CN117951455B - On-line monitoring method for operation faults of scraper conveyor - Google Patents
On-line monitoring method for operation faults of scraper conveyor Download PDFInfo
- Publication number
- CN117951455B CN117951455B CN202410330956.1A CN202410330956A CN117951455B CN 117951455 B CN117951455 B CN 117951455B CN 202410330956 A CN202410330956 A CN 202410330956A CN 117951455 B CN117951455 B CN 117951455B
- Authority
- CN
- China
- Prior art keywords
- data
- scraper
- abnormal data
- suspected
- anomaly
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 240
- 230000005856 abnormality Effects 0.000 claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 117
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- -1 gangue Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/02—Control devices, e.g. for safety, warning or fault-correcting detecting dangerous physical condition of load carriers, e.g. for interrupting the drive in the event of overheating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an online monitoring method for operation faults of a scraper conveyor, which comprises the following steps: acquiring a scraper operation data sequence; screening all suspected abnormal data in each scraper operation data sequence segment according to the noise abnormal credibility factors to obtain all noise abnormal data in each scraper operation data sequence segment; acquiring an abnormality potential factor of each target abnormal data in each denoised scraper operation data sequence segment; and carrying out fault monitoring on the scraper conveyor according to the abnormal possible factors. The invention improves the accuracy of detecting the operation faults of the scraper conveyor.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an online monitoring method for operation faults of a scraper conveyor.
Background
The scraper conveyor is mechanical conveying equipment for conveying materials horizontally or slightly obliquely, and drives a scraper chain through a transmission device so that the scraper above the scraper chain pushes granular materials or small block materials such as gangue, coal mines and the like to be conveyed to another point. The transmission device is the core of the whole instrument for working, so that the working condition of the rotating shaft of the transmission device needs to be monitored in real time, and the stable working of the rotating shaft is ensured.
When vibration data acquired by a vibration sensor are monitored in real time by using a standard score algorithm (Z-score), due to the change characteristics of vibration data of a rotating shaft of the scraper conveyor, the deviation degree of real abnormal vibration data and noise data is large, so that when the abnormal data are detected, the abnormal vibration data and the noise data are difficult to distinguish, and the abnormal data with smaller deviation degree value cannot be processed by the standard score algorithm, so that the accuracy of detecting operation faults of the scraper conveyor is low.
Disclosure of Invention
In order to solve the problems, the invention provides an online monitoring method for operation faults of a scraper conveyor, which comprises the following steps:
acquiring a scraper operation data sequence, wherein the scraper operation data sequence comprises scraper vibration data, scraper motor rotating speed data and scraper load data at a plurality of sampling moments;
Dividing the scraper operation data sequence into a plurality of scraper operation data sequence segments, acquiring the deviation degree of vibration data at each sampling time in each scraper operation data sequence segment by using a standard fraction algorithm, and acquiring all suspected abnormal data in each scraper operation data sequence segment according to the deviation degree; acquiring the change rule degree of the suspected abnormal data according to the distribution condition of the vibration data at all sampling moments around the suspected abnormal data; acquiring noise anomaly credibility factors of the suspected anomaly data according to the rotating speed data of the scraper motor, the scraper load data, the change rule degree and the deviation degree of the suspected anomaly data corresponding to the sampling time; screening all suspected abnormal data in each scraper operation data sequence segment according to the noise abnormal credibility factors to obtain all noise abnormal data in each scraper operation data sequence segment;
Correcting the noise abnormal data to obtain all target abnormal data in the denoised scraper operation data sequence section; obtaining an abnormality potential factor of each target abnormal data according to the difference value of the vibration data between each target abnormal data and the adjacent sampling time, the noise abnormality credibility and the deviation degree;
And carrying out fault monitoring on the scraper conveyor according to the abnormal possible factors.
Preferably, the method for acquiring all suspected abnormal data in each scraper operation data sequence section according to the deviation degree includes the following specific steps:
Presetting a deviation parameter For any sampling time in any scraper operation data sequence section, if the absolute value of the deviation degree of vibration data of the sampling time is larger than/>And recording the vibration data at the sampling time as suspected abnormal data.
Preferably, the obtaining the degree of change rule of the suspected abnormal data according to the distribution condition of the vibration data at all sampling moments around the suspected abnormal data comprises the following specific methods:
Presetting a neighborhood parameter For any suspected abnormal data in any scraper operation data sequence section, acquiring a neighborhood time range of the suspected abnormal data; the calculation method for obtaining the change rule degree of the suspected abnormal data comprises the following steps:
In the method, in the process of the invention, Representing the degree of change regularity of suspected abnormal data; /(I)Representing the total number of all maximum values in vibration data at all sampling moments in a neighborhood moment range of suspected abnormal data; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataMaximum and/>Differences in the individual maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataMaximum and/>Differences in the individual maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataA plurality of maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataA plurality of maxima; /(I)Representing a neighborhood parameter; /(I)The representation takes absolute value.
Preferably, the method for obtaining the neighborhood time range of the suspected abnormal data includes the following specific steps:
Left side of the suspected abnormal data Sample time and right side/>And a time range formed by the sampling time is used as a neighborhood time range of the suspected abnormal data.
Preferably, the method for obtaining the noise anomaly confidence factor of the suspected anomaly data according to the rotating speed data and the load data of the scraper motor, the change rule degree and the deviation degree of the scraper motor at the sampling time corresponding to the suspected anomaly data comprises the following specific steps:
for any suspected abnormal data in any scraper operation data sequence segment, acquiring a first maximum value and a first minimum value of the suspected abnormal data;
Acquiring noise anomaly credibility of the suspected anomaly data according to the first maximum value, the first minimum value, the change rule degree, the deviation degree of the suspected anomaly data, and the scraper motor rotating speed data and the scraper load data of the corresponding sampling time;
And acquiring noise anomaly credibility of all suspected anomaly data in the scraper operation data sequence segment, and recording each noise anomaly credibility after linear normalization of all the noise anomaly credibility as a noise anomaly credibility factor.
Preferably, the obtaining the first maximum value and the first minimum value of the suspected abnormal data includes the specific steps of:
Recording the time interval between each maximum value in vibration data of all sampling moments in the neighborhood time range of the suspected abnormal data and the sampling moment of the suspected abnormal data as a first time interval of each maximum value, and taking the maximum value with the minimum first time interval as the first maximum value of the suspected abnormal data; and recording the time interval between each minimum value in vibration data of all sampling moments in the neighborhood time range of the suspected abnormal data and the sampling moment of the suspected abnormal data as a second time interval of each minimum value, and taking the minimum value with the minimum second time interval as a first minimum value of the suspected abnormal data.
Preferably, the obtaining the noise anomaly reliability of the suspected anomaly data according to the first maximum value, the first minimum value, the degree of change regularity, the degree of deviation of the suspected anomaly data, and the scraper motor rotation speed data and the scraper load data at the corresponding sampling time includes the specific steps of:
The reciprocal of the change rule degree of the suspected abnormal data is recorded as a first reciprocal; the absolute value of the deviation degree of the suspected abnormal data is recorded as a first absolute value; the sum of the scraper motor rotating speed data and the scraper load data at the sampling time corresponding to the suspected abnormal data is recorded as a first sum value; the absolute value of the difference value between the first maximum value and the first minimum value of the suspected abnormal data is recorded as a second absolute value, and a preset super parameter is obtained The sum of the first absolute value and the second absolute value is recorded as a second sum value, the ratio of the first sum value to the second sum value is recorded as a first ratio, and the result after normalization of the first ratio is recorded as a first result; and taking the cumulative multiplication result of the first absolute value, the first reciprocal and the first result as the noise anomaly credibility of the suspected anomaly data.
Preferably, the correcting the noise abnormal data obtains all target abnormal data in the denoised scraper operation data sequence section, including the following specific methods:
For any noise abnormal data in any scraper operation data sequence section, taking the average value of vibration data of two adjacent sampling moments of the noise abnormal data as the vibration data of the sampling moment corresponding to the noise abnormal data, and then marking the scraper operation data sequence section as a denoised scraper operation data sequence section; and recording all suspected abnormal data in the denoised scraper operation data sequence section as target abnormal data.
Preferably, the obtaining the abnormality probability factor of each target abnormality data according to the difference value, the noise abnormality reliability and the deviation degree of the vibration data between each target abnormality data and the adjacent sampling time comprises the following specific methods:
for any one target abnormal data in any one denoised scraper operation data sequence section, taking the difference value of the target abnormal data and the vibration data of the last sampling time of the sampling time corresponding to the target abnormal data as the adjacent vibration data difference value of the target abnormal data; the calculation method for obtaining the abnormal possibility of the target abnormal data comprises the following steps:
In the method, in the process of the invention, Representing an anomaly possibility of the target anomaly data; /(I)Adjacent vibration data differences representing the target anomaly data; /(I)The total number of all target abnormal data in the denoised scraper operation data sequence section is represented; /(I)Representing the/>, in the denoised scraper operation data sequence segmentTarget anomaly data; /(I)Representing the/>, in the denoised scraper operation data sequence segmentTarget anomaly data; /(I)Noise anomaly reliability representing the target anomaly data; /(I)Indicating the degree of deviation of the target abnormal data; /(I)Representing the absolute value.
Preferably, the fault monitoring for the scraper conveyor according to the abnormality potential factor comprises the following specific steps:
Presetting a quantity parameter For any target abnormal data in any denoised scraper operation data sequence segment, if the abnormality probability factor of the target abnormal data is greater than or equal to a preset credible threshold/>Recording the target abnormal data as real abnormal data; the total number of all real abnormal data in the denoised scraper operation data sequence section is recorded as the first number of the denoised scraper operation data sequence section; if the sum of the first number of all denoised flight operation data sequence segments is greater than the number parameter/>The scraper conveyor has operation faults and immediately starts an alarm.
The technical scheme of the invention has the beneficial effects that: according to the method, all suspected abnormal data in each scraper operation data sequence section are screened according to noise abnormality credibility factors, all noise abnormal data in each scraper operation data sequence section are obtained, abnormal vibration data and noise data are distinguished, the noise abnormal data are corrected, and all target abnormal data in the scraper operation data sequence section after denoising are obtained; according to the difference value, noise abnormality credibility and deviation degree of vibration data between each target abnormal data and adjacent sampling time, obtaining an abnormality probability factor of each target abnormal data, and carrying out fault monitoring on the scraper conveyor according to the abnormality probability factor, so that a denoised data sequence is obtained by correcting the noise data, and real abnormal data is obtained by analyzing the abnormality probability of the abnormal data with smaller deviation degree value, so that the accuracy of detecting the operation faults of the scraper conveyor is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for online monitoring of operation faults of a scraper conveyor according to the present invention;
FIG. 2 is a flow chart of the characteristic relation of the online monitoring method for the operation faults of the scraper conveyor.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of the specific implementation, structure, characteristics and effects of the online monitoring method for the operation fault of the scraper conveyor according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an online monitoring method for operation faults of a scraper conveyor, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for online monitoring operation faults of a scraper conveyor according to an embodiment of the present invention is shown, and the method includes the following steps:
Step S001: and acquiring a scraper operation data sequence, wherein the scraper operation data sequence comprises scraper vibration data, scraper motor rotating speed data and scraper load data at a plurality of sampling moments.
When the vibration data collected by the vibration sensor is detected abnormally by using the standard score algorithm, the denoised vibration data can be obtained after correcting the abnormal data with high deviation degree, so that the real abnormal vibration data can be marked.
Specifically, firstly, a scraper operation data sequence needs to be collected, and the specific process is as follows:
Collecting three data types, namely scraper vibration data, scraper motor rotating speed data and scraper load data, sequentially every 1 second as a sampling time, wherein the total collection time is 1 hour; and taking three data of the scraper vibration data, the scraper motor rotating speed data and the scraper load data at each sampling time as a scraper operation data sequence.
The scraper operation data sequence comprises scraper vibration data, scraper motor rotating speed data and scraper load data at a plurality of sampling moments; collecting vibration data of a rotating shaft of the scraper conveyor in the running process by utilizing a vibration sensor to obtain scraper vibration data; acquiring the rotating speed of a motor of the scraper conveyor in the running process by utilizing an infrared sensor to obtain rotating speed data of the scraper motor; the method comprises the steps that a pressure sensor is used for collecting the load weight of a scraper conveyor in the running process, so that scraper load data are obtained; referring to fig. 2, a flow chart of features of an online monitoring method for operation faults of a scraper conveyor is shown.
So far, the scraper operation data sequence is obtained through the method.
Step S002: dividing the scraper operation data sequence into a plurality of scraper operation data sequence segments, acquiring the deviation degree of vibration data at each sampling time in each scraper operation data sequence segment by using a standard fraction algorithm, and acquiring all suspected abnormal data in each scraper operation data sequence segment according to the deviation degree; acquiring the change rule degree of the suspected abnormal data according to the distribution condition of the vibration data at all sampling moments around the suspected abnormal data; acquiring noise anomaly credibility factors of the suspected anomaly data according to the rotating speed data of the scraper motor, the scraper load data, the change rule degree and the deviation degree of the suspected anomaly data corresponding to the sampling time; and screening all suspected abnormal data in each scraper operation data sequence segment according to the noise abnormal credibility factors to obtain all noise abnormal data in each scraper operation data sequence segment.
When vibration data at any one sampling time is analyzed in real time, the relationship between the vibration data far from the sampling time and the sampling time data is weak, so that only vibration data close to the sampling time data is selected to analyze the abnormality degree of the vibration data at the sampling time, and the authenticity and the instantaneity of data analysis are ensured.
Presetting a dividing parameterAnd a deviation parameter/>Wherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation.
Specifically, the scraper operation data sequence is uniformly divided intoThe method comprises the steps of obtaining vibration data deviation degree of each sampling time in any scraper operation data sequence segment by using a standard fraction algorithm; for any one sampling time, if the absolute value of the deviation degree of the vibration data of the sampling time is larger than/>The vibration data at the sampling moment is recorded as suspected abnormal data; and further obtaining all suspected abnormal data in the scraper operation data sequence section.
So far, all suspected abnormal data in each scraper operation data sequence segment are obtained.
In the working process of the scraper conveyor, external factors such as voltage and current, motor rotation speed, load weight and working time length all have influence on the vibration of the rotating shaft, when a certain external factor is changed, vibration data of the rotating shaft also changes along with the change degree of the external factor, so that originally stable periodic data are changed into high-frequency and disordered data, and noise anomaly reliability of suspected anomaly data points is analyzed by combining the external factors.
Presetting a neighborhood parameterWherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation.
Specifically, for any suspected abnormal data in any scraper running data sequence segment, the left side of the suspected abnormal data is providedSample time and right side/>A time range formed by the sampling time is used as a neighborhood time range of the suspected abnormal data; and acquiring all maximum values in the vibration data of all sampling moments in the neighborhood moment range of the suspected abnormal data, and acquiring the change rule degree of the suspected abnormal data according to the distribution condition of the vibration data of all sampling moments in the neighborhood moment range of the suspected abnormal data.
As an example, the calculation method for obtaining the change rule degree of each suspected abnormal data in each scraper operation data sequence segment is as follows:
In the method, in the process of the invention, Representing the degree of change regularity of suspected abnormal data; /(I)Representing the total number of all maximum values in vibration data at all sampling moments in a neighborhood moment range of suspected abnormal data; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataMaximum and/>Differences in the individual maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataMaximum and/>Differences in the individual maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataA plurality of maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataA plurality of maxima; /(I)Representing a neighborhood parameter; /(I)The representation takes absolute value.
If the sampling time of any one side of the suspected abnormal data is insufficientSelecting more sampling moments at the other side of the suspected abnormal data, so that the number of sampling moments in the neighborhood moment range of the suspected abnormal data reaches/>A plurality of; if the change frequency of the data in the neighborhood time range of the suspected abnormal data is faster and the periodicity is not met among the vibration data, the noise abnormality reliability of the current suspected abnormal data is higher,The periodicity of the data change in the neighborhood time range of the suspected abnormal data is represented.
So far, the change rule degree of each suspected abnormal data in each scraper operation data sequence section is obtained.
The influence of the vibration data at the sampling moment is analyzed by combining other dimension data of the sampling moment corresponding to the suspected abnormal data; the higher the motor rotating speed of the scraper conveyor at the sampling time is, the smaller the vibration variation amplitude of the rotating shaft of the scraper conveyor is, namely the higher the reliability of the suspected abnormal data for representing noise abnormality is, and the same is true otherwise; meanwhile, as the load weight of the surface of the scraper conveyor changes during operation, the rotation resistance of the rotating shaft can be increased due to the increase of the surface load, so that the larger the vibration data of the rotating shaft changes, and the noise anomaly credibility of the suspected abnormal data point is determined by combining the change rule degree of the suspected abnormal data point.
Specifically, for any one piece of suspected abnormal data in any piece of scraper operation data sequence section, recording a time interval between each maximum value in vibration data of all sampling time in a neighborhood time range of the suspected abnormal data and the suspected abnormal data as a first time interval of each maximum value, and taking a maximum value with the minimum first time interval as a first maximum value of the suspected abnormal data; recording the time interval between each minimum value in vibration data of all sampling moments in the neighborhood time range of the suspected abnormal data and the sampling moment of the suspected abnormal data as a second time interval of each minimum value, and taking the minimum value with the minimum second time interval as a first minimum value of the suspected abnormal data; and obtaining noise anomaly credibility factors of the suspected anomaly data according to the scraper motor rotating speed data, the scraper load data, the change rule degree and the deviation degree of the sampling time corresponding to the suspected anomaly data.
As an example, the calculation method for obtaining the noise anomaly reliability of each suspected anomaly data in each scraper operation data sequence segment is as follows:
In the method, in the process of the invention, Noise anomaly reliability indicating suspected anomaly data; /(I)Representing the degree of change regularity of suspected abnormal data; /(I)Indicating the degree of deviation of the suspected abnormal data; /(I)The scraper motor rotating speed data which represents the sampling time corresponding to the suspected abnormal data; /(I)Scraper load data representing sampling time corresponding to suspected abnormal data; /(I)A first maximum value representing suspected abnormal data; /(I)A first minimum value representing suspected abnormal data; /(I)The representation takes absolute value; /(I)Representing a normalization function; /(I)Representing preset super parameters, preset/>, the implementationFor preventing denominator from being 0.
And acquiring noise anomaly credibility of all suspected anomaly data in the scraper operation data sequence segment, and recording each noise anomaly credibility after linear normalization of all the noise anomaly credibility as a noise anomaly credibility factor.
Presetting a trusted thresholdWherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation.
For any suspected abnormal data in any scraper operation data sequence section, if the noise abnormal credibility factor of the suspected abnormal data is larger than or equal to a credibility threshold valueAnd recording the suspected abnormal data as noise abnormal data.
So far, all noise abnormal data in each scraper operation data sequence segment are obtained through the method.
Step S003: correcting the noise abnormal data to obtain all target abnormal data in the denoised scraper operation data sequence section; and acquiring an abnormality probability factor of each target abnormal data according to the difference value, the noise abnormality credibility and the deviation degree of the vibration data between each target abnormal data and the adjacent sampling time.
It should be noted that, by analyzing the noise anomaly reliability of the suspected anomaly data, the suspected anomaly data points that partially meet the noise anomaly reliability requirement are screened out, and because there may be cases where there is a lower anomaly expression but actually the anomaly data, that is, the change of the vibration data accords with the change of other data in the scene, but the change degree of the data may not accord with the normal change degree, etc., the residual suspected anomaly data in the data segment needs to be analyzed again, and the anomaly reliability of the residual suspected data points is calculated.
Specifically, for any noise abnormal data in any scraper operation data sequence section, taking an average value of vibration data of two adjacent sampling moments of the noise abnormal data as vibration data of the sampling moment corresponding to the noise abnormal data, and then marking the scraper operation data sequence section as a denoised scraper operation data sequence section; and recording all suspected abnormal data in the denoised scraper operation data sequence section as target abnormal data.
So far, all target abnormal data in each denoised scraper operation data sequence segment are obtained.
It should be noted that, for the target abnormal data with different change trend in the denoised scraper operation data sequence section and the change trend of the normal data, the target abnormal data is similar to the average value of the vibration data in the denoised scraper operation data sequence section, that is, the abnormal performance of the standard score algorithm is lower, but the target abnormal data actually belongs to the abnormal data, so that the target abnormal data cannot be marked as the abnormal data by directly using the standard score algorithm; since abnormal data in the denoised scraper running data sequence section is shown to be different from adjacent data or vibration data variation between other data and the adjacent data, analysis is performed by combining the variation degree of the adjacent data in the adjacent data, and if the variation between the data and the neighborhood data point and the variation between the other data in the denoised scraper running data sequence section and the neighborhood data point are larger, the possibility of abnormality of the current data is larger.
Specifically, for any one target abnormal data in any one denoised scraper operation data sequence segment, taking the difference value between the target abnormal data and the vibration data of the last sampling time of the sampling time corresponding to the target abnormal data as the adjacent vibration data difference value of the target abnormal data, and acquiring the abnormality probability factor of each target abnormal data according to the difference value, the noise abnormality reliability and the deviation degree of the vibration data between each target abnormal data and the adjacent sampling time.
As an example, a calculation method of acquiring an abnormality probability of each target abnormality data in each denoised squeegee operation data sequence section:
In the method, in the process of the invention, Representing the abnormal possibility of any target abnormal data in any denoised scraper operation data sequence segment; /(I)Adjacent vibration data differences representing the target anomaly data; /(I)The total number of all target abnormal data in the denoised scraper operation data sequence section is represented; /(I)Representing the/>, in the denoised scraper operation data sequence segmentTarget anomaly data; representing the/>, in the denoised scraper operation data sequence segment Target anomaly data; /(I)Noise anomaly reliability representing the target anomaly data; /(I)Indicating the degree of deviation of the target abnormal data; /(I)Representing the absolute value.
And acquiring the abnormal possibility of all target abnormal data in the denoised scraper operation data sequence section, and marking each abnormal possibility after linear normalization of all the abnormal possibility as an abnormal possibility factor.
So far, the anomaly possibility factors of each target anomaly data in each denoised scraper operation data sequence segment are obtained through the method.
Step S004: and carrying out fault monitoring on the scraper conveyor according to the abnormal possible factors.
Presetting a quantity parameterWherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation.
Specifically, for any one target abnormal data in any one denoised scraper operation data sequence segment, if the abnormality probability factor of the target abnormal data is greater than or equal to a trusted threshold valueRecording the target abnormal data as real abnormal data; the total number of all real abnormal data in the denoised scraper operation data sequence section is recorded as the first number of the denoised scraper operation data sequence section; if the sum of the first number of all denoised flight operation data sequence segments is greater than the number parameter/>The scraper conveyor has operation faults and immediately starts an alarm.
This embodiment is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. An online monitoring method for operation faults of a scraper conveyor is characterized by comprising the following steps:
acquiring a scraper operation data sequence, wherein the scraper operation data sequence comprises scraper vibration data, scraper motor rotating speed data and scraper load data at a plurality of sampling moments;
Dividing the scraper operation data sequence into a plurality of scraper operation data sequence segments, acquiring the deviation degree of vibration data at each sampling time in each scraper operation data sequence segment by using a standard fraction algorithm, and acquiring all suspected abnormal data in each scraper operation data sequence segment according to the deviation degree; acquiring the change rule degree of the suspected abnormal data according to the distribution condition of the vibration data at all sampling moments around the suspected abnormal data; acquiring noise anomaly credibility factors of the suspected anomaly data according to the rotating speed data of the scraper motor, the scraper load data, the change rule degree and the deviation degree of the suspected anomaly data corresponding to the sampling time; screening all suspected abnormal data in each scraper operation data sequence segment according to the noise abnormal credibility factors to obtain all noise abnormal data in each scraper operation data sequence segment;
Correcting the noise abnormal data to obtain all target abnormal data in the denoised scraper operation data sequence section; obtaining an abnormality potential factor of each target abnormal data according to the difference value of the vibration data between each target abnormal data and the adjacent sampling time, the noise abnormality credibility and the deviation degree;
carrying out fault monitoring on the scraper conveyor according to the abnormal possible factors;
according to the distribution condition of vibration data at all sampling moments around the suspected abnormal data, the change rule degree of the suspected abnormal data is obtained, and the method comprises the following specific steps:
Presetting a neighborhood parameter For any suspected abnormal data in any scraper operation data sequence section, acquiring a neighborhood time range of the suspected abnormal data; the calculation method for obtaining the change rule degree of the suspected abnormal data comprises the following steps:
In the method, in the process of the invention, Representing the degree of change regularity of suspected abnormal data; /(I)Representing the total number of all maximum values in vibration data at all sampling moments in a neighborhood moment range of suspected abnormal data; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataSampling time corresponding to each maximum value; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataMaximum and/>Differences in the individual maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataMaximum and/>Differences in the individual maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataA plurality of maxima; /(I)Vibration data representing all sampling times within a neighborhood time range of suspected abnormal dataA plurality of maxima; /(I)Representing a neighborhood parameter; /(I)Representing taking absolute value
The method for obtaining the noise anomaly credibility factor of the suspected anomaly data according to the scraper motor rotating speed data, the scraper load data, the change rule degree and the deviation degree of the suspected anomaly data at the corresponding sampling time comprises the following specific steps:
for any suspected abnormal data in any scraper operation data sequence segment, acquiring a first maximum value and a first minimum value of the suspected abnormal data;
Acquiring noise anomaly credibility of the suspected anomaly data according to the first maximum value, the first minimum value, the change rule degree, the deviation degree of the suspected anomaly data, and the scraper motor rotating speed data and the scraper load data of the corresponding sampling time;
Acquiring noise anomaly credibility of all suspected anomaly data in the scraper operation data sequence segment, and marking each noise anomaly credibility after linear normalization of all the noise anomaly credibility as a noise anomaly credibility factor;
according to the difference value, noise anomaly reliability and deviation degree of vibration data between each target anomaly data and adjacent sampling time, acquiring anomaly probability factors of each target anomaly data, wherein the specific method comprises the following steps:
for any one target abnormal data in any one denoised scraper operation data sequence section, taking the difference value of the target abnormal data and the vibration data of the last sampling time of the sampling time corresponding to the target abnormal data as the adjacent vibration data difference value of the target abnormal data; the calculation method for obtaining the abnormal possibility of the target abnormal data comprises the following steps:
In the method, in the process of the invention, Representing an anomaly possibility of the target anomaly data; /(I)Adjacent vibration data differences representing the target anomaly data; /(I)The total number of all target abnormal data in the denoised scraper operation data sequence section is represented; /(I)Representing the/>, in the denoised scraper operation data sequence segmentTarget anomaly data; /(I)Representing the/>, in the denoised scraper operation data sequence segmentTarget anomaly data; /(I)Noise anomaly reliability representing the target anomaly data; /(I)Indicating the degree of deviation of the target abnormal data; Representing the absolute value.
2. The online monitoring method for operation faults of the scraper conveyor according to claim 1, wherein the obtaining all suspected abnormal data in each scraper operation data sequence section according to the deviation degree comprises the following specific steps:
Presetting a deviation parameter For any sampling time in any scraper operation data sequence section, if the absolute value of the deviation degree of vibration data of the sampling time is larger than/>And recording the vibration data at the sampling time as suspected abnormal data.
3. The online monitoring method for operation faults of a scraper conveyor according to claim 1, wherein the neighborhood time range for acquiring the suspected abnormal data comprises the following specific steps:
Left side of the suspected abnormal data Sample time and right side/>And a time range formed by the sampling time is used as a neighborhood time range of the suspected abnormal data.
4. The online monitoring method for operation faults of a scraper conveyor according to claim 1, wherein the obtaining of the first maximum value and the first minimum value of the suspected abnormal data comprises the following specific steps:
Recording the time interval between each maximum value in vibration data of all sampling moments in the neighborhood time range of the suspected abnormal data and the sampling moment of the suspected abnormal data as a first time interval of each maximum value, and taking the maximum value with the minimum first time interval as the first maximum value of the suspected abnormal data; and recording the time interval between each minimum value in vibration data of all sampling moments in the neighborhood time range of the suspected abnormal data and the sampling moment of the suspected abnormal data as a second time interval of each minimum value, and taking the minimum value with the minimum second time interval as a first minimum value of the suspected abnormal data.
5. The online monitoring method for operation faults of a scraper conveyor according to claim 1, wherein the obtaining the noise anomaly credibility of the suspected anomaly data according to the first maximum value, the first minimum value, the degree of change regularity, the degree of deviation of the suspected anomaly data, and the scraper motor rotation speed data and the scraper load data of the corresponding sampling time comprises the following specific steps:
The reciprocal of the change rule degree of the suspected abnormal data is recorded as a first reciprocal; the absolute value of the deviation degree of the suspected abnormal data is recorded as a first absolute value; the sum of the scraper motor rotating speed data and the scraper load data at the sampling time corresponding to the suspected abnormal data is recorded as a first sum value; the absolute value of the difference value between the first maximum value and the first minimum value of the suspected abnormal data is recorded as a second absolute value, and a preset super parameter is obtained The sum of the first absolute value and the second absolute value is recorded as a second sum value, the ratio of the first sum value to the second sum value is recorded as a first ratio, and the result after normalization of the first ratio is recorded as a first result; and taking the cumulative multiplication result of the first absolute value, the first reciprocal and the first result as the noise anomaly credibility of the suspected anomaly data.
6. The online monitoring method for operation faults of a scraper conveyor according to claim 1, wherein the method for correcting noise abnormal data to obtain all target abnormal data in a denoised scraper operation data sequence segment comprises the following specific steps:
For any noise abnormal data in any scraper operation data sequence section, taking the average value of vibration data of two adjacent sampling moments of the noise abnormal data as the vibration data of the sampling moment corresponding to the noise abnormal data, and then marking the scraper operation data sequence section as a denoised scraper operation data sequence section; and recording all suspected abnormal data in the denoised scraper operation data sequence section as target abnormal data.
7. The online monitoring method for operation faults of the scraper conveyor according to claim 1, wherein the fault monitoring for the scraper conveyor according to the abnormality potential factor comprises the following specific steps:
Presetting a quantity parameter For any target abnormal data in any denoised scraper operation data sequence segment, if the abnormality probability factor of the target abnormal data is greater than or equal to a preset credible threshold/>Recording the target abnormal data as real abnormal data; the total number of all real abnormal data in the denoised scraper operation data sequence section is recorded as the first number of the denoised scraper operation data sequence section; if the sum of the first number of all denoised flight operation data sequence segments is greater than the number parameter/>The scraper conveyor has operation faults and immediately starts an alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410330956.1A CN117951455B (en) | 2024-03-22 | 2024-03-22 | On-line monitoring method for operation faults of scraper conveyor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410330956.1A CN117951455B (en) | 2024-03-22 | 2024-03-22 | On-line monitoring method for operation faults of scraper conveyor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117951455A CN117951455A (en) | 2024-04-30 |
| CN117951455B true CN117951455B (en) | 2024-06-07 |
Family
ID=90793017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410330956.1A Active CN117951455B (en) | 2024-03-22 | 2024-03-22 | On-line monitoring method for operation faults of scraper conveyor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117951455B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118259064A (en) * | 2024-05-10 | 2024-06-28 | 国网山西省电力公司忻州供电公司 | Power system equipment operation load abnormality monitoring method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017197875A1 (en) * | 2016-05-17 | 2017-11-23 | 中国矿业大学 | Apparatus and method for tension monitoring of chain of scraper conveyor |
| WO2018142703A1 (en) * | 2017-02-02 | 2018-08-09 | 日本電信電話株式会社 | Anomaly factor estimation device, anomaly factor estimation method, and program |
| WO2022037172A1 (en) * | 2020-08-17 | 2022-02-24 | 南京磐能电力科技股份有限公司 | Anomalous sampled data value repair method and apparatus |
| CN114253779A (en) * | 2021-12-01 | 2022-03-29 | 北京经纬恒润科技股份有限公司 | CAN bus data anomaly detection method, device and equipment |
| WO2023283987A1 (en) * | 2021-07-15 | 2023-01-19 | 中国科学院深圳先进技术研究院 | Sensor security detection method and device for unmanned system, and storage medium |
| CN116595470A (en) * | 2023-07-17 | 2023-08-15 | 北京云摩科技股份有限公司 | Method for monitoring chain load of scraper |
| CN116879662A (en) * | 2023-09-06 | 2023-10-13 | 山东华尚电气有限公司 | Transformer fault detection method based on data analysis |
| CN117312972A (en) * | 2023-11-30 | 2023-12-29 | 山西海诚智能制造有限公司 | Method for identifying health state of scraper conveyor speed reducer |
| CN117436024A (en) * | 2023-12-19 | 2024-01-23 | 湖南翰文云机电设备有限公司 | Fault diagnosis method and system based on drilling machine operation data analysis |
| CN117649412A (en) * | 2024-01-30 | 2024-03-05 | 山东海天七彩建材有限公司 | Aluminum material surface quality detection method |
| CN117668730A (en) * | 2023-12-14 | 2024-03-08 | 郑州恒达智控科技股份有限公司 | Load abnormality detection method for underground coal mine scraper based on deep learning algorithm |
| CN117708747A (en) * | 2024-02-04 | 2024-03-15 | 吉林交通职业技术学院 | Method for monitoring track vibration data abnormality in train operation |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7653235B2 (en) * | 2005-10-27 | 2010-01-26 | Honeywell International Inc. | Surface anomaly detection system and method |
| JP2019016209A (en) * | 2017-07-07 | 2019-01-31 | 株式会社東芝 | Diagnosis device, diagnosis method, and computer program |
| US11194691B2 (en) * | 2019-05-31 | 2021-12-07 | Gurucul Solutions, Llc | Anomaly detection using deep learning models |
-
2024
- 2024-03-22 CN CN202410330956.1A patent/CN117951455B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017197875A1 (en) * | 2016-05-17 | 2017-11-23 | 中国矿业大学 | Apparatus and method for tension monitoring of chain of scraper conveyor |
| WO2018142703A1 (en) * | 2017-02-02 | 2018-08-09 | 日本電信電話株式会社 | Anomaly factor estimation device, anomaly factor estimation method, and program |
| WO2022037172A1 (en) * | 2020-08-17 | 2022-02-24 | 南京磐能电力科技股份有限公司 | Anomalous sampled data value repair method and apparatus |
| WO2023283987A1 (en) * | 2021-07-15 | 2023-01-19 | 中国科学院深圳先进技术研究院 | Sensor security detection method and device for unmanned system, and storage medium |
| CN114253779A (en) * | 2021-12-01 | 2022-03-29 | 北京经纬恒润科技股份有限公司 | CAN bus data anomaly detection method, device and equipment |
| CN116595470A (en) * | 2023-07-17 | 2023-08-15 | 北京云摩科技股份有限公司 | Method for monitoring chain load of scraper |
| CN116879662A (en) * | 2023-09-06 | 2023-10-13 | 山东华尚电气有限公司 | Transformer fault detection method based on data analysis |
| CN117312972A (en) * | 2023-11-30 | 2023-12-29 | 山西海诚智能制造有限公司 | Method for identifying health state of scraper conveyor speed reducer |
| CN117668730A (en) * | 2023-12-14 | 2024-03-08 | 郑州恒达智控科技股份有限公司 | Load abnormality detection method for underground coal mine scraper based on deep learning algorithm |
| CN117436024A (en) * | 2023-12-19 | 2024-01-23 | 湖南翰文云机电设备有限公司 | Fault diagnosis method and system based on drilling machine operation data analysis |
| CN117649412A (en) * | 2024-01-30 | 2024-03-05 | 山东海天七彩建材有限公司 | Aluminum material surface quality detection method |
| CN117708747A (en) * | 2024-02-04 | 2024-03-15 | 吉林交通职业技术学院 | Method for monitoring track vibration data abnormality in train operation |
Non-Patent Citations (4)
| Title |
|---|
| 一种基于改进EMD的风机振动信号异常检测方法;马宏陆;葛琳琳;牛强;夏士雄;;南京师大学报(自然科学版);20170320(01);正文全文 * |
| 基于改进萤火虫算法神经网络的刮板输送机减速器故障诊断;毛君;郭浩;陈洪月;;机械强度;20190606(03);正文全文 * |
| 基于深度视觉的筛板故障智能检测方法研究;杨林顺;郑伟;张帅帅;杨明锦;彭晨;;选煤技术;20200425(02);正文全文 * |
| 基于混沌差分进化FCM的刮板输送机故障诊断;崔宏尧;刘敏智;;煤矿机械;20201010(10);正文全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117951455A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A novel statistical time-frequency analysis for rotating machine condition monitoring | |
| CA2634328C (en) | Method and system for trend detection and analysis | |
| CN110276416A (en) | A kind of rolling bearing fault prediction technique | |
| CN117951455B (en) | On-line monitoring method for operation faults of scraper conveyor | |
| CN114167838B (en) | Multi-scale health assessment and fault prediction method for servo system | |
| Gowid et al. | A novel robust automated FFT-based segmentation and features selection algorithm for acoustic emission condition based monitoring systems | |
| US11630028B2 (en) | Method and controller for deciding whether a bearing is faulty or not | |
| CN111307438B (en) | Rotary machine vibration fault diagnosis method and system based on information entropy | |
| JPH11173909A (en) | Method and apparatus for judging abnormality | |
| CN109238455B (en) | A kind of characteristic of rotating machines vibration signal monitoring method and system based on graph theory | |
| CN117439827B (en) | Network flow big data analysis method | |
| Zan et al. | Research on early fault diagnosis of rolling bearing based on VMD | |
| CN116773961A (en) | Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis | |
| CN110398384A (en) | The machine health monitoring of rotating machinery | |
| CN117454283A (en) | State evaluation method for wind turbine generator operation detection data | |
| CN118051863B (en) | Health data acquisition system and method based on digital metering technology | |
| Istiaque et al. | Classification of Bearing Fault Using Radial Basis Neural Network and Genetic Algorithm | |
| Tajiani et al. | RUL prediction of bearings using empirical wavelet transform and Bayesian approach | |
| JPH11173956A (en) | Method and apparatus for judging quality | |
| CN118310786B (en) | Intelligent measuring method and system for blade load of industrial fan | |
| CN117273547B (en) | Production equipment operation data processing method based on edge calculation | |
| Lin et al. | Fault diagnosis of rolling bearings using multifractal detrended fluctuation analysis and Mahalanobis distance criterion | |
| CN115446662B (en) | Cutter vibration signal processing method based on CEEMDAN-IFTC-PSR | |
| Ignasiak et al. | Long term vibration data analysis from wind turbine-statistical vs energy based features | |
| CN113609207B (en) | Data preprocessing method for slope deformation monitoring data |
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 |