CN116295847A - Power equipment fault diagnosis system and diagnosis method - Google Patents
Power equipment fault diagnosis system and diagnosis method Download PDFInfo
- Publication number
- CN116295847A CN116295847A CN202310093839.3A CN202310093839A CN116295847A CN 116295847 A CN116295847 A CN 116295847A CN 202310093839 A CN202310093839 A CN 202310093839A CN 116295847 A CN116295847 A CN 116295847A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- fault diagnosis
- growth
- data
- configuring
- 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 55
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 5
- 238000007405 data analysis Methods 0.000 claims abstract description 4
- 238000012423 maintenance Methods 0.000 claims description 33
- 230000012010 growth Effects 0.000 claims description 31
- 230000011218 segmentation Effects 0.000 claims description 16
- 230000004913 activation Effects 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 description 8
- 238000010438 heat treatment Methods 0.000 description 6
- 206010063385 Intellectualisation Diseases 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000035040 seed growth Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0003—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiant heat transfer of samples, e.g. emittance meter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention discloses a power equipment fault diagnosis system and a diagnosis method, wherein the power equipment fault diagnosis system comprises: the device comprises a processor, and an acquisition unit and a detection unit which are electrically connected with the processor; the acquisition unit is configured to acquire temperature data and change information of the power equipment in different states; the detection unit is configured to acquire the temperature data acquired by the acquisition unit for data analysis; the processor is configured to receive the temperature data acquired by the acquisition unit and call the detection unit to diagnose the power equipment fault in the first state.
Description
Technical Field
The invention belongs to the field of fault diagnosis, and particularly relates to a power equipment fault diagnosis system and a power equipment fault diagnosis method.
Background
With the increasing of national level, the electricity demand increases increasingly, promotes electric power system security and reliability, and guarantee electricity utilization becomes the important importance, and power equipment has played vital effect wherein, and relevant data expression, and three-quarter trouble in the electric power system is all because power equipment trouble causes, because power equipment voltage grade is high, and the heat failure rate is high, and the heat failure point is various, need spend a large amount of manpower and materials to carry out fault diagnosis and maintenance to power equipment.
Most of the existing power equipment fault diagnosis is to carry out periodic detection through a handheld temperature measuring gun of a patrol personnel, and because the mode is relatively dependent on the working experience of the patrol personnel, the possibility of certain misjudgment is low in intellectualization, and the thermal fault of the power equipment cannot be detected through intelligent means, so that the damage of the power equipment is caused.
Disclosure of Invention
The invention aims to provide a power equipment fault diagnosis system which aims to solve the technical problems that the detection efficiency is low, misjudgment is easy to occur and the intellectualization is low in the prior art.
One of the purposes of the invention is to provide a power equipment fault diagnosis method.
To achieve one of the above objects, an embodiment of the present invention provides a power equipment fault diagnosis system, including: the device comprises a processor, and an acquisition unit and a detection unit which are electrically connected with the processor;
the acquisition unit is configured to acquire temperature data and change information of the power equipment in different states;
the detection unit is configured to acquire the temperature data acquired by the acquisition unit for data analysis;
the processor is configured to receive the temperature data acquired by the acquisition unit and call the detection unit to diagnose the power equipment fault in the first state.
As a further improvement of an embodiment of the present invention, the power equipment fault diagnosis system further includes a power equipment management module, where the power equipment management module is electrically connected to the collection unit, and the power equipment management module is configured to record the temperature data collected by the collection unit under a corresponding power equipment directory, so as to be used as reference data for overhauling.
As a further improvement of an embodiment of the present invention, the power equipment fault diagnosis system further includes a system maintenance module, where the system maintenance module is electrically connected to the processor, and the system maintenance module is used for authority setting, data maintenance and password modification of the system;
the data maintenance includes updating, importing, exporting, or backing up of data.
As a further improvement of an embodiment of the present invention, the power equipment fault system further includes an expert database and a maintenance decision unit, the expert database is electrically connected with the maintenance decision unit, the maintenance decision unit generates a corresponding maintenance decision according to the power equipment fault diagnosis result detected by the detection unit, and the expert database stores the maintenance decision data to generate an expert database.
To achieve one of the above objects, an embodiment of the present invention provides a power equipment failure diagnosis method applied to the power equipment failure diagnosis system of any one of the above claims; the power equipment fault diagnosis method comprises the following steps:
s1, configuring sampling interval time, collecting infrared images with different sampling time, and preprocessing the infrared images;
s2, configuring a target area, and dividing the infrared image according to the target area to obtain a plurality of divided images;
s3, respectively extracting characteristic values of a plurality of segmented images, and inputting the characteristic values into a fault diagnosis model;
s4, outputting fault information through a fault diagnosis model;
and S5, displaying the fault information according to a preset mode.
As a further improvement of an embodiment of the present invention, the step S1 of "acquiring infrared images with different sampling times and preprocessing the infrared images" specifically includes:
defining W as an N-type odd window, wherein W comprises N pixels 2 ；
Defining an original image as f (x, y), and denoising the original image through median filtering to obtain a new gray image g (x, y);
the denoising calculation formula is as follows:
g(x,y)＝median{f(x-k,y-l),(k,l)∈W}
wherein W is the selected window size, and f (x-k, y-l) is the window W pixel gray value.
As a further improvement of an embodiment of the present invention, the step S2 of configuring the target area and dividing the infrared image according to the target area includes the following steps:
s211, dividing the infrared image by an otsu algorithm and a region growing method to generate a gray level image;
s212, traversing the gray level diagram, generating a threshold histogram, searching for the median of found pixel points, and taking the median of the pixel points as an initial seed point;
s213, respectively configuring a segmentation threshold and a gray level similarity threshold as growth criteria;
s214, configuring a growth stopping condition, starting growth through the initial seed point, updating a pixel gray average value in the growth, and stopping segmentation if the gray average value meets the growth stopping condition, so as to generate a segmentation region.
As a further improvement of an embodiment of the present invention, the "configuring the segmentation threshold and the gray-scale similarity threshold as the growth criteria" in step S213 specifically includes:
configuring a segmentation threshold S and a gray level similarity threshold T, wherein the growth criterion expression is as follows:
wherein the method comprises the steps of
Representing the pixel gray average value, and beta (x, y) represents the pixel average value taking (x, y) as the middle pixel point;
wherein the method comprises the steps of
Wherein λ represents a correction coefficient, M represents the number of pixels, and +.>
Representing the pixel gray level average before updating.
As a further improvement of an embodiment of the present invention, in step S3, "extracting feature values of a plurality of segmented images respectively, inputting the feature values into a fault diagnosis model", wherein the fault diagnosis model is a multi-hidden-layer neural network model, and includes a plurality of self-encoders, and the multi-hidden-layer neural network model is formed by stacking a plurality of self-encoders;
the self-encoder comprises an input layer, a hidden layer and an output layer, wherein the self-encoder updates network parameters of the self-encoder by adopting a batch gradient descent method in the training process, extracts hidden features in the input layer to reconstruct original input data, and outputs the original input data through the output layer.
As a further improvement of an embodiment of the present invention, the input of the self-encoder network is X, and the encoding formula is as follows:
B＝λ1(MX+n)
wherein B represents the activation value of the hidden layer, lambda 1 Representing an activation function of the coding network, M represents a weight between an input layer and a hidden layer, and n represents a bias vector of the coding network;
the decoding formula of the self-coding network is as follows:
J＝λ2(M′B+n′)
wherein J represents a reconstruction value of the input data X, lambda 2 The activation function of the decoding network is represented, M 'represents the weights of the hidden layer and the output layer, and n' represents the bias vector of the decoding network.
Compared with the prior art, the power equipment fault diagnosis system provided by the invention,
according to the method, the thermal infrared image of the power equipment is acquired, the infrared image is analyzed, the fault type and the fault information of the power equipment are judged, and intelligent maintenance decision is generated intelligently, so that the intelligent fault detection is realized.
Drawings
FIG. 1 is a block diagram of a power equipment fault diagnosis system in one embodiment of the present invention;
FIG. 2 is a block diagram of a system maintenance module in one embodiment of the invention;
FIG. 3 is a flow chart of a method for diagnosing a power plant fault in an embodiment of the present invention;
FIG. 4 is a flow chart of an infrared image segmentation method in an embodiment of the invention;
FIG. 5 is a schematic diagram of a model of a multi-hidden neural network in accordance with an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the invention and structural, methodological, or functional modifications of these embodiments that may be made by one of ordinary skill in the art are included within the scope of the invention.
Example 1
As shown in fig. 1-2, the present invention discloses a power equipment fault diagnosis system, comprising: the device comprises a processor, and an acquisition unit and a detection unit which are electrically connected with the processor;
the acquisition unit is configured to acquire temperature data and change information of the power equipment in different states;
the detection unit is configured to acquire the temperature data acquired by the acquisition unit for data analysis;
the processor is configured to receive the temperature data acquired by the acquisition unit and call the detection unit to diagnose the power equipment fault in the first state.
According to the embodiment of the invention, the power equipment fault diagnosis system further comprises a power equipment management module, wherein the power equipment management module is electrically connected with the acquisition unit, and the power equipment management module is configured to record the temperature data acquired by the acquisition unit under a corresponding power equipment catalog so as to be conveniently used as reference data for overhaul.
According to the embodiment of the invention, the power equipment fault diagnosis system further comprises a system maintenance module, wherein the system maintenance module is electrically connected with the processor and is used for authority setting, data maintenance and password change of the system;
data maintenance includes updating, importing, exporting, or backing up of data.
Specifically, when a thermal fault occurs in a device, generally, due to an increase in load of the heating device or an increase in temperature of an environment surrounding the device, in order to minimize an influence of a load difference generated by the heating device and the temperature of the environment surrounding the device, a relative temperature difference judging method is adopted. The method is widely applied, can be used for thermal fault diagnosis of the power equipment heated by voltage and current at the same time, and has the following judgment formula:
wherein delta represents the relative temperature difference, T 1 The test temperature of the heating point is represented by T 2 Indicating the normal temperature of the heating point, T 0 Represents a reference ambient temperature τ 1 Indicating the test temperature rise of the heating point, tau 2 Indicating the normal temperature rise of the heating spot.
According to the embodiment of the invention, the power equipment fault system further comprises an expert database and a maintenance decision unit, wherein the expert database is electrically connected with the maintenance decision unit, the maintenance decision unit generates a corresponding maintenance decision according to the power equipment fault diagnosis result detected by the detection unit, and the expert database stores maintenance decision data to generate an expert database.
Example two
As shown in fig. 3 to 5, to achieve one of the above objects, an embodiment of the present invention provides a power equipment fault diagnosis method, which is applied to the power equipment fault diagnosis system of any one of the above claims; the power equipment fault diagnosis method comprises the following steps:
s1, configuring sampling interval time, collecting infrared images with different sampling time, and preprocessing the infrared images;
s2, configuring a target area, and dividing the infrared image according to the target area to obtain a plurality of divided images;
s3, respectively extracting characteristic values of a plurality of segmented images, and inputting the characteristic values into a fault diagnosis model;
specifically, a feature is a way to describe a high-dimensional image with a low-dimensional vector, which expresses a feature set of things or the nature of things. There are also various methods for selecting feature values according to the characteristics of the image itself. Images are generally described in terms of color, texture, spatial relationships, shape, etc.
S4, outputting fault information through a fault diagnosis model;
and S5, displaying the fault information according to a preset mode.
Specifically, assume that the gray value of the pixel of the acquired infrared image is U g The temperature value as a function of the gray value of the image pixel is as follows:
U g ＝KεF(T)
wherein K is a constant, epsilon represents a target heat generation rate, T represents a target temperature, and the temperature value of the power equipment test point can be calculated by analyzing the gray value of the target area of the infrared image.
According to the embodiment of the present invention, the step S1 of collecting the infrared images with different sampling times and preprocessing the infrared images specifically includes:
defining W as an N-type odd window, wherein W comprises N pixels 2 ；
Defining an original image as f (x, y), and denoising the original image through median filtering to obtain a new gray image g (x, y);
the denoising calculation formula is as follows:
g(x,y)＝median{f(x-k,y-l),(k,l)∈W}
wherein W is the selected window size, f (x-k, y-l) is the window W pixel gray value
According to an embodiment of the present invention, the step S2 of configuring the target area and dividing the infrared image according to the target area includes the following steps:
s211, dividing the infrared image by an otsu algorithm and a region growing method to generate a gray level image;
s212, traversing the gray level diagram, generating a threshold histogram, searching for the median of found pixel points, and taking the median of the pixel points as an initial seed point;
s213, respectively configuring a segmentation threshold and a gray level similarity threshold as growth criteria;
s214, configuring a growth stopping condition, starting growth through the initial seed point, updating a pixel gray average value in the growth, and stopping segmentation if the gray average value meets the growth stopping condition, so as to generate a segmentation region.
Specifically, the region growing method of the present application is an image dividing method of serial region division, in which pixels are gathered according to the attributes of similar pixels in the same region, from an initial region, merging neighboring pixels or other regions having the same attributes into a current region, gradually expanding until the region has no pixel points or other regions can be merged, from a specific pixel, gradually adding neighboring pixels according to a specific standard, and when certain conditions are reached, the region growing is ended.
Furthermore, the seed pixels in the region growing method are selected as follows, the temperature of the power equipment in the working period is generally higher than the ambient temperature, the thermal infrared imager collects the thermal radiation of the power equipment and forms an infrared image, the temperature is in direct proportion to the brightness, and therefore the pixel point with the maximum brightness in the infrared image can be selected when the seed pixel point is selected.
The termination conditions for the region growing method are determined as follows:
assuming that the gradation is randomly distributed within the image and the range of the growth threshold is set too large, the growth of the seeds is stopped in advance, resulting in insufficient segmentation. Assuming that the boundary of the image is unclear and the range of the growth threshold is set too small, this in turn leads to a phenomenon that the growth of the region cannot be terminated, resulting in over-segmentation.
When the region growing method is actually applied to extract the target region, the selection of the seed pixels needs to be selected according to the image characteristics, for example, the collected infrared image of the power equipment usually has larger heat radiation in the target region, so that the point with larger heat radiation in the infrared image can be also set as a seed growing point.
Determining a growth criterion; when a seed pixel is selected, how to determine the growth criterion is the core, and a gray threshold is generally set to select a similar gray as the growth criterion.
Growth cut-off conditions; setting a cut-off condition in the seed growth process, and ending the growth when the growth area exceeds the corresponding gray threshold value, namely ending the segmentation.
According to the embodiment of the present invention, "configuring the segmentation threshold and the gray-scale similarity threshold as the growth criteria" in step S213 specifically includes:
configuring a segmentation threshold S and a gray level similarity threshold T, wherein the growth criterion expression is as follows:
wherein the method comprises the steps of
Representing the pixel gray average value, and beta (x, y) represents the pixel average value taking (x, y) as the middle pixel point;
wherein the method comprises the steps of
Wherein λ represents a correction coefficient, M represents the number of pixels, and +.>
Representing the pixel gray level average before updating.
In a specific real-time mode of the invention, the fault diagnosis model is a neural network model, and the neural network model comprises,
In a specific embodiment of the present invention, the fault diagnosis model is a multi-hidden layer neural network model, including a plurality of self-encoders, and the multi-hidden layer neural network model is formed by stacking the plurality of self-encoders;
the self-encoder comprises an input layer, a hidden layer and an output layer, wherein the self-encoder updates network parameters of the self-encoder by adopting a batch gradient descent method in the training process, extracts hidden features in the input layer to reconstruct original input data, and outputs the original input data through the output layer.
In the training process of the neural network model, firstly, the acquired infrared image data is subjected to block dimension reduction, the original image is divided into a plurality of small blocks in an overlapped mode, the maximum characteristic value of each small picture is extracted independently, then the characteristic values of each small block are integrated to form a new characteristic vector for representing the information of the original image, and the characteristic vector subjected to dimension reduction and the one-dimensional bearing fault information are subjected to fusion processing of a data layer to obtain the original input of the deep learning fault model.
Specifically, the deep neural network is a multi-hidden neural network formed by stacking a plurality of self-encoders, layer-by-layer feature extraction from bottom to top is adopted in an unsupervised learning stage, the output of the former self-encoder is used as the input of the latter self-encoder, then the result of unsupervised layer-by-layer feature representation is used as the initial value of a back propagation optimization algorithm, supervised parameter fine tuning is carried out, and more abstract feature representation is extracted from original input information.
Further, the input from the encoder network is X, and the encoding formula is as follows:
B＝λ1(MX+n)
wherein B represents the activation value of the hidden layer, lambda 1 Representing an activation function of the coding network, M represents a weight between an input layer and a hidden layer, and n represents a bias vector of the coding network;
the decoding formula of the self-coding network is as follows:
J＝λ2(M′B+n′)
wherein J represents a reconstruction value of the input data X, lambda 2 The activation function of the decoding network is represented, M 'represents the weights of the hidden layer and the output layer, and n' represents the bias vector of the decoding network.
In summary, the method and the device for detecting the faults of the power equipment acquire the thermal infrared image of the power equipment, analyze the infrared image, judge the fault type and fault information of the power equipment, intelligently generate maintenance decisions and realize the intellectualization of fault detection.
It should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is for clarity only, and that the skilled artisan should recognize that the embodiments may be combined as appropriate to form other embodiments that will be understood by those skilled in the art.
The above list of detailed descriptions is only specific to practical embodiments of the present invention, and they are not intended to limit the scope of the present invention, and all equivalent embodiments or modifications that do not depart from the spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A power equipment fault diagnosis system, characterized by comprising: the device comprises a processor, and an acquisition unit and a detection unit which are electrically connected with the processor;
the acquisition unit is configured to acquire temperature data and change information of the power equipment in different states;
the detection unit is configured to acquire the temperature data acquired by the acquisition unit for data analysis;
the processor is configured to receive the temperature data acquired by the acquisition unit and call the detection unit to diagnose the power equipment fault in the first state.
2. The power equipment fault diagnosis system according to claim 1, further comprising a power equipment management module, wherein the power equipment management module is electrically connected to the collection unit, and the power equipment management module is configured to record the temperature data collected by the collection unit under a corresponding power equipment directory so as to be used as reference data for maintenance.
3. The power equipment fault diagnosis system according to claim 1, further comprising a system maintenance module electrically connected to the processor, the system maintenance module being used for authority setting, data maintenance and password modification of the system;
the data maintenance includes updating, importing, exporting, or backing up of data.
4. The power equipment fault diagnosis system according to claim 1, further comprising an expert database and a maintenance decision unit, wherein the expert database is electrically connected with the maintenance decision unit, the maintenance decision unit generates a corresponding maintenance decision according to the power equipment fault diagnosis result detected by the detection unit, and the expert database stores the maintenance decision data to generate an expert database.
5. A power equipment failure diagnosis method, characterized in that the power equipment failure diagnosis method is applied to the power equipment failure diagnosis system according to any one of claims 1 to 4; the power equipment fault diagnosis method comprises the following steps:
s1, configuring sampling interval time, collecting infrared images with different sampling time, and preprocessing the infrared images;
s2, configuring a target area, and dividing the infrared image according to the target area to obtain a plurality of divided images;
s3, respectively extracting characteristic values of a plurality of segmented images, and inputting the characteristic values into a fault diagnosis model;
s4, outputting fault information through a fault diagnosis model;
and S5, displaying the fault information according to a preset mode.
6. The method for diagnosing a power apparatus failure according to claim 5, wherein the step S1 of collecting the infrared images at different sampling times and preprocessing the infrared images specifically comprises:
defining W as an N-type odd window, wherein W comprises N pixels 2 ；
Defining an original image as f (x, y), and denoising the original image through median filtering to obtain a new gray image g (x, y);
the denoising calculation formula is as follows:
g(x,y)＝median{f(x-k,y-l),(k,l)∈W}
wherein W is the selected window size, and f (x-k, y-l) is the window W pixel gray value.
7. The power equipment failure diagnosis method according to claim 5, wherein the step S2 of configuring the target area and dividing the infrared image according to the target area includes the steps of:
s211, dividing the infrared image by an otsu algorithm and a region growing method to generate a gray level image;
s212, traversing the gray level diagram, generating a threshold histogram, searching for the median of found pixel points, and taking the median of the pixel points as an initial seed point;
s213, respectively configuring a segmentation threshold and a gray level similarity threshold as growth criteria;
s214, configuring a growth stopping condition, starting growth through the initial seed point, updating a pixel gray average value in the growth, and stopping segmentation if the gray average value meets the growth stopping condition, so as to generate a segmentation region.
8. The power equipment fault diagnosis method according to claim 7, wherein the step S213 of configuring the division threshold and the gray-scale similarity threshold as the growth criteria, respectively, specifically comprises:
configuring a segmentation threshold S and a gray level similarity threshold T, wherein the growth criterion expression is as follows:
wherein the method comprises the steps of
Representing the pixel gray average value, and beta (x, y) represents the pixel average value taking (x, y) as the middle pixel point;
wherein the method comprises the steps of
Wherein λ represents a correction coefficient, M represents the number of pixels, and +.>
Representing the pixel gray level average before updating.
9. The power equipment fault diagnosis method according to claim 5, wherein in step S3, "extracting feature values of a plurality of divided images, respectively, and inputting the feature values into a fault diagnosis model", wherein the fault diagnosis model is a multi-hidden layer neural network model including a plurality of self-encoders, the multi-hidden layer neural network model being formed by stacking a plurality of self-encoders;
the self-encoder comprises an input layer, a hidden layer and an output layer, wherein the self-encoder updates network parameters of the self-encoder by adopting a batch gradient descent method in the training process, extracts hidden features in the input layer to reconstruct original input data, and outputs the original input data through the output layer.
10. The method of claim 9, wherein the input to the self-encoder network is X, and the encoding formula is as follows:
B＝λ 1 (MX+n)
wherein B represents the activation value of the hidden layer, lambda 1 Representing an activation function of the coding network, M represents a weight between an input layer and a hidden layer, and n represents a bias vector of the coding network;
the decoding formula of the self-coding network is as follows:
J＝λ 2 (M′B+n′)
wherein J represents a reconstruction value of the input data X, lambda 2 The activation function of the decoding network is represented, M 'represents the weights of the hidden layer and the output layer, and n' represents the bias vector of the decoding network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310093839.3A CN116295847A (en) | 2023-02-10 | 2023-02-10 | Power equipment fault diagnosis system and diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310093839.3A CN116295847A (en) | 2023-02-10 | 2023-02-10 | Power equipment fault diagnosis system and diagnosis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116295847A true CN116295847A (en) | 2023-06-23 |
Family
ID=86815896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310093839.3A Pending CN116295847A (en) | 2023-02-10 | 2023-02-10 | Power equipment fault diagnosis system and diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116295847A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117392130A (en) * | 2023-12-12 | 2024-01-12 | 山东海纳智能装备科技股份有限公司 | On-line fault diagnosis system based on infrared image |
-
2023
- 2023-02-10 CN CN202310093839.3A patent/CN116295847A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117392130A (en) * | 2023-12-12 | 2024-01-12 | 山东海纳智能装备科技股份有限公司 | On-line fault diagnosis system based on infrared image |
| CN117392130B (en) * | 2023-12-12 | 2024-02-23 | 山东海纳智能装备科技股份有限公司 | On-line fault diagnosis system based on infrared image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110555819B (en) | Equipment monitoring method, device and equipment based on infrared and visible light image fusion | |
| CN110458839B (en) | Effective wire and cable monitoring system | |
| CN106778687B (en) | Fixation point detection method based on local evaluation and global optimization | |
| WO2019000818A1 (en) | Method and device for monitoring icing of wind turbine blade | |
| CN113324864B (en) | Pantograph carbon slide plate abrasion detection method based on deep learning target detection | |
| CN116295847A (en) | Power equipment fault diagnosis system and diagnosis method | |
| CN112669287B (en) | Electrical equipment temperature monitoring method based on image recognition | |
| CN110070024B (en) | Method and system for identifying skin pressure injury thermal imaging image and mobile phone | |
| CN109886931A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on BP neural network | |
| CN109886932A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on SVM | |
| CN112883802A (en) | Method for identifying destructive event of pipeline optical fiber vibration safety early warning system | |
| CN114898261A (en) | Sleep quality assessment method and system based on fusion of video and physiological data | |
| CN115908354A (en) | Photovoltaic panel defect detection method based on double-scale strategy and improved YOLOV5 network | |
| CN117671396A (en) | Intelligent monitoring and early warning system and method for construction progress | |
| CN113084193A (en) | In-situ quality comprehensive evaluation method for selective laser melting technology | |
| Guo et al. | Fault diagnosis of power equipment based on infrared image analysis | |
| CN116071299A (en) | Insulator RTV spraying defect detection method and system | |
| KR102342495B1 (en) | Method and Apparatus for Creating Labeling Model with Data Programming | |
| CN114858301A (en) | Object surface temperature measuring system, measuring method, intelligent terminal and storage medium | |
| CN112241707A (en) | Wind-powered electricity generation field intelligence video identification device | |
| CN113034465B (en) | Power equipment thermal fault monitoring method, device and medium based on infrared image | |
| CN117576564B (en) | Disease and pest identification early warning method and system for tea planting | |
| CN117079221B (en) | Construction safety monitoring method and device for underground engineering of pumping and storing power station | |
| CN117392130B (en) | On-line fault diagnosis system based on infrared image | |
| CN117745730B (en) | Polyester filament yarn detection method and system based on image processing technology |
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 |