detection, so that the numerical evaluation of the magnetic powder detection fault condition is realized, and further the more accurate evaluation of the magnetic powder detection fault condition of the first scaffold to be detected is realized; relative to the bulletin number: according to the welding detection system and method based on edge calculation, which are disclosed by the application of the patent publication CN113780900B, in the embodiment of the application, through acquiring ultrasonic basic data and reflected sound wave signal data in ultrasonic detection, then calculating an ultrasonic detection evaluation index of a first scaffold to be detected according to the acquired ultrasonic basic data and reflected sound wave signal data and combining an ultrasonic weight and the reflected sound wave weight, finally evaluating the ultrasonic detection fault degree of the first scaffold to be detected through the calculated ultrasonic detection evaluation index, and comprehensively analyzing the fault degree of the first scaffold to be detected by combining the results corresponding to magnetic powder detection and ray detection, the numerical evaluation of the ultrasonic detection fault condition of the first scaffold to be detected is realized, and further more accurate evaluation of the ultrasonic detection fault condition of the first scaffold to be detected is realized.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (6)
1. The welding detection method based on the scaffold is characterized by comprising the following steps of:
S1, preprocessing an obtained initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted;
s2, extracting preset features of a welding image of the scaffold to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, if the prediction result is faulty, marking the faulty scaffold to be a first scaffold to be detected, otherwise, putting into practical application;
s3, performing magnetic powder detection on the first scaffold to be detected to obtain a magnetic powder detection evaluation index, comparing the magnetic powder detection evaluation index with a corresponding threshold value, executing S4 if the magnetic powder detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the magnetic powder detection evaluation index is used for describing the magnetic powder detection fault degree of the first scaffold to be detected;
S4, carrying out ultrasonic detection on the first scaffold to be detected to obtain an ultrasonic detection evaluation index, comparing the ultrasonic detection evaluation index with a corresponding threshold value, executing S5 if the ultrasonic detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the ultrasonic detection evaluation index is used for describing the ultrasonic detection fault degree of the first scaffold to be detected;
S5, performing ray detection on the first scaffold to be detected to obtain a ray detection evaluation index, comparing the ray detection evaluation index with a corresponding threshold value, executing S6 if the ray detection evaluation index is smaller than the corresponding threshold value, otherwise executing S7, wherein the ray detection evaluation index is used for describing the ray detection fault degree of the first scaffold to be detected;
S6, combining the acquired magnetic powder detection evaluation index and ultrasonic detection evaluation index to obtain a fault detection index, and analyzing the fault condition of the first scaffold to be detected according to the fault detection index, wherein the fault detection index represents comprehensive evaluation of magnetic powder detection, ultrasonic detection and ray detection results;
s7, acquiring a corresponding fault position according to the analysis and comparison result, and feeding back to the client;
The specific acquisition method of the fault detection index is as follows:
acquiring a magnetic powder detection index, an ultrasonic detection index and a radial detection index of a first scaffold to be detected, and acquiring a corresponding threshold value and a reference deviation;
and calculating a fault detection index of the first scaffold to be detected according to the acquired data, wherein the fault detection index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Represents a natural constant of the natural product,The number of the first scaffold to be detected is indicated,,For the total number of scaffolds to be tested,Is the firstA failure detection index of a first scaffold to be detected,Is the firstMagnetic powder detection evaluation indexes of the first scaffold to be detected,For the threshold value of the magnetic particle inspection evaluation index,For the reference deviation of the magnetic powder test evaluation index,Is the firstUltrasonic detection evaluation indexes of the first scaffold to be detected,The threshold value of the index is evaluated for ultrasonic detection,For the ultrasonic detection the reference deviation of the evaluation index,Is the firstThe radiographic inspection evaluation index of the first scaffold to be inspected,The threshold value of the index is evaluated for the radiation detection,The reference deviation of the index is evaluated for the radiation detection,Evaluating the reference relative deviation of the index for magnetic powder detection;
The specific acquisition method of the magnetic powder detection evaluation index comprises the following steps:
Acquiring magnetic field basic data in magnetic powder detection and property basic data of a welding part of a first scaffold to be detected, wherein the magnetic field basic data comprise magnetic field intensity, magnetic powder coverage time and magnetic powder coverage area, and the property basic data comprise magnetic permeability and roughness;
According to the obtained magnetic field basic data and the obtained property basic data, calculating a magnetic powder detection evaluation index of the first scaffold to be detected by combining magnetic field weights, wherein the magnetic field weights are used for describing the influence degree of the magnetic field basic data and the property basic data on the magnetic powder detection evaluation index, the magnetic field weights comprise a first magnetic field weight, a second magnetic field weight, a third magnetic field weight, a fourth magnetic field weight and a fifth magnetic field weight, and the magnetic powder detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Represent the firstThe number of the welding parts in the first scaffold to be detected,,Is the firstThe total number of welding sites in the first scaffold to be tested,Is the firstFirst scaffold to be detectedThe magnetic field strength of the individual welding sites,Is the firstFirst scaffold to be detectedThe reference magnetic field strength of the individual weld sites,Is the firstFirst scaffold to be detectedThe magnetic permeability of the individual welded portions,Is the firstThe reference permeability of the first scaffold to be detected,Is the firstFirst scaffold to be detectedThe magnetic powder covering time of each welding part,In order to refer to the magnetic powder coverage time,Is the firstFirst scaffold to be detectedThe magnetic powder coverage area of each welding part,Is the firstFirst scaffold to be detectedThe reference magnetic powder coverage area of each welding part,Is the firstFirst scaffold to be detectedThe roughness of the individual welded portions is such that,Is the firstThe reference roughness of the first scaffold to be detected,For the first magnetic field weight,For the second magnetic field weight,For the third magnetic field weight,For the fourth magnetic field weight,Is the fifth magnetic field weight;
the specific acquisition method of the ultrasonic detection evaluation index comprises the following steps:
Acquiring ultrasonic basic data and reflected sound wave signal data in ultrasonic detection, wherein the ultrasonic basic data comprises ultrasonic probe frequency, beam angle and gain, and the reflected sound wave signal data comprises sound wave amplitude and sound wave time;
according to the obtained ultrasonic basic data and reflected sound wave signal data, calculating an ultrasonic detection evaluation index of a first scaffold to be detected by combining an ultrasonic weight and a reflected sound wave weight, wherein the ultrasonic weight is used for describing the influence degree of the ultrasonic basic data on the ultrasonic detection evaluation index, the reflected sound wave weight is used for describing the influence degree of the reflected sound wave signal data on the ultrasonic detection evaluation index, the ultrasonic weight comprises a first ultrasonic weight, a second ultrasonic weight and a third ultrasonic weight, the reflected sound wave weight comprises a first reflected sound wave weight and a second reflected sound wave weight, and the ultrasonic detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Is the firstFirst scaffold to be detectedThe ultrasonic probe frequency of each welding site,Is the firstFirst scaffold to be detectedThe reference ultrasonic probe frequency of each weld site,Is the firstFirst scaffold to be detectedThe beam angle of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference beam angles of the individual weld sites,Is the firstFirst scaffold to be detectedThe gain of the individual welded locations is such that,Is the firstFirst scaffold to be detectedThe reference gain of the individual weld sites,In order to refer to the gain deviation,Is the firstFirst scaffold to be detectedThe sound wave amplitude of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference sound wave amplitude of the individual weld sites,For the reference acoustic wave amplitude deviation,Is the firstFirst scaffold to be detectedThe sonic time of each weld site,Is the firstFirst scaffold to be detectedThe reference sonic times of the individual weld sites,For the first ultrasonic weight to be applied,For the second ultrasonic weight to be applied,For the third ultrasonic weight, the first ultrasonic weight,For the first reflected sound wave weight,Weighting the second reflected sound wave;
the specific acquisition method of the ray detection evaluation index is as follows:
Acquiring radiation basic data in radiation detection and transmission image data of a transmission image, wherein the radiation basic data comprises radiation source energy, radiation exposure time and radiation intensity, and the transmission image data comprises image contrast and image brightness;
According to the obtained ray basic data and transmission image data, acquiring a ray detection evaluation index of a first scaffold to be detected by combining a ray weight, wherein the ray weight is used for describing the influence degree of the ray basic data and the transmission image data on the ray detection evaluation index, the ray weight comprises a first ray weight, a second ray weight, a third ray weight, a fourth ray weight and a fifth ray weight, and the ray detection evaluation index is calculated by adopting the following formula:
;
In the method, in the process of the invention, Is the firstFirst scaffold to be detectedThe energy of the radiation source at the welding site,Is the firstFirst scaffold to be detectedThe reference source energy of the individual weld sites,For reference to the source energy deviation,Is the firstFirst scaffold to be detectedThe radiation exposure time of the individual weld sites,Is the firstFirst scaffold to be detectedThe reference radiation exposure time of the individual weld sites,For the reference radiation exposure time deviation,Is the firstFirst scaffold to be detectedThe intensity of the radiation at the individual weld sites,Is the firstFirst scaffold to be detectedThe reference ray intensities of the individual weld sites,For the reference ray intensity deviation to be present,Is the firstFirst scaffold to be detectedThe image contrast of the individual weld sites is,Is the firstFirst scaffold to be detectedThe contrast of the reference image of the individual weld sites,For the reference image contrast deviation,Is the firstFirst scaffold to be detectedThe brightness of the image of the individual welded locations,Is the firstFirst scaffold to be detectedThe reference image brightness of the individual weld sites,For the reference image brightness deviation,For the first ray weight to be given,For the second ray weight,For the third ray weight,For the fourth ray weight,And the fifth ray weight.
2. The scaffold-based welding detection method according to claim 1, wherein the specific obtaining method of the prediction result is as follows:
step one, obtaining preset characteristics in a welding image of a scaffold to be predicted;
Step two, constructing a preset feature data set, wherein the preset feature data set is a preset feature data set in a scaffold welding image to be predicted, and the preset feature data set is divided into a training feature set and a verification feature set according to a preset proportion, and the preset feature data is used for describing the properties of preset features;
Step three, a training machine model is obtained, wherein the training machine model is a converged model obtained by carrying out model training on a preset machine learning model by using a training feature set, and the preset machine learning model is a model selected according to the characteristics of preset feature data;
Step four, acquiring a verification machine model, wherein the verification machine model is a model obtained by performing model verification on a training machine model by using a verification feature set;
Fifthly, predicting the welding condition of the scaffold to be detected by using a verification machine model to obtain a prediction result;
and step six, judging whether the welding condition of the scaffold to be detected has faults or not according to the prediction result, if the prediction result is that the scaffold to be detected has faults, continuing to detect the fault position, and if the scaffold to be detected has no faults, putting the scaffold to practical application.
3. The welding detection method based on the scaffold as claimed in claim 1, wherein the specific method of magnetic powder detection is as follows:
Performing magnetic powder detection by adding a magnetic field to the welding part of the first scaffold to be detected, obtaining the magnetic powder distribution condition of the welding part of the first scaffold to be detected, and performing comparative analysis on the magnetic powder distribution condition and the reference magnetic powder distribution condition to obtain a first analysis result of the welding part;
and comparing the first analysis result of the welding part with a magnetic powder detection reference threshold, if the magnetic powder detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, and otherwise, the corresponding welding part has no fault.
4. A scaffold-based welding inspection method according to claim 3, wherein the specific method of ultrasonic inspection is as follows:
Ultrasonic detection is carried out by transmitting ultrasonic waves to a welding part of the first scaffold to be detected, and corresponding reflected sound waves are received;
Acquiring the sound wave reflection condition of the welding part of the first scaffold to be detected according to the received reflected sound wave, and comparing and analyzing the sound wave reflection condition with the reference sound wave reflection condition to obtain a second analysis result of the welding part;
And comparing the second analysis result of the welding part with an ultrasonic detection reference threshold, if the ultrasonic detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, otherwise, the corresponding welding part has no fault.
5. A scaffold-based welding inspection method according to claim 3, wherein the specific method of radiation inspection is as follows:
Radiation detection is carried out by irradiating rays to the welding part of the first scaffold to be detected, a transmission image of the welding part of the first scaffold to be detected is obtained, and the radiation absorption condition is recorded according to the image;
comparing and analyzing the ray absorption condition with the reference ray absorption condition to obtain a third analysis result of the welding part;
And comparing the third analysis result of the welding part with a ray detection reference threshold, if the ray detection reference threshold is met, the corresponding welding part is the fault position of the first scaffold to be detected, otherwise, the corresponding welding part has no fault.
6. A system for applying the scaffold-based welding detection method of any one of claims 1-5, comprising a welding image acquisition module, a failure prediction module, a magnetic particle detection module, an ultrasonic detection module, a radiation detection module, an analysis evaluation module, and a positioning feedback module;
The welding image acquisition module is used for preprocessing the acquired initial scaffold welding image to be predicted to obtain a scaffold welding image to be predicted;
The fault prediction module is used for carrying out preset feature extraction on the welding image of the scaffold to be predicted, predicting the welding condition of the scaffold to be detected by using a machine learning method to obtain a prediction result, if the prediction result is faulty, marking the scaffold to be detected with the fault as a first scaffold to be detected, otherwise, putting the scaffold to be detected into practical application;
the magnetic powder detection module is used for carrying out magnetic powder detection on the first scaffold to be detected to obtain a magnetic powder detection evaluation index, comparing the magnetic powder detection evaluation index with a corresponding threshold value, executing the function of the ultrasonic detection module if the magnetic powder detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and the magnetic powder detection evaluation index is used for describing the magnetic powder detection fault degree of the first scaffold to be detected;
the ultrasonic detection module is used for carrying out ultrasonic detection on the first scaffold to be detected to obtain an ultrasonic detection evaluation index, comparing the ultrasonic detection evaluation index with a corresponding threshold value, executing the function of the ray detection module if the ultrasonic detection evaluation index is smaller than the corresponding threshold value, otherwise executing the function of the positioning feedback module, and describing the ultrasonic detection fault degree of the first scaffold to be detected;
The ray detection module is used for carrying out ray detection on the first scaffold to be detected to obtain a ray detection evaluation index, comparing the ray detection evaluation index with a corresponding threshold value, executing the function of the analysis evaluation module if the ray detection evaluation index is smaller than the corresponding threshold value, and executing the function of the positioning feedback module if the ray detection evaluation index is smaller than the corresponding threshold value, wherein the ray detection evaluation index is used for describing the ray detection fault degree of the first scaffold to be detected;
The analysis evaluation module is used for obtaining a fault detection index by combining the obtained magnetic powder detection evaluation index and the ultrasonic detection evaluation index, analyzing the fault condition of the first scaffold to be detected according to the fault detection index, wherein the fault detection index represents comprehensive evaluation of the magnetic powder detection, ultrasonic detection and ray detection results;
the positioning feedback module is used for acquiring the corresponding fault position and feeding back to the client.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410547601.8A CN118130487B (en) | 2024-05-06 | 2024-05-06 | Welding detection method and system based on scaffold |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410547601.8A CN118130487B (en) | 2024-05-06 | 2024-05-06 | Welding detection method and system based on scaffold |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118130487A CN118130487A (en) | 2024-06-04 |
CN118130487B true CN118130487B (en) | 2024-07-26 |
Family
ID=91238160
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410547601.8A Active CN118130487B (en) | 2024-05-06 | 2024-05-06 | Welding detection method and system based on scaffold |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118130487B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118465071B (en) * | 2024-07-11 | 2024-10-18 | 深圳三扬轴业股份有限公司 | High-precision nondestructive flaw detection method and system based on hardware shaft |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107174867A (en) * | 2016-02-26 | 2017-09-19 | 侯英翔 | Coal does new material, dedusting and improvement haze again after mixing and mix with other materials |
CN117825516A (en) * | 2024-03-04 | 2024-04-05 | 陕西昌硕科技有限公司 | Ultrasonic defect detection system and method with accurate positioning |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10104175A (en) * | 1996-10-01 | 1998-04-24 | Shimadzu Corp | X-ray inspection apparatus for specifying material quality |
KR20120032590A (en) * | 2010-09-29 | 2012-04-06 | 한국전력공사 | Ultrasonic flaw detector and ultrasonic flaw detecting method |
JP5740509B1 (en) * | 2014-04-21 | 2015-06-24 | ジオ・サーチ株式会社 | A method for exploring damage to steel deck slabs. |
GB201413566D0 (en) * | 2014-07-31 | 2014-09-17 | V Viz Ltd | System for non-destructive detection of internal defects |
DE102020107779A1 (en) * | 2020-03-20 | 2021-09-23 | Schaeffler Technologies AG & Co. KG | Method and test system for testing a bipolar plate of a fuel cell |
CN213120569U (en) * | 2020-05-28 | 2021-05-04 | 中国人民解放军空军工程大学 | Portable aircraft communication navigation system check out test set |
CN113138227B (en) * | 2021-04-14 | 2024-03-08 | 西安热工研究院有限公司 | Welding joint combination detection method in high-temperature state |
-
2024
- 2024-05-06 CN CN202410547601.8A patent/CN118130487B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107174867A (en) * | 2016-02-26 | 2017-09-19 | 侯英翔 | Coal does new material, dedusting and improvement haze again after mixing and mix with other materials |
CN117825516A (en) * | 2024-03-04 | 2024-04-05 | 陕西昌硕科技有限公司 | Ultrasonic defect detection system and method with accurate positioning |
Also Published As
Publication number | Publication date |
---|---|
CN118130487A (en) | 2024-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wronkowicz et al. | Assessment of uncertainty in damage evaluation by ultrasonic testing of composite structures | |
US20180120268A1 (en) | Wrinkle Characterization and Performance Prediction for Composite Structures | |
CN112816556B (en) | Defect detection method, device, equipment and storage medium | |
CN118130487B (en) | Welding detection method and system based on scaffold | |
Aleshin et al. | Applying nondestructive testing to quality control of additive manufactured parts | |
CN112816557B (en) | Defect detection method, device, equipment and storage medium | |
Nath et al. | Reliability assessment of manual ultrasonic time of flight diffraction (TOFD) inspection for complex geometry components | |
Amirafshari et al. | Estimation of weld defects size distributions, rates and probability of detections in fabrication yards using a Bayesian theorem approach | |
Amrhein et al. | Characterization of computer tomography scanners using the probability of detection method | |
da Silva et al. | Nondestructive inspection reliability: state of the art | |
Keßler et al. | „Reliability Assessment of NDT in Civil Engineering–the German Approach for Standardization (normPOD)” | |
Carvalho et al. | Reliability of the manual and automatic ultrasonic technique in the detection of pipe weld defects | |
Hanks et al. | Effect of surface roughness on ultrasonic inspection of electron beam melting ti‐6AL‐4V | |
Henry et al. | Optimization of an angle-beam ultrasonic approach for characterization of impact damage in composites | |
Lee et al. | Structural health monitoring on ships using acoustic emission testing | |
Becker et al. | Integration of NDT into life time management | |
WO2022209169A1 (en) | Information processing device, determination method, and determination program | |
Jenson et al. | The SISTAE project: simulation and statistics for non destructive evaluation | |
Sani et al. | EVALUATION OF WELD DEFECT SIGNAL FEATURES USING ULTRASONIC FULL WAVE PULSE ECHO METHOD. | |
Rohrschneider et al. | Further development of the ultrasonic testing of hollow axles | |
Lubeigt et al. | Flaws detection and localization in weld structure using the topological energy method | |
Sharma et al. | Coda waves for health monitoring of composites under low-velocity impact | |
Bond et al. | Ultrasonic imaging and sizing | |
Tsukada et al. | 1. General and reviews | |
Matveev | 1. General and reviews |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |