CN116739996A - Power transmission line insulator fault diagnosis method based on deep learning - Google Patents

Abstract

The invention relates to a transmission line insulator fault diagnosis method based on deep learning, which includes the following steps. Step 1: Collect and process image information and working condition information of the transmission line insulator; Step 2: According to the insulator image data and insulator working condition characteristics The matrix data trains the insulator fault diagnosis model; Step 3: Determine the training effect of the transmission line insulator fault diagnosis model and save the trained model; Step 4: Apply the insulator fault diagnosis model to the online fault diagnosis of transmission line insulators. The transmission line insulator fault diagnosis method based on deep learning provided by the present invention can accurately classify different fault types, greatly improve the transmission line insulator fault diagnosis speed, and realize the transmission line insulator fault diagnosis by integrating the data preprocessing process and the end-to-end deep learning network. End-to-end fault diagnosis, simplifying the fault diagnosis process and achieving higher fault diagnosis accuracy.

Description

Deep learning-based fault diagnosis method for transmission line insulators

Technical field

This application relates to the technical field related to physical component fault diagnosis, and specifically relates to a deep learning-based method for fault diagnosis of transmission line insulators.

Background technique

Insulator (Insulator) is a physical component installed between conductors of different potentials or between conductors and grounding components and can withstand voltage and mechanical stress. There are many types of insulators in different shapes. Although the structures and shapes of different types of insulators are quite different, they are all composed of insulating parts and connecting fittings. Transmission line insulators are the component that accounts for the largest share in the entire power system. At the same time, transmission line failures are directly related to them to a large extent. Insulator failures directly or indirectly lead to most failures of transmission lines. There are many types of transmission line insulators. According to their different materials, they can be divided into three main types: porcelain insulators, glass insulators and composite insulators. Different types of insulators are prone to different fault types. In the long-term operation of transmission lines, insulators will be affected by many external environments, such as climate effects, temperature changes, etc., and differences in current and voltage of transmission lines will also affect the state of the insulators; in addition, the mechanical load of the insulators will also affect the condition of the insulator. At present, the possible fault types of transmission line insulators under various working conditions can be summarized as arc crawling, string loss, self-explosion, fracture, resistance degradation and surface contamination.

Traditional transmission line insulator fault diagnosis methods include the following, namely: the spark gap method, which is based on whether the insulator can produce discharge, which is a major basis for judging whether the insulator is faulty; the small ball discharge method, which is based on the voltage of the insulator. Distribution, fault diagnosis is performed by measuring the small balls at both ends of the insulator and observing their discharge distance. Both methods have the disadvantages of being unable to determine the specific fault category and low diagnostic accuracy; the infrared thermal imaging method, mainly According to the principle of thermal effect on the surface of the insulator, the surface temperature of the faulty insulator will be lower than that of the normal insulator. Although this method has a high accuracy, it still has the disadvantage of being unable to diagnose the specific fault type; the leakage current detection method can detect the current flowing through both ends of the insulator through the current sensor. The leakage current is measured to achieve fault diagnosis of the insulator, but this method cannot achieve live detection and the diagnosis cost is too high. Fault diagnosis technology based on deep learning visual recognition has developed rapidly and has also been applied in the field of transmission line insulator fault diagnosis. However, existing methods only achieve diagnosis of multiple fault categories through insulator images and do not consider the impact of working conditions on insulator faults. However, faults with no obvious visual changes such as resistance degradation cannot be detected at all.

As the attention mechanism network in deep learning becomes more and more widely used, visual question and answer task networks that combine the attention mechanism and deep convolutional neural networks have been developed; compared with diagnostic methods that rely solely on images, the attention mechanism and convolutional neural network are based on The deep neural network of the network can realize the combined analysis of image features and insulator operating condition features, which has more advantages in the field of insulator fault diagnosis.

Contents of the invention

In order to overcome the shortcomings of the existing technology, the deep learning-based transmission line insulator fault diagnosis method provided by the present invention can accurately classify different fault types and greatly improve the speed of transmission line insulator fault diagnosis. By integrating the data preprocessing process and end-to-end depth The learning network realizes end-to-end fault diagnosis of transmission line insulators, simplifies the fault diagnosis process, and obtains higher fault diagnosis accuracy.

In order to achieve the above object, the solution adopted by the present invention is:

A method for fault diagnosis of transmission line insulators based on deep learning, which includes the following steps:

Step 1: Collect and process image information and working condition information of transmission line insulators;

Collect image information of transmission line insulators, adjust the image scale through pixel sampling, and perform normalization processing to obtain insulator image data;

Collect the working condition information of transmission line insulators, including insulator material, transmission voltage, transmission current, insulator mechanical load, steel cap temperature, insulator temperature, ambient temperature and weather conditions, a total of 8-dimensional data, standardize the 8-dimensional data, and fill it with background data Obtain uniform-dimensional insulator operating condition characteristic matrix data;

Step 2: Train the insulator fault diagnosis model based on the insulator image data and the insulator working condition characteristic matrix data;

Establish training data based on the insulator image data and insulator working condition characteristic matrix data in step 1, divide the training data into a training data set and a verification data set in proportion, and transfer the training data set to the transmission line insulator fault diagnosis model based on deep learning. Training; the training of the transmission line insulator fault diagnosis model based on deep learning includes: ICN deep learning module, ECNN deep learning module, TSAN deep learning module, joint attention mechanism layer and output fully connected layer;

The key model structure of the TSAN deep learning module is the self-attention mechanism layer. The expression of the self-attention mechanism layer is as follows:

In the formula: Attention (Q, K, V) represents the self-attention mechanism function; Q represents the first intermediate data of the self-attention mechanism layer; K represents the second intermediate data of the self-attention mechanism layer; V represents the self-attention mechanism The third intermediate data of the layer; Swish represents the first activation function of the self-attention mechanism layer; _Wi represents the first learning parameter of the self-attention mechanism layer; b _i represents the second learning parameter of the self-attention mechanism layer; d represents The vector length of the first intermediate data Q and the second intermediate data K of the self-attention mechanism layer; x represents the input of the self-attention mechanism layer of the TSAN deep learning module; i represents different parameter numbers;

The joint attention mechanism layer can realize the fusion of insulator image features and insulator operating condition semantic features. The joint attention module is trained together with the feature extraction network and automatically optimizes learning parameters; the expression of the joint attention mechanism layer is as follows:

In the formula: α represents the first intermediate data of the joint attention mechanism layer; U represents the first learning parameter of the joint attention mechanism layer; y represents the output of the deep learning module of the ICN network and ECNN network; l represents the joint attention mechanism layer The second learning parameter; β represents the second intermediate data of the joint attention mechanism layer; sigmoid represents the first activation function of the joint attention mechanism layer; Swishb represents the second activation function of the joint attention mechanism layer; z represents the TSAN deep learning module Self-attention mechanism layer output; m represents the fourth learning parameter of the joint attention mechanism layer; output represents the joint attention mechanism layer output;

The activation function in the output fully connected layer is softmax, and the specific expression is as follows:

In the formula: j represents the neuron number of the fully connected layer; C ^j represents the output of the j-th neuron; ω ^j represents the first learning parameter of the output fully connected layer; β ^j represents the second learning parameter of the output fully connected layer; class ^j represents the probability that the input data belongs to the jth defect category; * represents matrix multiplication; softmax represents the activation function in the output fully connected layer;

Step 3: Determine the training effect of the transmission line insulator fault diagnosis model and save the trained model;

The training effect of the transmission line insulator fault diagnosis model is judged based on the verification data set in step 2. The transmission line insulator fault diagnosis model based on deep learning outputs the fault type of the abnormal insulator. The model is completed when the average absolute error of the verification data set is less than 0.9%. Train and save the trained transmission line insulator fault diagnosis model parameters. The average absolute error calculation formula is as follows:

In the formula: Lmp represents the average absolute error of the data set; N represents the number of batches in the data set; k represents the batch number; ACC _k represents the absolute accuracy of the network inference result in the kth batch;

Step 4: Apply the insulator fault diagnosis model to online fault diagnosis of transmission line insulators;

The input data for online fault diagnosis first needs to undergo the same data preprocessing operation as the training data in step 1, and then input the insulator fault diagnosis model based on deep learning to obtain the transmission line insulator fault type, and finally complete the transmission line insulator fault diagnosis.

Preferably, the training data in step 2 needs to use the fault diagnosis results of professional transmission line engineers to create real fault condition labels. The fault conditions of insulators include arc creep, string loss, self-explosion, fracture, resistance degradation and surface contamination. 6 categories.

Preferably, the feature extraction network of the deep learning-based transmission line insulator fault diagnosis model in step 2 includes a convolution layer, a deconvolution layer, a Concat mechanism, an activation function, a pooling layer and a fully connected layer. The ICN deep learning module, ECNN deep learning module and TSAN deep learning module, joint attention mechanism layer and output fully connected layer.

Preferably, the deep learning-based transmission line insulator fault diagnosis model in step 2 needs to calculate the cross-entropy loss function, as shown below:

In the formula: L represents the cross entropy loss function; M represents the total number of fault categories; y ⁱ represents the confidence of the i-th fault category; y ⁱ represents whether it is actually the fault category.

Preferably, the insulator image data in step 2 needs to be input into the ICN network for feature integration. The output data of the ICN network is then input into the ECNN network to obtain the insulator image feature data. The insulator working condition feature data is input into the TSAN deep learning module to obtain the insulator. Working condition semantic feature data, then the insulator image feature data and insulator working condition semantic feature data are transferred to the joint attention mechanism module, and finally the diagnosis result is output through the output fully connected layer;

Preferably, the ICN deep learning module and ECNN deep learning module in step 2 are specifically:

The ICN deep learning module uses three downsampling convolution layers and a maximum pooling with a stride of 2 and a deconvolution layer corresponding to the downsampling convolution;

The convolution kernel size of the two convolution layers included in the ECNN deep learning module is both 5 and the convolution step size is 1. Two maximum pooling series structures with a step size of 2 are used, with a total of four pools. chemical layer.

Preferably, in the joint attention mechanism layer in step 2, the degree of influence of the insulator operating condition information is obtained through the fully connected layer and the Sigmoid function, and then combined with the real image feature data of the insulator obtained by the ICN and ECNN deep learning modules to obtain The affected feature data is integrated and fault diagnosis results are output through the Softmax function.

Preferably, the TSAN deep learning module uses a multi-head self-attention mechanism with 8 heads as well as a feature expansion layer and a fully connected layer; the TSAN deep learning module can realize fault diagnosis of automatically extracting insulator working condition data Sensitive information, TSAN is trained together with the entire network, and can automatically optimize learning parameters; the diagnostic sensitive information of insulator operating condition data obtained by the TSAN deep learning module can affect the final fault diagnosis results through the joint attention mechanism module.

Compared with the prior art, the beneficial effects of the present invention are:

(1) The network model proposed by the present invention uses an insulator operating condition data feature extraction network based on a self-attention mechanism, which can perform parameter optimization together with the entire network to realize the quantification of the impact of insulator operating conditions on diagnostic results; it uses a joint attention mechanism based on The fault diagnosis results output network, the network output module can perform parameter optimization together with the overall network, realizing the correlation and result output of the influence of insulator working condition characteristics and insulator image characteristics.

(2) The deep learning-based transmission line insulator fault diagnosis method provided by the present invention can greatly improve the speed of transmission line insulator fault diagnosis, and can accurately classify different fault types, providing a reference for subsequent fault resolution and elimination, and helping to quickly restore power supply. . The deep learning-based transmission line insulator fault diagnosis method provided by the present invention realizes end-to-end fault diagnosis of transmission line insulators by integrating the data preprocessing process and the end-to-end deep learning network.

(3) The present invention provides users with a more convenient diagnosis method, which can be operated without mastering a large amount of professional transmission engineering knowledge, simplifies the insulator fault diagnosis process, and enables ordinary workers to realize insulator fault diagnosis after completing data collection; By using the designed network structure, higher fault diagnosis accuracy is achieved than existing deep learning networks.

Description of drawings

Figure 1 is a control block diagram of a transmission line insulator fault diagnosis method based on deep learning according to an embodiment of the present invention;

Figure 2 is a schematic flowchart of the steps of a transmission line insulator fault diagnosis method based on deep learning according to an embodiment of the present invention;

Figure 3 is a structural diagram of a network model according to an embodiment of the present invention;

Figure 4 is a calculation diagram of the joint attention mechanism layer in the network model according to the embodiment of the present invention;

Figure 5 is a calculation diagram of the multi-head self-attention layer in the network model according to the embodiment of the present invention;

Figure 6 is a diagram showing changes in loss value and accuracy rate during the network training process according to the embodiment of the present invention;

Figure 7 is a confusion matrix diagram of the network inference results considering only two fault types according to the embodiment of the present invention;

Figure 8 is an example of a real image of an insulator used in an embodiment of the present invention.

Detailed ways

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

The network model proposed by the embodiment of the present invention uses an insulator working condition data feature extraction network based on the self-attention mechanism to realize the quantification of the impact of the insulator working condition on the diagnosis results, and uses a fault diagnosis result output network based on the joint attention mechanism to realize the insulator The correlation between the influence of working condition characteristics and the insulator image features and the result output; the transmission line insulator fault diagnosis method based on deep learning can greatly improve the speed of transmission line insulator fault diagnosis, and can accurately classify different fault types, providing a basis for subsequent fault resolution and elimination Provide a reference to help restore power quickly. The deep learning-based fault diagnosis method for transmission line insulators provided by the present invention realizes end-to-end fault diagnosis of transmission line insulators by integrating the data preprocessing process and the end-to-end deep learning network; this case simplifies the insulator fault diagnosis process and enables Ordinary workers can diagnose insulator faults after completing data collection, and the accuracy of fault diagnosis is improved. Figure 1 shows a control block diagram of a transmission line insulator fault diagnosis method based on deep learning according to an embodiment of the present invention.

The embodiment of the present invention provides a method for fault diagnosis of transmission line insulators based on deep learning. Figure 2 is a schematic flowchart of the steps of the method of fault diagnosis of transmission line insulators based on deep learning according to the embodiment of the present invention; in order to prove the applicability of the present invention property, apply it to the instance, including the following steps:

S1: Collect and process image information and working condition information of transmission line insulators;

The image information of the transmission line insulator is collected, the image scale is adjusted through pixel sampling, and normalized processing is performed to obtain the insulator image data. The input image of the network is shown in Figure 8, which is an example of a real image of the insulator used in the embodiment of the present invention.

Collect the working condition information of transmission line insulators, including insulator material, transmission voltage, transmission current, insulator mechanical load, steel cap temperature, insulator temperature, ambient temperature and weather conditions, a total of 8-dimensional data, standardize the 8-dimensional data, and fill it with background data Obtain the insulator operating condition characteristic matrix data with uniform dimensions. The insulator operating condition data is a one-dimensional array containing eight data elements.

S2: Train the insulator fault diagnosis model based on the insulator image data and the insulator working condition characteristic matrix data;

Establish training data based on the insulator image data and insulator working condition characteristic matrix data in S1, divide the training data into training data sets and verification data sets in proportion, and transfer the training data set to the transmission line insulator fault diagnosis model based on deep learning for training ; The training data needs to use the fault diagnosis results of professional transmission line engineers to create real fault condition labels. The fault conditions of insulators include arc creep, string loss, self-explosion, fracture, resistance degradation and surface contamination, a total of 6 categories. The category labels of the data set It is given in the form of six-dimensional one-hot encoding.

The training of the transmission line insulator fault diagnosis model based on deep learning includes: ICN deep learning module, ECNN deep learning module, TSAN deep learning module, joint attention mechanism layer and output fully connected layer; as shown in Figure 4, an embodiment of the present invention Computational diagram of the joint attention mechanism layer in the network model. The feature extraction network of the transmission line insulator fault diagnosis model based on deep learning includes the ICN deep learning module and ECNN deep learning module composed of convolution layer, deconvolution layer, Concat mechanism, activation function, pooling layer and fully connected layer. and TSAN deep learning module, joint attention mechanism layer and output fully connected layer. Figure 3 shows a network model structure diagram according to an embodiment of the present invention. The TSAN deep learning module uses a multi-head self-attention mechanism with 8 heads, as well as a feature expansion layer and a fully connected layer; Figure 5 shows the calculation diagram of the multi-head self-attention layer in the network model of the embodiment of the present invention. The TSAN deep learning module can automatically extract sensitive fault diagnosis information from insulator working condition data. TSAN is trained together with the entire network and can automatically optimize learning parameters; the diagnostic sensitive information from insulator working condition data obtained by the TSAN deep learning module can be collected through joint attention. The force mechanism module affects the final fault diagnosis result. When the fault category is 6 and the batch size is set to 2, an example of the final result output by the network is as follows:

Afterwards, conditional statements are used to convert the output data into fault category output to complete the model inference process.

The insulator image data needs to be input into the ICN network for feature integration. The output data of the ICN network is then input into the ECNN network to obtain the insulator image feature data. The insulator working condition feature data is input into the TSAN deep learning module to obtain the insulator working condition semantic feature data. The insulator image features are then The data and insulator operating condition semantic feature data are passed into the joint attention mechanism module, and finally the diagnosis result is output through the output fully connected layer; the ICN deep learning module uses three downsampling convolutional layers and a maximum pooling with a step size of 2 And the deconvolution layer corresponding to the downsampling convolution; the convolution kernel size of the two convolution layers included in the ECNN deep learning module is both 5 and the convolution step size is 1. Two steps of 2 are used. Maximum pooling cascade structure, with a total of four pooling layers.

In the joint attention mechanism layer, the degree of influence of the insulator working condition information is obtained through the fully connected layer and the Sigmoid function, and then combined with the real image feature data of the insulator obtained by the ICN and ECNN deep learning modules, the affected integrated feature data is obtained and output through the Softmax function Fault diagnosis results.

The key model structure of the TSAN deep learning module is the self-attention mechanism layer. The expression of the self-attention mechanism layer is as follows:

In the formula: Attention (Q, K, V) represents the self-attention mechanism function; Q represents the first intermediate data of the self-attention mechanism layer; K represents the second intermediate data of the self-attention mechanism layer; V represents the self-attention mechanism The third intermediate data of the layer; Swish represents the first activation function of the self-attention mechanism layer; _Wi represents the first learning parameter of the self-attention mechanism layer; b _i represents the second learning parameter of the self-attention mechanism layer; d represents The vector length of the first intermediate data Q and the second intermediate data K of the self-attention mechanism layer; x represents the input of the self-attention mechanism layer of the TSAN deep learning module; i represents different parameter numbers.

The joint attention mechanism layer can realize the fusion of insulator image features and insulator operating condition semantic features. The joint attention module is trained together with the feature extraction network and automatically optimizes the learning parameters; the expression of the joint attention mechanism layer is as follows:

In the formula: α represents the first intermediate data of the joint attention mechanism layer; U represents the first learning parameter of the joint attention mechanism layer; y represents the output of the deep learning module of the ICN network and ECNN network; l represents the joint attention mechanism layer The second learning parameter; β represents the second intermediate data of the joint attention mechanism layer; sigmoid represents the first activation function of the joint attention mechanism layer; Swishb represents the second activation function of the joint attention mechanism layer; z represents the TSAN deep learning module Self-attention mechanism layer output; m represents the fourth learning parameter of the joint attention mechanism layer; output represents the joint attention mechanism layer output.

The activation function in the output fully connected layer is softmax, and the specific expression is as follows:

In the formula: j represents the neuron number of the fully connected layer; C ^j represents the output of the j-th neuron; ω ^j represents the first learning parameter of the output fully connected layer; β ^j represents the second learning parameter of the output fully connected layer; class ^j Indicates the probability that the input data belongs to the jth defect category; * indicates matrix multiplication; softmax indicates the activation function in the output fully connected layer.

The transmission line insulator fault diagnosis model based on deep learning needs to calculate the cross-entropy loss function. Figure 6 shows the loss value and accuracy change diagram of the network training process according to the embodiment of the present invention; as follows:

In the formula: L represents the cross entropy loss function; M represents the total number of fault categories; y ⁱ represents the confidence of the i-th fault category; y ⁱ represents whether it is actually the fault category.

S3: Determine the training effect of the transmission line insulator fault diagnosis model and save the trained model;

The training effect of the transmission line insulator fault diagnosis model is judged based on the verification data set in S2. The transmission line insulator fault diagnosis model based on deep learning outputs the fault type of the abnormal insulator. The model completes training when the average absolute error of the verification data set is less than 0.9%. , save the trained transmission line insulator fault diagnosis model parameters, and the average absolute error calculation formula is as follows:

In the formula: Lmp represents the average absolute error of the data set; N represents the number of batches in the data set; k represents the batch number; ACC _k represents the absolute accuracy of the network inference result in the kth batch.

S4: Apply the insulator fault diagnosis model to online fault diagnosis of transmission line insulators;

The input data for online fault diagnosis first needs to undergo the same data preprocessing operations as the training data in S1, and then input the insulator fault diagnosis model based on deep learning to obtain the transmission line insulator fault type, and finally complete the transmission line insulator fault diagnosis. Figure 7 shows a confusion matrix diagram of network inference results considering only two fault types according to the embodiment of the present invention. Through the analysis of the confusion matrix, it can be seen that the present invention has a good effect on fault diagnosis of transmission line insulators and can satisfy Actual usage requirements.

In summary, the prediction results of the transmission line insulator fault diagnosis method based on deep learning in this case have proven to be very effective.

(1) The embodiment of the present invention processes actual transmission line data through an insulator operating condition data feature extraction network based on a self-attention mechanism, and can perform parameter optimization together with the entire network to achieve quantification of the impact of insulator operating conditions on diagnostic results; use Based on the fault diagnosis result output network of the joint attention mechanism, the network output module can perform parameter optimization together with the overall network, realizing the correlation and result output of the influence of insulator working condition characteristics and insulator image characteristics.

(2) The deep learning-based transmission line insulator fault diagnosis method provided by the embodiment of the present invention can greatly improve the speed of transmission line insulator fault diagnosis, and can accurately classify different fault types, providing a reference for subsequent fault resolution and elimination, and helping to quickly Restore power. The deep learning-based transmission line insulator fault diagnosis method provided by the present invention realizes end-to-end fault diagnosis of transmission line insulators by integrating the data preprocessing process and the end-to-end deep learning network.

(3) The embodiment of the present invention simplifies the insulator fault diagnosis process, which can be operated without mastering a large amount of professional transmission engineering knowledge, so that ordinary workers can realize insulator fault diagnosis after completing data collection. It can be seen from the comparison of diagnosis results , this case can improve the accuracy of fault diagnosis and meet actual use needs.

The above-described embodiments are only descriptions of preferred embodiments of the present invention and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, those of ordinary skill in the art may make various modifications to the technical solutions of the present invention. All modifications and improvements shall fall within the protection scope determined by the claims of the present invention.

Claims (8)

1. The power transmission line insulator fault diagnosis method based on deep learning is characterized by comprising the following steps of:

step 1: acquiring and processing image information and working condition information of an insulator of a power transmission line;

acquiring image information of an insulator of the power transmission line, performing image scale adjustment through pixel sampling, and performing normalization processing to obtain data of the insulator image;

collecting working condition information of an insulator of a power transmission line, wherein the working condition information comprises 8-dimensional data of insulator materials, power transmission voltage, power transmission current, mechanical load of the insulator, steel cap temperature, insulator temperature, environmental temperature and weather conditions, the 8-dimensional data are standardized, and uniform-dimensional insulator working condition characteristic matrix data are obtained through background data filling;

step 2: training an insulator fault diagnosis model according to the insulator image data and the insulator working condition characteristic matrix data;

constructing training data according to the insulator image data and the insulator working condition characteristic matrix data in the step 1, dividing the training data into a training data set and a verification data set according to a proportion, and transmitting the training data set into a power transmission line insulator fault diagnosis model based on deep learning for training; the deep learning-based power transmission line insulator fault diagnosis model training comprises the following steps: the system comprises an ICN deep learning module, an ECNN deep learning module, a TSAN deep learning module, a common attention mechanism layer and an output full-connection layer;

the key model structure of the TSAN deep learning module is a self-attention mechanism layer, and the self-attention mechanism layer expression is as follows:

wherein: attention (Q, K, V) represents a self-Attention mechanism function; q represents first intermediate data of the self-attention mechanism layer; k represents second intermediate data of the self-attention mechanism layer; v represents third intermediate data of the self-attention mechanism layer; swish represents the first activation function of the self-attention mechanism layer; w (W) _i A first learning parameter representing a self-attention mechanism layer; b _i A second learning parameter representing a self-attention mechanism layer; d represents the vector length of the first intermediate data Q and the second intermediate data K of the self-attention mechanism layer; x represents the self-attention mechanism layer input of the TSAN deep learning module; i represents different parameter numbers;

the common attention mechanism layer can realize the fusion of the characteristics of the insulator sub-images and the semantic characteristics of the working conditions of the insulators, and the common attention module trains together with the characteristic extraction network and automatically optimizes learning parameters; the expression of the common attention mechanism layer is as follows:

wherein: alpha represents first intermediate data of the common attention mechanism layer; u represents a first learning parameter of the common attention mechanism layer; y represents the deep learning module output of the ICN network and the ECNN network; l represents a second learning parameter of the common attention mechanism layer; beta represents second intermediate data of the common attention mechanism layer; sigmoid represents a common attention mechanism layer first activation function; swishb represents a second activation function of the common attention mechanism layer; z represents the self-attention mechanism layer output of the TSAN deep learning module; m represents a fourth learning parameter of the common attention mechanism layer; output represents the common attention mechanism layer output;

the activation function in the output full-connection layer is softmax, and the specific expression is as follows:

wherein: j represents the full connection layer neuron number; c (C) ^j An output representing a j-th neuron; omega ^j A first learning parameter representing an output full connection layer; beta ^j A second learning parameter representing an output full connection layer; class of things ^j Representing a probability that the input data belongs to a j-th defect class; * Representing a matrix multiplication; softmax represents the activation function in the output fully connected layer;

step 3: determining the training effect of a fault diagnosis model of the insulator of the power transmission line, and storing the trained model;

judging the training effect of the transmission line insulator fault diagnosis model according to the verification data set in the step 2, outputting the fault type of the abnormal insulator based on the transmission line insulator fault diagnosis model subjected to deep learning, finishing training by the model when the average absolute error of the verification data set is less than 0.9%, and storing the trained transmission line insulator fault diagnosis model parameters, wherein the average absolute error calculation formula is as follows:

wherein: lmp represents the average absolute error of the dataset; n represents the number of data sets batch; k represents a batch number; ACC (ACC) _k Representing the absolute accuracy of the network reasoning result in the kth batch;

step 4: applying an insulator fault diagnosis model to online fault diagnosis of the insulator of the power transmission line;

the input data of the on-line fault diagnosis firstly needs to be subjected to the data preprocessing operation which is the same as that of the training data in the step 1, and the data is transmitted into an insulator fault diagnosis model based on deep learning to obtain the fault type of the insulator of the power transmission line, and finally the fault diagnosis of the insulator of the power transmission line is completed.

2. The deep learning-based power transmission line insulator fault diagnosis method according to claim 1, wherein the training data in the step 2 is required to make a real fault condition label by using a fault diagnosis result of a professional power transmission line engineer, and the fault condition of the insulator includes 6 categories of arc climbing, string falling, self-explosion, fracture, resistance degradation and surface pollution.

3. The deep learning-based power transmission line insulator fault diagnosis method according to claim 1, wherein the feature extraction network of the deep learning-based power transmission line insulator fault diagnosis model in step 2 comprises an ICN deep learning module and an ECNN deep learning module and a TSAN deep learning module, a common attention mechanism layer and an output full connection layer, each of which is composed of a convolution layer, a deconvolution layer, a Concat mechanism, an activation function, a pooling layer and a full connection layer.

4. The deep learning-based power transmission line insulator fault diagnosis method according to claim 1, wherein the deep learning-based power transmission line insulator fault diagnosis model in step 2 needs to calculate a cross entropy loss function as follows:

wherein: l represents a cross entropy loss function; m represents the total number of fault categories; y is ⁱ Representing the confidence of the ith fault class; y is ⁱ Indicating whether it is actually the fault category.

5. The deep learning-based power transmission line insulator fault diagnosis method according to claim 1, wherein the insulator image data in the step 2 is required to be input into an ICN network for feature integration, the output data of the ICN network is input into the ECNN network to obtain insulator image feature data, the insulator condition feature data is input into a TSAN deep learning module to obtain insulator condition semantic feature data, the insulator image feature data and the insulator condition semantic feature data are input into a common attention mechanism module, and finally a diagnosis result is output through an output full connection layer.

6. The deep learning-based power transmission line insulator fault diagnosis method according to claim 1, wherein the ICN deep learning module and the ECNN deep learning module in step 2 specifically are:

the ICN deep learning module uses three downsampling convolution layers and a maximum value pooling with a step length of 2, and deconvolution layers corresponding to downsampling convolution;

the ECNN deep learning module comprises two convolution layers, wherein the convolution kernel sizes of the two convolution layers are 5, the convolution step sizes are 1, a maximum value pooling series structure with the two step sizes of 2 is used, and the total number of the two pooling layers is four.

7. The deep learning-based power transmission line insulator fault diagnosis method according to claim 1, wherein the degree of influence of the insulator working condition information is obtained through a full connection layer and a Sigmoid function in the common attention mechanism layer in the step 2, and then the actual image feature data of the insulator obtained by the ICN and ECNN deep learning module is combined to obtain the affected integrated feature data and output a fault diagnosis result through a Softmax function.

8. The deep learning-based transmission line insulator fault diagnosis method according to claim 3, wherein a multi-head self-attention mechanism with the number of heads of 8, a characteristic unfolding layer and a full connection layer are used in the TSAN deep learning module; the TSAN deep learning module can automatically extract fault diagnosis sensitive information of insulator working condition data, and the TSAN training together with the whole network can automatically optimize learning parameters; the diagnosis sensitive information of the insulator working condition data obtained by the TSAN deep learning module can influence a final fault diagnosis result through the common attention mechanism module.