A method and system for detecting insulation of high voltage cables for mining

Abstract

The present invention relates to the technical field of cable detection. The present invention discloses a method and system for detecting insulation of a high-voltage cable for mining. The method comprises obtaining a camera image and an infrared image of a cable joint, and then respectively extracting a first image feature and a second image feature based on the two images. Then, the features are fused to generate a comprehensive feature, and the feature is input into a pre-established fault diagnosis model to determine the fault category of the cable. If the fault category of the cable is determined to be a cable body fault, the location of the cable fault is determined by using a time domain reflection method, crack data is obtained based on a cable body image, and a crack coefficient is calculated. Finally, the level of the cable body fault is determined according to the type of the body crack and the crack coefficient. This process is crucial for rapid fault location in a mine environment, and can quickly determine the location of insulation damage when a cable body fault occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of cable detection, and more specifically, to a method and system for detecting the insulation of a high-voltage cable for mining. Background Art

[0002] Mine cables are key equipment for power supply in coal mines, and are essential for ensuring safe and efficient production in mines. However, the underground environment of coal mines is harsh, and cables are subjected to electrical, thermal, chemical and other stresses. The surface insulation layer is prone to damage and cracks, which leads to a decrease in insulation level, shortening the life of the cable, and even causing arcs, causing dangerous accidents such as gas and coal dust explosions, threatening the safety of underground workers. Therefore, it is necessary to monitor the insulation status of high-voltage cables in coal mines in a timely manner, locate the damaged position, and repair or replace them. Traditional cable detection methods mostly use manual power-off inspections, but they are inefficient and easy to delay production. With the development of artificial intelligence technology, methods for detecting cables using artificial intelligence technology have emerged, but their application in mine environments still faces some challenges;

[0003] For example, the patent with publication number CN115409820A provides a cable defect detection method and system based on artificial intelligence. The patent obtains the storage data of the cable system, obtains the influencing factors affecting the cable system based on the storage data analysis, and calculates the probability of defects in the current cable system through the artificial intelligence model. Although the patent uses artificial intelligence technology to detect cables, for cables in a mine environment, the failure frequency of cable joints is usually much greater than the failure frequency of the cable body. Therefore, it is crucial to quickly locate the fault. At the same time, when a fault occurs in the cable body, the location of the insulation damage must also be quickly located.

[0004] In view of this, the present invention proposes a method and system for detecting insulation of a high-voltage cable for mining to solve the above-mentioned problem. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for detecting insulation of a high-voltage cable for mining.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for detecting insulation of a high-voltage cable for mining, comprising:

[0008] S10: Responding to a cable abnormality signal, acquiring a camera image and an infrared image of the cable joint, wherein the cable abnormality signal is used to indicate cable insulation damage;

[0009] S20: obtaining a first image feature and a second image feature based on the camera image and the infrared image, generating a fusion feature based on the first image feature and the second image feature, inputting the fusion feature into a pre-built fault diagnosis model, and obtaining a cable fault category, where the cable fault category includes a cable joint fault and a cable body fault;

[0010] S30: When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflectometry method, a cable body image is obtained according to the cable fault location, and the cable body image is input into a pre-built fault classification model to obtain a body crack category;

[0011] S40: determining crack data based on the cable body image, calculating crack coefficient according to the crack data, determining cable body fault level according to the body crack type and crack coefficient, and issuing corresponding warning information according to the cable body fault level.

[0012] Furthermore, the first image feature includes a texture feature and a shape feature, the second image feature includes a heat distribution feature, and the method for generating a fusion feature according to the first image feature and the second image feature includes:

[0013] The first image feature and the second image feature are cascaded and fused to generate a fused feature.

[0014] Furthermore, the method for constructing the fault diagnosis model includes:

[0015] Obtain i groups of data, where i is a positive integer greater than 1, and the data includes historical fusion features and historical cable fault categories. The historical fusion features and historical cable fault categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical fusion features in the training set are used as input data, and the historical cable fault categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set, and a classifier that meets the preset accuracy is output as a fault diagnosis model.

[0016] Furthermore, the method for determining the cable fault location according to the time domain reflectometry method includes:

[0017] Acquire pulse data emitted from the fault location according to detectors at both ends of the cable, and determine the cable fault location based on the pulse data, the pulse data including pulse propagation speed and pulse propagation time;

[0018] Methods for determining cable fault locations based on pulse data include: F = ;

[0019] In the formula, F is the distance between the fault location and one end of the cable, It is the pulse propagation time required for the pulse signal sent from the fault location to reach one end of the cable. It is the pulse propagation time required for the pulse signal sent from the fault location to reach the other end of the cable. is the cable length, is the pulse propagation speed.

[0020] Furthermore, the method for constructing the fault classification model includes:

[0021] Obtain h groups of data, where h is a positive integer greater than 1, and the data include historical cable body images and historical body crack categories. Use the historical cable body images and historical body crack categories as sample sets, divide the sample sets into training sets and test sets, build a classifier, use the historical cable body images in the training set as input data, use the historical body crack categories in the training set as output data, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets the preset accuracy as a fault classification model.

[0022] Furthermore, the crack data includes crack length, crack width and crack depth, and the method for determining the crack data based on the cable body image includes:

[0023] The cable body image is converted into a cable grayscale image, and the cable grayscale image is segmented by region growing to obtain a crack area map. The crack area map is input into a pre-built deep neural network model to obtain the crack length, crack width and crack depth output by the deep neural network model.

[0024] Furthermore, the method for calculating the crack coefficient according to the crack data includes: Ckt= ;

[0025] Where Ckt is the crack coefficient, is the crack length, is the crack width, is the crack depth, and are all weight coefficients.

[0026] Furthermore, the cable body fault level includes a slight fault, a moderate fault and a severe fault. The method for determining the cable body fault level according to the body crack type and the crack coefficient includes:

[0027] When the main body crack type is a circumferential crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a slight fault;

[0028] When the main body crack type is a circumferential crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a moderate fault;

[0029] When the main body crack type is an axial crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a moderate fault;

[0030] When the main body crack type is an axial crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a severe fault;

[0031] When the main body crack type is an inclined crack, the cable main body fault level is a severe fault.

[0032] A mining high-voltage cable insulation detection system, which is used to implement the above-mentioned mining high-voltage cable insulation detection method, comprises:

[0033] Data acquisition module: responding to cable abnormality signals to acquire camera images and infrared images of cable joints, wherein the cable abnormality signals are used to indicate cable insulation damage;

[0034] Fault determination module: obtains first image features and second image features based on the camera image and the infrared image respectively, generates fusion features based on the first image features and the second image features, inputs the fusion features into the pre-built fault diagnosis model, and obtains the cable fault category, which includes cable joint fault and cable body fault;

[0035] Position determination module: When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflectometry method, the cable body image is obtained according to the cable fault location, and the cable body image is input into the pre-built fault classification model to obtain the body crack category;

[0036] Level determination module: Determine crack data based on the cable body image, calculate crack coefficient based on crack data, determine cable body fault level based on body crack type and crack coefficient, and issue corresponding warning information based on cable body fault level.

[0037] A computer-readable storage medium stores a computer program, and when the computer program is executed, the above-mentioned method for detecting insulation of a high-voltage cable for mining is implemented.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention first obtains a camera image and an infrared image of a cable joint, and then, based on the two images, extracts a first image feature and a second image feature respectively, then fuses these features to generate a comprehensive feature, and inputs it into a pre-established fault diagnosis model to determine the fault category of the cable. If the fault category of the cable is determined to be a cable body fault, the location of the cable fault is determined using a time domain reflection method. Next, a cable body image is obtained according to the cable fault location, and inputted into a pre-established fault classification model to determine the category of the body crack. After the category of the body crack is determined, crack data is obtained based on the cable body image, and a crack coefficient is calculated. Finally, the level of the cable body fault is determined based on the category of the body crack and the crack coefficient. This process is crucial for rapid fault location in a mine environment, and can quickly determine the location of insulation damage when a cable body fault occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of a method for detecting insulation of a high-voltage cable for mining in the present invention;

[0041] Figure 2 It is a schematic diagram of positioning by time domain reflectometry in the present invention;

[0042] Figure 3 A schematic diagram of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1: Please refer to Figure 1 As shown, this embodiment discloses a method for detecting insulation of a high-voltage cable for mining, comprising:

[0045] S10: Responding to a cable abnormality signal, acquiring a camera image and an infrared image of the cable joint, wherein the cable abnormality signal is used to indicate cable insulation damage;

[0046] It should be noted that the cable abnormal signal is used to indicate cable insulation damage. The cable abnormal signal includes but is not limited to current abnormal signal and voltage fluctuation signal. Insulation damage causes voltage fluctuation or instability. Insulation damage causes current abnormality, such as a sudden increase or decrease in current. Both the current abnormal signal and the voltage fluctuation signal can be directly obtained by monitoring the cable.

[0047] It is understandable that, in a mine environment, the failure frequency of the cable joint is usually much greater than the failure frequency of the cable body. Therefore, when a cable fails, the camera image and infrared image of the cable joint should be quickly obtained, and the camera image and infrared image should be used to determine whether the cable joint has failed. This can quickly locate the fault and enhance the response rate of the detection system.

[0048] S20: obtaining a first image feature and a second image feature based on the camera image and the infrared image, generating a fusion feature based on the first image feature and the second image feature, inputting the fusion feature into a pre-built fault diagnosis model, and obtaining a cable fault category, where the cable fault category includes a cable joint fault and a cable body fault;

[0049] It should be noted that the first image feature includes but is not limited to texture feature and shape feature, the second image feature includes heat distribution feature, and both the first image feature and the second image feature can be obtained by a feature extraction algorithm. Existing feature extraction algorithms include, for example, the Canny edge detection algorithm and the directional gradient histogram algorithm, which will not be described in detail in this embodiment;

[0050] The method for generating a fusion feature according to a first image feature and a second image feature includes:

[0051] Cascadingly fusing the first image feature and the second image feature to generate a fused feature;

[0052] It can be understood that cascade fusion refers to cascading two feature vectors together to form a longer vector. The above cascade fusion is only an exemplary description, and fusion can also be performed in other ways, such as feature transformation, etc. This embodiment is not limited to this.

[0053] The construction method of the fault diagnosis model includes:

[0054] Obtain i groups of data, where i is a positive integer greater than 1, and the data includes historical fusion features and historical cable fault categories. The historical fusion features and historical cable fault categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical fusion features in the training set are used as input data, and the historical cable fault categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set. A classifier that meets a preset accuracy is output as a fault diagnosis model, and the classifier is preferably a naive Bayes model or a support vector machine model.

[0055] It is worth noting that the historical fusion feature in this embodiment is used to indicate whether a cable joint fails. When the insulation of the cable joint is damaged, the corresponding first image feature and the second image feature will also be different. For example, when the insulation of the cable joint is damaged, it will cause the local temperature to rise, and then there will be obvious hot spots or hot spots in the infrared image. These hot spots are usually displayed as bright areas in the infrared image, reflecting abnormal heat distribution;

[0056] S30: When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflectometry method, a cable body image is obtained according to the cable fault location, and the cable body image is input into a pre-built fault classification model to obtain a body crack category;

[0057] Methods for locating cable faults based on time domain reflectometry include:

[0058] Acquire pulse data emitted from the fault location according to detectors at both ends of the cable, and determine the cable fault location based on the pulse data, the pulse data including pulse propagation speed and pulse propagation time;

[0059] Methods for determining cable fault locations based on pulse data include: F = ;

[0060] In the formula, F is the distance between the fault location and one end of the cable, It is the pulse propagation time required for the pulse signal sent from the fault location to reach one end of the cable. It is the pulse propagation time required for the pulse signal sent from the fault location to reach the other end of the cable. is the cable length, is the pulse propagation speed;

[0061] Combine the following Figure 2 For detailed explanation:

[0062] like Figure 2 As shown in the figure, the cable is equipped with detectors at both ends A and B. The cable fault is at C. Due to the partial discharge phenomenon caused by the cable fault, two pulse signals will be generated at the same time. The pulse signal refers to the voltage pulse signal, and the two pulse signals move along the cable to ends A and B respectively. The moving speed of the two pulse signals is the same, both It can be understood that in this embodiment, the coordinate axis is established with the A end of the cable as the origin. F The positive and negative represent the direction of the coordinate axis, which is calculated by F The position of C can be determined;

[0063] In an embodiment of the present invention, after determining the cable fault position, the camera can be called to obtain a cable body image at the cable fault position according to the mapping relationship between the cable fault position and the camera position. The cable body image can be an infrared image. The body crack categories include axial cracks, circumferential cracks and oblique cracks. Axial cracks refer to cracks extending along the cable axis, circumferential cracks refer to cracks around the cable cross section, and oblique cracks refer to cracks extending obliquely along the cable insulation layer or outer sheath.

[0064] The construction method of the fault classification model includes:

[0065] Obtain h groups of data, where h is a positive integer greater than 1, and the data includes historical cable body images and historical body crack categories. The historical cable body images and historical body crack categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical cable body images in the training set are used as input data, and the historical body crack categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set, and a classifier that meets a preset accuracy is output as a fault classification model, and the classifier is preferably a naive Bayes model or a support vector machine model.

[0066] S40: determining crack data based on the cable body image, calculating a crack coefficient based on the crack data, determining a cable body fault level based on the body crack type and the crack coefficient, and issuing corresponding warning information based on the cable body fault level;

[0067] In an embodiment of the present invention, the crack data includes crack length, crack width and crack depth, and the method for determining the crack data based on the cable body image includes:

[0068] The cable body image is converted into a cable grayscale image, the cable grayscale image is segmented by region growing to obtain a crack region map, and the crack region map is input into a pre-built deep neural network model to obtain the crack length, crack width and crack depth output by the deep neural network model;

[0069] It should be noted that training a deep neural network model using historical data is an existing technology, and this embodiment will not be elaborated on in detail.

[0070] Methods for calculating crack coefficients based on crack data include: Ckt = ;

[0071] Where Ckt is the crack coefficient, is the crack length, is the crack width, is the crack depth, and All are weight coefficients;

[0072] It should be noted that the crack length, crack width and crack depth are proportional to the degree of cable damage, so the crack coefficient is also proportional to the degree of cable damage;

[0073] The cable body fault level includes mild fault, moderate fault and severe fault. The method of determining the cable body fault level according to the body crack type and crack coefficient includes:

[0074] When the main body crack type is a circumferential crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a slight fault;

[0075] When the main body crack type is a circumferential crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a moderate fault;

[0076] When the main body crack type is an axial crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a moderate fault;

[0077] When the main body crack type is an axial crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a severe fault;

[0078] When the main body crack type is an inclined crack, the cable main body fault level is a severe fault;

[0079] It is understandable that, generally speaking, axial cracks are more serious than circumferential cracks because axial cracks directly affect the insulation performance of the cable and the integrity of the conductor, while oblique cracks usually cross the insulation layer and may cause the insulation layer to peel or separate, which is more likely to cause the degradation of the cable insulation performance and the occurrence of electrical failures;

[0080] In this embodiment, a camera image and an infrared image of the cable joint are first obtained, and a first image feature and a second image feature are obtained based on the camera image and the infrared image respectively. A fusion feature is generated based on the first image feature and the second image feature, and the fusion feature is input into a pre-built fault diagnosis model to obtain the cable fault category. When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflection method, and the cable body image is obtained according to the cable fault location. The cable body image is input into a pre-built fault classification model to obtain the body crack category, and crack data is determined based on the cable body image. The crack coefficient is calculated based on the crack data, and the cable body fault level is determined according to the body crack category and the crack coefficient. Therefore, this embodiment can perform rapid fault location in a mine environment, which is very important, and when a cable body fault occurs, the insulation damage can also be quickly located.

[0081] Embodiment 2: Based on Embodiment 1, this embodiment provides a mining high-voltage cable insulation detection system, including:

[0082] Data acquisition module: responding to cable abnormality signals to acquire camera images and infrared images of cable joints, wherein the cable abnormality signals are used to indicate cable insulation damage;

[0083] It should be noted that the cable abnormal signal is used to indicate cable insulation damage. The cable abnormal signal includes but is not limited to current abnormal signal and voltage fluctuation signal. Insulation damage causes voltage fluctuation or instability. Insulation damage causes current abnormality, such as a sudden increase or decrease in current. Both the current abnormal signal and the voltage fluctuation signal can be directly obtained by monitoring the cable.

[0084] It is understandable that, in a mine environment, the failure frequency of the cable joint is usually much greater than the failure frequency of the cable body. Therefore, when a cable fails, the camera image and infrared image of the cable joint should be quickly obtained, and the camera image and infrared image should be used to determine whether the cable joint has failed. This can quickly locate the fault and enhance the response rate of the detection system.

[0085] Fault determination module: obtains first image features and second image features based on the camera image and the infrared image respectively, generates fusion features based on the first image features and the second image features, inputs the fusion features into the pre-built fault diagnosis model, and obtains the cable fault category, which includes cable joint fault and cable body fault;

[0086] It should be noted that the first image feature includes but is not limited to texture feature and shape feature, the second image feature includes heat distribution feature, and both the first image feature and the second image feature can be obtained by a feature extraction algorithm. Existing feature extraction algorithms include, for example, the Canny edge detection algorithm and the directional gradient histogram algorithm, which will not be described in detail in this embodiment;

[0087] The method for generating a fusion feature according to a first image feature and a second image feature includes:

[0088] Cascadingly fusing the first image feature and the second image feature to generate a fused feature;

[0089] It can be understood that cascade fusion refers to cascading two feature vectors together to form a longer vector. The above cascade fusion is only an exemplary description, and fusion can also be performed in other ways, such as feature transformation, etc. This embodiment is not limited to this.

[0090] The construction method of the fault diagnosis model includes:

[0091] Obtain i groups of data, where i is a positive integer greater than 1, and the data includes historical fusion features and historical cable fault categories. The historical fusion features and historical cable fault categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical fusion features in the training set are used as input data, and the historical cable fault categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set. A classifier that meets a preset accuracy is output as a fault diagnosis model, and the classifier is preferably a naive Bayes model or a support vector machine model.

[0092] It is worth noting that the historical fusion feature in this embodiment is used to indicate whether a cable joint fails. When the insulation of the cable joint is damaged, the corresponding first image feature and the second image feature will also be different. For example, when the insulation of the cable joint is damaged, it will cause the local temperature to rise, and then there will be obvious hot spots or hot spots in the infrared image. These hot spots are usually displayed as bright areas in the infrared image, reflecting abnormal heat distribution;

[0093] Position determination module: When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflectometry method, the cable body image is obtained according to the cable fault location, and the cable body image is input into the pre-built fault classification model to obtain the body crack category;

[0094] Methods for locating cable faults based on time domain reflectometry include:

[0095] Acquire pulse data emitted from the fault location according to detectors at both ends of the cable, and determine the cable fault location based on the pulse data, the pulse data including pulse propagation speed and pulse propagation time;

[0096] Methods for determining cable fault locations based on pulse data include: F = ;

[0097] In the formula, F is the distance between the fault location and one end of the cable, It is the pulse propagation time required for the pulse signal sent from the fault location to reach one end of the cable. It is the pulse propagation time required for the pulse signal sent from the fault location to reach the other end of the cable. is the cable length, is the pulse propagation speed;

[0098] Combine the following Figure 2 For detailed explanation:

[0099] like Figure 2As shown in the figure, the cable is equipped with detectors at both ends A and B. The cable fault is at C. Due to the partial discharge phenomenon caused by the cable fault, two pulse signals will be generated at the same time. The pulse signal refers to the voltage pulse signal, and the two pulse signals move along the cable to ends A and B respectively. The moving speed of the two pulse signals is the same, both It can be understood that in this embodiment, the coordinate axis is established with the A end of the cable as the origin. F The positive and negative represent the direction of the coordinate axis, which is calculated by F The position of C can be determined;

[0100] In an embodiment of the present invention, after determining the cable fault position, the camera can be called to obtain a cable body image at the cable fault position according to the mapping relationship between the cable fault position and the camera position. The cable body image can be an infrared image. The body crack categories include axial cracks, circumferential cracks and oblique cracks. Axial cracks refer to cracks extending along the cable axis, circumferential cracks refer to cracks around the cable cross section, and oblique cracks refer to cracks extending obliquely along the cable insulation layer or outer sheath.

[0101] The construction method of the fault classification model includes:

[0102] Obtain h groups of data, where h is a positive integer greater than 1, and the data includes historical cable body images and historical body crack categories. The historical cable body images and historical body crack categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical cable body images in the training set are used as input data, and the historical body crack categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set, and a classifier that meets a preset accuracy is output as a fault classification model, and the classifier is preferably a naive Bayes model or a support vector machine model.

[0103] Level determination module: determines crack data based on the cable body image, calculates crack coefficient based on crack data, determines cable body fault level based on body crack type and crack coefficient, and issues corresponding warning information based on cable body fault level;

[0104] In an embodiment of the present invention, the crack data includes crack length, crack width and crack depth, and the method for determining the crack data based on the cable body image includes:

[0105] The cable body image is converted into a cable grayscale image, the cable grayscale image is segmented by region growing to obtain a crack region map, and the crack region map is input into a pre-built deep neural network model to obtain the crack length, crack width and crack depth output by the deep neural network model;

[0106] It should be noted that training a deep neural network model using historical data is an existing technology, and this embodiment will not be elaborated on in detail.

[0107] Methods for calculating crack coefficients based on crack data include: Ckt = ;

[0108] Where Ckt is the crack coefficient, is the crack length, is the crack width, is the crack depth, and All are weight coefficients;

[0109] It should be noted that the crack length, crack width and crack depth are proportional to the degree of cable damage, so the crack coefficient is also proportional to the degree of cable damage;

[0110] The cable body fault level includes mild fault, moderate fault and severe fault. The method of determining the cable body fault level according to the body crack type and crack coefficient includes:

[0111] When the main body crack type is a circumferential crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a slight fault;

[0112] When the main body crack type is a circumferential crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a moderate fault;

[0113] When the main body crack type is an axial crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a moderate fault;

[0114] When the main body crack type is an axial crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a severe fault;

[0115] When the main body crack type is an inclined crack, the cable main body fault level is a severe fault;

[0116] It is understandable that, generally speaking, axial cracks are more serious than circumferential cracks because axial cracks directly affect the insulation performance of the cable and the integrity of the conductor, while oblique cracks usually cross the insulation layer and may cause the insulation layer to peel or separate, which is more likely to cause the degradation of the cable insulation performance and the occurrence of electrical failures.

[0117] Embodiment 3: This embodiment discloses an electronic device, including a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, a method for detecting insulation of a high-voltage cable for mining provided by the above methods is implemented. The interface includes a network interface and a data interface. The network interface includes a wired or wireless interface, and the data interface includes an input or output interface.

[0118] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for detecting insulation of a high-voltage cable for mining in the embodiment of this application, based on the method for detecting insulation of a high-voltage cable for mining introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements the electronic device used in the method for detecting insulation of a high-voltage cable for mining in the embodiment of this application, it belongs to the scope of protection of this application.

[0119] Embodiment 4: Figure 3 As shown, this embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned method for detecting insulation of a high-voltage cable for mining is implemented.

[0120] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0121] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0122] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0127] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0128] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting insulation of a high-voltage cable for mining, characterized in that: include: S10: Responding to a cable abnormality signal, acquiring a camera image and an infrared image of the cable joint, wherein the cable abnormality signal is used to indicate cable insulation damage; S20: obtaining a first image feature and a second image feature based on the camera image and the infrared image, generating a fusion feature based on the first image feature and the second image feature, inputting the fusion feature into a pre-built fault diagnosis model, and obtaining a cable fault category, where the cable fault category includes a cable joint fault and a cable body fault; S30: When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflectometry method, a cable body image is obtained according to the cable fault location, and the cable body image is input into a pre-built fault classification model to obtain a body crack category; S40: determining crack data based on the cable body image, calculating crack coefficient according to the crack data, determining cable body fault level according to the body crack type and crack coefficient, and issuing corresponding warning information according to the cable body fault level.

2. A method for detecting insulation of a high-voltage cable for mining according to claim 1, characterized in that: The first image feature includes a texture feature and a shape feature, the second image feature includes a heat distribution feature, and the method for generating a fusion feature according to the first image feature and the second image feature includes: The first image feature and the second image feature are cascaded and fused to generate a fused feature.

3. A method for detecting insulation of a high-voltage cable for mining according to claim 1, characterized in that: The method for constructing the fault diagnosis model comprises: Obtain i groups of data, where i is a positive integer greater than 1, and the data includes historical fusion features and historical cable fault categories. The historical fusion features and historical cable fault categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical fusion features in the training set are used as input data, and the historical cable fault categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set, and a classifier that meets the preset accuracy is output as a fault diagnosis model.

4. A method for detecting insulation of a high-voltage cable for mining according to claim 1, characterized in that: The method for determining the cable fault location according to the time domain reflectometry method comprises: Acquire pulse data emitted from the fault location according to detectors at both ends of the cable, and determine the cable fault location based on the pulse data, the pulse data including pulse propagation speed and pulse propagation time; Methods for determining cable fault locations based on pulse data include: F = ; In the formula, F is the distance between the fault location and one end of the cable, It is the pulse propagation time required for the pulse signal sent from the fault location to reach one end of the cable. It is the pulse propagation time required for the pulse signal sent from the fault location to reach the other end of the cable. is the cable length, is the pulse propagation speed.

5. A method for detecting insulation of a high-voltage cable for mining according to claim 1, characterized in that: The method for constructing the fault classification model includes: Obtain h groups of data, where h is a positive integer greater than 1, and the data include historical cable body images and historical body crack categories. Use the historical cable body images and historical body crack categories as sample sets, divide the sample sets into training sets and test sets, build a classifier, use the historical cable body images in the training set as input data, use the historical body crack categories in the training set as output data, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets the preset accuracy as a fault classification model.

6. A method for detecting insulation of a high-voltage cable for mining according to claim 1, characterized in that: The crack data includes crack length, crack width and crack depth. The method for determining the crack data based on the cable body image includes: The cable body image is converted into a cable grayscale image, and the cable grayscale image is segmented by region growing to obtain a crack area map. The crack area map is input into a pre-built deep neural network model to obtain the crack length, crack width and crack depth output by the deep neural network model.

7. A method for detecting insulation of a high-voltage cable for mining according to claim 6, characterized in that: The method for calculating the crack coefficient according to the crack data includes: Ckt= ; Where Ckt is the crack coefficient, is the crack length, is the crack width, is the crack depth, and are all weight coefficients.

8. A method for detecting insulation of a high-voltage cable for mining according to claim 7, characterized in that: The cable body fault level includes a slight fault, a moderate fault and a severe fault. The method for determining the cable body fault level according to the body crack type and the crack coefficient includes: When the main body crack type is a circumferential crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a slight fault; When the main body crack type is a circumferential crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a moderate fault; When the main body crack type is an axial crack and the crack coefficient is less than the preset first coefficient threshold, the cable main body fault level is a moderate fault; When the main body crack type is an axial crack and the crack coefficient is greater than or equal to the preset first coefficient threshold, the cable main body fault level is a severe fault; When the main body crack type is an inclined crack, the cable main body fault level is a severe fault.

9. A mining high-voltage cable insulation detection system, which is used to implement a mining high-voltage cable insulation detection method according to any one of claims 1 to 8, characterized in that: include: Data acquisition module: responding to cable abnormality signals to acquire camera images and infrared images of cable joints, wherein the cable abnormality signals are used to indicate cable insulation damage; Fault determination module: obtains first image features and second image features based on the camera image and the infrared image respectively, generates fusion features based on the first image features and the second image features, inputs the fusion features into the pre-built fault diagnosis model, and obtains the cable fault category, which includes cable joint fault and cable body fault; Position determination module: When the cable fault category is a cable body fault, the cable fault location is determined according to the time domain reflectometry method, the cable body image is obtained according to the cable fault location, and the cable body image is input into the pre-built fault classification model to obtain the body crack category; Level determination module: Determine crack data based on the cable body image, calculate crack coefficient based on crack data, determine cable body fault level based on body crack type and crack coefficient, and issue corresponding warning information based on cable body fault level.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for detecting insulation of a high-voltage cable for mining according to any one of claims 1 to 8 is implemented.

Images