Power equipment defect identification method and system based on edge cloud collaboration

Abstract

The invention discloses a power equipment defect identification method and system based on edge cloud collaboration, and relates to the technical field of power equipment defect identification, and the method comprises the steps that a data collection device collects monitoring data of power equipment in real time, and sends the monitoring data to an edge computing gateway in a monitoring area; the edge computing gateway receives the monitoring data, pre-processes the monitoring data, obtains the pre-processed monitoring data and uploads the pre-processed monitoring data to the cloud data center; the cloud data center receives the preprocessed monitoring data, performs electrical equipment defect identification on the received data by adopting a multi-mode defect identification model to obtain a real-time defect identification result, and processes the real-time defect identification result by adopting a maintenance strategy generation model to obtain a real-time maintenance strategy; and sending the real-time maintenance strategy to the edge computing gateway. According to the method, an edge cloud cooperation mechanism is adopted, power equipment defect identification is performed on monitoring data of power equipment timely and efficiently, and a defect identification result is analyzed to obtain a corresponding maintenance strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment defect identification, and specifically to a power equipment defect identification method and system based on edge-cloud collaboration. Background Art

[0002] Power equipment is an important part of the power system, and its health is directly related to the safe and stable operation of the power system. Equipment defects may lead to accidents such as power outages, fires, and even explosions, which have a serious impact on people's lives and production. Therefore, timely identification of power equipment defects is crucial to ensure the safety of the power system.

[0003] The existing power equipment defect identification technology has the following defects: Traditional power equipment defect identification usually performs data processing locally, but this method is inefficient when processing large amounts of data and is easily limited by the computing power of the equipment, resulting in insufficient real-time monitoring and analysis capabilities for power equipment and an inability to detect potential defects and faults in a timely manner. Existing power equipment defect identification often relies on a single type of monitoring data, such as image recognition or sensor data, and lacks fusion analysis of multi-source data. The limitations of a single data source may lead to low accuracy in defect identification, increasing the risk of misdiagnosis and missed diagnosis. The existing defect identification of power equipment lacks a response mechanism. After the power equipment defects are discovered, maintenance is carried out according to the preset maintenance strategy. However, the preset maintenance strategy is often based on experience and lacks data-driven intelligent decision-making support, which may lead to unreasonable resource allocation or wrong processing decisions, affecting the stable operation and economic benefits of the power system. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for identifying defects in power equipment based on edge-cloud collaboration, which solves the problems of low data processing efficiency, insufficient real-time monitoring and analysis capabilities, and low accuracy of defect identification in the prior art.

[0005] The present invention is achieved through the following technical solutions: In a first aspect, an embodiment of the present invention provides a method for identifying defects in power equipment based on edge-cloud collaboration, comprising the following steps: The data acquisition device collects monitoring data of the power equipment in real time, and sends the monitoring data of the power equipment to the edge computing gateway in the monitoring area; The edge computing gateway receives the monitoring data of the power equipment sent by the data acquisition device, preprocesses the monitoring data of the power equipment to obtain the preprocessed monitoring data, and uploads the preprocessed monitoring data to the cloud data center; The cloud data center receives the preprocessed monitoring data sent by the edge computing gateway, uses the constructed multimodal defect recognition model to identify the defects of the power equipment on the preprocessed monitoring data, and obtains real-time defect recognition results, uses the constructed maintenance strategy generation model to process the real-time defect identification results, obtains the real-time maintenance strategy, and sends the real-time maintenance strategy to the edge computing gateway.

[0006] Furthermore, before the step of the data acquisition device collecting monitoring data of the power equipment in real time, it also includes: taking minimizing the edge-cloud collaborative deployment cost as the optimization goal, using an intelligent optimization algorithm to generate an edge-cloud collaborative deployment plan for the power system, and using an artificial intelligence algorithm in the cloud data center to build a multimodal defect recognition model and a maintenance strategy generation model.

[0007] Furthermore, the edge-cloud collaborative deployment scheme for the power system generated by using the intelligent optimization algorithm adopts the ICPO optimization algorithm to generate the edge-cloud collaborative deployment scheme for the power system, specifically including: Taking minimizing the edge-cloud collaborative deployment cost as the optimization goal, the objective function of the ICPO optimization algorithm is set, and the ICPO individuals of the ICPO optimization algorithm are encoded to obtain the individual encoding format; According to the objective function, set the fitness function of the ICPO optimization algorithm, and set the ICPO population parameters and the maximum number of iterations of the ICPO optimization algorithm; According to the individual coding format and ICPO population parameters, the ICPO population is initialized to obtain an initial ICPO population including a number of initial ICPO individuals; According to the fitness function, ICPO population parameters and the maximum number of iterations, the initial ICPO population is iterated to find the best ICPO individual. The individual coding vector corresponding to the optimal ICPO individual is decoded to obtain the optimal edge-cloud collaborative deployment scheme for the power system.

[0008] Furthermore, the method of using artificial intelligence algorithms to construct a multimodal defect recognition model and a maintenance strategy generation model in a cloud data center specifically includes: Collecting some historical monitoring data, preprocessing the historical monitoring data, and obtaining the preprocessed historical monitoring data; Based on the preprocessed historical monitoring data, a multimodal fusion deep learning algorithm is used to build a multimodal defect recognition model and obtain several historical defect recognition results; According to the historical defect recognition results, a maintenance strategy generation model is constructed using a reinforcement learning algorithm, and several historical maintenance strategy generation experiences are obtained.

[0009] Furthermore, based on the preprocessed historical monitoring data, the specific method of using the multimodal fusion deep learning algorithm to construct a multimodal defect recognition model includes: The preprocessed historical monitoring data are divided into a model training set and a model test set in a ratio of 7:3; An initial multimodal defect recognition model is constructed using a CNN-LSTM-Attention-Elman algorithm, wherein the multimodal defect recognition model includes an image feature extraction module constructed based on a CNN algorithm, an operation feature extraction module constructed based on an LSTM algorithm, an attention weight module constructed based on an Attention mechanism, and a defect recognition module constructed based on an Elman algorithm. The initial multimodal defect recognition model is optimized and trained using a model training set to obtain an optimized multimodal defect recognition model. The optimized multimodal defect recognition model is tested using the model test set to obtain the corresponding model accuracy; If the model accuracy is greater than the accuracy threshold, the optimal multimodal defect recognition model is output, otherwise, the optimization training continues.

[0010] Furthermore, the maintenance strategy generation model is constructed based on the DQN algorithm. The maintenance strategy generation model includes an intelligent agent, an experience replay pool, and a deep Q network. According to the historical defect recognition results, the specific method of using the reinforcement learning algorithm to construct the maintenance strategy generation model includes: Generate questions based on the maintenance strategy, set up the simulation environment of the DQN algorithm, and build the intelligent agent and experience replay pool; According to the states involved in the historical defect recognition results, the state space of the DQN algorithm is defined, and the input layer of the deep Q network is constructed according to the data structure of the historical defect recognition results; According to the actions involved in the maintenance strategy, define the action space of the DQN algorithm, and construct the output layer of the deep Q network according to the data structure of the maintenance strategy; According to the input layer and the output layer, several hidden layers are set to construct the corresponding deep Q network, connecting the input layer to the state space and the output layer to the action space; Define the reward function of the DQN algorithm based on the impact of each action in the action space; Based on the state space, action space and reward function, several historical defect recognition results are used to optimize the training of the deep Q network and the intelligent agent, build a maintenance strategy generation model, and generate several historical maintenance strategy generation experiences; Several historical maintenance strategy generation experiences are stored in the experience replay pool of the maintenance strategy generation model.

[0011] Furthermore, the monitoring data of the power equipment includes real-time image monitoring data and real-time operation monitoring data, the edge computing gateway receives the monitoring data sent by the data acquisition device, preprocesses the monitoring data of the power equipment to obtain the preprocessed monitoring data, and uploads the preprocessed monitoring data to the cloud data center. The specific method includes: The edge computing gateway performs image preprocessing on the real-time image monitoring data to obtain the preprocessed real-time image monitoring data; The edge computing gateway performs data preprocessing on the real-time operation monitoring data to obtain the preprocessed real-time operation monitoring data; Integrate the preprocessed real-time image monitoring data and the preprocessed real-time operation monitoring data of the same power equipment to obtain the preprocessed monitoring data; The pre-processed monitoring data is compressed and encrypted to obtain an encrypted data compression package, which is then uploaded to the cloud data center.

[0012] Furthermore, the cloud data center receives the preprocessed monitoring data sent by the edge computing gateway, and uses the constructed multimodal defect recognition model to perform power equipment defect recognition on the preprocessed monitoring data, and the specific method for obtaining the real-time defect recognition result includes: The cloud data center receives the pre-processed monitoring data, decrypts and decompresses the encrypted data compression package, and obtains the decrypted pre-processed monitoring data; The image feature extraction module extracts the real-time image features of the decrypted pre-processed real-time image monitoring data; The operation feature extraction module extracts the real-time operation features of the decrypted pre-processed real-time operation monitoring data; Using the attention weight value preset by the attention weight module, the real-time image features and the real-time operation features are weightedly spliced ​​to obtain the real-time weighted splicing features; The defect recognition module is used to perform defect recognition on the real-time weighted splicing features to obtain real-time defect recognition results.

[0013] Furthermore, the specific method of using the constructed maintenance strategy generation model to process the real-time defect identification result to obtain the real-time maintenance strategy includes: The cloud data center updates the state space of the maintenance strategy generation model based on the real-time defect identification results to obtain an updated state space; Extracting a number of historical maintenance strategy generation experiences from the experience replay pool, and updating the action space of the maintenance strategy generation model based on the number of historical maintenance strategy generation experiences to obtain an updated action space; Inputting the updated state space into the input layer of the deep Q network of the maintenance strategy generation model, and connecting the updated action space to the output layer of the deep Q network to obtain an updated deep Q network; Based on the updated deep Q network, use the agent to control the updated deep Q network and output the Q values ​​of possible actions in the updated action space; Iteratively update the Q value according to the preset reward function to obtain an updated Q value until the number of iterations reaches the threshold; According to the greedy strategy, the possible action with the highest updated Q value in each iteration is used as the execution action of the corresponding state; Integrate the execution actions corresponding to all states in the updated state space to obtain the real-time maintenance strategy, and return it to the corresponding edge computing gateway.

[0014] In the second aspect, an embodiment of the present invention provides a power equipment defect identification system based on edge-cloud collaboration, which is used to implement the power equipment defect identification method based on edge-cloud collaboration described in the above embodiment. The system includes a cloud data center, several edge computing gateways and several data acquisition devices. The data acquisition device is arranged at the power equipment, and is used to collect the monitoring data of the power equipment in real time, and send the monitoring data of the power equipment to the edge computing gateway in the monitoring area; The edge computing gateway is used to receive the monitoring data of the power equipment sent by the data acquisition device, pre-process the monitoring data of the power equipment to obtain the pre-processed monitoring data, and upload the pre-processed monitoring data to the cloud data center; The cloud data center is used to receive the preprocessed monitoring data sent by the edge computing gateway, use the constructed multimodal defect recognition model to identify the defects of the power equipment on the preprocessed monitoring data, obtain real-time defect recognition results, use the maintenance strategy generation model to process the real-time defect recognition results, obtain the real-time maintenance strategy, and send the real-time maintenance strategy to the edge computing gateway.

[0015] Compared with the prior art, the present invention has the following advantages and beneficial effects: The embodiment of the present invention discloses a method for identifying defects in power equipment based on edge-cloud collaboration, introduces an edge-cloud collaboration mechanism, combines edge computing with cloud computing, effectively solves the deficiencies of traditional power equipment defects in data processing capability and real-time performance, strengthens data information interaction, and avoids the data island effect; the edge computing gateway in the monitoring area pre-processes the collected real-time monitoring data, reduces the computing burden of the cloud data center, and improves the efficiency of data processing; the constructed multimodal defect recognition model can integrate monitoring data of different modes for data analysis, timely discover potential defects and faults, improve efficiency, and improve the accuracy and reliability of defect identification; the constructed maintenance strategy generation model provides a response mechanism, which can intelligently generate maintenance strategies based on real-time defect identification results, optimize resource allocation, and provide guidance for processing decisions, greatly improving the timeliness and reliability of defect maintenance.

[0016] This method can generate an adaptive edge-cloud collaborative deployment plan for the power system, complete the deployment of a distributed edge-cloud collaborative architecture, reduce deployment costs, and improve the efficiency of data processing and transmission.

[0017] An embodiment of the present invention discloses an electric power equipment defect identification system based on edge-cloud collaboration and an electric power equipment defect identification method based on edge-cloud collaboration. They are based on the same inventive concept and have the same beneficial effects, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 A flow chart of a method for identifying defects in power equipment based on edge-cloud collaboration provided by an embodiment of the present invention; Figure 2 A structural block diagram of a power equipment defect identification system based on edge-cloud collaboration provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention. Example

[0020] like Figure 1As shown, the first embodiment of the present invention provides a method for identifying defects in power equipment based on edge-cloud collaboration, comprising the following steps: S1: Generate an edge-cloud collaborative deployment plan and use artificial intelligence algorithms to build a multimodal defect recognition model and maintenance strategy generation model in the cloud data center, including the following steps: S1-1: Taking minimizing the cost of edge-cloud collaborative deployment as the optimization goal, the Improved Crested Porcupine Optimizer (ICPO) is used to optimize and generate an edge-cloud collaborative deployment solution for the power system, including the following steps: S1-1-1: Taking minimizing the edge-cloud collaborative deployment cost as the optimization goal, set the objective function of the ICPO optimization algorithm, and encode the ICPO individuals of the ICPO optimization algorithm to obtain the individual encoding format.

[0021] S1-1-2: According to the objective function, set the fitness function of the ICPO optimization algorithm, and set the ICPO population parameters and maximum number of iterations of the ICPO optimization algorithm. The formula is: (1) In formula (1), is the fitness function; For ICPO individuals No. The cost of edge-cloud collaborative deployment, including hardware cost, communication cost, monitoring range cost, etc. For the Item cost weight; is the cost indicator; is the ICPO individual indicator, and n is a natural number.

[0022] S1-1-3: According to the individual coding format and ICPO population parameters, the Circle chaotic mapping sequence is used to initialize the ICPO population to obtain an initial ICPO population containing several initial ICPO individuals. The formula is: (2) In formula (2), It is the initial ICPO individual of Circle chaos mapping; is the randomly generated initial ICPO individual; It is the individual indicator of ICPO.

[0023] S1-1-4: According to the fitness function, ICPO population parameters and the maximum number of iterations, the initial ICPO population is iterated to find the best ICPO individual. Specifically, the following steps are included: S1-1-4-1: Introduce a cyclic population reduction mechanism to limit the number of individuals in the ICPO population parameters and obtain the updated ICPO population parameters for the next iteration. The formula is: (3) In formula (3), For the The number of individuals in the ICPO population parameter of the iteration; For the The number of individuals in the ICPO population parameter of the iteration; is the minimum number of individuals in the ICPO population parameter; Evaluate arguments for functions; Evaluate loop parameters for a function; is the maximum function evaluation loop parameter; t is the number of iterations indicator.

[0024] S1-1-4-2: According to the fitness function, calculate the initial fitness value of the initial ICPO individuals in the initial ICPO population.

[0025] S1-1-4-3: According to the initial fitness value and the updated ICPO population parameters, the first defense strategy, the second defense strategy, the third defense strategy and the fourth defense strategy are used to update the initial ICPO population to obtain an updated ICPO population.

[0026] Among them, the formula of the first defense strategy is: (4) In formula (4), For the updated ICPO individuals within the first defense range; The initial ICPO individual within the first defense range; is a random number based on normal distribution; is a random value in the interval [0,1]; It is the optimal solution within the first defense range; is the vector generated between the true optimal solution within the first defense range and the optimal solution randomly selected from the ICPO population; It is the individual indicator of ICPO.

[0027] The formula for the second defense strategy is: (5) In formula (5), For the updated ICPO individuals within the second defense range; The initial ICPO individual within the second defense range; is the search upper limit vector of the second defense range; is a random value in the interval [0,1]; Respectively Initial ICPO individuals; are two random integers between [1,S]; is the vector generated between the true optimal solution within the second defense range and the optimal solution randomly selected from the ICPO population.

[0028] The formula for the third defense strategy is: (6) In formula (6), For the updated ICPO individuals within the third defense range; The initial ICPO individual within the third defense range; is the search upper limit vector of the third defense range; Respectively Initial ICPO individuals; is a random integer between [1,S]; The odor diffusion factor defined for the fitness function; It is a defense factor; Control parameters for the search direction.

[0029] The formula for the fourth defense strategy is: (7) In formula (7), For the updated ICPO individuals within the fourth defense range; The initial ICPO individual within the fourth defense range; It is the optimal solution within the fourth defense range; All are random values ​​in the interval [0,1]; It is a defense factor; Control parameters for search direction; is the average force affecting the search direction; is the convergence speed factor.

[0030] S1-1-4-4: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the updated ICPO population to generate a dynamic reverse ICPO population. The formula is: (8) In formula (8), It is a dynamically reversed ICPO individual; is the decreasing inertia coefficient; are the maximum and minimum values ​​of the vector space respectively; For the updated ICPO individual.

[0031] S1-1-4-5: According to the fitness function, calculate the fitness values ​​of all ICPO individuals in the updated ICPO population and the dynamically reversed ICPO population, take the ICPO individual with the minimum fitness value as the optimal ICPO individual, and retain the optimal ICPO individual.

[0032] S1-1-4-6: If the number of iterations of iterative optimization reaches the maximum number of iterations or the fitness value of the optimal ICPO individual meets the requirements, the optimal ICPO individual will be output.

[0033] S1-1-5: Decode the individual coding vector corresponding to the optimal ICPO individual to obtain the optimal edge-cloud collaborative deployment solution for the power system. The optimal edge-cloud collaborative deployment solution includes the number of edge computing gateways, the location of edge computing gateways, the number of data acquisition devices, the location of data acquisition devices, the communication connection relationship between data acquisition devices and edge computing gateways, etc.

[0034] S1-2: Collect some historical monitoring data, and pre-process the some historical monitoring data to obtain some pre-processed historical monitoring data.

[0035] Preprocessing includes image preprocessing of historical image monitoring data in historical monitoring data and data preprocessing of historical operation monitoring data; image preprocessing includes Gaussian denoising, translation, scaling, cropping, grayscale processing and data enhancement, etc., and data preprocessing includes data cleaning, data dimensionality reduction and magnitude normalization processing, etc., to improve data quality and provide data support for subsequent model construction.

[0036] S1-3: Based on several pre-processed historical monitoring data, a multimodal defect recognition model is constructed using a multimodal fusion deep learning algorithm, and several historical defect recognition results are generated.

[0037] The multimodal defect recognition model is constructed based on the CNN-LSTM-Attention-Elman algorithm, and the multimodal defect recognition model includes an image feature extraction module constructed based on a convolutional neural network (CNN) algorithm, an operation feature extraction module constructed based on a long short-term memory network (LSTM) algorithm, an attention weight module constructed based on the Attention mechanism, and a defect recognition module constructed based on the Elman algorithm. The image feature extraction module and the operation feature extraction module are both connected to the attention weight module, and the attention weight module is connected to the defect recognition module.

[0038] The CNN network is highly compatible with the two-dimensional structure of the image. The pixels of the image are arranged in a fixed grid. CNN can effectively extract local features through convolution layers. Through multi-layer convolution and pooling operations, it can gradually abstract the high-level features of the image, so that it performs well in identifying complex objects and can extract deep features in the image. The LSTM network can learn to retain important information in long time series and ignore unimportant information through the gate mechanism, which makes the LSTM network have significant advantages when processing sequence data. The LSTM network can capture long-term dependencies in the data and extract data features in the running data sequence. The attention weight module automatically gives different levels of attention to different parts of the input feature sequence through the set attention weight value, which significantly improves the model's ability to process multimodal long sequence features because it allows the model to focus on the most relevant part of the input feature sequence when predicting each output. The Elman network enhances the traditional classifier by introducing context units (or state units). These context units can store past information, thereby affecting the current network output and achieving more accurate and efficient defect recognition prediction.

[0039] The specific method of using the multimodal fusion deep learning algorithm to build a multimodal defect recognition model includes the following steps: S1-3-1: Divide a number of pre-processed historical monitoring data into a model training set and a model test set in a ratio of 7:3; S1-3-2: Use the CNN-LSTM-Attention-Elman algorithm to build an initial multimodal defect recognition model, input the model training set, optimize the initial multimodal defect recognition model, and obtain an optimized multimodal defect recognition model; S1-3-3: Input the model test set, perform model testing on the optimized multimodal defect recognition model, and obtain the corresponding model accuracy; S1-3-4: If the model accuracy is greater than the accuracy threshold, the optimal multimodal defect recognition model is output and several historical defect recognition results are generated. Otherwise, the optimization training continues.

[0040] S1-4: Based on several historical defect recognition results, a maintenance strategy generation model is constructed using a reinforcement learning algorithm, and several historical maintenance strategy generation experiences are generated. The maintenance strategy generation model is constructed based on the Deep Q Network (DQN) algorithm, and the maintenance strategy generation model is provided with an intelligent agent, an experience replay pool, and a Deep Q Network.

[0041] The specific method of using reinforcement learning algorithm to build a maintenance strategy generation model includes the following steps: S1-4-1: Generate questions based on the maintenance strategy, set up the simulation environment of the DQN algorithm, and build the intelligent agent and experience replay pool; S1-4-2: Define the state space of the DQN algorithm based on the states involved in the historical defect recognition results, and construct the input layer of the deep Q network based on the data structure of the historical defect recognition results; S1-4-3: Define the action space of the DQN algorithm according to the actions involved in the maintenance strategy, and construct the output layer of the deep Q network according to the data structure of the maintenance strategy; S1-4-4: According to the input layer and the output layer, set several hidden layers, build the corresponding deep Q network, connect the input layer to the state space, and connect the output layer to the action space; S1-4-5: Define the reward function of the DQN algorithm based on the impact of each action in the action space; S1-4-6: Based on the state space, action space and reward function, use several historical defect recognition results to optimize the training of the deep Q network and the intelligent agent, build a maintenance strategy generation model, and generate several historical maintenance strategy generation experiences; S1-4-7: Store several historical maintenance strategy generation experiences into the experience playback pool of the maintenance strategy generation model.

[0042] S2: According to the edge-cloud collaborative deployment plan, an edge computing gateway is set up in each monitoring area in the power system, and a data acquisition device is set up at each power equipment in the monitoring area.

[0043] S3: Use the edge computing gateway to preprocess the real-time monitoring data of the power equipment collected by the data acquisition device in the monitoring area, obtain the preprocessed real-time monitoring data, and upload it to the cloud data center.

[0044] Among them, real-time monitoring data includes real-time image monitoring data and real-time operation monitoring data; real-time operation monitoring data includes power data of power equipment, current, voltage, power, load, operating time, etc., as well as temperature, humidity, pressure, etc. of the environment in which the power equipment is located; real-time operation monitoring data is used to analyze the internal defects of power equipment, such as operating defects under high temperature, operating vibration defects, etc., and real-time image monitoring data is used to analyze the external defects of power equipment, such as damage to the insulation layer, dust accumulation on insulators, aging of the chassis, etc.

[0045] The method of using an edge computing gateway to preprocess the real-time monitoring data of power equipment collected by a data collection device in a monitoring area, obtaining the preprocessed real-time monitoring data, and uploading it to a cloud data center includes the following steps: S3-1: Use a data acquisition device to collect real-time monitoring data of power equipment and send the real-time monitoring data to an edge computing gateway in the monitoring area; S3-2: Use the edge computing gateway to perform image preprocessing on the real-time image monitoring data in the real-time monitoring data to obtain preprocessed real-time image monitoring data; S3-3: Use the edge computing gateway to preprocess the real-time operation monitoring data in the real-time monitoring data to obtain the preprocessed real-time operation monitoring data; S3-4: Integrate the preprocessed real-time image monitoring data and the preprocessed real-time operation monitoring data of the same power equipment to obtain preprocessed real-time monitoring data; S3-5: compress and encrypt the pre-processed real-time monitoring data to obtain an encrypted data compression package, and upload the encrypted data compression package to the cloud data center.

[0046] The source of the key used to encrypt the data compression package is: based on a trusted organization, using an asymmetric encryption algorithm to generate keys for each edge computing gateway, and the obtained public and private keys are obtained by the following specific acquisition method: A-1: Based on a trusted institution, perform key initialization to obtain public parameters, master key and initial key. The formula is: (9) In formula (9), is a public parameter; is the master key; is the initial key; Integer domain A random number; Both are target hash functions; Both are cyclic groups The random number of the generator; is a random number Bilinear map of .

[0047] A-2: Use an asymmetric encryption algorithm to generate a public-private key pair for the edge computing gateway; (10) In formula (10), Edge computing gateway The private key of Integer domain A random number; Edge computing gateway The second private key parameter; Public parameters The target hash hash function; Indicator for edge computing gateway; is the master key; is the initial key; Edge computing gateway 's public key; Cyclic group The random number of the generator; Edge computing gateway Attribute information of the .

[0048] A-3: Store the private key in the public-private key pair to the corresponding edge computing gateway, and store the public key in the public-private key pair to the cloud data center to encrypt the data compression package. The formula is: (11) In formula (11), It is the encrypted data compression package; is an asymmetric encryption function; It is a data compression package; Edge computing gateway The private key of Indicates the quantity of edge computing gateway.

[0049] S4: Based on the cloud data center, according to the pre-processed real-time monitoring data, a multimodal defect recognition model is used to perform defect recognition and obtain real-time defect recognition results, including the following steps: S4-1: Based on the cloud data center, receive the encrypted data compression package sent by the edge computing gateway, decrypt and decompress it, obtain the decrypted pre-processed real-time monitoring data, and decrypt the encrypted data compression package. The formula is: (12) In formula (12), It is the compressed data package after decryption; is an asymmetric decryption function; It is the encrypted data compression package; Edge computing gateway The public key of

[0050] S4-2: Use the image feature extraction module of the multimodal defect recognition model to extract the real-time image features of the real-time image monitoring data in the decrypted pre-processed real-time monitoring data.

[0051] S4-3: Use the operation feature extraction module to extract the real-time operation features of the real-time operation monitoring data in the decrypted pre-processed real-time monitoring data.

[0052] S4-4: According to the attention weight value preset by the attention weight module, the real-time image features and the real-time operation features are weightedly spliced ​​to obtain the real-time weighted splicing features.

[0053] S4-5: Use the defect recognition module to perform defect recognition based on the real-time weighted splicing features to obtain real-time defect recognition results.

[0054] S5: Based on the cloud data center, according to the real-time defect identification results, the maintenance strategy generation model is used to generate the maintenance strategy, obtain the real-time maintenance strategy, and return it to the corresponding edge computing gateway, including the following steps: S5-1: Based on the cloud data center, according to the real-time defect identification results, the state space of the maintenance strategy generation model is updated to obtain the updated state space ,in, For the updated Status value, is the state indicator, is the total number of state space dimensions.

[0055] S5-2: Extract several historical maintenance strategy generation experiences from the experience playback pool, and update the action space of the maintenance strategy generation model based on several historical maintenance strategy generation experiences to obtain an updated action space ,in, For the updated Action value, is the action indicator, is the total number of action space dimensions.

[0056] S5-3: Input the updated state space into the input layer of the deep Q network of the maintenance strategy generation model, and connect the updated action space to the output layer of the deep Q network to obtain an updated deep Q network.

[0057] S5-4: Based on the updated deep Q network, use the agent to control the updated deep Q network and output the Q values ​​of possible actions in the updated action space.

[0058] S5-5: According to the preset reward function, the Q value is iteratively updated to obtain an updated Q value until the number of iterations reaches the threshold. The formula is: (13) In formula (13), The updated status value and the updated action value The corresponding updated Q value; Status value and action value The corresponding predicted Q value; is the learning rate; is the highest predicted Q value; It is a comprehensive indicator; To update the parameters.

[0059] S5-6: According to the greedy strategy, the possible action with the highest updated Q value in each iteration is used as the execution action of the corresponding state.

[0060] S5-7: Integrate the execution actions corresponding to all states in the updated state space to obtain the real-time maintenance strategy, and return it to the corresponding edge computing gateway.

[0061] An edge-cloud collaboration-based power equipment defect identification method provided by an embodiment of the present invention introduces an edge-cloud collaboration mechanism, combines edge computing with cloud computing, effectively solves the deficiencies of traditional power equipment defects in data processing capability and real-time performance, strengthens data information interaction, and avoids the data island effect; generates an adaptive edge-cloud collaboration deployment plan for the power system, completes the distributed edge-cloud collaboration architecture deployment, reduces deployment costs, and improves data processing and transmission efficiency; the constructed multimodal defect recognition model can integrate monitoring data of different modes for data analysis, timely discover potential defects and faults, improve efficiency, and improve the accuracy and reliability of defect identification; the edge computing gateway in the monitoring area pre-processes the collected real-time monitoring data, reduces the computing burden of the cloud data center, and improves the efficiency of data processing; the constructed maintenance strategy generation model provides a response mechanism, which can intelligently generate maintenance strategies based on real-time defect identification results, optimize resource allocation, and provide guidance for processing decisions, greatly improving the timeliness and reliability of defect maintenance. Example

[0062] like Figure 2 As shown, this embodiment provides a power equipment defect identification system based on edge-cloud collaboration, which is used to implement a power equipment defect identification method based on edge-cloud collaboration. The system includes a cloud data center, several edge computing gateways, and several data acquisition devices. The cloud data center is respectively communicated with the edge computing gateways of several monitoring areas in the power system, and each edge computing gateway is respectively communicated with the several data acquisition devices in the corresponding monitoring area, and each data acquisition device is arranged at the power equipment; A data acquisition device, used to collect real-time monitoring data of corresponding power equipment and send the real-time monitoring data to an edge computing gateway in the monitoring area; The edge computing gateway is used to receive the monitoring data sent by the data acquisition device in the monitoring area, perform preprocessing, obtain the preprocessed monitoring data, and upload it to the cloud data center; The cloud data center is used to receive the preprocessed monitoring data sent by the edge computing gateway, use the constructed multimodal defect recognition model to identify the defects of power equipment on the preprocessed monitoring data, obtain real-time defect recognition results, use the maintenance strategy generation model to process the real-time defect identification results, obtain the real-time maintenance strategy, and send the real-time maintenance strategy to the edge computing gateway.

[0063] The cloud data center is provided with an initialization unit, a defect identification unit, and a maintenance strategy generation unit connected in sequence; An initialization unit is used to generate an edge-cloud collaborative deployment plan and use artificial intelligence algorithms to build a multimodal defect recognition model and a maintenance strategy generation model in the cloud data center; A defect recognition unit is used to perform defect recognition based on the preprocessed monitoring data using a multimodal defect recognition model to obtain real-time defect recognition results; The maintenance strategy generation unit is used to generate maintenance strategies based on the real-time defect identification results using the maintenance strategy generation model, obtain the real-time maintenance strategies, and return them to the corresponding edge computing gateway.

[0064] An embodiment of the present invention provides an edge-cloud collaboration-based power equipment defect identification system, which introduces an edge-cloud collaboration mechanism, combines edge computing with cloud computing, effectively solves the deficiencies of traditional power equipment defects in data processing capabilities and real-time performance, strengthens data information interaction, and avoids the data island effect; generates an adaptive edge-cloud collaboration deployment plan for the power system, completes the distributed edge-cloud collaboration architecture deployment, reduces deployment costs, and improves data processing and transmission efficiency; the constructed multimodal defect recognition model can integrate monitoring data of different modes for data analysis, timely discover potential defects and faults, improve efficiency, and improve the accuracy and reliability of defect identification; the edge computing gateway in the monitoring area pre-processes the collected real-time monitoring data, reduces the computing burden of the cloud data center, and improves the efficiency of data processing; the constructed maintenance strategy generation model provides a response mechanism, which can intelligently generate maintenance strategies based on real-time defect identification results, optimize resource allocation, and provide guidance for processing decisions, greatly improving the timeliness and reliability of defect maintenance.

[0065] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying defects in power equipment based on edge-cloud collaboration, characterized in that: The following steps are involved: The data acquisition device collects monitoring data of the power equipment in real time, and sends the monitoring data of the power equipment to the edge computing gateway in the monitoring area; The edge computing gateway receives the monitoring data of the power equipment sent by the data acquisition device, preprocesses the monitoring data of the power equipment to obtain the preprocessed monitoring data, and uploads the preprocessed monitoring data to the cloud data center; The cloud data center receives the preprocessed monitoring data sent by the edge computing gateway, uses the constructed multimodal defect recognition model to identify the defects of the power equipment on the preprocessed monitoring data, and obtains real-time defect recognition results, uses the constructed maintenance strategy generation model to process the real-time defect identification results, obtains the real-time maintenance strategy, and sends the real-time maintenance strategy to the edge computing gateway.

2. The power equipment defect identification method based on edge-cloud collaboration according to claim 1 is characterized in that: Before the step of the data acquisition device collecting monitoring data of the power equipment in real time, it also includes: taking minimizing the edge-cloud collaborative deployment cost as the optimization goal, using an intelligent optimization algorithm to generate an edge-cloud collaborative deployment plan for the power system, and using an artificial intelligence algorithm in the cloud data center to build a multimodal defect recognition model and a maintenance strategy generation model.

3. The power equipment defect identification method based on edge-cloud collaboration according to claim 2 is characterized in that: The method of using an intelligent optimization algorithm to generate an edge-cloud collaborative deployment scheme for a power system uses an ICPO optimization algorithm to generate an edge-cloud collaborative deployment scheme for a power system, specifically including: Taking minimizing the edge-cloud collaborative deployment cost as the optimization goal, the objective function of the ICPO optimization algorithm is set, and the ICPO individuals of the ICPO optimization algorithm are encoded to obtain the individual encoding format; According to the objective function, set the fitness function of the ICPO optimization algorithm, and set the ICPO population parameters and the maximum number of iterations of the ICPO optimization algorithm; According to the individual coding format and ICPO population parameters, the ICPO population is initialized to obtain an initial ICPO population including a number of initial ICPO individuals; According to the fitness function, ICPO population parameters and the maximum number of iterations, the initial ICPO population is iterated to find the best ICPO individual. The individual coding vector corresponding to the optimal ICPO individual is decoded to obtain the optimal edge-cloud collaborative deployment scheme for the power system.

4. The power equipment defect identification method based on edge-cloud collaboration according to claim 3 is characterized in that: The method of using an artificial intelligence algorithm to construct a multimodal defect recognition model and a maintenance strategy generation model in a cloud data center specifically includes: Collecting some historical monitoring data, preprocessing the historical monitoring data, and obtaining the preprocessed historical monitoring data; Based on the preprocessed historical monitoring data, a multimodal fusion deep learning algorithm is used to build a multimodal defect recognition model and obtain several historical defect recognition results; According to the historical defect recognition results, a maintenance strategy generation model is constructed using a reinforcement learning algorithm, and several historical maintenance strategy generation experiences are obtained.

5. The power equipment defect identification method based on edge-cloud collaboration according to claim 4 is characterized in that: The specific method of constructing a multimodal defect recognition model based on the preprocessed historical monitoring data using a multimodal fusion deep learning algorithm includes: The preprocessed historical monitoring data are divided into a model training set and a model test set in a ratio of 7:3; An initial multimodal defect recognition model is constructed using a CNN-LSTM-Attention-Elman algorithm, wherein the multimodal defect recognition model includes an image feature extraction module constructed based on a CNN algorithm, an operation feature extraction module constructed based on an LSTM algorithm, an attention weight module constructed based on an Attention mechanism, and a defect recognition module constructed based on an Elman algorithm. The initial multimodal defect recognition model is optimized and trained using a model training set to obtain an optimized multimodal defect recognition model. The optimized multimodal defect recognition model is tested using the model test set to obtain the corresponding model accuracy; If the model accuracy is greater than the accuracy threshold, the optimal multimodal defect recognition model is output, otherwise, the optimization training continues.

6. The power equipment defect identification method based on edge-cloud collaboration according to claim 5 is characterized in that: The maintenance strategy generation model is constructed based on the DQN algorithm. The maintenance strategy generation model includes an intelligent agent, an experience replay pool, and a deep Q network. According to the historical defect recognition results, the specific method of using the reinforcement learning algorithm to construct the maintenance strategy generation model includes: Generate questions based on the maintenance strategy, set up the simulation environment of the DQN algorithm, and build the intelligent agent and experience replay pool; According to the states involved in the historical defect recognition results, the state space of the DQN algorithm is defined, and the input layer of the deep Q network is constructed according to the data structure of the historical defect recognition results; According to the actions involved in the maintenance strategy, define the action space of the DQN algorithm, and construct the output layer of the deep Q network according to the data structure of the maintenance strategy; According to the input layer and the output layer, several hidden layers are set to construct the corresponding deep Q network, connecting the input layer to the state space and the output layer to the action space; Define the reward function of the DQN algorithm based on the impact of each action in the action space; Based on the state space, action space and reward function, several historical defect recognition results are used to optimize the training of the deep Q network and the intelligent agent, build a maintenance strategy generation model, and generate several historical maintenance strategy generation experiences; Several historical maintenance strategy generation experiences are stored in the experience replay pool of the maintenance strategy generation model.

7. The power equipment defect identification method based on edge-cloud collaboration according to claim 6 is characterized in that: The monitoring data of the power equipment includes real-time image monitoring data and real-time operation monitoring data. The edge computing gateway receives the monitoring data of the power equipment sent by the data acquisition device, preprocesses the monitoring data of the power equipment to obtain the preprocessed monitoring data, and uploads the preprocessed monitoring data to the cloud data center. The specific method includes: The edge computing gateway performs image preprocessing on the real-time image monitoring data to obtain the preprocessed real-time image monitoring data; The edge computing gateway performs data preprocessing on the real-time operation monitoring data to obtain the preprocessed real-time operation monitoring data; Integrate the preprocessed real-time image monitoring data and the preprocessed real-time operation monitoring data of the same power equipment to obtain the preprocessed monitoring data; The pre-processed monitoring data is compressed and encrypted to obtain an encrypted data compression package, which is then uploaded to the cloud data center.

8. The power equipment defect identification method based on edge-cloud collaboration according to claim 7 is characterized in that: The cloud data center receives the pre-processed monitoring data sent by the edge computing gateway, and uses the constructed multi-modal defect recognition model to perform power equipment defect recognition on the pre-processed monitoring data, and the specific method for obtaining the real-time defect recognition result includes: The cloud data center receives the pre-processed monitoring data, decrypts and decompresses the encrypted data compression package, and obtains the decrypted pre-processed monitoring data; The image feature extraction module extracts the real-time image features of the decrypted pre-processed real-time image monitoring data; The operation feature extraction module extracts the real-time operation features of the decrypted pre-processed real-time operation monitoring data; Using the attention weight value preset by the attention weight module, the real-time image features and the real-time operation features are weightedly spliced ​​to obtain the real-time weighted splicing features; The defect recognition module is used to perform defect recognition on the real-time weighted splicing features to obtain real-time defect recognition results.

9. The power equipment defect identification method based on edge-cloud collaboration according to claim 8 is characterized in that: The specific method of using the constructed maintenance strategy generation model to process the real-time defect identification result to obtain the real-time maintenance strategy includes: The cloud data center updates the state space of the maintenance strategy generation model based on the real-time defect identification results to obtain an updated state space; Extracting a number of historical maintenance strategy generation experiences from the experience replay pool, and updating the action space of the maintenance strategy generation model based on the number of historical maintenance strategy generation experiences to obtain an updated action space; Inputting the updated state space into the input layer of the deep Q network of the maintenance strategy generation model, and connecting the updated action space to the output layer of the deep Q network to obtain an updated deep Q network; Based on the updated deep Q network, use the agent to control the updated deep Q network and output the Q values ​​of possible actions in the updated action space; Iteratively update the Q value according to the preset reward function to obtain an updated Q value until the number of iterations reaches the threshold; According to the greedy strategy, the possible action with the highest updated Q value in each iteration is used as the execution action of the corresponding state; Integrate the execution actions corresponding to all states in the updated state space to obtain the real-time maintenance strategy and return it to the corresponding edge computing gateway.

10. A power equipment defect identification system based on edge-cloud collaboration, used to implement the power equipment defect identification method based on edge-cloud collaboration as described in any one of claims 1 to 9, characterized in that: The system includes a cloud data center, several edge computing gateways and several data acquisition devices, wherein the data acquisition devices are arranged at the power equipment and are used to collect monitoring data of the power equipment in real time and send the monitoring data of the power equipment to the edge computing gateways in the monitoring area; The edge computing gateway is used to receive the monitoring data of the power equipment sent by the data acquisition device, pre-process the monitoring data of the power equipment to obtain the pre-processed monitoring data, and upload the pre-processed monitoring data to the cloud data center; The cloud data center is used to receive the preprocessed monitoring data sent by the edge computing gateway, use the constructed multimodal defect recognition model to identify the defects of the power equipment on the preprocessed monitoring data, obtain real-time defect recognition results, use the maintenance strategy generation model to process the real-time defect recognition results, obtain the real-time maintenance strategy, and send the real-time maintenance strategy to the edge computing gateway.

Images