CN117436019A - Fault identification method and device of sensing equipment - Google Patents
Fault identification method and device of sensing equipment Download PDFInfo
- Publication number
- CN117436019A CN117436019A CN202311459062.4A CN202311459062A CN117436019A CN 117436019 A CN117436019 A CN 117436019A CN 202311459062 A CN202311459062 A CN 202311459062A CN 117436019 A CN117436019 A CN 117436019A
- Authority
- CN
- China
- Prior art keywords
- result
- performance data
- fault
- clustering
- acquiring
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000000737 periodic effect Effects 0.000 claims abstract description 14
- 238000007621 cluster analysis Methods 0.000 claims abstract description 12
- 238000012800 visualization Methods 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 24
- 230000009467 reduction Effects 0.000 claims description 21
- 238000002372 labelling Methods 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 21
- 238000010586 diagram Methods 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003442 weekly effect Effects 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
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- 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
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a fault identification method and device of sensing equipment, wherein the method comprises the following steps: acquiring performance data of the sensing equipment in a period to be measured; performing cluster analysis on the performance data to obtain a cluster result; performing modal analysis on the clustering result to obtain a modal analysis result; performing visualization processing on the clustering result to generate a clustering image; identifying the clustered images to obtain a fault identification result; and acquiring periodic information of the faults based on the fault identification result and the modal analysis result. The invention can promote the comprehensiveness of fault detection.
Description
Technical Field
The present invention relates to the field of fault detection technologies, and in particular, to a fault identification method and apparatus for a sensing device.
Background
The problems of abnormal fault detection of the light CT equipment in the existing soft direct current converter valve system are as follows:
firstly, the traditional threshold value alarming mode is adopted by the existing light CT detection method, so that the detection timeliness is poor;
secondly, through individual early faults or abnormal faults in a certain group of optical CT components, the monitoring faults of the whole converter valve equipment are easy to cause false alarm;
thirdly, the operation rule of the optical CT is not carefully excavated under the influence of the operation states of the environment and the field equipment at present.
Therefore, the technical problem that the fault detection of the sensing device in the prior art is not comprehensive is needed to be solved.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a fault identification method and equipment of sensing equipment, which are used for solving the technical problem that the fault detection of the sensing equipment in the prior art is not comprehensive enough.
The embodiment of the invention provides a fault identification method of sensing equipment, which comprises the following steps:
acquiring performance data of the sensing equipment in a period to be measured;
performing cluster analysis on the performance data to obtain a cluster result;
performing modal analysis on the clustering result to obtain a modal analysis result;
performing visualization processing on the clustering result to generate a clustering image;
identifying the clustered images to obtain a fault identification result;
and acquiring periodic information of the faults based on the fault identification result and the modal analysis result.
Optionally, in an embodiment of the present invention, acquiring performance data of the sensing device in a period to be measured includes: acquiring initial performance data related to the sensing device in the period to be measured; carrying out noise reduction treatment on the initial performance data to obtain initial performance data after the noise reduction treatment; and carrying out standardization processing on the initial performance data after the noise reduction processing to obtain the performance data.
Optionally, in an embodiment of the present invention, identifying the clustered images to obtain a fault identification result includes: inputting the clustered images into a trained neural network model, and outputting the fault recognition result, wherein the neural network model is obtained through sample set training, and the sample set comprises: and labeling the history clustered images.
Optionally, in an embodiment of the present invention, the method further includes: labeling the historical clustering results related to faults based on the actual fault logs of the sensing equipment, and acquiring labeled historical clustering images;
the embodiment of the invention also provides a fault recognition device of the sensing equipment, which comprises:
the first acquisition module is used for acquiring performance data of the sensing equipment in a period to be measured;
the cluster analysis module is used for carrying out cluster analysis on the performance data to obtain a cluster result;
the modal analysis module is used for carrying out modal analysis on the clustering result to obtain a modal analysis result;
the visualization module is used for carrying out visualization processing on the clustering result to generate a clustering image;
the identification module is used for identifying the clustered images and acquiring a fault identification result;
and the second acquisition module is used for acquiring periodic information of the faults based on the fault identification result and the modal analysis result.
Optionally, in an embodiment of the present invention, the first obtaining module includes: a first acquisition unit for acquiring initial performance data related to the sensing device within the period to be measured; the noise reduction unit is used for carrying out noise reduction treatment on the initial performance data and acquiring the initial performance data after the noise reduction treatment; and the normalization unit is used for performing normalization processing on the initial performance data after the noise reduction processing to obtain the performance data.
Optionally, in an embodiment of the present invention, the identification module includes: the input unit is used for inputting the clustered images into a trained neural network model and outputting the fault recognition result, wherein the neural network model is obtained through sample set training, and the sample set comprises: and labeling the history clustered images.
Optionally, in an embodiment of the present invention, the method further includes: and the labeling unit is used for labeling the historical clustering results relevant to faults based on the actual fault logs of the sensing equipment, and acquiring labeled historical clustering images.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the fault identification method of the sensing equipment when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the fault identification method of the sensing device when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program realizes the fault identification method of the sensing device when being executed by a processor.
According to the fault identification method provided by the embodiment of the invention, the performance data of the sensing equipment in the period to be detected is obtained; performing cluster analysis on the performance data to obtain a cluster result; performing modal analysis on the clustering result to obtain a modal analysis result; performing visualization processing on the clustering result to generate a clustering image; identifying the clustered images to obtain a fault identification result; and acquiring periodic information of the faults based on the fault identification result and the modal analysis result. The comprehensiveness of fault detection for the sensing equipment 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. In the drawings:
FIG. 1 is a flow chart of a fault identification method of a sensing device in an embodiment of the invention;
FIG. 2 is a schematic diagram of corresponding quadrants of a model analysis result according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of feature extraction and clustering results in an embodiment of the present invention;
FIG. 4 is a flow chart of data preprocessing in an embodiment of the invention;
FIG. 5 is a flow chart of a preferred method of fault identification of a sensing device in an embodiment of the present invention;
FIG. 6 is a schematic diagram of a fault recognition device of a sensing apparatus according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Fig. 1 is a flowchart of a fault identification method of a sensing device according to an embodiment of the present invention, where an execution body of the fault identification method of the sensing device provided by the embodiment of the present invention includes, but is not limited to, a computer. The method shown in the figure comprises the following steps:
step S101, acquiring performance data of the sensing equipment in a period to be measured;
in the above steps, the performance data of the sensing device in the time period to be measured is obtained, and after the performance data is obtained, the data is cleaned, denoised to extract the data, and it should be noted that the performance data includes but is not limited to: current, vibration data.
Step S102, performing cluster analysis on the performance data to obtain a cluster result;
in the above steps, the performance data is subjected to an unsupervised clustering analysis, and the clustering algorithm includes, but is not limited to: OPTICS algorithm. Specifically, an unsupervised clustering algorithm (e.g., K-means clustering, DBSCAN, OPTICS, etc.) may be used to sample the data curve of the light CT every 8 hours for unsupervised clustering. The space-time characteristic image data are divided into different clustering groups, because a plurality of light CT exist time and space characteristics in a flexible direct current converter valve system, and in order to capture the change of space mode distribution with time in the light CT, a dynamic space-time clustering method based on an OPTICS idea is provided, firstly, the distance between each point in space is calculated in a certain time window, then a plurality of core positions are found, then the belonging types of other uncertain positions are gradually judged, so that the space mode division of the data in the specific time window is realized, and then the change of the space mode with time is described through a sliding time window. A framework for detecting anomalies in dynamic regions is proposed, wherein the sparsity and the heterogeneity of data are reduced by dynamically dividing the regions, and then anomaly metrics of different regions are calculated to determine whether anomalies occur.
Step S103, carrying out modal analysis on the clustering result to obtain a modal analysis result;
in the above step, the clustering result is subjected to modal analysis to obtain periodic performance of the clustering result, for example, in which period a certain clustering result periodically appears.
Specifically, the calculation of the correlation coefficients is provided by the corr function in pandas, which by default calculates pearson correlation coefficients, the calculated spearman and kendel coefficients can be specified by the method parameters. The consistency index is considered herein to be the average of the correlation coefficients over the period t.
Wherein (1)>Corr (x, y) is averaged over a time period, T is time.
Step one, according to the sensor consistency index, SI (i), i=1, 2, …, S, we note that the sensor consistency index has a threshold value thre_si:
a) If SI (i) < thre_SI, the first sensor is an anomaly sensor;
b) If SI (i) is more than or equal to thre_SI, the first sensor is a normal sensor;
step two, calculating the sample ratio CRI (C) of all clusters, c=1, 2, …, C:
a) If CRI (c) > thre_cri, the second class corresponds to the primary modality;
b) If CRI (c) is less than or equal to thre_CRI, the second class corresponds to the secondary mode;
3) The CPI (c, w) and CSI (c) indices for all clusters are calculated and the [ (max) CPI (c, w) -thre_CPI, CSI(s) -thre_CSI ] profiles are plotted, and the classes that appear in different quadrants will be determined to belong to different modalities:
a) The first quadrant corresponds to the light CT global periodic mode;
b) The second quadrant corresponds to a light CT global contingency modality;
c) The third quadrant corresponds to a light CT local contingency mode;
d) The fourth quadrant corresponds to the light CT local periodic modality.
If CPI (c, w) is more than or equal to thre_ cri, the method indicates that the class shows obvious time periodicity on a time period (such as one day or one week) and corresponds to the periodical mode of the light CT;
if CPI (c, w). Ltoreq.thre_ cri, this indicates that the class will only appear in a relatively small amount of time, corresponding to the contingent modality.
If CSI(s) is less than or equal to thre_csi, the class is considered to reflect the overall characteristic and corresponds to the overall mode, otherwise, the class is considered to be the local mode.
Fig. 2 is a schematic diagram of a corresponding quadrant of a model analysis result in an embodiment of the present invention, as shown in fig. 2, the periodicity of the class c over the entire data set is evaluated, i.e. the periodicity index CPI of the class c for the week w, where the formula of CPI is expressed as:
and, in addition, the processing unit,representing the periodic index of the c-th class of sensor i occurrence over the week w. For sensor i, I note that the number of times that class c appears on week w (i.e., fixed appears on week w, w=1, 2, …, 7) in the clustering result is(w)，cpi i,c (w) (i.e., duty cycle) represents class c in sensor iIs a periodic manifestation of (c).
The primary modes represent in the time dimension, most of the time running in these primary modes, while the secondary modes refer to only a fraction of the time running in these secondary modes; "Global" means the modality in which most sensors will appear, whereas "conversely" means that only a few joints are operating in that modality.
Step S104, carrying out visualization processing on the clustering result to generate a clustered image;
in the above steps, the clustering result is visualized, fig. 3 is a schematic diagram of feature extraction and clustering result in the embodiment of the present invention, and as shown in fig. 3, data are clustered into data clusters with different color shades, and two-dimensionally arranged on coordinate axes.
Step S105, identifying the clustered images and obtaining a fault identification result;
in the step, the clustered images are input into a trained deep learning model for identifying the clustered images, so that a fault identification result is output, and the purpose of detecting faults is achieved. Image detection algorithms include, but are not limited to: faster R-CNN convolutional neural network algorithm.
And step S106, acquiring periodic information of the faults based on the fault identification result and the modal analysis result.
In the above steps, the fault recognition result and the modal analysis result are combined to obtain the fault information of the sensing device and the periodicity of the fault information, for example, whether the fault occurs in the period of the sensing device corresponding to the clustering result and the periodicity of the fault occurrence, that is, in which period the fault occurs frequently, specifically, whether the data point in the clustering result corresponding to the fault recognition result is abnormal is judged, taking the abnormality/fault as an example, and then the periodicity evaluation result of the data point by the modal analysis result is used to obtain the periodicity evaluation of the fault point, that is, what periodicity rule the fault point is abnormal, and the fault point generally corresponds to a certain period of a certain sensing device, the periodicity result of the output fault information is whether the sensing device is abnormal in the period, and the abnormality often occurs in a weekly period.
Compared with the technical scheme in the prior art, the embodiment of the invention has the advantages that the performance data of the sensing equipment in the period to be measured are obtained; performing cluster analysis on the performance data to obtain a cluster result; performing modal analysis on the clustering result to obtain a modal analysis result; performing visualization processing on the clustering result to generate a clustering image; identifying the clustered images to obtain a fault identification result; based on the fault identification result and the modal analysis result, the periodic information of the fault is obtained, and the comprehensiveness of fault detection can be improved, so that the technical problem that the fault detection of the sensing equipment in the prior art is not complete enough is solved.
As one embodiment of the present invention, acquiring performance data of a sensing device during a period to be measured includes: acquiring initial performance data related to the sensing device in the period to be measured; carrying out noise reduction treatment on the initial performance data to obtain initial performance data after the noise reduction treatment; and carrying out standardization processing on the initial performance data after the noise reduction processing to obtain the performance data.
In the above alternative embodiment, fig. 4 is a flowchart of data preprocessing in the embodiment of the present invention, as shown in fig. 4, the data is first acquired and fused, and intelligent screening and weight evaluation of monitoring indexes, high-speed processing of massive data, and accurate extraction of deep essential features of an optical CT state are required to be solved. It should be noted that noise is random error and variance of variables, and is error between observation points and real points, and a common processing method includes two steps of carrying out box division operation on data, equally-frequency or equally-width box division, then using average number, median or boundary value of each box to replace all numbers in the box, playing a role of smoothing data, establishing a regression model of the variables and predicted variables, and according to regression coefficients and predicted variables, inverting approximation values of the independent variables to obtain cleaned performance data.
As one embodiment of the present invention, identifying the clustered images to obtain a fault identification result includes: inputting the clustered images into a trained neural network model, and outputting the fault recognition result, wherein the neural network model is obtained through sample set training, and the sample set comprises: and labeling the history clustered images.
In the above alternative embodiment, training the neural network model by using the noted historical cluster pattern as a sample set to obtain a fault detection model for the clustered image, and then inputting the clustered image into the trained fault detection model to output a fault detection result, where the neural network model includes but is not limited to: faster-RCNN.
As an embodiment of the present invention, further comprising: and marking the historical clustering results relevant to faults based on the actual fault logs of the sensing equipment, and acquiring marked historical clustering images.
FIG. 5 is a flowchart of a fault identification method of a preferred sensing device in an embodiment of the present invention, as shown in FIG. 5, firstly performing data cleaning, then performing unsupervised clustering on the data, then performing analysis labeling on historical data to train a fault detection model, performing fault detection by using the trained model, and finally matching a fault solution through a historical fault database based on a fault detection result.
Specifically, the fault description information is extracted through the output fault detection result, and the same or similar fault solutions are searched in the historical fault database through the fault description information to obtain the fault solutions, so that the faults are solved.
Aiming at the characteristics of the space-time characteristics of the light CT, the scheme adopts an unsupervised method to perform data mining clustering so as to find the running mode of the light CT. Compared with the traditional threshold value alarming mode, the method greatly improves timeliness of light CT detection, captures abnormal states more quickly, alarms in real time and is beneficial to reducing potential loss and risk.
By converting the result of the unsupervised clustering mode into an image form, the scheme presents the data rule in a more visual way. Compared with the traditional data points, the image can better reflect the change and trend of the equipment state, so that an operator can more easily understand and interpret the data, and the operation state of the equipment can be better mastered.
The scheme adopts an image recognition method to monitor the real-time light CT state, thereby realizing the real-time monitoring of the equipment state. Compared with the traditional method, the scheme can be used for accurately knowing the running state of the light CT, timely detecting equipment abnormality and potential problems, avoiding the condition of missing report and false report and improving the accuracy and reliability of monitoring.
Through the application of the unsupervised clustering and image recognition technology, the technical scheme of the invention can be used for deeply knowing the operation rule and the performance change of the optical CT. The method provides more valuable information for project managers and related personnel of power industry companies, is beneficial to making more reasonable equipment maintenance and management decisions, and improves the stability and reliability of equipment.
The technical scheme of the invention brings a plurality of advantages and benefits in the field of optical CT detection. By the application of an unsupervised method and an image recognition technology, the device state monitoring and abnormality detection are realized more quickly, accurately and in real time, and the production efficiency of power industry companies and the stability of device operation are improved.
Fig. 6 is a schematic diagram of a fault recognition device of a sensing device according to an embodiment of the present invention, where the embodiment of the present invention further provides a fault recognition device of a sensing device, and a module in the figure includes:
a first obtaining module 61, configured to obtain performance data of the sensing device in a period to be measured;
the cluster analysis module 62 is configured to perform cluster analysis on the performance data to obtain a cluster result;
the modal analysis module 63 is configured to perform modal analysis on the clustering result, and obtain a modal analysis result;
the visualization module 64 is configured to perform visualization processing on the clustering result to generate a clustered image;
the identifying module 65 is configured to identify the clustered images, and obtain a fault identification result;
the second obtaining module 66 is configured to obtain periodic information of the fault based on the fault identification result and the modal analysis result.
In an embodiment of the present invention, the first obtaining module includes: a first acquisition unit for acquiring initial performance data related to the sensing device within the period to be measured; the noise reduction unit is used for carrying out noise reduction treatment on the initial performance data and acquiring the initial performance data after the noise reduction treatment; and the normalization unit is used for performing normalization processing on the initial performance data after the noise reduction processing to obtain the performance data.
In an embodiment of the present invention, the identification module includes: the input unit is used for inputting the clustered images into a trained neural network model and outputting the fault recognition result, wherein the neural network model is obtained through sample set training, and the sample set comprises: and labeling the history clustered images.
In an embodiment of the present invention, the method further includes: and the labeling unit is used for labeling the historical clustering results relevant to faults based on the actual fault logs of the sensing equipment, and acquiring labeled historical clustering images.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the fault identification method of the sensing equipment when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the fault identification method of the sensing device when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program realizes the fault identification method of the sensing device when being executed by a processor.
Fig. 7 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, as shown in fig. 7, where the electronic device includes: a processor (processor) 701, a memory (memory) 702, and a bus 703.
The processor 701 and the memory 702 perform communication with each other through the bus 703.
The processor 701 is configured to invoke the program instructions in the memory 702 to execute the methods provided in the above method embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A method for fault identification of a sensing device, comprising:
acquiring performance data of the sensing equipment in a period to be measured;
performing cluster analysis on the performance data to obtain a cluster result;
performing modal analysis on the clustering result to obtain a modal analysis result;
performing visualization processing on the clustering result to generate a clustering image;
identifying the clustered images to obtain a fault identification result;
and acquiring periodic information of the faults based on the fault identification result and the modal analysis result.
2. The method of claim 1, wherein obtaining performance data of the sensing device over the period of time to be measured comprises:
acquiring initial performance data of the sensing equipment in the period to be measured;
carrying out noise reduction treatment on the initial performance data to obtain initial performance data after the noise reduction treatment;
and carrying out standardization processing on the initial performance data after the noise reduction processing to obtain the performance data.
3. The method of claim 1, wherein identifying the clustered images to obtain a failure recognition result comprises:
inputting the clustered images into a trained neural network model, and outputting the fault recognition result, wherein the neural network model is obtained through sample set training, and the sample set comprises: and labeling the history clustered images.
4. A method as recited in claim 3, further comprising:
and marking the historical clustering results relevant to faults based on the actual fault logs of the sensing equipment, and acquiring marked historical clustering images.
5. A fault recognition device for a sensing apparatus, comprising:
the first acquisition module is used for acquiring performance data of the sensing equipment in a period to be measured;
the cluster analysis module is used for carrying out cluster analysis on the performance data to obtain a cluster result;
the modal analysis module is used for carrying out modal analysis on the clustering result to obtain a modal analysis result;
the visualization module is used for carrying out visualization processing on the clustering result to generate a clustering image;
the identification module is used for identifying the clustered images and acquiring a fault identification result;
and the second acquisition module is used for acquiring periodic information of the faults based on the fault identification result and the modal analysis result.
6. The apparatus of claim 5, wherein the first acquisition module comprises:
a first obtaining unit, configured to obtain initial performance data of the sensing device in the period to be measured;
the noise reduction unit is used for carrying out noise reduction treatment on the initial performance data and acquiring the initial performance data after the noise reduction treatment;
and the normalization unit is used for performing normalization processing on the initial performance data after the noise reduction processing to obtain the performance data.
7. The apparatus of claim 5, wherein the identification module comprises:
the input unit is used for inputting the clustered images into a trained neural network model and outputting the fault recognition result, wherein the neural network model is obtained through sample set training, and the sample set comprises: and labeling the history clustered images.
8. The apparatus as recited in claim 7, further comprising:
and the labeling unit is used for labeling the historical clustering results relevant to faults based on the actual fault logs of the sensing equipment, and acquiring labeled historical clustering images.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 4 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311459062.4A CN117436019A (en) | 2023-11-03 | 2023-11-03 | Fault identification method and device of sensing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311459062.4A CN117436019A (en) | 2023-11-03 | 2023-11-03 | Fault identification method and device of sensing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117436019A true CN117436019A (en) | 2024-01-23 |
Family
ID=89549563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311459062.4A Pending CN117436019A (en) | 2023-11-03 | 2023-11-03 | Fault identification method and device of sensing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117436019A (en) |
-
2023
- 2023-11-03 CN CN202311459062.4A patent/CN117436019A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schlechtingen et al. | Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: System description | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN106780121B (en) | Power consumption abnormity identification method based on power consumption load mode analysis | |
| CN113128561A (en) | Machine tool bearing fault diagnosis method | |
| EP2442288A1 (en) | Device abnormality monitoring method and system | |
| US20120304008A1 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
| CN112179691B (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
| CN112414694B (en) | Equipment multistage abnormal state identification method and device based on multivariate state estimation technology | |
| CN111737909A (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN111583592B (en) | Experimental environment safety early warning method based on multidimensional convolution neural network | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN113339204A (en) | Wind driven generator fault identification method based on hybrid neural network | |
| CN114519923A (en) | Intelligent diagnosis and early warning method and system for power plant | |
| Kannan et al. | Nominal features-based class specific learning model for fault diagnosis in industrial applications | |
| CN115526515A (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN116520806A (en) | Intelligent fault diagnosis system and method for industrial system | |
| CN113574480A (en) | Apparatus for predicting equipment damage | |
| CN113919540A (en) | Method for monitoring running state of production process and related equipment | |
| CN113283546A (en) | Furnace condition abnormity alarm method and system of heating furnace integrity management centralized control device | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN117436019A (en) | Fault identification method and device of sensing equipment | |
| Jastrzebska et al. | Measuring wind turbine health using fuzzy-concept-based drifting models | |
| CN115600695A (en) | Fault diagnosis method of metering equipment | |
| CN112228042B (en) | Method for judging working condition similarity of pumping well based on cloud edge cooperative computing | |
| CN116956089A (en) | Training method and detection method for temperature anomaly detection model of electrical equipment |
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 |