Electrical cabinet fault assessment method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an electrical cabinet fault assessment method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a state image of the electrical cabinet; the state image of the electrical cabinet comprises temperature rise information, position information and device information of the to-be-tested electrical device; the device information comprises at least one of the following information: the name of the to-be-tested electric device, the model of the to-be-tested electric device, the category of the to-be-tested electric device and the identification code of the to-be-tested electric device; performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of the to-be-detected electrical device; wherein the target area comprises at least one of a wire inlet point area, a device front area and a wire outlet point area; fitting based on the image of the target area of the to-be-tested electric device to obtain a temperature rise curve of the target area of the to-be-tested electric device; and according to the temperature rise curve of the target area of the to-be-tested electric device and a fault assessment condition corresponding to the type of the to-be-tested electric device, performing fault assessment on the target area of the to-be-tested electric device to obtain an assessment result.

Description

Technical Field

[0001] The present application relates to the technical field of rail vehicle fault processing, and in particular, to an electrical cabinet fault assessment method, device, electronic equipment and storage medium. Background Art

[0002] In the high-speed railway transportation network, the electrical cabinet is a key component of the high-speed EMU, and its stability is directly related to the reliable operation of the high-speed railway transportation network. Due to the design and selection of electrical components in the electrical cabinet, installation quality and aging of electrical components, the temperature rise of electrical components will be abnormal and cause failures, which will lead to the failure of the high-speed railway transportation network to operate normally. Therefore, how to detect and evaluate the temperature rise of electrical components has become one of the problems that need to be solved in the industry. Summary of the invention

[0003] The embodiments of the present application provide an electrical cabinet fault assessment method, device, electronic device, and storage medium.

[0004] A first aspect of an embodiment of the present application provides an electrical cabinet fault assessment method, comprising:

[0005] Acquire a status image of the electrical cabinet; the status image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested;

[0006] Performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area;

[0007] Obtaining a temperature rise curve of the target area of ​​the electrical device to be tested based on image fitting of the target area of ​​the electrical device to be tested;

[0008] According to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested, a fault assessment is performed on the target area of ​​the electrical device to be tested to obtain an assessment result.

[0009] In an optional embodiment of the present application, obtaining the state image of the electrical cabinet includes:

[0010] Obtain a two-dimensional temperature field image of the electrical components to be tested in the electrical cabinet;

[0011] Converting the two-dimensional temperature field image into a grayscale image, and performing filtering and / or noise reduction processing on the grayscale image;

[0012] Obtaining a two-dimensional temperature rise image of the electrical device under test based on the processed grayscale image and the real-time ambient temperature of the electrical cabinet; wherein the two-dimensional temperature rise image of the electrical device under test includes temperature rise information of the electrical device under test;

[0013] Acquire a color image of the electrical cabinet, and perform target recognition on the color image of the electrical cabinet to obtain actual layout information of each electrical component to be tested;

[0014] Extracting text and patterns from the theoretical layout image of the electrical cabinet to obtain theoretical layout information of each electrical device to be tested; wherein the theoretical layout information of each electrical device to be tested includes: theoretical positions of each electrical device to be tested and device information of each electrical device to be tested;

[0015] Matching the actual layout information of each electrical device to be tested with the theoretical layout information of each electrical device to be tested to obtain an actual layout image of the electrical cabinet;

[0016] Based on the two-dimensional temperature rise images of each electrical component to be tested and the actual layout image of the electrical cabinet, a state image of the electrical cabinet is obtained.

[0017] In an optional embodiment of the present application, the performing target recognition on the color image of the electrical cabinet to obtain actual layout information of each electrical component to be tested includes:

[0018] Performing edge detection on the color image of the electrical cabinet to identify the outline of each electrical component to be tested and obtain the actual position of each electrical component to be tested;

[0019] and / or,

[0020] The text and pattern in the theoretical layout image of the electrical cabinet are extracted to obtain the theoretical layout information of each electrical device to be tested, including:

[0021] Perform edge detection on the theoretical layout image of the electrical cabinet to identify the outline of each electrical component to be tested and obtain the theoretical position of each electrical component to be tested;

[0022] The text area in the theoretical layout image of the electrical cabinet is detected to identify the device information of each electrical device to be tested.

[0023] In an optional embodiment of the present application, the step of performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested includes:

[0024] The size of the state image of the electrical cabinet is adjusted, and the adjusted image is input into a target recognition model, so as to use the target recognition model to identify each electrical device to be tested in the state image of the electrical cabinet; wherein the target recognition model is obtained by training based on training data; the training data includes: two-dimensional temperature rise images of the electrical device to be tested under standard working conditions and fault working conditions, boundary information of the electrical device to be tested, and the category of the electrical device to be tested;

[0025] After determining each electrical component to be tested in the state image of the electrical cabinet based on the output result of the target recognition model, the state image of the electrical cabinet is segmented using an image segmentation model to obtain an image of a target area of ​​each electrical component to be tested; wherein the loss function used to train the image segmentation model includes a cross entropy loss function.

[0026] In an optional embodiment of the present application, the step of obtaining a temperature rise curve of the target area of ​​the electrical device to be tested based on the image fitting of the target area of ​​the electrical device to be tested includes:

[0027] The image of the target area of ​​the electrical device to be tested is input into a linear regression model to obtain a temperature rise curve of the target area of ​​the electrical device to be tested; wherein the loss function used to train the linear regression model includes a mean square error loss function.

[0028] In an optional embodiment of the present application, performing fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested includes:

[0029] Determining an actual temperature rise value of a target area of ​​the electrical device to be tested according to a temperature rise curve of the target area of ​​the electrical device to be tested;

[0030] Determining a fault assessment condition corresponding to the type of the electrical device to be tested; wherein the assessment condition includes a standard temperature rise value of the target area;

[0031] Determine the difference between the actual temperature rise value and the standard temperature rise value;

[0032] When the difference exceeds a preset difference threshold, it is determined that a fault occurs in the target area of ​​the electrical device to be tested.

[0033] In an optional embodiment of the present application, after determining that a fault occurs in the target area of ​​the electrical device to be tested, the method further includes:

[0034] At T1>t1, or, δ t≥δ1 and T1>t2, it is determined that an emergency fault occurs in the target area of ​​the electrical device to be tested; wherein T1 represents the hot spot temperature of the target area; t1 represents the first emergency fault temperature threshold; δ t Relative temperature difference, δ t =(T1-T2) / (T1-T0)×100%, T1 represents the normal temperature of the target area, T0 represents the ambient temperature of the electrical cabinet; δ1 represents the first relative temperature difference threshold; t2 represents the second emergency fault temperature threshold;

[0035] At t3≤T1≤t1, or, δ t ≥δ2 and T1<t2, it is determined that a serious fault occurs in the target area of ​​the electrical device to be tested; wherein t3 represents the first serious fault temperature threshold, t3<t1; δ2 represents the second relative temperature difference threshold, δ2<δ1;

[0036] In δ t ≥δ3 and T1<t4, it is determined that a general fault occurs in the target area of ​​the electrical device to be tested; δ3 represents the third relative temperature difference threshold, δ3<δ2; t4 represents the second severe fault temperature threshold, t4<t2;

[0037] Accordingly, the evaluation result includes at least one of the following: device information of the faulty electrical device, location information of the faulty electrical device, the fault area of ​​the faulty device and the fault level of the fault area; the fault level includes: emergency fault, serious fault and general fault.

[0038] A second aspect of an embodiment of the present application provides an electrical cabinet fault assessment device, comprising:

[0039] An acquisition unit, used to acquire a state image of the electrical cabinet; the state image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested;

[0040] An image segmentation unit is used to perform image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area;

[0041] A fitting unit, configured to obtain a temperature rise curve of the target area of ​​the electrical device to be tested based on an image fitting of the target area of ​​the electrical device to be tested;

[0042] The fault assessment unit is used to perform fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested to obtain an assessment result.

[0043] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0044] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0045] The electrical cabinet fault assessment method provided by the present application obtains a state image of the electrical cabinet; the state image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested; the state image of the electrical cabinet is segmented to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area; the electrical device to be tested is obtained based on image fitting of the target area of ​​the electrical device to be tested. a temperature rise curve of a target area of ​​the electrical device to be tested; and according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested, a fault assessment is performed on the target area of ​​the electrical device to be tested to obtain an assessment result. In this way, by real-time monitoring of the temperature rise of the electrical device to be tested in the electrical cabinet, and combining with image segmentation and other technologies, the electrical device and the specific area where the fault occurs can be accurately located. Thus, the electrical device and the fault area where the fault occurs in the electrical cabinet can be determined in real time and accurately, which is beneficial to the preventive maintenance of the high-speed railway transportation network, and further beneficial to ensuring the safe and reliable operation of the high-speed railway transportation network. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0047] Figure 1 A flowchart of an electrical cabinet fault assessment method provided in one embodiment of the present application;

[0048] Figure 2 A schematic diagram of a scenario of an electrical cabinet fault assessment method provided by an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a processing scenario of a two-dimensional temperature field image provided by an embodiment of the present application;

[0050] Figure 4A schematic diagram of a scenario for obtaining a status image of an electrical cabinet is provided for one embodiment of the present application;

[0051] Figure 5 A schematic diagram of the structure of a gas cabinet fault assessment device provided in one embodiment of the present application;

[0052] Figure 6 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0053] In the process of realizing this application, the inventor found that real-time monitoring of the temperature rise of electrical components in the electrical cabinet is very important for evaluating the working status of the electrical cabinet. In the related art, there are two main solutions for monitoring the temperature rise of electrical components in the electrical cabinet: one is to use a handheld infrared thermal imager to detect the electrical components; the other is to stick a color-changing temperature sensor to the electrical components to be monitored in advance.

[0054] Among them, for the solution of handheld infrared thermal imager detection, the surface temperature of electrical components is determined by detecting the infrared radiation emitted by the object. This solution is affected by environmental factors, operator skills and other factors, and can only be implemented after the rail vehicle is put into storage. However, the change in working conditions after the rail vehicle is put into storage will lead to inaccurate temperature rise monitoring, and the fault point cannot be accurately located. Further inspection is usually required, which increases the fault diagnosis cycle and labor costs.

[0055] For the scheme of using color-changing temperature sensing for near-monitoring, the color-changing temperature sensor is a device that uses the property that the color of the material changes with temperature to monitor the temperature. Due to the durability of the color-changing material of the color-changing temperature sensor and environmental factors, temperature range limitations, color recognition problems, poor stability and low resolution, this scheme cannot meet the high-precision monitoring needs of the electrical cabinet.

[0056] In order to overcome the above-mentioned problems, the present application provides an electrical cabinet fault assessment method, which monitors the temperature rise of the electrical components to be tested in the electrical cabinet in real time, and combines image segmentation and other technologies to accurately locate the faulty electrical components and specific areas. Thus, the faulty electrical components and their fault areas in the electrical cabinet can be determined in real time and accurately, which is conducive to the preventive maintenance of the high-speed railway transportation network, and further helps to ensure the safe and reliable operation of the high-speed railway transportation network.

[0057] The solutions in the embodiments of the present application can be implemented using various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0058] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0059] Figure 1 A flowchart of an electrical cabinet fault assessment method provided in one embodiment of the present application; Figure 2 A schematic diagram of a scenario of an electrical cabinet fault assessment method provided in one embodiment of the present application.

[0060] See also Figure 1 and Figure 2 The electrical cabinet fault assessment method provided in the embodiment of the present application comprises the following steps:

[0061] Step 110, obtaining a status image of the electrical cabinet; the status image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested;

[0062] Step 120, performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area;

[0063] Step 130, obtaining a temperature rise curve of the target area of ​​the electrical device to be tested based on image fitting of the target area of ​​the electrical device to be tested;

[0064] Step 140 : performing a fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested to obtain an assessment result.

[0065] In step 110, the two-dimensional temperature field image of the electrical cabinet of the operating vehicle can be obtained in real time through the infrared module, and the two-dimensional temperature field image of the electrical cabinet is processed to obtain a processed image. The color image of the interior of the electrical cabinet is also obtained in real time through the visible light camera, and the theoretical layout image of the electrical cabinet is obtained. The color image of the interior of the electrical cabinet is merged with the theoretical layout image of the electrical cabinet to obtain the actual layout information of the interior of the electrical cabinet. Finally, based on the processed image and the actual layout information of the interior of the electrical cabinet, the state image of the electrical cabinet is obtained.

[0066] The state image of the electrical cabinet can reflect multi-dimensional information. For example, the state image of the electrical cabinet can reflect the temperature rise information of each electrical device to be tested, the position information of the electrical device to be tested, the device information of the electrical device to be tested, etc.

[0067] The position information of the electrical device under test may include one of the following: the position of the electrical device under test in the vehicle, the position of the electrical device under test in the electrical cabinet. For example, the position of the electrical device under test in the vehicle may be represented as row 1, car 1, electrical cabinet 01.

[0068] The device information of the electrical device under test includes: any one or any combination of the name of the electrical device under test, the model of the electrical device under test, the category of the electrical device under test, and the identification code of the electrical device under test. The name of the electrical device under test can specifically be a functional name, such as a sewage tank electric heating circuit breaker, a warm water tank heating circuit breaker, a main air compressor power supply circuit breaker, etc.

[0069] Optionally, the device information of the electrical device under test includes: the name of the electrical device under test, the model of the electrical device under test, and the identification code of the electrical device under test; the name or model of the electrical device under test can reflect the category of the electrical device under test. In addition, according to actual needs, the state image of the electrical cabinet can also include information such as the hot spot temperature of each electrical device under test.

[0070] In step 120, images of various target areas of the electrical device to be tested are generated. Exemplarily, a neural network target recognition algorithm is used to identify the type of each electrical device to be tested in the electrical cabinet state image containing multi-dimensional information, and then image segmentation is performed based on the recognition result to segment target areas such as the line entry point area, device front area, and line exit point area of ​​the electrical device to be tested, thereby facilitating accurate positioning of the fault area of ​​the faulty electrical device.

[0071] The segmented images of the same type of electrical devices under test can be set in the same data set, so as to facilitate the comparison between the images in the data set and the corresponding fault assessment conditions; generally speaking, the same type of electrical devices under test correspond to the same fault assessment conditions.

[0072] In step 130, the image of the target area of ​​the electrical device to be tested may be input into a pre-trained linear regression model to obtain a temperature rise curve of the target area of ​​the electrical device to be tested; wherein the loss function used in training the linear regression model includes a mean square error loss function.

[0073] Since the linear regression model has a certain robustness to outliers, and after research, it is found that the two-dimensional temperature rise image and the actual temperature rise are roughly linear, the linear regression model is used to fit the temperature rise curve for the fitting of the two-dimensional temperature rise image of the electrical device and the actual temperature rise. The linear fitting formula is shown in the following formula 1:

[0074] y=β0+β1x1+β2x2+...+β n x n +ε(Formula 1);

[0075] Among them, y represents temperature, x1, x2, ..., x n Indicates the factors affecting temperature rise, β1, β2, ..., β n represents the regression coefficient and ε is the error term.

[0076] When training a neural network, the loss function used is the mean square error (MSE) loss function. The formula of the mean square error loss function is shown in Formula 2 below:

[0077]

[0078] Among them, y i is the actual temperature rise, is the temperature rise predicted by the network and N is the number of samples.

[0079] In this embodiment, the segmented images of each target area of ​​the electrical device to be tested are sent to a neural network for regression calculation and standard temperature rise comparison, so that it can be determined whether a fault occurs in the part of the electrical device to be tested under the working state according to the comparison result.

[0080] In step 140, the information represented by the temperature rise curve of the target area of ​​the electrical device to be tested is compared with the fault assessment condition corresponding to the type of the electrical device to be tested. If the information represented by the temperature rise curve meets the fault assessment condition, it is determined that the target area of ​​the electrical device to be tested has a fault, and an assessment result is generated based on the faulty electrical device, the faulty area, the actual location information of the faulty electrical device, etc. If it is determined that none of the electrical devices to be tested has a fault, no assessment result may be generated, or an assessment result indicating that all the electrical devices to be tested are normal may be generated.

[0081] The electrical cabinet fault assessment method provided in the present embodiment obtains a state image of the electrical cabinet; the state image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested; the state image of the electrical cabinet is segmented to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area; the target area of ​​the electrical device to be tested is obtained based on image fitting of the target area of ​​the electrical device to be tested The temperature rise curve of the target area of ​​the electrical device to be tested is obtained; according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment conditions corresponding to the type of the electrical device to be tested, a fault assessment is performed on the target area of ​​the electrical device to be tested to obtain an assessment result. In this way, the temperature rise of the electrical device to be tested in the electrical cabinet is monitored in real time, and the faulty electrical device and specific area can be accurately located in combination with image segmentation and other technologies. Therefore, the faulty electrical device and its fault area in the electrical cabinet can be determined in real time and accurately, which is conducive to the preventive maintenance of the high-speed railway transportation network, and further helps to ensure the safe and reliable operation of the high-speed railway transportation network.

[0082] Please refer to Figure 3 and Figure 4 In some embodiments, step 110, obtaining a status image of the electrical cabinet, may include the following steps a1 to a4:

[0083] Step a1, obtaining a two-dimensional temperature field image of the electrical device to be tested in the electrical cabinet, and obtaining a two-dimensional temperature rise image of the electrical device to be tested based on the two-dimensional temperature field image of the electrical device to be tested; the two-dimensional temperature rise image of the electrical device to be tested includes temperature rise information of the electrical device to be tested;

[0084] Step a2: acquiring a color image of the electrical cabinet, and performing target recognition on the color image of the electrical cabinet to obtain actual layout information of each electrical component to be tested;

[0085] Step a3, extracting the text and pattern in the theoretical layout image of the electrical cabinet to obtain the theoretical layout information of each electrical device to be tested; wherein the theoretical layout information of each electrical device to be tested includes: the theoretical position of each electrical device to be tested and the device information of each electrical device to be tested;

[0086] Step a4: obtaining a state image of the electrical cabinet based on the two-dimensional temperature rise image, actual layout information and theoretical layout information of each electrical component to be tested.

[0087] In step a1, an infrared temperature measurement module may be installed in the electrical cabinet. The specific installation position and number of the infrared temperature measurement module may be set according to actual needs to achieve real-time acquisition of each electrical component to be tested in the electrical cabinet.

[0088] In the specific implementation process, Figure 3 As shown, a two-dimensional temperature field image of the electrical device to be tested in the electrical cabinet is obtained, the two-dimensional temperature field image of the electrical device to be tested is converted into a grayscale image, and the grayscale image of the electrical device to be tested is filtered and / or denoised. Figure 2 Shown is a relay type

[0089] A two-dimensional temperature rise image of the electrical device to be tested is obtained based on the processed grayscale image and the real-time ambient temperature of the electrical cabinet; wherein the real-time temperature information of the electrical device to be tested. Optionally, the two-dimensional temperature rise image of the electrical device to be tested is obtained based on the processed grayscale image and the real-time ambient temperature of the electrical cabinet, including: subtracting the temperature detected in real time in the processed grayscale image from the real-time ambient temperature of the electrical cabinet to obtain the two-dimensional temperature rise image of the electrical device to be tested.

[0090] The temperature rise value in the temperature rise information of the electrical device to be tested can be represented by the following formula 3:

[0091] I diff (x,y)=|I1(x,y)-I2(x,y)|(Formula 3);

[0092] The above formula is I diff (x,y) represents the temperature rise value of the two-dimensional temperature rise image at the pixel (x,y); I1(x,y) represents the value of the pixel (x,y) in the two-dimensional temperature field data, that is, the temperature value of the two-dimensional temperature rise image at the pixel (x,y); I2(x,y) represents the real-time ambient temperature of the real-time electrical cabinet.

[0093] It can be understood that: there are usually a large number of electrical devices to be tested in the electrical cabinet. In the process of implementing this embodiment, the above steps can be performed in sequence to obtain a two-dimensional temperature rise image of each electrical device to be tested, and the above images of each electrical device to be tested can also be batch processed. The specific settings can be made according to actual needs.

[0094] In step a2, a visible light camera may be installed in the electrical cabinet. The specific installation position and number of infrared temperature measurement modules may be set according to actual needs to achieve real-time acquisition of each electrical component to be tested in the electrical cabinet.

[0095] The color image obtained by the visible light camera can reflect the layout of each electrical device under test. After obtaining the color image, the target recognition algorithm is used to identify the actual layout information of each electrical device under test, and the actual layout information includes the actual position information. For example, the preset point in the electrical cabinet can be used as the origin and a three-dimensional coordinate system can be established. The actual position information of the electrical device under test includes: the coordinate information of the feature points such as the center or vertex of the electrical device under test in the three-dimensional coordinate system.

[0096] Optionally, edge detection can be performed on the color image of the electrical cabinet to identify the outline of each electrical device to be tested and obtain the actual position of each electrical device to be tested. Exemplarily, the Sobel edge detection method can be used to identify the outline of each electrical device to be tested in the color image. In the specific implementation process, the color image is preprocessed, and the preprocessing may include at least one of the following: conversion to grayscale image form, filtering, performing appropriate morphological operations on the actual layout image after preprocessing, adaptively adjusting algorithm parameters, and performing Sobel edge detection to identify the actual position of each electrical device to be tested in the actual layout image.

[0097] In step a3, a theoretical layout image of the electrical cabinet is obtained, and the distribution of each electrical device to be tested can be reflected in the theoretical layout image. Exemplarily, the theoretical layout information of each electrical device to be tested in the theoretical layout image of the electrical cabinet can be extracted using a text and pattern extraction algorithm. The theoretical layout information of the electrical device to be tested includes: the theoretical position of the electrical device to be tested and the device information of the electrical device to be tested.

[0098] Optionally, step a3 includes the following steps a31 and a32:

[0099] Step a31, performing edge detection on the theoretical layout image of the electrical cabinet to identify the contours of each electrical component to be tested and obtain the theoretical position of each electrical component to be tested;

[0100] Step a32: Detect the text area in the theoretical layout image of the electrical cabinet to identify the device information of each electrical device to be tested.

[0101] In step a31, the Sobel edge detection method is used to identify the contour of the electrical device to be tested in the theoretical layout image of the electrical cabinet. The edge can be detected by calculating the gradient amplitude of each pixel in the theoretical layout image. The Sobel operator uses two 3×3 convolution kernels, corresponding to the gradients in the x direction (horizontal) and y direction (vertical) of the image. The following are the two convolution kernels of the Sobel operator as shown in Formula 4 and Formula 5 respectively:

[0102] Horizontal direction (Gx):

[0103]

[0104] Vertical direction (Gy):

[0105]

[0106] By using the above convolution kernel to perform convolution operation on the theoretical layout image, the gradient amplitude of the theoretical layout image in the horizontal and vertical directions can be obtained respectively. The output of the Sobel operator consists of the amplitude and direction of the gradient, and only the gradient amplitude is used as the basis for edge detection. The calculation formula of the gradient amplitude G is shown in Formula 6:

[0107]

[0108] Among them, Gx and Gy are the gradient amplitudes obtained by convolving the theoretical layout image with the above convolution kernels respectively.

[0109] In step a32, the edge detection result in step a31 is used to identify the area that may contain text through connected component analysis; wherein, the non-text area can be filtered by setting specific conditions such as area and shape ratio. For the text area where text is identified, morphological operations such as erosion and dilation can be used to improve the clarity of the text. The morphological operation formula can adopt conventional settings, or adaptively adjust the conventional settings according to actual needs. For example, the morphological operation formula is shown in Formula 7:

[0110] B(x,y)=max (x',y’)∈N A(x'+x,y'+y) (Formula 7);

[0111] Wherein, A represents the original image, B represents the expanded image, N represents the structural element; x' and y' represent the coordinate points in the pixel coordinate system of the original image; x and y represent the coordinate points in the pixel coordinate system of the expanded image.

[0112] After the morphological operation, the image can also be processed by Gaussian blur processing to remove noise and make the image smoother. The Gaussian blur formula can use conventional settings, or adaptively adjust the conventional settings according to actual needs. For example, the Gaussian blur formula is shown in the following formula 8:

[0113] I'(x,y,σ)=G(x,y,σ)*I(x,y) (Formula 8);

[0114] Among them, I'(x,y) represents the original image; G(x,y,σ) represents the Gaussian kernel; σ represents the scale parameter; x and y represent the coordinate points in the pixel coordinate system in the image.

[0115] Use Tesseract to convert the text in the processed image into text data through OCR technology. Use scale space to detect key points in the image, and use gradient amplitude and direction information to build unique descriptors for these key points. These descriptors play an important role in image recognition and matching. Among them, the scale space amplitude calculation formula is shown in Formula 9 below:

[0116]

[0117] Where D(x, y, σ) represents the amplitude calculated in scale space; x and y represent the coordinate points in the pixel coordinate system of the image; σ represents the scale parameter; D x and D y is the first derivative of the image in the horizontal and vertical directions;

[0118] The calculation formula of scale space gradient θ is shown in the following formula 10:

[0119]

[0120] If D x (x, y, σ) < 0, then θ increases by π. Combining the electrical component contour recognition and electrical component model and identification code recognition in the electrical cabinet theoretical layout image, the electrical component theoretical position information contained in the electrical cabinet theoretical layout image is obtained.

[0121] In step a4, the actual layout information is matched with the theoretical layout information to obtain the actual layout position of the electrical device to be tested. The various image information is fused by coordinate transformation to obtain the state image of the electrical cabinet containing multi-dimensional information.

[0122] like Figure 4 As shown, exemplarily, step a4 includes the following steps a41 and a42:

[0123] Step a41, matching the actual layout information of each electrical device to be tested with the theoretical layout information of each electrical device to be tested to obtain an actual layout image of the electrical cabinet;

[0124] Step a42: obtaining a state image of the electrical cabinet based on the two-dimensional temperature rise images of each electrical component to be tested and the actual layout image of the electrical cabinet.

[0125] In step a42, since the actual layout image of the electrical cabinet and the two-dimensional temperature rise image of the electrical device to be tested are taken at the same angle, the difference in coordinates is a constant value. Therefore, through the affine transformation, each pixel in the actual layout image of the electrical cabinet has corresponding temperature rise information, thereby obtaining a multi-dimensional information fused electrical cabinet state image. Among them, the affine transformation formula can adopt conventional settings, or adaptively adjust the conventional settings in combination with actual needs. For example, the affine transformation formula is shown in Formula 11:

[0126]

[0127] Where (x′, y′) represents the transformed coordinates, (x, y) represents the original coordinates, and the matrix Defines the part of the linear transformation, the vector Defines the part of the translation.

[0128] By properly adjusting the linear transformation and translation part of the matrix, the actual layout image of the electrical cabinet can be matched with the two-dimensional temperature rise image of the electrical device to be tested.

[0129] In some embodiments, step 120, performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested, includes the following steps b1 to b2:

[0130] Step b1, adjusting the size of the state image of the electrical cabinet, and inputting the adjusted image into a target recognition model, so as to use the target recognition model to identify each electrical component to be tested in the state image of the electrical cabinet; wherein the target recognition model is obtained by training based on training data; the training data includes: two-dimensional temperature rise images of the electrical component to be tested under standard working conditions and fault working conditions, boundary information of the electrical component to be tested, and the category of the electrical component to be tested;

[0131] Step b2: after determining each electrical component to be tested in the state image of the electrical cabinet based on the output result of the target recognition model, use the image segmentation model to perform image segmentation on the state image of the electrical cabinet to obtain an image of the target area of ​​each electrical component to be tested; wherein the loss function used for training the image segmentation model includes a cross entropy loss function.

[0132] In step b2, after identifying each electrical device to be tested in the state image of the electrical cabinet, the state image of the electrical cabinet is segmented using a pre-trained image segmentation model. The image segmentation model may use a fully convolutional network (FCN), where the fully connected layer is replaced by a convolutional layer, so that the image segmentation model can accept an input image of any size and generate an output result of the same spatial dimension as the input, so that this embodiment is suitable for scenarios where the image sizes are not completely consistent when segmenting each target area of ​​the electrical device to be tested.

[0133] In addition, before step b2 or step b1, image preprocessing may be performed first, and the preprocessing includes operations such as denoising, contrast enhancement, and normalization, so as to facilitate the accuracy of subsequent operations.

[0134] In the process of training the image segmentation model, by setting appropriate convolution kernel parameters, the convolution kernel extracts effective image features and learns through FCN. The formula of the convolution operation in FCN is shown in the following formula 12:

[0135] (f*g)(i,j)=∑ m ∑ n f(m,n)·g(im,jn) (Formula 12);

[0136] Where f represents the input feature map, g represents the convolution kernel, (i, j) represents the position of the output feature map, and (m, n) represents the index of the element in the convolution kernel.

[0137] After the convolution layer, the maximum pooling operation is used to reduce the spatial size of the feature, thereby reducing the number of parameters and the amount of calculation, and enhancing the stability of feature detection. The formula for the maximum pooling operation is shown in Formula 13 below:

[0138] (P max f)(i,j)=max m，n∈Ω(i，j) f(i+m, j+n) (Formula 13);

[0139] Where Pmax represents the maximum pooling operation; Ω(i, j) represents the set of all positions within the pooling window centered at (i, j).

[0140] When training the image segmentation model, since it is necessary to segment the various parts of the electrical device, it is a multi-classification problem. Therefore, the loss function selected in this embodiment is the cross entropy loss function. The cross entropy loss function is used to quantify the difference between the predicted value and the actual value of the image segmentation model. Among them, the cross entropy loss function formula is shown in the following formula 14:

[0141]

[0142] Where M represents the total number of categories; yo,c represents a binary indicator (0 or 1), which is 1 if sample o belongs to category c and 0 otherwise; po,c represents the probability that sample o belongs to category c.

[0143] Optionally, the image segmentation model is used to segment each electrical device to be tested into three target areas, namely: the line entry point area, the device front area, and the line exit point area. In addition, the image segmentation model can upsample the output of the last convolution layer to the same size as the original image and output the segmentation results of each part of the electrical device.

[0144] Optionally, morphological operations can be used to optimize and refine the segmentation results output by the image segmentation model to improve the accuracy of subsequent fault assessment.

[0145] In some embodiments, step 140, performing a fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested, includes the following steps c1 to c4:

[0146] Step c1, determining an actual temperature rise value of the target area of ​​the electrical device to be tested according to a temperature rise curve of the target area of ​​the electrical device to be tested;

[0147] Step c2, determining the fault evaluation condition corresponding to the type of the electrical device to be tested; wherein the evaluation condition includes the standard temperature rise value of the target area;

[0148] Step c3, determining the difference between the actual temperature rise value and the standard temperature rise value;

[0149] Step c4: when the difference exceeds a preset difference threshold, it is determined that a fault occurs in the target area of ​​the electrical device to be tested.

[0150] In step c2, this embodiment takes the three categories of electrical devices to be tested as an example, the three categories are contactors, relays and circuit breakers; the three categories of electrical devices have their own corresponding fault assessment conditions. Among them, the fault assessment conditions of different categories of electrical devices can be the same or different, and can be set according to actual needs.

[0151] In step c3, the difference obtained is the absolute value of the actual temperature rise value and the standard temperature rise value. The standard temperature rise value can be obtained based on experimental data, simulation data or historical data to obtain the temperature rise value of the electrical device under normal working conditions.

[0152] In step c4, the difference is compared with a preset difference threshold to achieve fault judgment. If the difference exceeds the preset difference threshold, it is determined that a fault occurs in the target area of ​​the electrical device under test; if the difference is less than or equal to the difference threshold, it is determined that the temperature rise of the target area of ​​the electrical device under test is normal. Specifically, the fault evaluation formula is shown in the following formula 15:

[0153]

[0154] in, Indicates the actual temperature rise value determined based on the temperature rise curve of the target area of ​​the electrical device to be tested; std Represents the standard temperature rise value; Threshold is the corresponding threshold value.

[0155] In some examples, a fault assessment result may be directly generated based on the fault judgment result of step c4.

[0156] In other examples, after determining that a fault occurs in the target area of ​​the electrical device to be tested, the fault level can be further determined to facilitate timely adoption of appropriate strategies based on the fault level. The fault levels include: emergency fault, severe fault, and general fault.

[0157] Exemplarily, after determining that a fault occurs in the target area of ​​the electrical device to be tested, the following steps c5 to c7 may also be included:

[0158] Step c5: When T1>t1, or, δ t≥δ1 and T1>t2, it is determined that an emergency fault occurs in the target area of ​​the electrical device to be tested; wherein T1 represents the hot spot temperature of the target area; t1 represents the first emergency fault temperature threshold; δ t Relative temperature difference, δ t =(T1-T2) / (T1-T0)×100%, T1 represents the normal temperature of the target area, T0 represents the ambient temperature of the electrical cabinet; δ1 represents the first relative temperature difference threshold; t2 represents the second emergency fault temperature threshold;

[0159] Step c6: at t3≤T1≤t1, or, δ t ≥δ2 and T1<t2, it is determined that a serious fault occurs in the target area of ​​the electrical device to be tested; wherein t3 represents the first serious fault temperature threshold, t3<t1; δ2 represents the second relative temperature difference threshold, δ2<δ1;

[0160] Step c7: t ≥δ3 and T1<t4, it is determined that a general fault occurs in the target area of ​​the electrical device to be tested; δ3 represents the third relative temperature difference threshold, δ3<δ2; t4 represents the second severe fault temperature threshold, t4<t2.

[0161] The hot spot temperature is the temperature of a point with the highest temperature in the target area of ​​the electrical device to be tested. The method for obtaining the hot spot temperature can be set according to actual needs. For example, the hot spot temperature can be obtained by using the detection result of the temperature sensor of the electrical device to be tested itself; the hot spot temperature can also be obtained by using a two-dimensional temperature field image of the electrical device to be tested.

[0162] In specific implementation, the hot spot temperature T1 of the target area can be compared with t1. If T1>t1, it is determined that an emergency fault occurs in the target area of ​​the electrical device to be tested; if T1≤t1, T1 is compared with t3. If t3≤T1, it is determined that a serious fault occurs in the target area of ​​the electrical device to be tested; if and T1<t3, it is determined that a general fault occurs in the target area of ​​the electrical device to be tested.

[0163] Alternatively, the relative temperature difference δ of the target area t Compare with δ1 and compare the hot spot temperature T1 with t2. If δ t ≥δ1 and T1>t2, it is determined that an emergency fault occurs in the target area of ​​the electrical device under test. t <δ1, then δ t Compared with δ2, if δ t ≥δ2 and T1<t2, it is determined that a serious fault has occurred in the target area of ​​the electrical device under test. t <δ2, then δ t Compared with δ3, if δ t≥δ3 and T1<t4, it is determined that a serious fault has occurred in the target area of ​​the electrical device under test. t If <δ3, it means that the fault judgment mechanism is wrong, and a prompt message is generated to promptly remind relevant personnel to conduct a review or other operations.

[0164] It is understandable that: in the above steps, the size relationship between t1 and t2 can be set according to actual needs, for example, t1<t2, or t1>t2, or t1=t2. The size relationship between t3 and t4 can be set according to actual needs, for example, t3<t4, or t3>t4, or t3=t4.

[0165] Accordingly, the evaluation result includes at least one of the following: device information of the faulty electrical device, location information of the faulty electrical device, the fault area of ​​the faulty device and the fault level of the fault area; the fault levels include: emergency fault, serious fault and general fault.

[0166] It can be understood that the above thresholds can be set according to actual needs and are not specifically limited in this embodiment.

[0167] Taking a contactor-type electrical device under test as an example, the fault level evaluation conditions are shown in Table 1 below.

[0168] Table 1 Fault level evaluation conditions of contactor type electrical devices under test

[0169]

[0170] The fault level evaluation conditions of the relay type electrical device under test and the circuit breaker type electrical device under test may be similar to the fault evaluation conditions of the contactor type electrical device under test, and will not be described in detail in this embodiment.

[0171] In the above embodiment, optionally, emergency faults can be further divided into level one emergency faults and level two emergency faults, and serious faults can be further divided into level one serious faults and level two serious faults; wherein, the level of level one emergency fault is higher than level two emergency faults, the level of level two emergency faults is higher than level one serious faults, the level of level one serious faults is higher than the level of level two serious faults, and the level of level two serious faults is higher than the level of general faults. Accordingly, the fault level evaluation conditions are further refined. The evaluation results include at least one of the following: device information of the faulty electrical device, location information of the faulty electrical device, fault area of ​​the faulty device and fault level of the fault area; fault levels include: level one emergency fault, level two emergency fault, level one serious fault, level two serious fault and general fault.

[0172] This embodiment solves the problem of long-term non-contact online temperature monitoring of high-speed rail electrical cabinets by matching and fusing multi-source data such as the temperature information of electrical components contained in the two-dimensional temperature field, the location and model of electrical components contained in the color image and layout design drawing, and performing electrical component fault diagnosis in the temperature rise dimension, thereby achieving precise diagnosis and positioning, thereby realizing preventive maintenance and enhancing the reliability of high-speed rail operations.

[0173] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0174] In addition, the environmental monitoring of the electrical cabinet can be used to assist in fault diagnosis and evaluation. That is, by combining the driving history data and the equipment temperature history data, the correlation between the driving status and the temperature can be combined to make the fault diagnosis more practical and accurate. For example, the temperature of a train may rise when it runs at high speed. It is more accurate to have a correlation rather than to assume that there is a fault when the temperature rises.

[0175] Based on the historical data of high-speed rail travel and equipment temperature, the correlation between each electrical equipment and the high-speed rail travel status is counted, and based on the correlation, all electrical equipment is divided into relevant equipment and unrelated equipment.

[0176] For relevant equipment, a first temperature prediction model is trained based on the high-speed rail travel history data, equipment operation history data, and equipment temperature history data; for irrelevant equipment, a second temperature prediction model is trained based on the equipment operation history data and equipment temperature history data;

[0177] The real-time equipment operation data of each electrical equipment and the real-time travel data of the high-speed rail are collected, and the expected temperature of each electrical equipment is obtained based on the real-time equipment operation data, the real-time travel data, the first temperature prediction model and the second temperature prediction model; based on the expected temperature and the real-time temperature, the abnormal condition of each electrical equipment is judged.

[0178] The method of statistically analyzing the correlation between each electrical device and the running status of the high-speed rail is as follows:

[0179] The speed time series of the high-speed rail travel history data is marked as V;

[0180] Mark each moment as t, then the velocity at the tth moment in the velocity time series V is marked as v_t;

[0181] Mark each electrical equipment with a number i;

[0182] The temperature time series of the i-th electrical equipment is marked as Wi, and the parameter value at the t-th moment in the temperature time series Wi is wi_t;

[0183] For the i-th electrical equipment:

[0184] Calculate the correlation ri of the velocity time series and the temperature time series based on the velocity time series and the temperature time series;

[0185] Based on the correlation ri and the length of the temperature time series, calculate the t statistic ts_i of the i-th electrical equipment;

[0186] Then, under the t distribution with n-2 degrees of freedom, find the corresponding critical value Where α is the preset significance level; where n is the length of the speed time series;

[0187] If |ts_i| is greater than the critical value, the i-th electrical equipment is classified as related equipment; otherwise, the i-th electrical equipment is classified as unrelated equipment.

[0188] Figure 5 A schematic diagram of the structure of a gas cabinet fault assessment device provided in one embodiment of the present application.

[0189] See also Figure 5 , an embodiment of the present application provides an electrical cabinet fault assessment device, comprising:

[0190] The acquisition unit 510 is used to acquire a state image of the electrical cabinet; the state image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested;

[0191] The image segmentation unit 520 is used to perform image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area;

[0192] A fitting unit 530, configured to obtain a temperature rise curve of the target area of ​​the electrical device to be tested based on the image fitting of the target area of ​​the electrical device to be tested;

[0193] The fault assessment unit 540 is used to perform fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested, and obtain an assessment result.

[0194] In some embodiments, the acquisition unit is specifically used to:

[0195] Obtain a two-dimensional temperature field image of the electrical components to be tested in the electrical cabinet;

[0196] Converting the two-dimensional temperature field image into a grayscale image, and performing filtering and / or noise reduction processing on the grayscale image;

[0197] Obtaining a two-dimensional temperature rise image of the electrical device to be tested based on the processed grayscale image and the real-time ambient temperature of the electrical cabinet; wherein the two-dimensional temperature rise image of the electrical device to be tested includes temperature rise information of the electrical device to be tested;

[0198] Acquire a color image of the electrical cabinet, perform target recognition on the color image of the electrical cabinet, and obtain actual layout information of each electrical component to be tested;

[0199] Extracting text and patterns from the theoretical layout image of the electrical cabinet to obtain theoretical layout information of each electrical device to be tested; wherein the theoretical layout information of each electrical device to be tested includes: theoretical positions of each electrical device to be tested and device information of each electrical device to be tested;

[0200] Matching the actual layout information of each electrical device to be tested with the theoretical layout information of each electrical device to be tested to obtain an actual layout image of the electrical cabinet;

[0201] Based on the two-dimensional temperature rise images of each electrical component to be tested and the actual layout image of the electrical cabinet, a state image of the electrical cabinet is obtained.

[0202] In some embodiments, the acquisition unit is specifically used to:

[0203] Edge detection is performed on the color image of the electrical cabinet to identify the outline of each electrical component to be tested and obtain the actual position of each electrical component to be tested.

[0204] In some embodiments, the acquisition unit is specifically used to:

[0205] Perform edge detection on the theoretical layout image of the electrical cabinet to identify the outline of each electrical component to be tested and obtain the theoretical position of each electrical component to be tested;

[0206] The text area in the theoretical layout image of the electrical cabinet is detected to identify the device information of each electrical device to be tested.

[0207] In some embodiments, the image segmentation unit is specifically used to:

[0208] The size of the state image of the electrical cabinet is adjusted, and the adjusted image is input into a target recognition model, so as to use the target recognition model to identify each electrical component to be tested in the state image of the electrical cabinet; wherein the target recognition model is obtained by training based on training data; the training data includes: two-dimensional temperature rise images of the electrical component to be tested under standard working conditions and fault working conditions, boundary information of the electrical component to be tested, and the category of the electrical component to be tested;

[0209] After determining each electrical component to be tested in the state image of the electrical cabinet based on the output result of the target recognition model, the state image of the electrical cabinet is segmented using the image segmentation model to obtain an image of the target area of ​​each electrical component to be tested; wherein the loss function used in training the image segmentation model includes a cross entropy loss function.

[0210] In some embodiments, the fitting unit is specifically configured to:

[0211] An image of a target area of ​​the electrical device to be tested is input into a linear regression model to obtain a temperature rise curve of the target area of ​​the electrical device to be tested; wherein the loss function used in training the linear regression model includes a mean square error loss function.

[0212] In some embodiments, the fault assessment unit is specifically configured to:

[0213] Determine the actual temperature rise value of the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested;

[0214] Determine the fault evaluation condition corresponding to the type of the electrical device to be tested; wherein the evaluation condition includes the standard temperature rise value of the target area;

[0215] Determine the difference between the actual temperature rise value and the standard temperature rise value;

[0216] When the difference exceeds a preset difference threshold, it is determined that a fault occurs in the target area of ​​the electrical device to be tested.

[0217] In some embodiments, the fault assessment unit is specifically configured to:

[0218] At T1>t1, or, δ t ≥δ1 and T1>t2, it is determined that an emergency fault occurs in the target area of ​​the electrical device to be tested; wherein T1 represents the hot spot temperature of the target area; t1 represents the first emergency fault temperature threshold; δ t Relative temperature difference, δ t =(T1-T2) / (T1-T0)×100%, T1 represents the normal temperature of the target area, T0 represents the ambient temperature of the electrical cabinet; δ1 represents the first relative temperature difference threshold; t2 represents the second emergency fault temperature threshold;

[0219] At t3≤T1≤t1, or, δ t ≥δ2 and T1<t2, it is determined that a serious fault occurs in the target area of ​​the electrical device to be tested; wherein t3 represents the first serious fault temperature threshold, t3<t1; δ2 represents the second relative temperature difference threshold, δ2<δ1;

[0220] In δ t ≥δ3 and T1<t4, it is determined that a general fault occurs in the target area of ​​the electrical device to be tested; δ3 represents the third relative temperature difference threshold, δ3<δ2; t4 represents the second severe fault temperature threshold, t4<t2.

[0221] In some embodiments, the evaluation result includes at least one of the following: device information of the faulty electrical device, location information of the faulty electrical device, fault area of ​​the faulty device and fault level of the fault area; fault levels include: emergency fault, serious fault and general fault.

[0222] For the specific definition of the above-mentioned electrical cabinet fault assessment device, please refer to the definition of the electrical cabinet fault assessment method above, which will not be repeated here. Each module in the above-mentioned electrical cabinet fault assessment device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0223] In one embodiment, an electronic device is provided, the internal structure diagram of the electronic device can be as follows: Figure 6 As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an electrical cabinet fault assessment method as described above is implemented. It includes: a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, any step in the electrical cabinet fault assessment method as described above is implemented.

[0224] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any step in the above electrical cabinet fault assessment method can be implemented.

[0225] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0226] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0227] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0228] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0229] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0230] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for evaluating electrical cabinet faults, characterized in that: include: Get status images of electrical cabinets; The state image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested; Performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area; Obtaining a temperature rise curve of the target area of ​​the electrical device to be tested based on image fitting of the target area of ​​the electrical device to be tested; According to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested, a fault assessment is performed on the target area of ​​the electrical device to be tested to obtain an assessment result.

2. The electrical cabinet fault assessment method according to claim 1, characterized in that: The step of obtaining the state image of the electrical cabinet comprises: Obtain a two-dimensional temperature field image of the electrical components to be tested in the electrical cabinet; Converting the two-dimensional temperature field image into a grayscale image, and performing filtering and / or noise reduction processing on the grayscale image; Obtaining a two-dimensional temperature rise image of the electrical device under test based on the processed grayscale image and the real-time ambient temperature of the electrical cabinet; wherein the two-dimensional temperature rise image of the electrical device under test includes temperature rise information of the electrical device under test; Acquire a color image of the electrical cabinet, and perform target recognition on the color image of the electrical cabinet to obtain actual layout information of each electrical component to be tested; Extracting text and patterns from the theoretical layout image of the electrical cabinet to obtain theoretical layout information of each electrical device to be tested; wherein the theoretical layout information of each electrical device to be tested includes: theoretical positions of each electrical device to be tested and device information of each electrical device to be tested; Matching the actual layout information of each electrical device to be tested with the theoretical layout information of each electrical device to be tested to obtain an actual layout image of the electrical cabinet; Based on the two-dimensional temperature rise images of each electrical component to be tested and the actual layout image of the electrical cabinet, a state image of the electrical cabinet is obtained.

3. The electrical cabinet fault assessment method according to claim 2, characterized in that: The target recognition is performed on the color image of the electrical cabinet to obtain the actual layout information of each electrical device to be tested, including: Performing edge detection on the color image of the electrical cabinet to identify the outline of each electrical component to be tested and obtain the actual position of each electrical component to be tested; and / or, The text and pattern in the theoretical layout image of the electrical cabinet are extracted to obtain the theoretical layout information of each electrical device to be tested, including: Perform edge detection on the theoretical layout image of the electrical cabinet to identify the outline of each electrical component to be tested and obtain the theoretical position of each electrical component to be tested; The text area in the theoretical layout image of the electrical cabinet is detected to identify the device information of each electrical device to be tested.

4. The electrical cabinet fault assessment method according to claim 1, characterized in that: The step of performing image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested includes: The size of the state image of the electrical cabinet is adjusted, and the adjusted image is input into a target recognition model, so as to use the target recognition model to identify each electrical device to be tested in the state image of the electrical cabinet; wherein the target recognition model is obtained by training based on training data; the training data includes: two-dimensional temperature rise images of the electrical device to be tested under standard working conditions and fault working conditions, boundary information of the electrical device to be tested, and the category of the electrical device to be tested; After determining each electrical component to be tested in the state image of the electrical cabinet based on the output result of the target recognition model, the state image of the electrical cabinet is segmented using an image segmentation model to obtain an image of a target area of ​​each electrical component to be tested; wherein the loss function used to train the image segmentation model includes a cross entropy loss function.

5. The electrical cabinet fault assessment method according to claim 1, characterized in that: The step of obtaining a temperature rise curve of the target area of ​​the electrical device to be tested based on the image fitting of the target area of ​​the electrical device to be tested comprises: The image of the target area of ​​the electrical device to be tested is input into a linear regression model to obtain a temperature rise curve of the target area of ​​the electrical device to be tested; wherein the loss function used to train the linear regression model includes a mean square error loss function.

6. The electrical cabinet fault assessment method according to claim 1, characterized in that: The step of performing a fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested comprises: Determining an actual temperature rise value of a target area of ​​the electrical device to be tested according to a temperature rise curve of the target area of ​​the electrical device to be tested; Determining a fault assessment condition corresponding to the type of the electrical device to be tested; wherein the assessment condition includes a standard temperature rise value of the target area; Determine the difference between the actual temperature rise value and the standard temperature rise value; When the difference exceeds a preset difference threshold, it is determined that a fault occurs in the target area of ​​the electrical device to be tested.

7. The electrical cabinet fault assessment method according to claim 6, characterized in that: After determining that a fault occurs in the target area of ​​the electrical device to be tested, the method further includes: At T1>t1, or, δ t ≥δ1 and T1>t2, it is determined that an emergency fault occurs in the target area of ​​the electrical device to be tested; wherein T1 represents the hot spot temperature of the target area; t1 represents the first emergency fault temperature threshold; δ t Relative temperature difference, δ t =(T1-T2) / (T1-T0)×100%, T1 represents the normal temperature of the target area, T0 represents the ambient temperature of the electrical cabinet; δ1 represents the first relative temperature difference threshold; t2 represents the second emergency fault temperature threshold; At t3≤T1≤t1, or, δ t ≥δ2 and T1<t2, it is determined that a serious fault occurs in the target area of ​​the electrical device to be tested; wherein t3 represents the first serious fault temperature threshold, t3<t1; δ2 represents the second relative temperature difference threshold, δ2<δ1; In δ t ≥δ3 and T1<t4, it is determined that a general fault occurs in the target area of ​​the electrical device to be tested; δ3 represents the third relative temperature difference threshold, δ3<δ2; t4 represents the second severe fault temperature threshold, t4<t2; Accordingly, the evaluation result includes at least one of the following: device information of the faulty electrical device, location information of the faulty electrical device, the fault area of ​​the faulty device and the fault level of the fault area; the fault level includes: emergency fault, serious fault and general fault.

8. An electrical cabinet fault assessment device, characterized in that: include: An acquisition unit, used for acquiring a status image of the electrical cabinet; The state image of the electrical cabinet includes: temperature rise information, position information, and device information of the electrical device to be tested; the device information includes at least one of the following: the name of the electrical device to be tested, the model of the electrical device to be tested, the category of the electrical device to be tested, and the identification code of the electrical device to be tested; An image segmentation unit is used to perform image segmentation on the state image of the electrical cabinet to obtain an image of a target area of ​​the electrical device to be tested; wherein the target area includes at least one of the following: an incoming line point area, a device front area, and an outgoing line point area; A fitting unit, configured to obtain a temperature rise curve of the target area of ​​the electrical device to be tested based on an image fitting of the target area of ​​the electrical device to be tested; The fault assessment unit is used to perform fault assessment on the target area of ​​the electrical device to be tested according to the temperature rise curve of the target area of ​​the electrical device to be tested and the fault assessment condition corresponding to the type of the electrical device to be tested to obtain an assessment result.

9. An electronic device, comprising: The method comprises a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images