Cable operation state monitoring method and system based on deep learning

Abstract

The invention discloses a cable operation state monitoring method and system based on deep learning. The method comprises the following steps: acquiring cable state data acquired in real time in sensing equipment; monitoring and performing preliminary scoring and feedback of the cable operation state based on a preset cable state data operation range; based on a feature screening strategy, performing deep extraction on the cable state data subjected to feature extraction based on the HOG to obtain cable state feature data; and building a cable operation state monitoring model based on the BP neural network optimized by the improved genetic algorithm, and carrying out deep monitoring feedback on the obtained cable state feature data. The cable operation state is monitored based on the cable operation state monitoring model, adaptive adjustment is performed according to the current algorithm, and the monitoring effect of the BP neural network is improved; and a deep monitoring result is fed back through a plurality of alarm modes, so that the operation state of the cable can be received and monitored to the maximum extent, and the abnormal state of the cable can be quickly processed.

Description

Technical Field

[0001] The present invention relates to the field of cable technology, and in particular to a cable operation status monitoring method and system based on deep learning. Background Art

[0002] Power cables are cables used to transmit and distribute electrical energy. Power cables are commonly used in urban underground power grids, power station lead-out lines, internal power supply of industrial and mining enterprises, and underwater transmission lines across rivers and seas. In power lines, the proportion of cables is gradually increasing. Power cables are cable products used to transmit and distribute high-power electrical energy in the trunk lines of power systems. Existing power cable operation status monitoring and control systems usually first use maintenance to handle the abnormality after detecting an operation abnormality, and then replace the entire cable after the maintenance fails. Therefore, once the maintenance fails, the overall efficiency of cable abnormality handling will be low.

[0003] In the prior art, deep learning algorithms are often introduced into equipment status monitoring, such as BP neural network to learn and monitor the cable operation status. BP neural network can make the status expression more reflect the real status of cable equipment and realize daily equipment monitoring of cable equipment. However, the learning speed of BP neural network is slow and it is easy to fall into the situation of local extreme value, which makes the training fail. It is not conducive to the real-time monitoring of the cable operation status. Moreover, the equipment monitoring alarm in the prior art only uses a single alarm method, which cannot ensure that the cable equipment operation status is received to the maximum extent and realize the safety protection of the cable equipment operation. Summary of the invention

[0004] In order to solve the technical problems existing in the background technology, the present invention proposes a cable operation status monitoring method and system based on deep learning.

[0005] The present invention proposes a cable operation status monitoring method based on deep learning, comprising the following steps: S1: Collect the cable status data obtained in real time in the sensor equipment, and filter the cable status data based on the improved wavelet threshold algorithm; S2: Monitor the cable status data after filtering, and make a preliminary score and feedback on the cable operation status based on the preset cable status data operation range. When the monitored cable status data exceeds the cable status depth monitoring score threshold, go to S3, otherwise return to S1; S3: Based on the feature screening strategy, the cable status data extracted based on HOG is deeply extracted to obtain the cable status feature data; S4: A cable operation status monitoring model is built based on the BP neural network optimized by the improved genetic algorithm to conduct in-depth monitoring and feedback of the acquired cable status characteristic data.

[0006] Preferably, the cable status data in S1 includes cable operation electrical quantity data and cable operation physical quantity data.

[0007] Preferably, the data filtering process in S1 is specifically as follows:

[0008]

[0009] in, For the Layer estimated wavelet coefficients; For the decomposition Layer True wavelet coefficients; After selection Threshold value; is a mathematical constant; is a step function; is the median function; is a high-order factor.

[0010] Preferably, in S2, the cable data is graded according to the operating range of the cable status data, and status feedback of the cable data is performed according to the grade division result of the current cable data.

[0011] Preferably, the rating levels include abnormal, average, good and excellent.

[0012] Preferably, S3 performs feature extraction and feature screening on the cable operation states scored as abnormal, general and good according to the state feedback results described in S2.

[0013] Preferably, the feature screening strategy described in S3 is as follows: Get A collection of pattern classes:

[0014] in, For the The following model class The first cable status data HOG features; for Total number of cable status data in class mode; The number of HOG features for each cable status data; In each mode there are Cable status data, total cable status data, then there is HOG features, the feature set is ; Calculate the average distance of samples under the same condition :

[0015] in, For the The following model class The first cable status data HOG features; For the The following model class The first cable status data HOG features; Averaging to get the average intra-class distance :

[0016] Calculated variance factor :

[0017] Calculate the average distance between cable status data under different conditions :

[0018] Calculate the average inter-class distance between cable status data under different conditions :

[0019] in, For the The average distance between cable status data in each mode; calculate The variance factor :

[0020] Calculate the compensation factor for:

[0021] Calculate and normalize:

[0022] in, The first Cable status characteristic data.

[0023] Preferably, the cable operation status monitoring model in S4 is specifically constructed as follows: The input layer of the BP neural network contains neurons, and the hidden layer contains neurons, and the output layer contains neurons, Hidden layer output for:

[0024] Output layer output for:

[0025] in, The input layer neurons and hidden layer The weights between neurons, The input layer The output signal of a neuron, The hidden layer The neurons in the output layer The weights between neurons, is the activation function; Based on the improved genetic algorithm, the initial weights and output layer thresholds in the BP neural network are optimized: Population by Composed of chromosomes, Chromosomes contain Gene sequences are iterated by crossover and mutation, and the scoring error function is set as the fitness function value. The larger the fitness value, the greater the probability of being selected. The population is optimized based on the following selection probability, crossover probability and mutation probability: The probability of selection of chromosome as follows;

[0026] in, For the The inverse of the fitness value of the chromosome; The crossover probability of genes on chromosomes for:

[0027] in, represents the crossover probability of the gene, and Respectively represent the minimum crossover probability and maximum crossover probability of the gene, represents the fitness of the gene, represents the minimum fitness of the gene, represents the average fitness of the gene, is a mathematical constant; The probability of mutation of genes on chromosomes is:

[0028] in, represents the probability of gene mutation; and They represent the minimum and maximum mutation probabilities of the gene respectively.

[0029] Preferably, the in-depth monitoring feedback in S4 is based on information alerts, email alerts, telephone alerts and network alerts.

[0030] The present invention proposes a cable operation status monitoring system based on deep learning, comprising: Data acquisition module: used to collect the cable status data obtained in real time in the sensing equipment; Condition monitoring module: used for preliminary monitoring, scoring and feedback of cable condition data; Feature extraction module: used to perform deep extraction of cable status data based on HOG feature extraction based on feature screening strategy to obtain cable status feature data; Deep monitoring module: used to build a cable operation status monitoring model based on the BP neural network optimized by the improved genetic algorithm to conduct deep monitoring and feedback on the acquired cable status characteristic data; The data acquisition module also includes a data filtering unit, which is used to filter the cable status data based on an improved wavelet threshold algorithm; The state monitoring module includes a state scoring unit and a state feedback unit. The state scoring unit performs a preliminary scoring of the cable operation state based on a preset cable state data operation range; The state feedback unit performs feedback based on the scoring result of the state scoring unit.

[0031] The cable operation status monitoring method and system based on deep learning proposed in the present invention have the following beneficial effects: The present invention performs real-time monitoring of the cable operation status based on the BP neural network improved by the improved genetic algorithm, performs adaptive adjustment according to the current algorithm, and improves the monitoring effect of the BP neural network. It also feeds back the in-depth monitoring results through a variety of alarm methods, which can ensure that the cable operation status is received and monitored to the maximum extent, and can quickly handle the abnormal status of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flow chart of a cable operation status monitoring method based on deep learning proposed by the present invention; Figure 2 This is a monitoring effect diagram of a cable operation status monitoring method based on deep learning proposed by the present invention; Figure 3 This is a block diagram of a cable operation status monitoring system based on deep learning proposed in the present invention.

[0033] The meanings of the marks in the figure are: 100, data acquisition module; 110, data filtering unit; 200, state monitoring module; 210, state scoring unit; 220, state feedback unit; 300, scoring feedback module; 400, depth monitoring module. DETAILED DESCRIPTION

[0034] Reference Figure 1 , this embodiment provides a cable operation status monitoring method based on deep learning, including: S1: Collect the cable status data obtained in real time in the sensor device, and filter the cable status data based on the improved wavelet threshold algorithm; the specific steps are as follows: Based on sensor equipment, two types of cable status data are collected: cable operation electrical quantity data (such as current, voltage and partial discharge, etc.) and cable operation physical quantity data (such as cable operation temperature, ambient temperature, ambient humidity, etc.).

[0035] Processing the cable status data based on data cleaning, data filtering, missing value filling and data feature extraction operations; Data cleaning processing includes the removal of duplicate data and normalization of data of different dimensions, which can effectively improve the data processing speed.

[0036] The data filtering process is as follows:

[0037]

[0038] in, For the Layer estimated wavelet coefficients; For the decomposition Layer True wavelet coefficients; After selection Threshold value; is a mathematical constant; is a step function; is the median function; is a high-order factor; Traditional data filtering processing is based on hard threshold filtering to remove noise coefficients, but traditional denoising has data jumps, over-smoothing and other problems, which reduces the data representation ability; therefore, the above-mentioned multi-layer threshold method is adopted to estimate the threshold, improve the filtering function, and enhance the filtering ability of the function.

[0039] S2: Monitor the cable status data after filtering, and make a preliminary score and feedback on the cable operation status based on the preset cable status data operation range. When the monitored cable status data exceeds the cable status depth monitoring score threshold, go to S3, otherwise return to S1; the specific steps are as follows: The cable data is graded according to the operating range. The grades of abnormal, general, good and excellent correspond to less than 60 points, 60-80 points, 80-90 points and more than 90 points respectively. The upper and lower floating ranges of the rated cable status data can be divided according to the different types of cable status data for scoring. For excellence, For good, For general, more than The cable data status is abnormal; and the cable data status feedback is performed according to the current cable data scoring result. If the current cable status data changes within the range of If the score is above 90 points, the cable operation status at this time is judged to be excellent, and there is no need to further monitor the cable operation status, which can save computing resources and improve the efficiency of cable operation status monitoring; if the current cable status data changes within the range of If the score is between 80 and 90, the cable operation status is considered good, and the cable operation status is further monitored and fed back in real time; if the current cable operation status data changes within the range of to When the score is below 80 points, further monitoring will be carried out. In the actual operation monitoring process of the cable, through real-time data collection and monitoring, the changes in the range can be timely Further monitoring and feedback of the cable operation status within the good state range can basically ensure that the cable runs in the best working state and improve the operation efficiency of the cable.

[0040] The cable status data performs preliminary monitoring of the cable status based on the preset cable status data operating range, and can calculate the percentage change between the cable status data and the rated data.

[0041] S3: Based on the feature screening strategy, the cable status data extracted based on HOG is deeply extracted to obtain the cable status feature data; the specific steps are as follows: Get A collection of pattern classes:

[0042] in, For the The following model class The first cable status data HOG features; for Total number of cable status data in class mode; The number of HOG features for each cable status data; In each mode there are Cable status data, total cable status data, then there is HOG features, the feature set is ; Calculate the average distance of samples under the same condition :

[0043] in, For the The following model class The first cable status data HOG features; For the The following model class The first cable status data HOG features; Averaging to get the average intra-class distance :

[0044] Calculated variance factor :

[0045] Calculate the average distance between cable status data under different conditions :

[0046] Calculate the average inter-class distance between cable status data under different conditions :

[0047] in, For the The average distance between cable status data in each mode; calculate The variance factor :

[0048] Calculate the compensation factor for:

[0049] Calculate and normalize:

[0050] in, The first Cable status characteristic data.

[0051] The feature extraction algorithm is based on the feature screening strategy. It obtains the inter-class distance between feature categories and the intra-class distance of features, and obtains feature scores according to their wallpapers, thereby reducing data dimensionality and improving the data representation ability.

[0052] S4: Building a cable operation status monitoring model based on the BP neural network optimized by the improved genetic algorithm to conduct in-depth monitoring and feedback of the acquired cable status characteristic data; the specific steps are as follows: The cable operation status monitoring model is built based on the BP neural network optimized by genetic algorithm to further monitor and feedback the cable operation status that is scored as abnormal, general and good: The input layer of the BP neural network contains neurons, and the hidden layer contains neurons, and the output layer contains neurons, Hidden layer output for:

[0053] Output layer output for:

[0054] in, The input layer neurons and hidden layer The weights between neurons, The input layer The output signal of a neuron, The hidden layer The neurons in the output layer The weights between neurons, is the activation function; Based on the improved genetic algorithm, the initial weights and output layer thresholds in the BP neural network are optimized: Population by Composed of chromosomes, Chromosomes contain Gene sequences are iterated by crossover and mutation, and the scoring error function is set as the fitness function value. The larger the fitness value, the greater the probability of being selected. The population is optimized based on the following selection probability, crossover probability and mutation probability: The probability of selection of chromosome as follows;

[0055] in, For the The inverse of the fitness value of the chromosome; The crossover probability of genes on chromosomes for:

[0056] in, represents the crossover probability of the gene, and Respectively represent the minimum crossover probability and maximum crossover probability of the gene, represents the fitness of the gene, represents the minimum fitness of the gene, represents the average fitness of the gene, is a mathematical constant; The probability of mutation of genes on chromosomes is:

[0057] in, represents the probability of gene mutation; and They represent the minimum and maximum mutation probabilities of the gene respectively.

[0058] Through the improvement of the improved genetic algorithm mentioned above, it is possible to effectively retain excellent individuals, accelerate the elimination of inferior individuals, coordinate the contradiction between the diversity of the middle thousand and the convergence of the algorithm, make adaptive adjustments according to the current state of the BP neural network, and improve the monitoring effect of the BP neural network.

[0059] In the prior art, the cable operation status is monitored based on the BP neural network. It can automatically extract reasonable solution rules by learning the instance set with correct cable operation status data, that is, it has self-learning ability and certain promotion and generalization capabilities; however, the learning speed of the BP neural network is slow and it is easy to fall into the situation of local extreme values, causing training failure. Therefore, the present invention monitors the cable operation status by improving the BP neural network improved by the genetic algorithm. The specific monitoring accuracy can be referred to Figure 2 ,according to Figure 2 It can be clearly observed that the monitoring effect of the BP neural network optimized by the genetic algorithm is better than that of the BP neural network, and the monitoring accuracy of the cable operation status is significantly improved.

[0060] Feedback of in-depth monitoring results based on multiple alarm methods such as information alarm, email alarm, telephone alarm and network alarm can ensure that the cable operation status is received and monitored to the maximum extent, and can quickly deal with abnormal cable conditions.

[0061] Reference Figure 3 , this embodiment provides a cable operation status monitoring system based on deep learning, including: Data acquisition module 100: used to collect cable status data acquired in real time in the sensing device; Status monitoring module 200: used for preliminary monitoring, scoring and feedback of cable status data; Feature extraction module 300: used to perform deep extraction on the cable status data extracted based on HOG to obtain cable status feature data based on feature screening strategy; In-depth monitoring module 400: used to build a cable operation status monitoring model based on the BP neural network optimized by the improved genetic algorithm to perform in-depth monitoring and feedback on the acquired cable status characteristic data; The data acquisition module 100 further includes a data filtering unit 110, which is used to filter the cable status data based on an improved wavelet threshold algorithm; The state monitoring module 200 includes a state scoring unit 210 and a state feedback unit 220. The status scoring unit 210 performs a preliminary scoring of the cable operation status based on a preset cable status data operation range; The state feedback unit 220 provides feedback based on the scoring result of the state scoring unit 210 .

[0062] 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. A cable operation status monitoring method based on deep learning, characterized in that: The steps include: S1: Collect the cable status data obtained in real time in the sensor equipment, and filter the cable status data based on the improved wavelet threshold algorithm; S2: Monitor the cable status data after filtering, and make a preliminary score and feedback on the cable operation status based on the preset cable status data operation range. When the monitored cable status data exceeds the cable status depth monitoring score threshold, go to S3, otherwise return to S1; S3: Based on the feature screening strategy, the cable status data extracted based on HOG is deeply extracted to obtain the cable status feature data; S4: A cable operation status monitoring model is built based on the BP neural network optimized by the improved genetic algorithm to conduct in-depth monitoring and feedback of the acquired cable status characteristic data.

2. The cable operation status monitoring method based on deep learning according to claim 1 is characterized in that: The cable status data in S1 includes cable operation electrical quantity data and cable operation physical quantity data.

3. The cable operation status monitoring method based on deep learning according to claim 1 is characterized in that: The improved wavelet threshold algorithm described in S1 is as follows: in, For the Layer estimated wavelet coefficients; For the decomposition Layer True wavelet coefficients; After selection Threshold value; is a mathematical constant; is a step function; is the median function; is a high-order factor.

4. The cable operation status monitoring method based on deep learning according to claim 1 is characterized in that: In S2, the cable data is graded according to the operating range of the cable status data, and status feedback of the cable data is performed according to the scoring grade division result of the current cable data.

5. The cable operation status monitoring method based on deep learning according to claim 4 is characterized in that: The rating levels include abnormal, fair, good and excellent.

6. The cable operation status monitoring method based on deep learning according to claim 5 is characterized in that: S3 extracts and screens the cable operation states scored as abnormal, normal, and good according to the state feedback results described in S2.

7. The cable operation status monitoring method based on deep learning according to claim 1 is characterized in that: The feature screening strategy described in S3 is as follows: Get A collection of pattern classes: in, For the The following model class The first cable status data HOG features; for Total number of cable status data in class mode; The number of HOG features for each cable status data; In each mode there are Cable status data, total cable status data, then there is HOG features, the feature set is ; Calculate the average distance of samples under the same condition : in, For the The following model class The first cable status data HOG features; For the The following model class The first cable status data HOG features; Averaging to get the average intra-class distance : Calculated variance factor : Calculate the average distance between cable status data under different conditions : Calculate the average inter-class distance between cable status data under different conditions : in, For the The average distance between cable status data in each mode; calculate The variance factor : Calculate the compensation factor for: Calculate and normalize: in, The first Cable status characteristic data.

8. The cable operation status monitoring method based on deep learning according to claim 1 is characterized in that: The cable operation status monitoring model described in S4 is specifically constructed as follows: The input layer of the BP neural network contains neurons, and the hidden layer contains neurons, and the output layer contains neurons, Hidden layer output for: Output layer output for: in, The input layer neurons and hidden layer The weights between neurons, The input layer The output signal of a neuron, The hidden layer The neurons in the output layer The weights between neurons, is the activation function; Based on the improved genetic algorithm, the initial weights and output layer thresholds in the BP neural network are optimized: Population by Composed of chromosomes, Chromosomes contain Gene sequences are iterated by crossover and mutation, and the scoring error function is set as the fitness function value. The larger the fitness value, the greater the probability of being selected. The population is optimized based on the following selection probability, crossover probability and mutation probability: The probability of selection of chromosome as follows; in, For the The inverse of the fitness value of the chromosome; The crossover probability of genes on chromosomes for: in, represents the crossover probability of the gene, and Respectively represent the minimum crossover probability and maximum crossover probability of the gene, represents the fitness of the gene, represents the minimum fitness of the gene, represents the average fitness of the gene, is a mathematical constant; The probability of mutation of genes on chromosomes is: in, represents the probability of gene mutation; and They represent the minimum and maximum mutation probabilities of the gene respectively.

9. The cable operation status monitoring method based on deep learning according to claim 1 is characterized in that: The in-depth monitoring feedback described in S4 is based on information alerts, email alerts, telephone alerts and network alerts.

10. A cable operation status monitoring system based on deep learning using the method described in any one of claims 1 to 9, characterized in that: include: Data acquisition module (100): used to collect cable status data acquired in real time in the sensing device; Status monitoring module (200): used for preliminary monitoring, scoring and feedback of cable status data; Feature extraction module (300): used to perform deep extraction on the cable status data extracted based on HOG based on a feature screening strategy to obtain cable status feature data; A deep monitoring module (400): used to build a cable operation status monitoring model based on a BP neural network optimized by an improved genetic algorithm to perform deep monitoring and feedback on the acquired cable status characteristic data; The data acquisition module (100) further comprises a data filtering unit (110), wherein the data filtering unit (110) is used to perform filtering processing on the cable status data based on an improved wavelet threshold algorithm; The state monitoring module (200) comprises a state scoring unit (210) and a state feedback unit (220). The state scoring unit (210) performs a preliminary scoring of the cable operation state based on a preset cable state data operation range; The state feedback unit (220) provides feedback based on the scoring result of the state scoring unit (210).

Images