CN117932358A - Intelligent remote electric field fault diagnosis method and system - Google Patents
Intelligent remote electric field fault diagnosis method and system Download PDFInfo
- Publication number
- CN117932358A CN117932358A CN202410157331.XA CN202410157331A CN117932358A CN 117932358 A CN117932358 A CN 117932358A CN 202410157331 A CN202410157331 A CN 202410157331A CN 117932358 A CN117932358 A CN 117932358A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- data set
- equipment
- matching
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000005684 electric field Effects 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 119
- 230000002159 abnormal effect Effects 0.000 claims description 57
- 238000012423 maintenance Methods 0.000 claims description 56
- 238000011156 evaluation Methods 0.000 claims description 22
- 238000000605 extraction Methods 0.000 claims description 15
- 238000001228 spectrum Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 18
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an intelligent remote electric field fault diagnosis method and system, and relates to the field of wind power plants. The method comprises the following steps: establishing a device data set of a wind power plant; using the equipment attribute data as matching data, and constructing a first fault detection data set through big data matching; extracting equipment working characteristics by using equipment working data in the equipment data set, and constructing a second fault detection data set through big data matching; after the equipment of the wind farm sends out the early warning signal, extracting wind farm equipment data in a preset time window of the early warning signal; the wind power plant equipment data are used as fault data, the fault data are sent to a cloud, and fault similarity matching of a first fault detection data set and a second fault detection data set is executed; and integrating the fault similar matching results, and generating a fault diagnosis result according to the integrated results. The technical problems of poor reliability and efficiency of fault diagnosis in the prior art are solved, and the technical effect of improving the accuracy and efficiency of fault diagnosis of wind power plant equipment is achieved.
Description
Technical Field
The invention relates to the field of wind farms, in particular to an intelligent remote electric field fault diagnosis method and system.
Background
With the increasing demand for energy and the increasing awareness of environmental protection, wind power generation is widely used as a clean and renewable energy source. In wind farms, wind power plants are critical components, the proper operation of which is critical for the stability and reliability of the wind farm. However, wind power plants inevitably have various faults during long-term operation, which may cause the plant to be stopped or reduce the operating efficiency, severely affecting the power generation. The traditional fault detection and diagnosis method mainly depends on manual experience and observation, has the problems of high misjudgment rate, low efficiency, poor reliability and the like, and cannot meet the requirements of large-scale wind farms.
Disclosure of Invention
The embodiment of the application provides an intelligent remote electric field fault diagnosis method and system, which solve the technical problems of poor reliability and efficiency of fault diagnosis in the prior art.
In view of the above problems, the embodiment of the application provides an intelligent remote electric field fault diagnosis method and system.
In a first aspect of the embodiment of the present application, there is provided an intelligent remote electric field fault diagnosis method, the method including:
Establishing an equipment data set of a wind power plant, wherein equipment attribute data and equipment working data are stored in the equipment data set;
using the equipment attribute data in the equipment data set as matching data, and constructing a first fault detection data set through big data matching;
Extracting equipment working characteristics by using equipment working data in the equipment data set, and constructing a second fault detection data set through big data matching;
After the equipment of the wind farm sends out the early warning signal, extracting wind farm equipment data in a preset time window of the early warning signal;
taking the wind farm equipment data as fault data, sending the fault data to a cloud, and executing fault similarity matching of the first fault detection data set and the second fault detection data set;
And integrating the fault similar matching result, and generating a fault diagnosis result according to the integrated result, wherein the fault diagnosis result is provided with a maintenance scheme identifier.
In a second aspect of the embodiments of the present application, there is provided an intelligent remote electric field fault diagnosis system, the system comprising:
the system comprises a data set establishing module, a data set generating module and a data set generating module, wherein the data set establishing module is used for establishing a device data set of a wind power plant, and device attribute data and device working data are stored in the device data set;
The first matching module is used for constructing a first fault detection data set through big data matching by taking the equipment attribute data in the equipment data set as matching data;
the second matching module is used for extracting equipment working characteristics according to the equipment working data in the equipment data set and constructing a second fault detection data set through big data matching;
The extraction module is used for extracting wind power plant equipment data in a preset time window of the early warning signal after equipment of the wind power plant sends the early warning signal;
the third matching module is used for taking the wind power plant equipment data as fault data, sending the fault data to the cloud, and executing fault similarity matching of the first fault detection data set and the second fault detection data set;
The fault diagnosis module is used for integrating the fault similar matching results and generating a fault diagnosis result according to the integrated results, wherein the fault diagnosis result is provided with a maintenance scheme identifier.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
First, a device dataset of a wind farm is established, comprising device attribute data and device operational data. Next, a first failure detection dataset is constructed using big data matching techniques with the device attribute data as matching data. And (3) analyzing and comparing the equipment attribute data to find a similar fault sample, so as to realize the primary detection of equipment faults. Meanwhile, on the basis of the equipment working data, the equipment working characteristics are extracted, and a second fault detection data set is constructed by utilizing a big data matching technology. Therefore, the equipment working data can be compared with known fault samples, and the accuracy of fault detection is further improved. And after the equipment of the wind power plant sends out the early warning signal, extracting wind power plant equipment data in a preset time window of the early warning signal. And sending the data to the cloud for processing as fault data. And at the cloud end, performing fault similarity matching of the first fault detection data set and the second fault detection data set. By matching the fault data with known fault samples, similar fault conditions are found. And finally, integrating the fault similarity matching result, and generating a fault diagnosis result according to the integrated result. The technical problems of poor reliability and efficiency of fault diagnosis in the prior art are solved, and the technical effect of improving the accuracy and efficiency of fault diagnosis of wind power plant equipment is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent remote electric field fault diagnosis method according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of an intelligent remote electric field fault diagnosis system according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a data set establishing module 11, a first matching module 12, a second matching module 13, an extracting module 14, a third matching module 15 and a fault diagnosis module 16.
Detailed Description
The embodiment of the application solves the technical problems of poor reliability and efficiency of fault diagnosis in the prior art by providing the intelligent remote electric field fault diagnosis method and system.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent remote electric field fault diagnosis method, where the method includes:
Establishing an equipment data set of a wind power plant, wherein equipment attribute data and equipment working data are stored in the equipment data set;
The device attribute data describes the characteristics and specifications of the device, while the device operational data records the status and performance of the device during operation. By collecting and storing device attribute data and device operational data, a comprehensive device dataset of the wind farm can be established for subsequent fault detection, prediction and maintenance work.
Using the equipment attribute data in the equipment data set as matching data, and constructing a first fault detection data set through big data matching;
And cleaning and standardizing the equipment attribute data to ensure the consistency and comparability of the data. Then, key features such as device model number, manufacturer information, rated power, etc. are extracted from the processed device attribute data. And calculating cosine similarity or Euclidean distance between feature vectors of the equipment attribute data to obtain a similarity value between the equipment. And selecting a sample which is most similar to the target device as a matching sample according to the similarity between the devices. And correlating the matching sample with the corresponding fault condition to construct a first fault detection data set. The first fault detection data set is comprised of matching samples and their corresponding fault conditions.
Extracting equipment working characteristics by using equipment working data in the equipment data set, and constructing a second fault detection data set through big data matching;
Features associated with the fault are extracted from the device operational data, including sensor data, operation logs, device status information, and the like. And matching through big data, finding a sample similar to the working characteristics of the target equipment, and constructing a second fault detection data set. The second fault detection data set contains samples similar to the target device operating characteristics and their fault conditions.
After the equipment of the wind farm sends out the early warning signal, extracting wind farm equipment data in a preset time window of the early warning signal;
When the equipment of the wind farm is monitored to send out the early warning signal, the starting time and the ending time of the preset time window can be determined according to the sending time of the early warning signal. And extracting equipment data related to the early warning signals from a data acquisition system of the wind power plant, and selecting corresponding equipment data for extraction according to the types and fault characteristics of the early warning signals.
Taking the wind farm equipment data as fault data, sending the fault data to a cloud, and executing fault similarity matching of the first fault detection data set and the second fault detection data set;
Uploading the wind farm equipment data to the cloud, performing fault similarity matching by using the first fault detection data set, and if the first fault detection data set fails to find a sample similar to the wind farm equipment data, performing matching by using the second fault detection data set.
Further, the step of sending the wind farm equipment data to a cloud as fault data, and executing fault similarity matching of the first fault detection data set and the second fault detection data set, further includes:
storing the first fault detection data set and the second fault detection data set to a cloud;
respectively executing data preprocessing on the first fault detection data set and the second fault detection data set, wherein the data preprocessing comprises data wavelet denoising and data normalization processing;
Performing time sequence feature and frequency spectrum feature extraction on the first fault detection data set and the second fault detection data set after data preprocessing;
constructing a fault detection model according to the time sequence feature and the frequency spectrum feature extraction result, and storing the fault detection model in a cloud;
And completing the similar matching through the fault detection model.
And storing the first fault detection data set and the second fault detection data set to the cloud end so as to facilitate subsequent processing and analysis. And carrying out wavelet denoising and normalization processing on the data set stored in the cloud so as to improve the data quality and reliability. And performing time sequence feature and frequency spectrum feature extraction on the preprocessed data set to acquire key information and features in the data set. By combining the time sequence characteristics and the frequency spectrum characteristics, a wind power plant equipment fault detection model can be built by adopting a deep learning neural network, and the built fault detection model is stored in a cloud end so as to be convenient for subsequent use and access. And performing similarity matching by using a fault detection model stored in a cloud, comparing and analyzing the wind power plant equipment data with the model, and judging whether the equipment has an abnormality or a fault condition.
Further, the method further comprises:
performing data anomaly analysis in a data set on a target detection data set, and establishing data point anomalies, wherein the target detection data set is a first fault detection data set or a second fault detection data set after data preprocessing, and the data point anomalies are marked by anomaly values;
Acquiring a data time identifier of a target detection data set, and carrying out abnormal clustering on data according to the data time identifier and the data point abnormality to generate an abnormal clustering result;
And extracting the characteristic change of the abnormal clustering result to finish the time sequence characteristic extraction.
And carrying out data anomaly analysis on the preprocessed first fault detection data set or the preprocessed second fault detection data set, establishing data point anomalies and identifying the anomalies. Data time identifiers are extracted from the target detection dataset for subsequent data clustering and timing feature extraction. And carrying out abnormal clustering on the target detection data set by using the data time identification and the data point abnormal value. And classifying the data points with similar abnormal modes into the same category by using a clustering algorithm, and generating an abnormal clustering result. And extracting characteristic change of the abnormal clustering result. By comparing the trend of each abnormal cluster data point over time, time sequence features such as mean, variance, slope, etc. are extracted.
Further, the method further comprises:
Constructing a first abnormal sub-network according to the time sequence features and the frequency spectrum features extracted by the first fault detection data set, wherein a second abnormal sub-network is constructed according to the time sequence features and the frequency spectrum features extracted by the second fault detection data set;
Building a fault detection model by using the first abnormal sub-network and the second abnormal sub-network, and analyzing the fault data into a time sequence data set and calibrating fault characteristics after the fault data are sent to a cloud;
The network sensitivity of two sub-networks in the fault detection model is adjusted according to the calibration fault characteristics, and the time sequence data set is respectively input into the adjusted first abnormal sub-network and second abnormal sub-network;
and respectively obtaining output results of the first abnormal subnetwork and the second abnormal subnetwork, and completing similar matching based on the matching degree of the output results.
Timing and spectral features are extracted from the first set of fault detection data and used to construct a first abnormal subnetwork. Likewise, timing and spectral features are extracted from the second set of fault detection data and a second abnormal subnetwork is constructed. And combining the first abnormal subnetwork with the second abnormal subnetwork to build a fault detection model. After the fault data are sent to the cloud, the fault data are analyzed into a time sequence data set, and calibrated fault characteristics are extracted. And according to the calibrated fault characteristics, adjusting the network sensitivity of the two sub-networks in the fault detection model. And respectively inputting the adjusted first abnormal subnetwork and the second abnormal subnetwork into a time sequence data set, and respectively obtaining output results of the first abnormal subnetwork and the second abnormal subnetwork. And carrying out similar matching based on the matching degree of the output result, and judging whether the fault data is similar to the known abnormal mode.
And integrating the fault similar matching result, and generating a fault diagnosis result according to the integrated result, wherein the fault diagnosis result is provided with a maintenance scheme identifier.
And integrating the collected fault similarity matching results, and carrying out fault diagnosis based on the integrated results and combining the current fault phenomenon and information to obtain a fault diagnosis result.
Further, the method further comprises:
Establishing a maintenance scheme library, wherein the maintenance scheme library is constructed according to historical faults and fault maintenance result evaluation;
after the fault diagnosis result is generated, carrying out scheme matching of a maintenance scheme library according to the fault diagnosis result to obtain a maintenance scheme set;
Acquiring maintenance requirements of a user, and analyzing and establishing an evaluation fitness function according to the maintenance requirements;
And screening the maintenance scheme set through the evaluation fitness function, and establishing a maintenance scheme identification of the fault diagnosis result according to the screening result.
And collecting information of historical faults and fault maintenance results, including fault types, solutions, maintenance steps, required materials and the like, and arranging the information into a maintenance scheme library. And matching the generated fault diagnosis result with information in the maintenance scheme library so as to obtain a maintenance scheme set. The maintenance requirements of the user are known through questionnaires and the like, and an evaluation fitness function is established based on the maintenance requirements and is used for screening a maintenance scheme set. And screening the maintenance scheme set by using the evaluation fitness function, removing schemes which do not meet the requirements of users, and retaining the schemes which meet the requirements. And establishing a maintenance scheme identifier for the fault diagnosis result according to the screening result, for example, associating a maintenance scheme meeting the requirements with the fault diagnosis result so as to facilitate management.
Further, the method further comprises:
Obtaining an analysis result of maintenance requirements, wherein the analysis result comprises normalized proportions of speed characteristics, steady-state characteristics and load characteristics;
Establishing an evaluation fitness function of the corresponding characteristic according to the speed characteristic, the steady-state characteristic and the load characteristic respectively, and performing function weighting through the normalized proportion;
and screening the maintenance scheme set through the evaluation fitness function according to the weighted result.
After the maintenance requirements of the user are obtained, the requirements are analyzed, and analysis results of the maintenance requirements are obtained, wherein the analysis results comprise normalized proportions of speed characteristics, steady-state characteristics and load characteristics. The speed characteristics represent the requirements of the running speed of the equipment, the steady-state characteristics represent the performance requirements of the equipment in a steady state, the load characteristics represent the working requirements of the equipment under different load conditions, and the like. And respectively establishing evaluation fitness functions of the corresponding features aiming at the speed features, the steady-state features and the load features. And weighting the evaluation fitness functions of the speed feature, the steady-state feature and the load feature according to the normalization proportion, specifically multiplying the evaluation fitness function of each feature by the corresponding normalization proportion to obtain the weighted fitness function. And screening the maintenance scheme set by using the weighted fitness function. For each maintenance scheme, its evaluation value under the weighted fitness function is calculated. According to the magnitude of the evaluation value, an appropriate maintenance scheme is selected and retained.
Further, the method further comprises:
judging whether the fault diagnosis result meets a preset abnormal threshold value or not;
if the preset abnormal threshold cannot be met, generating a continuous supervision instruction, wherein the continuous supervision instruction is provided with a sensitive mark;
And continuously monitoring the equipment of the wind power plant through the continuous supervision instruction.
Comparing the diagnosis result with a preset abnormal threshold value, judging whether the preset abnormal threshold value is met, and if the fault diagnosis result does not meet the preset abnormal threshold value, namely exceeds the allowed normal range, generating a continuous supervision instruction with a sensitive mark by the system so as to ensure the safety and confidentiality of the instruction. The continuous supervision instruction is a continuous monitoring and guiding mode aiming at the equipment, mainly aims at continuously monitoring the running state of the equipment and providing timely guidance and support so as to ensure that the equipment is in a normal working range and performs necessary repair and adjustment when required. After the equipment of the wind power plant receives the continuous supervision instruction, corresponding operation and adjustment can be performed according to the instruction. Meanwhile, the equipment is continuously monitored to ensure that faults are repaired in time or the state of the equipment is adjusted and kept in a normal working range.
In summary, the embodiment of the application has at least the following technical effects:
First, a device dataset of a wind farm is established, comprising device attribute data and device operational data. Next, a first failure detection dataset is constructed using big data matching techniques with the device attribute data as matching data. And (3) analyzing and comparing the equipment attribute data to find a similar fault sample, so as to realize the primary detection of equipment faults. Meanwhile, on the basis of the equipment working data, the equipment working characteristics are extracted, and a second fault detection data set is constructed by utilizing a big data matching technology. Therefore, the equipment working data can be compared with known fault samples, and the accuracy of fault detection is further improved. And after the equipment of the wind power plant sends out the early warning signal, extracting wind power plant equipment data in a preset time window of the early warning signal. And sending the data to the cloud for processing as fault data. And at the cloud end, performing fault similarity matching of the first fault detection data set and the second fault detection data set. By matching the fault data with known fault samples, similar fault conditions are found. And finally, integrating the fault similarity matching result, and generating a fault diagnosis result according to the integrated result. The technical problems of poor reliability and efficiency of fault diagnosis in the prior art are solved, and the technical effect of improving the accuracy and efficiency of fault diagnosis of wind power plant equipment is achieved.
Example two
Based on the same inventive concept as the intelligent remote electric field fault diagnosis method in the foregoing embodiments, as shown in fig. 2, the present application provides an intelligent remote electric field fault diagnosis system, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein, the system includes:
a data set establishing module 11, where the data set establishing module 11 is configured to establish a device data set of a wind farm, where the device data set stores device attribute data and device working data;
A first matching module 12, where the first matching module 12 is configured to construct a first fault detection data set by big data matching with device attribute data in the device data set as matching data;
The second matching module 13 is used for extracting equipment working characteristics according to the equipment working data in the equipment data set, and constructing a second fault detection data set through big data matching;
The extraction module 14 is used for extracting wind power plant equipment data in a preset time window of the early warning signal after the equipment of the wind power plant sends the early warning signal;
The third matching module 15 is configured to send the wind farm equipment data to a cloud as fault data, and perform fault similarity matching of the first fault detection data set and the second fault detection data set;
the fault diagnosis module 16 is configured to integrate the fault similarity matching result and generate a fault diagnosis result according to the integrated result, where the fault diagnosis result carries a maintenance scheme identifier.
Further, the third matching module 15 is configured to perform the following method:
storing the first fault detection data set and the second fault detection data set to a cloud;
respectively executing data preprocessing on the first fault detection data set and the second fault detection data set, wherein the data preprocessing comprises data wavelet denoising and data normalization processing;
Performing time sequence feature and frequency spectrum feature extraction on the first fault detection data set and the second fault detection data set after data preprocessing;
constructing a fault detection model according to the time sequence feature and the frequency spectrum feature extraction result, and storing the fault detection model in a cloud;
And completing the similar matching through the fault detection model.
Further, the third matching module 15 is configured to perform the following method:
performing data anomaly analysis in a data set on a target detection data set, and establishing data point anomalies, wherein the target detection data set is a first fault detection data set or a second fault detection data set after data preprocessing, and the data point anomalies are marked by anomaly values;
Acquiring a data time identifier of a target detection data set, and carrying out abnormal clustering on data according to the data time identifier and the data point abnormality to generate an abnormal clustering result;
And extracting the characteristic change of the abnormal clustering result to finish the time sequence characteristic extraction.
Further, the third matching module 15 is configured to perform the following method:
Constructing a first abnormal sub-network according to the time sequence features and the frequency spectrum features extracted by the first fault detection data set, wherein a second abnormal sub-network is constructed according to the time sequence features and the frequency spectrum features extracted by the second fault detection data set;
Building a fault detection model by using the first abnormal sub-network and the second abnormal sub-network, and analyzing the fault data into a time sequence data set and calibrating fault characteristics after the fault data are sent to a cloud;
The network sensitivity of two sub-networks in the fault detection model is adjusted according to the calibration fault characteristics, and the time sequence data set is respectively input into the adjusted first abnormal sub-network and second abnormal sub-network;
and respectively obtaining output results of the first abnormal subnetwork and the second abnormal subnetwork, and completing similar matching based on the matching degree of the output results.
Further, the fault diagnosis module 16 is configured to perform the following method:
Establishing a maintenance scheme library, wherein the maintenance scheme library is constructed according to historical faults and fault maintenance result evaluation;
after the fault diagnosis result is generated, carrying out scheme matching of a maintenance scheme library according to the fault diagnosis result to obtain a maintenance scheme set;
Acquiring maintenance requirements of a user, and analyzing and establishing an evaluation fitness function according to the maintenance requirements;
And screening the maintenance scheme set through the evaluation fitness function, and establishing a maintenance scheme identification of the fault diagnosis result according to the screening result.
Further, the fault diagnosis module 16 is configured to perform the following method:
Obtaining an analysis result of maintenance requirements, wherein the analysis result comprises normalized proportions of speed characteristics, steady-state characteristics and load characteristics;
Establishing an evaluation fitness function of the corresponding characteristic according to the speed characteristic, the steady-state characteristic and the load characteristic respectively, and performing function weighting through the normalized proportion;
and screening the maintenance scheme set through the evaluation fitness function according to the weighted result.
Further, the fault diagnosis module 16 is configured to perform the following method:
judging whether the fault diagnosis result meets a preset abnormal threshold value or not;
if the preset abnormal threshold cannot be met, generating a continuous supervision instruction, wherein the continuous supervision instruction is provided with a sensitive mark;
And continuously monitoring the equipment of the wind power plant through the continuous supervision instruction.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. An intelligent remote electric field fault diagnosis method, characterized in that the method comprises the following steps:
Establishing an equipment data set of a wind power plant, wherein equipment attribute data and equipment working data are stored in the equipment data set;
using the equipment attribute data in the equipment data set as matching data, and constructing a first fault detection data set through big data matching;
Extracting equipment working characteristics by using equipment working data in the equipment data set, and constructing a second fault detection data set through big data matching;
After the equipment of the wind farm sends out the early warning signal, extracting wind farm equipment data in a preset time window of the early warning signal;
taking the wind farm equipment data as fault data, sending the fault data to a cloud, and executing fault similarity matching of the first fault detection data set and the second fault detection data set;
And integrating the fault similar matching result, and generating a fault diagnosis result according to the integrated result, wherein the fault diagnosis result is provided with a maintenance scheme identifier.
2. The method of claim 1, wherein the sending the wind farm device data as fault data to a cloud performs fault affinity matching of the first and second fault detection data sets, further comprising:
storing the first fault detection data set and the second fault detection data set to a cloud;
respectively executing data preprocessing on the first fault detection data set and the second fault detection data set, wherein the data preprocessing comprises data wavelet denoising and data normalization processing;
Performing time sequence feature and frequency spectrum feature extraction on the first fault detection data set and the second fault detection data set after data preprocessing;
constructing a fault detection model according to the time sequence feature and the frequency spectrum feature extraction result, and storing the fault detection model in a cloud;
And completing the similar matching through the fault detection model.
3. The method of claim 2, wherein the method further comprises:
performing data anomaly analysis in a data set on a target detection data set, and establishing data point anomalies, wherein the target detection data set is a first fault detection data set or a second fault detection data set after data preprocessing, and the data point anomalies are marked by anomaly values;
Acquiring a data time identifier of a target detection data set, and carrying out abnormal clustering on data according to the data time identifier and the data point abnormality to generate an abnormal clustering result;
And extracting the characteristic change of the abnormal clustering result to finish the time sequence characteristic extraction.
4. The method of claim 2, wherein the method further comprises:
Constructing a first abnormal sub-network according to the time sequence features and the frequency spectrum features extracted by the first fault detection data set, wherein a second abnormal sub-network is constructed according to the time sequence features and the frequency spectrum features extracted by the second fault detection data set;
Building a fault detection model by using the first abnormal sub-network and the second abnormal sub-network, and analyzing the fault data into a time sequence data set and calibrating fault characteristics after the fault data are sent to a cloud;
The network sensitivity of two sub-networks in the fault detection model is adjusted according to the calibration fault characteristics, and the time sequence data set is respectively input into the adjusted first abnormal sub-network and second abnormal sub-network;
and respectively obtaining output results of the first abnormal subnetwork and the second abnormal subnetwork, and completing similar matching based on the matching degree of the output results.
5. The method of claim 1, wherein the method further comprises:
Establishing a maintenance scheme library, wherein the maintenance scheme library is constructed according to historical faults and fault maintenance result evaluation;
after the fault diagnosis result is generated, carrying out scheme matching of a maintenance scheme library according to the fault diagnosis result to obtain a maintenance scheme set;
Acquiring maintenance requirements of a user, and analyzing and establishing an evaluation fitness function according to the maintenance requirements;
And screening the maintenance scheme set through the evaluation fitness function, and establishing a maintenance scheme identification of the fault diagnosis result according to the screening result.
6. The method of claim 5, wherein the method further comprises:
Obtaining an analysis result of maintenance requirements, wherein the analysis result comprises normalized proportions of speed characteristics, steady-state characteristics and load characteristics;
Establishing an evaluation fitness function of the corresponding characteristic according to the speed characteristic, the steady-state characteristic and the load characteristic respectively, and performing function weighting through the normalized proportion;
and screening the maintenance scheme set through the evaluation fitness function according to the weighted result.
7. The method of claim 1, wherein the method further comprises:
judging whether the fault diagnosis result meets a preset abnormal threshold value or not;
if the preset abnormal threshold cannot be met, generating a continuous supervision instruction, wherein the continuous supervision instruction is provided with a sensitive mark;
And continuously monitoring the equipment of the wind power plant through the continuous supervision instruction.
8. An intelligent remote electric field fault diagnosis system, the system comprising:
the system comprises a data set establishing module, a data set generating module and a data set generating module, wherein the data set establishing module is used for establishing a device data set of a wind power plant, and device attribute data and device working data are stored in the device data set;
The first matching module is used for constructing a first fault detection data set through big data matching by taking the equipment attribute data in the equipment data set as matching data;
the second matching module is used for extracting equipment working characteristics according to the equipment working data in the equipment data set and constructing a second fault detection data set through big data matching;
The extraction module is used for extracting wind power plant equipment data in a preset time window of the early warning signal after equipment of the wind power plant sends the early warning signal;
the third matching module is used for taking the wind power plant equipment data as fault data, sending the fault data to the cloud, and executing fault similarity matching of the first fault detection data set and the second fault detection data set;
The fault diagnosis module is used for integrating the fault similar matching results and generating a fault diagnosis result according to the integrated results, wherein the fault diagnosis result is provided with a maintenance scheme identifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410157331.XA CN117932358A (en) | 2024-02-04 | 2024-02-04 | Intelligent remote electric field fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410157331.XA CN117932358A (en) | 2024-02-04 | 2024-02-04 | Intelligent remote electric field fault diagnosis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117932358A true CN117932358A (en) | 2024-04-26 |
Family
ID=90757389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410157331.XA Pending CN117932358A (en) | 2024-02-04 | 2024-02-04 | Intelligent remote electric field fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117932358A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118315037A (en) * | 2024-06-11 | 2024-07-09 | 江苏盖睿健康科技有限公司 | Fault diagnosis method and system for self-help physical examination machine |
-
2024
- 2024-02-04 CN CN202410157331.XA patent/CN117932358A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118315037A (en) * | 2024-06-11 | 2024-07-09 | 江苏盖睿健康科技有限公司 | Fault diagnosis method and system for self-help physical examination machine |
| CN118315037B (en) * | 2024-06-11 | 2024-10-22 | 江苏盖睿健康科技有限公司 | Fault diagnosis method and system for self-help physical examination machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460618A (en) | A kind of rolling bearing remaining life on-line prediction method and system | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN113657221B (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
| CN112179691B (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
| CN105626502B (en) | Plunger pump health evaluating method based on wavelet packet and laplacian eigenmaps | |
| CN109492790A (en) | Wind turbines health control method based on neural network and data mining | |
| CN114580666A (en) | Multi-mode fusion motor intelligent maintenance system | |
| CN110297207A (en) | Method for diagnosing faults, system and the electronic device of intelligent electric meter | |
| CN109034076A (en) | A kind of automatic clustering method and automatic cluster system of mechanical fault signals | |
| CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
| CN115409131A (en) | Production line abnormity detection method based on SPC process control system | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
| CN111046790A (en) | Pump bearing fault diagnosis method | |
| CN117782198B (en) | Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture | |
| CN118114019A (en) | Automatic identification method and system for power distribution network topology based on data analysis | |
| CN112381130A (en) | Cluster analysis-based power distribution room multivariate data anomaly detection method | |
| CN115186935B (en) | Electromechanical device nonlinear fault prediction method and system | |
| CN117993562A (en) | Wind turbine generator system fault prediction method and system based on artificial intelligent big data analysis | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN113671287B (en) | Intelligent detection method, system and readable storage medium for power grid automation terminal | |
| CN116816617A (en) | Wind turbine running state monitoring method | |
| CN116502043A (en) | Finish rolling motor state analysis method based on isolated forest algorithm | |
| Zhao et al. | Health indicator selection and health assessment of rolling element bearing |
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 |