Online monitoring method for mining high-voltage feed cable

Abstract

The invention discloses an online monitoring method for a mining high-voltage feed cable, and relates to the technical field of cables, a three-dimensional route distribution model is established based on a distribution route of the high-voltage feed cable and mine hole distribution data, a plurality of monitoring nodes are arranged, and real-time operation data of the high-voltage feed cable at the monitoring nodes are acquired through a sensor group; establishing a real-time fault prediction model according to the equipment aging coefficient, the historical fault data and the standard operation data, substituting the real-time operation data into the real-time fault prediction model to output an equipment fault prediction coefficient, and judging a fault node according to a preset equipment fault. The loss prediction coefficient is calculated according to the real-time operation data of the fault node and the fault influence coefficient so as to delimit the loss influence area, signals of different grades are generated according to the preset loss prediction interval for visual display, comprehensive evaluation of the feed cable can be realized, and the loss degree is judged according to the prediction result so as to improve the reliability of the feed cable. And the corresponding emergency operation is adopted.

Description

Technical Field

[0001] The invention relates to the technical field of cables, and in particular to an online monitoring method for a high-voltage feeder cable for mining. Background Art

[0002] High-voltage cable is a type of power cable, which refers to the power cable used to transmit power between 1kv-1000kv, and is mostly used in power transmission and distribution. Mine high-voltage cable is the medium for underground power transmission in coal mines, and plays a vital role in coal mine safety and load operation stability. Due to the harsh operating environment of mine cables, the probability of electrical failure caused by cables is relatively high, accounting for about 2 / 3 of the total number of power supply accidents, and is one of the main causes of major accidents such as gas and coal dust explosions.

[0003] Traditional cable insulation monitoring methods are mostly offline detection. These methods are all carried out in a power outage state, making it difficult to timely judge the insulation level of the cable during operation and unable to continuously reflect the cable operation status. In addition, offline detection is very blind, wasting manpower and material resources, and some offline detection methods may even damage the cable insulation. Therefore, in order to improve the continuity, reliability and safety of coal mine power supply, it is urgent to find a practical and effective method to monitor the working status of high-voltage cables in mines in real time online; In view of the above technical defects, a solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to achieve a comprehensive evaluation of feeder cables and to determine the extent of loss based on the prediction results so as to take corresponding emergency actions.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: an online monitoring method for a mining high-voltage feeder cable, comprising the following steps: Step 1: Obtain the distribution route of the high-voltage feeder cable from the database, and establish a three-dimensional space model based on the mine distribution data where the high-voltage feeder cable is located, and merge the distribution route with the three-dimensional space model to obtain a three-dimensional route distribution model; Step 2: Establish a risk assessment model based on the deep learning neural network and the parameter data of the high-voltage feeder cable, set monitoring nodes according to the fault impact coefficient output by the risk assessment model, and mark several monitoring nodes one by one in the three-dimensional route distribution model; Step 3: Set a sensor group at the monitoring node, and obtain real-time operation data of the high-voltage feeder cable at the monitoring node through the sensor group; Step 4: Obtain standard operation data and equipment historical data higher than the feeder cable, wherein the equipment historical data includes equipment basic parameters, equipment activation time and historical fault data, calculate the equipment aging coefficient according to the equipment activation time and equipment basic parameters, and establish a real-time fault prediction model according to the equipment aging coefficient, historical fault data and standard operation data; Step 5: Substitute the real-time operation data into the real-time fault prediction model, output the equipment fault prediction coefficient, and judge the possibility of equipment failure according to the preset equipment fault judgment threshold. If the equipment has the possibility of failure, mark the corresponding monitoring node as a faulty node; Step 6: Obtain the real-time operation data of the faulty node, calculate the loss prediction coefficient based on the real-time operation data of the faulty node and the fault impact coefficient, and then define the loss impact area, generate a first-level reminder signal, a second-level reminder signal or a third-level reminder signal according to the preset loss prediction interval, and send it to the remote control center.

[0006] Further, the specific process of setting the monitoring node: S101, obtaining parameter data of the high-voltage feeder cable from a database, the parameter data including rated voltage, maximum operating voltage, and insulation resistance, and obtaining environmental conditions of the mine where the high-voltage feeder cable is located, the environmental conditions including ambient temperature data, ambient humidity data, and dust concentration data; S102, preprocessing the parameter data of the high-voltage feeder cable and the environmental conditions of the mine where the high-voltage feeder cable is located according to a preset parameter standard format, and integrating them into a training data set, and dividing the training data set into a training set and a test set in a ratio of 8:2; S103, inputting the training set into a plurality of preset regression models to perform regression training on the plurality of models respectively, obtaining a plurality of regression models, inputting the test set into the plurality of regression models respectively for testing, and selecting the model with the highest comprehensive accuracy according to the test results, and using it as the final risk assessment model; S104, after setting the environmental condition of the mine where the high-voltage feeder cable is located as the maximum risk value, input the pre-trained risk assessment model to predict the fault risk of the high-voltage feeder cable, and then output the fault influence coefficient value r; S105 , setting the fault impact range R=k*r according to the fault impact coefficient value, where k is a preset proportionality coefficient, and setting a monitoring node within the range adjacent to R in the three-dimensional route distribution model.

[0007] Furthermore, the sensor group includes a voltage sensor, a current sensor, a power meter, a temperature sensor, a partial discharge detector and a vibration sensor, and the real-time operation data includes real-time voltage data, real-time current data, operating power data, real-time temperature data, partial discharge data and operating vibration frequency.

[0008] Furthermore, the specific process of calculating the equipment aging coefficient is as follows: S201, acquiring basic equipment parameters and equipment activation time, wherein the basic equipment parameters include an oxide concentration C in an insulating material of a feeder cable; S202. Calculate the aging rate d (v) of the feeder cable according to the following formula: , where α is the reaction rate constant, β is the reaction order, T is the operating temperature data of the feeder cable, and t is the total time from the equipment activation time to the real time.

[0009] Furthermore, the specific process of establishing a real-time fault prediction model is as follows: S301, obtaining standard operation data and historical fault data of the feeder cable, constructing a cable fault diagnosis historical data set, and constructing a state prediction historical data set in combination with the equipment aging coefficient; S302, enhancing the training data by rotating, scaling, and cropping, and normalizing the cable fault diagnosis historical data set and the state prediction historical data set by using the mean value minus standard deviation method, establishing a two-dimensional coordinate system with the time series as the horizontal coordinate and the characteristic value as the vertical coordinate, marking the characteristic values ​​in the cable fault diagnosis historical data set and the state prediction historical data set one by one in the two-dimensional coordinate system according to the time series, and connecting each characteristic value point in the two-dimensional coordinate system with a smooth curve to obtain a number of cable state fluctuation curve diagrams; S303, using the cable state fluctuation curve as training data, dividing the training data into a training set, a test set, and a validation set according to a proportion, learning through a gradient descent method, retraining the deep learning neural network, and obtaining a real-time fault prediction model; S304, and evaluating the model effect through the validation set, and outputting the optimized real-time fault prediction model.

[0010] Furthermore, the specific process of obtaining the faulty node is as follows: Substitute the real-time operation data into the real-time fault prediction model to obtain the equipment fault prediction coefficient We. If the equipment fault prediction coefficient We is greater than or equal to the preset equipment fault judgment threshold, it means that the equipment has the possibility of failure. At the same time, a primary warning signal is generated, and the coordinates of the monitoring node that generates the primary warning signal are obtained, and the monitoring node is marked as a faulty node; If the equipment failure prediction coefficient We is less than the preset equipment failure judgment threshold, no signal is generated.

[0011] Furthermore, the specific process of generating the first level reminder signal, the second level reminder signal or the third level reminder signal is as follows: S401, acquiring real-time operation data and standard operation data of each fault node, wherein the standard operation data includes standard voltage data U0, standard current data I0, standard power data W0, optimal temperature data T0, maximum partial discharge data Q0 and rated maximum vibration frequency F0; S402. Calculate the loss prediction coefficient ui according to the following formula in combination with the fault impact coefficient: , where Ui is the real-time voltage data, Ii is the real-time current data, Wi is the working power data, Ti is the real-time temperature data, Qi is the partial discharge data, Fi is the working vibration frequency, e1, e2, e3, e4, e5 are all preset weight coefficients, which are used to evaluate the impact of various operating data on the loss prediction coefficient. The loss prediction coefficient is used to indicate the degree of loss that may be caused by the feed voltage based on the current fault condition; S403, obtaining the real-time coordinates of each fault node, defining the loss impact radius Rt=e3*ui according to the loss prediction coefficient, where e3 is a preset proportional coefficient, taking the fault node as the center and the loss impact radius as the loss impact area, integrating the loss impact area into the three-dimensional route distribution model in a visual standard graphic to obtain a loss impact image; S404, grayscale processing is performed on the loss impact image to obtain a grayscale value Gi of the loss impact image. The grayscale value Gi is used to reflect the overlap of the visualized standard graphics in the loss impact image. The larger the grayscale value Gi, the greater the overlap of the loss impact area, which means that there are more damaged points in the feeder cable and the greater the loss caused. Conversely, the smaller the grayscale value Gi, the smaller the overlap of the loss impact area, which means that there are fewer damaged points in the feeder cable and the less loss caused. S405, obtaining a preset loss prediction interval (Gmin, Gmax), and if the gray value Gi of the loss-affected image is less than or equal to Gmin, generating a first-level warning signal; If the gray value Gi of the loss-affected image is less than Gmax and less than Gmin, a secondary warning signal is generated; If the gray value Gi of the loss-affected image is greater than or equal to Gmax, a third-level warning signal is generated.

[0012] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: The online monitoring method of the high-voltage feeder cable for mining establishes a three-dimensional route distribution model based on the distribution route of the high-voltage feeder cable and the mine distribution data, and a number of monitoring nodes, obtains the real-time operation data of the high-voltage feeder cable at the monitoring node through a sensor group, and establishes a real-time fault prediction model according to the equipment aging coefficient, historical fault data and standard operation data, substitutes the real-time operation data into the real-time fault prediction model to output the equipment fault prediction coefficient, judges the fault node according to the preset equipment fault, calculates the loss prediction coefficient according to the real-time operation data of the fault node and the fault influence coefficient, and then delineates the loss influence area, generates different levels of signals according to the preset loss prediction interval for visual display, can realize the comprehensive evaluation of the feeder cable, and judges the loss degree according to the prediction result, so as to take corresponding emergency operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic flow chart of the method of the present invention is shown. DETAILED DESCRIPTION

[0014] 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.

[0015] Example: Figure 1 As shown, an online monitoring method for a high-voltage feeder cable for a mine comprises the following steps: Step 1: Obtain the distribution route of the high-voltage feeder cable from the database, and establish a three-dimensional space model based on the mine distribution data where the high-voltage feeder cable is located, and merge the distribution route with the three-dimensional space model to obtain a three-dimensional route distribution model; Step 2: Establish a risk assessment model based on the deep learning neural network and the parameter data of the high-voltage feeder cable, set monitoring nodes according to the fault impact coefficient output by the risk assessment model, and mark several monitoring nodes one by one in the three-dimensional route distribution model; The specific process of setting up monitoring nodes: S101, obtaining parameter data of the high-voltage feeder cable from a database, the parameter data including rated voltage, maximum operating voltage, and insulation resistance, and obtaining environmental conditions of the mine where the high-voltage feeder cable is located, the environmental conditions including ambient temperature data, ambient humidity data, and dust concentration data; S102, preprocessing the parameter data of the high-voltage feeder cable and the environmental conditions of the mine where the high-voltage feeder cable is located according to a preset parameter standard format, and integrating them into a training data set, and dividing the training data set into a training set and a test set in a ratio of 8:2; S103, inputting the training set into a plurality of preset regression models to perform regression training on the plurality of models respectively, obtaining a plurality of regression models, inputting the test set into the plurality of regression models respectively for testing, and selecting the model with the highest comprehensive accuracy according to the test results, and using it as the final risk assessment model; S104, after setting the environmental condition of the mine where the high-voltage feeder cable is located as the maximum risk value, input the pre-trained risk assessment model to predict the fault risk of the high-voltage feeder cable, and then output the fault influence coefficient value r; S105 , setting the fault impact range R=k*r according to the fault impact coefficient value, where k is a preset proportionality coefficient, and setting a monitoring node within the range adjacent to R in the three-dimensional route distribution model.

[0016] Step 3: Set a sensor group at the monitoring node, and obtain real-time operation data of the high-voltage feeder cable at the monitoring node through the sensor group; The sensor group includes a voltage sensor, a current sensor, a power meter, a temperature sensor, a partial discharge detector and a vibration sensor, and the real-time operation data includes real-time voltage data, real-time current data, working power data, real-time temperature data, partial discharge data and working vibration frequency.

[0017] Step 4: Obtain standard operation data and equipment historical data higher than the feeder cable, wherein the equipment historical data includes equipment basic parameters, equipment activation time and historical fault data, calculate the equipment aging coefficient according to the equipment activation time and equipment basic parameters, and establish a real-time fault prediction model according to the equipment aging coefficient, historical fault data and standard operation data; The specific process of calculating the equipment aging factor is as follows: S201, acquiring basic equipment parameters and equipment activation time, wherein the basic equipment parameters include an oxide concentration C in an insulating material of a feeder cable; S202. Calculate the aging rate d (v) of the feeder cable according to the following formula: , where α is the reaction rate constant, β is the reaction order, T is the operating temperature data of the feeder cable, and t is the total time from the equipment activation time to the real time.

[0018] The specific process of establishing a real-time fault prediction model is as follows: S301, obtaining standard operation data and historical fault data of the feeder cable, constructing a cable fault diagnosis historical data set, and constructing a state prediction historical data set in combination with the equipment aging coefficient; S302, enhancing the training data by rotating, scaling, and cropping, and normalizing the cable fault diagnosis historical data set and the state prediction historical data set by using the mean value minus standard deviation method, establishing a two-dimensional coordinate system with the time series as the horizontal coordinate and the characteristic value as the vertical coordinate, marking the characteristic values ​​in the cable fault diagnosis historical data set and the state prediction historical data set one by one in the two-dimensional coordinate system according to the time series, and connecting each characteristic value point in the two-dimensional coordinate system with a smooth curve to obtain a number of cable state fluctuation curve diagrams; S303, using the cable state fluctuation curve as training data, dividing the training data into a training set, a test set, and a validation set according to a proportion, learning through a gradient descent method, retraining the deep learning neural network, and obtaining a real-time fault prediction model; S304, and evaluating the model effect through the validation set, and outputting the optimized real-time fault prediction model.

[0019] Step 5: Substitute the real-time operation data into the real-time fault prediction model, output the equipment fault prediction coefficient, and judge the possibility of equipment failure according to the preset equipment fault judgment threshold. If the equipment has the possibility of failure, mark the corresponding monitoring node as a faulty node; The specific process of getting the faulty node is as follows: Substitute the real-time operation data into the real-time fault prediction model to obtain the equipment fault prediction coefficient We. If the equipment fault prediction coefficient We is greater than or equal to the preset equipment fault judgment threshold, it means that the equipment has the possibility of failure. At the same time, a primary warning signal is generated, and the coordinates of the monitoring node that generates the primary warning signal are obtained, and the monitoring node is marked as a faulty node; If the equipment failure prediction coefficient We is less than the preset equipment failure judgment threshold, no signal is generated.

[0020] Step 6: Obtain the real-time operation data of the faulty node, calculate the loss prediction coefficient based on the real-time operation data of the faulty node and the fault impact coefficient, and then define the loss impact area, generate a first-level reminder signal, a second-level reminder signal or a third-level reminder signal according to the preset loss prediction interval, and send it to the remote control center.

[0021] The specific process of generating a first-level reminder signal, a second-level reminder signal or a third-level reminder signal is as follows: S401, acquiring real-time operation data and standard operation data of each fault node, wherein the standard operation data includes standard voltage data U0, standard current data I0, standard power data W0, optimal temperature data T0, maximum partial discharge data Q0 and rated maximum vibration frequency F0; S402. Calculate the loss prediction coefficient ui according to the following formula in combination with the fault impact coefficient: , where Ui is the real-time voltage data, Ii is the real-time current data, Wi is the working power data, Ti is the real-time temperature data, Qi is the partial discharge data, Fi is the working vibration frequency, e1, e2, e3, e4, e5 are all preset weight coefficients, which are used to evaluate the impact of various operating data on the loss prediction coefficient. The loss prediction coefficient is used to indicate the degree of loss that may be caused by the feed voltage based on the current fault condition; S403, obtaining the real-time coordinates of each fault node, defining the loss impact radius Rt=e3*ui according to the loss prediction coefficient, where e3 is a preset proportional coefficient, taking the fault node as the center and the loss impact radius as the loss impact area, integrating the loss impact area into the three-dimensional route distribution model in a visual standard graphic to obtain a loss impact image; S404, grayscale processing is performed on the loss impact image to obtain a grayscale value Gi of the loss impact image. The grayscale value Gi is used to reflect the overlap of the visualized standard graphics in the loss impact image. The larger the grayscale value Gi, the greater the overlap of the loss impact area, which means that there are more damaged points in the feeder cable and the greater the loss caused. Conversely, the smaller the grayscale value Gi, the smaller the overlap of the loss impact area, which means that there are fewer damaged points in the feeder cable and the less loss caused. S405, obtaining a preset loss prediction interval (Gmin, Gmax), and if the gray value Gi of the loss-affected image is less than or equal to Gmin, generating a first-level warning signal; If the gray value Gi of the loss-affected image is less than Gmax and less than Gmin, a secondary warning signal is generated; If the gray value Gi of the loss-affected image is greater than or equal to Gmax, a third-level warning signal is generated.

[0022] The present invention establishes a three-dimensional route distribution model based on the distribution route of high-voltage feeder cables and the mine distribution data, and a number of monitoring nodes, obtains the real-time operation data of the high-voltage feeder cables at the monitoring nodes through a sensor group, and establishes a real-time fault prediction model according to the equipment aging coefficient, historical fault data and standard operation data, substitutes the real-time operation data into the real-time fault prediction model to output the equipment fault prediction coefficient, judges the fault node according to the preset equipment fault, calculates the loss prediction coefficient according to the real-time operation data of the fault node and the fault influence coefficient, and then delineates the loss influence area, generates signals of different levels according to the preset loss prediction interval for visual display, can realize the comprehensive evaluation of the feeder cable, and judges the degree of loss according to the prediction result, so as to take corresponding emergency operations.

[0023] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0024] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An online monitoring method for a high voltage feeder cable for mining, characterized in that: The following steps are involved: Step 1: Obtain the distribution route of the high-voltage feeder cable from the database, and establish a three-dimensional space model based on the mine distribution data where the high-voltage feeder cable is located, and merge the distribution route with the three-dimensional space model to obtain a three-dimensional route distribution model; Step 2: Establish a risk assessment model based on the deep learning neural network and the parameter data of the high-voltage feeder cable, set monitoring nodes according to the fault impact coefficient output by the risk assessment model, and mark several monitoring nodes one by one in the three-dimensional route distribution model; Step 3: Set a sensor group at the monitoring node, and obtain real-time operation data of the high-voltage feeder cable at the monitoring node through the sensor group; Step 4: Obtain standard operation data and equipment historical data higher than the feeder cable, wherein the equipment historical data includes equipment basic parameters, equipment activation time and historical fault data, calculate the equipment aging coefficient according to the equipment activation time and equipment basic parameters, and establish a real-time fault prediction model according to the equipment aging coefficient, historical fault data and standard operation data; Step 5: Substitute the real-time operation data into the real-time fault prediction model, output the equipment fault prediction coefficient, and judge the possibility of equipment failure according to the preset equipment fault judgment threshold. If the equipment has the possibility of failure, mark the corresponding monitoring node as a faulty node; Step 6: Obtain the real-time operation data of the faulty node, calculate the loss prediction coefficient based on the real-time operation data of the faulty node and the fault impact coefficient, and then define the loss impact area, generate a first-level reminder signal, a second-level reminder signal or a third-level reminder signal according to the preset loss prediction interval, and send it to the remote control center.

2. The online monitoring method for a mining high voltage feeder cable according to claim 1, characterized in that: The specific process of setting up monitoring nodes: S101, obtaining parameter data of the high-voltage feeder cable from a database, the parameter data including rated voltage, maximum operating voltage, and insulation resistance, and obtaining environmental conditions of the mine where the high-voltage feeder cable is located, the environmental conditions including ambient temperature data, ambient humidity data, and dust concentration data; S102, preprocessing the parameter data of the high-voltage feeder cable and the environmental conditions of the mine where the high-voltage feeder cable is located according to a preset parameter standard format, and integrating them into a training data set, and dividing the training data set into a training set and a test set in a ratio of 8:2; S103, inputting the training set into a plurality of preset regression models to perform regression training on the plurality of models respectively, obtaining a plurality of regression models, inputting the test set into the plurality of regression models respectively for testing, and selecting the model with the highest comprehensive accuracy according to the test results, and using it as the final risk assessment model; S104, after setting the environmental condition of the mine where the high-voltage feeder cable is located as the maximum risk value, input the pre-trained risk assessment model to predict the fault risk of the high-voltage feeder cable, and then output the fault influence coefficient value r; S105 , setting the fault impact range R=k*r according to the fault impact coefficient value, where k is a preset proportionality coefficient, and setting a monitoring node within the range adjacent to R in the three-dimensional route distribution model.

3. The online monitoring method for a mining high voltage feeder cable according to claim 1, characterized in that: The sensor group includes a voltage sensor, a current sensor, a power meter, a temperature sensor, a partial discharge detector and a vibration sensor, and the real-time operation data includes real-time voltage data, real-time current data, working power data, real-time temperature data, partial discharge data and working vibration frequency.

4. The online monitoring method for a mining high voltage feeder cable according to claim 1, characterized in that: The specific process of calculating the equipment aging coefficient is as follows: S201, acquiring basic equipment parameters and equipment activation time, wherein the basic equipment parameters include an oxide concentration C in an insulating material of a feeder cable; S202. Calculate the aging rate d (v) of the feeder cable according to the following formula: , where α is the reaction rate constant, β is the reaction order, T is the operating temperature data of the feeder cable, and t is the total time from the equipment activation time to the real time.

5. The online monitoring method for a mining high voltage feeder cable according to claim 1, characterized in that: The specific process of establishing a real-time fault prediction model is as follows: S301, obtaining standard operation data and historical fault data of the feeder cable, constructing a cable fault diagnosis historical data set, and constructing a state prediction historical data set in combination with the equipment aging coefficient; S302, enhancing the training data by rotating, scaling, and cropping, and normalizing the cable fault diagnosis historical data set and the state prediction historical data set by using the mean value minus standard deviation method, establishing a two-dimensional coordinate system with the time series as the horizontal coordinate and the characteristic value as the vertical coordinate, marking the characteristic values ​​in the cable fault diagnosis historical data set and the state prediction historical data set one by one in the two-dimensional coordinate system according to the time series, and connecting each characteristic value point in the two-dimensional coordinate system with a smooth curve to obtain a number of cable state fluctuation curve diagrams; S303, using the cable state fluctuation curve as training data, dividing the training data into a training set, a test set, and a validation set according to a proportion, learning through a gradient descent method, retraining the deep learning neural network, and obtaining a real-time fault prediction model; S304, and evaluating the model effect through the validation set, and outputting the optimized real-time fault prediction model.

6. The online monitoring method for a mining high voltage feeder cable according to claim 1, characterized in that: The specific process of getting the faulty node is as follows: Substitute the real-time operation data into the real-time fault prediction model to obtain the equipment fault prediction coefficient We. If the equipment fault prediction coefficient We is greater than or equal to the preset equipment fault judgment threshold, it means that the equipment has the possibility of failure. At the same time, a primary warning signal is generated, and the coordinates of the monitoring node that generates the primary warning signal are obtained, and the monitoring node is marked as a faulty node; If the equipment failure prediction coefficient We is less than the preset equipment failure judgment threshold, no signal is generated.

7. The online monitoring method for a mining high voltage feeder cable according to claim 1, characterized in that: The specific process of generating a first-level reminder signal, a second-level reminder signal or a third-level reminder signal is as follows: S401, acquiring real-time operation data and standard operation data of each fault node, wherein the standard operation data includes standard voltage data U0, standard current data I0, standard power data W0, optimal temperature data T0, maximum partial discharge data Q0 and rated maximum vibration frequency F0; S402. Calculate the loss prediction coefficient ui according to the following formula in combination with the fault impact coefficient: , where Ui is the real-time voltage data, Ii is the real-time current data, Wi is the working power data, Ti is the real-time temperature data, Qi is the partial discharge data, Fi is the working vibration frequency, and e1, e2, e3, e4, and e5 are all preset weight coefficients; S403, obtaining the real-time coordinates of each fault node, defining the loss impact radius Rt=e3*ui according to the loss prediction coefficient, where e3 is a preset proportional coefficient, taking the fault node as the center and the loss impact radius as the loss impact area, integrating the loss impact area into the three-dimensional route distribution model in a visual standard graphic to obtain a loss impact image; S404, grayscale processing is performed on the loss impact image to obtain a grayscale value Gi of the loss impact image, where the grayscale value Gi is used to reflect the overlap of the visualized standard graph in the loss impact image; S405, obtaining a preset loss prediction interval (Gmin, Gmax), and if the gray value Gi of the loss-affected image is less than or equal to Gmin, generating a first-level warning signal; If the gray value Gi of the loss-affected image is less than Gmax and less than Gmin, a secondary warning signal is generated; If the grayscale value Gi of the loss-affected image is greater than or equal to Gmax, a third-level warning signal is generated.

Images