Methods, devices, and computer equipment for identifying industrial control commands in energy storage power stations

Abstract

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for identifying industrial control commands in energy storage power stations. The method includes: acquiring network communication data of the energy storage power station in real time; updating the current industrial control command identification model based on the network communication data when the network communication data meets preset conditions, thereby obtaining a new industrial control command identification model; acquiring the current network communication data of the energy storage power station, parsing and processing the current network communication data according to a preset industrial control protocol to obtain key fields of industrial control commands in the current network communication data; and inputting the key fields of industrial control commands as feature information into the new industrial control command identification model to obtain the industrial control command identification result corresponding to the current network communication data. This method can improve the accuracy of industrial control command identification.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for identifying industrial control commands in an energy storage power station. Background Technology

[0002] During the operation of an energy storage power station, a large number of industrial control commands are frequently transmitted in network communication. These commands are used for equipment control, status monitoring, and data acquisition.

[0003] However, with the increase in network scale and communication frequency, the accuracy and real-time performance of command recognition face significant challenges. Traditional industrial control systems rely on static rules or fixed protocol parsing methods to recognize commands, while the network traffic of energy storage power stations contains a large number of dynamic factors, such as changes in device access and updates in command types. This makes it difficult to cope with the frequently changing communication environment and diverse command types, resulting in poor accuracy in recognizing industrial control commands. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for identifying industrial control commands in energy storage power stations, which can improve the accuracy of industrial control command recognition, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for identifying industrial control commands in an energy storage power station, including:

[0006] Real-time acquisition of network communication data from energy storage power stations;

[0007] If the network communication data meets the preset conditions, the current industrial control instruction recognition model is updated according to the network communication data to obtain a new industrial control instruction recognition model;

[0008] The current network communication data of the energy storage power station is obtained, and the current network communication data is parsed and processed according to a preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data;

[0009] The key fields of the industrial control command are used as feature information and input into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data.

[0010] In one embodiment, the step of updating the current industrial control instruction recognition model based on the network communication data to obtain a new industrial control instruction recognition model when the network communication data meets preset conditions includes:

[0011] Based on the network communication data, the frequency of industrial control command transmission and the number of new devices connected within the preset time window are determined;

[0012] If the frequency of industrial control command transmission and / or the number of new devices connected exceed the corresponding preset threshold, the model weight and input feature weight of the current industrial control command recognition model are updated based on the network communication data within the preset time window to obtain a new industrial control command recognition model.

[0013] In one embodiment, the step of updating the current industrial control instruction recognition model based on the network communication data to obtain a new industrial control instruction recognition model when the network communication data meets preset conditions includes:

[0014] Based on the network communication data, determine the amount of network communication data and the number of industrial control command sending types within the preset time window;

[0015] If the amount of network communication data is less than the corresponding preset threshold, the model structure of the current industrial control instruction recognition model is trimmed according to the amount of network communication data to obtain a new industrial control instruction recognition model.

[0016] and / or

[0017] If the number of industrial control command sending types is less than the corresponding preset threshold, the input features of the current industrial control command recognition model are trimmed according to the number of industrial control command sending types to obtain a new industrial control command recognition model.

[0018] In one embodiment, the step of inputting the key fields of the industrial control instruction as feature information into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data includes:

[0019] The key fields of the industrial control instruction are preprocessed to obtain the preprocessed key fields of the industrial control instruction.

[0020] The preprocessed key fields of the industrial control instruction are standardized to obtain the standardized key fields of the industrial control instruction.

[0021] The standardized key fields of the industrial control instructions are converted into feature vectors;

[0022] The feature vector is input into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0023] In one embodiment, the new industrial control instruction recognition model includes a spatial feature extraction module, a short-time temporal feature extraction module, a long-time temporal feature extraction module, and a recognition module;

[0024] The step of inputting the feature vector into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data includes:

[0025] The spatial feature extraction module is used to perform spatial feature extraction processing on the feature vector to obtain the spatial features corresponding to the feature vector;

[0026] The spatial features are processed by the short-time temporal feature extraction module to obtain the short-time temporal features corresponding to the feature vector.

[0027] The long-time time series feature extraction module is used to perform long-time time series feature extraction processing on the short-time time series features to obtain the long-time time series features corresponding to the feature vector;

[0028] The long-term timing features are input into the recognition module to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0029] In one embodiment, after obtaining the industrial control instruction identification result corresponding to the current network communication data, the method further includes:

[0030] Monitor the status information and execution results of the target industrial control instruction; the target industrial control instruction is the industrial control instruction corresponding to the industrial control instruction identification result.

[0031] The status information and execution results are analyzed to obtain an execution report of the target industrial control instruction, and the execution report is uploaded to the blockchain network.

[0032] Secondly, this application also provides an energy storage power station industrial control command identification device, comprising:

[0033] The data acquisition module is used to acquire network communication data of the energy storage power station in real time;

[0034] The model update module is used to update the current industrial control instruction recognition model according to the network communication data when the network communication data meets the preset conditions, so as to obtain a new industrial control instruction recognition model.

[0035] The field parsing module is used to obtain the current network communication data of the energy storage power station, and to parse and process the current network communication data according to the preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data.

[0036] The instruction recognition module is used to input the key fields of the industrial control instruction as feature information into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0037] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0038] Real-time acquisition of network communication data from energy storage power stations;

[0039] If the network communication data meets the preset conditions, the current industrial control instruction recognition model is updated according to the network communication data to obtain a new industrial control instruction recognition model;

[0040] The current network communication data of the energy storage power station is obtained, and the current network communication data is parsed and processed according to a preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data;

[0041] The key fields of the industrial control command are used as feature information and input into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data.

[0042] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0043] Real-time acquisition of network communication data from energy storage power stations;

[0044] If the network communication data meets the preset conditions, the current industrial control instruction recognition model is updated according to the network communication data to obtain a new industrial control instruction recognition model;

[0045] The current network communication data of the energy storage power station is obtained, and the current network communication data is parsed and processed according to a preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data;

[0046] The key fields of the industrial control command are used as feature information and input into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data.

[0047] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0048] Real-time acquisition of network communication data from energy storage power stations;

[0049] If the network communication data meets the preset conditions, the current industrial control instruction recognition model is updated according to the network communication data to obtain a new industrial control instruction recognition model;

[0050] The current network communication data of the energy storage power station is obtained, and the current network communication data is parsed and processed according to a preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data;

[0051] The key fields of the industrial control command are used as feature information and input into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data.

[0052] The aforementioned method, device, computer equipment, computer-readable storage medium, and computer program product for recognizing industrial control commands in energy storage power stations first acquire network communication data of the energy storage power station in real time. By acquiring this data, the system can dynamically perceive the latest commands and status changes of each device within the energy storage power station, ensuring the real-time nature of industrial control command recognition. Next, when the network communication data meets preset conditions, the system updates the current industrial control command recognition model based on this data, resulting in a new model. Through monitoring and conditional judgment of the network communication data, the recognition model automatically updates under specific conditions, allowing it to adjust weights or structure according to the new communication data to adapt to changing factors in the scenario. This effectively improves the model's recognition accuracy and adaptability in different scenarios, avoiding recognition errors caused by data changes in traditional static models. Finally, the system acquires the current network communication data of the energy storage power station. The data, according to a preset industrial control protocol, is parsed and processed to obtain key fields of industrial control commands within the current network communication data. Through the preset parsing of the industrial control protocol, key fields of industrial control commands, such as command type, device identifier, and operating parameters, can be extracted from the raw data. This allows for accurate parsing of the core information of the industrial control commands, enabling the model to recognize and understand the specific meaning of each command, improving the precision of data parsing and ensuring the accuracy of recognition. Finally, the key fields of the industrial control commands are used as feature information and input into a new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data. The extracted key fields of the industrial control commands, as feature information input into the model, enhance the model's understanding and recognition capabilities of commands, helping the model quickly identify command types and corresponding operations, improving the model's recognition efficiency and accuracy, and enabling it to more accurately reflect the real-time command situation. In the above method, by acquiring network communication data from the energy storage power station in real time and dynamically updating the recognition model under specific conditions, it adapts to changes in the communication environment, improving the accuracy of recognition. By parsing the protocol to extract key fields of the instructions, feature information can be effectively extracted, and instruction types and parameters can be quickly identified, enabling real-time monitoring and efficient identification of industrial control instructions. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating a method for recognizing industrial control commands in an energy storage power station, as shown in one embodiment.

[0055] Figure 2 This is a flowchart illustrating the steps for obtaining industrial control command recognition results in one embodiment;

[0056] Figure 3 This is a flowchart illustrating the method for recognizing industrial control commands in an energy storage power station in another embodiment;

[0057] Figure 4 This is a structural block diagram of an energy storage power station industrial control command recognition device in one embodiment;

[0058] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] In one embodiment, such as Figure 1 As shown, a method for recognizing industrial control commands in an energy storage power station is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. In this embodiment, the method includes the following steps:

[0061] Step S101: Obtain network communication data of the energy storage power station in real time.

[0062] Network communication data refers to the industrial control commands, status information, and sensor data transmitted between devices within the energy storage power station and between the devices and the control center via the network. This data reflects the real-time control and monitoring information during the operation of the energy storage power station, including key information such as device status, operating commands, and feedback information, and possesses strong timeliness and dynamism.

[0063] For example, the terminal can acquire network communication data from an energy storage power station in real time through various methods. For instance, by connecting to a network switching device, the terminal can continuously monitor network communication traffic between devices within the energy storage power station, ensuring the integrity and real-time nature of the communication content through full data capture. Specifically, the terminal can capture all communication data packets in real time by connecting to the mirror port of the energy storage power station's network switch. The mirror port copies the entire energy storage power station's communication data to the terminal, which, through high-performance network cards and big data technology, ensures the complete recording and storage of all data packet content in a high-speed environment. The terminal also extracts initial information (such as IP address, port number, and data packet size) through basic protocol parsing, providing support for subsequent in-depth parsing and command recognition.

[0064] Step S102: If the network communication data meets the preset conditions, update the current industrial control instruction recognition model according to the network communication data to obtain a new industrial control instruction recognition model.

[0065] The preset conditions refer to specific triggering conditions used to determine changes in the network communication environment or business scenario, such as command sending frequency, data traffic, and the number of connected devices. When these factors in the network communication data exceed the preset thresholds, it is determined that the current recognition model may not be suitable for the new business scenario, thus triggering a model update.

[0066] For example, the terminal can determine whether preset conditions are met by monitoring the characteristics of network communication data in real time. For instance, the terminal can monitor the frequency of command transmission and the changing trends of data traffic. When significant changes in these characteristics are detected, the terminal can dynamically update the recognition model through incremental learning or online learning modules, enabling the model to adapt to new data distributions and command patterns. In specific implementations, the terminal can adjust the model's weights, the weights of input features, or the network structure according to the current scenario, thereby improving the model's recognition accuracy and adaptability in new scenarios, ultimately obtaining a new industrial control command recognition model suitable for the current business environment.

[0067] Step S103: Obtain the current network communication data of the energy storage power station, and parse and process the current network communication data according to the preset industrial control protocol to obtain the key fields of the industrial control instructions in the current network communication data.

[0068] Industrial control protocols refer to specific industrial control protocols used for communication between devices in energy storage power stations. These protocols define instruction formats, field types, and their structures to enable the identification and extraction of key information from instructions during parsing. Common industrial control protocols include Modbus and IEC 104, which cover key information such as instruction types, data content, and timestamps.

[0069] For example, the terminal can obtain key fields based on deep parsing of industrial protocols. In specific implementations, the terminal uses a parsing engine to parse network packets within the energy storage power station layer by layer, from the IP layer and transport layer (such as TCP / UDP) to the application layer protocols, ensuring data integrity and validity. The terminal first parses the IP layer and transport layer protocols of the communication data to ensure correct data transmission. Then, it performs deep parsing of the industrial control protocols at the application layer (such as IEC 61850 and IEC 104), focusing on extracting specific logical nodes, data objects, and remote control types within the protocols. For instance, for the IEC 104 protocol, the terminal can identify the structure of telemetry and remote control data, ensuring that the basic information of each instruction is accurately decomposed.

[0070] During the parsing process, the terminal gradually extracts key fields from industrial control behavior commands, such as "invokeID," "confirmedServiceRequest," "itemId," "Data," and "confirmedServiceResponse." These fields accurately describe the command type, target device, and operating parameters, ensuring the correct transmission and execution of commands in complex network environments. Based on long-term command data monitoring and parsing results, the terminal also constructs a command feature library. This feature library covers common command patterns and types in energy storage power stations, serving as an important reference for the identification model. When a new command arrives, the terminal compares its features to determine whether it conforms to a known pattern, ensuring the accuracy of identification and the reliability of command execution.

[0071] Step S104: Input the key fields of the industrial control instruction as feature information into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0072] Among them, key fields of industrial control instructions refer to important fields extracted from the instructions through protocol parsing. These fields describe the core content and attributes of the instructions, including information such as instruction type, target device, and data content. After feature processing, these key fields will serve as input features for the recognition model, used for the model's recognition and inference.

[0073] For example, after extracting key fields from industrial control instructions, the terminal can convert these fields into numerical feature vectors to adapt to the model's input requirements. In specific implementations, the terminal can map field data to different dimensions of the feature vector based on the characteristics of different fields. For instance, "itemId" can be mapped to the identifier of the target device, while the content of the "Data" field can be mapped to actual operational data values ​​or numerical sequences. Simultaneously, for time-related fields, the terminal can convert them into time-series features so that the model can capture temporal dependencies.

[0074] Next, the terminal inputs these feature vectors into the updated industrial control instruction recognition model. The recognition model typically includes a spatial feature extraction module, a short-term temporal feature extraction module, and a long-term temporal feature extraction module. The model first extracts the spatial distribution patterns from the features using a convolutional neural network (CNN), and then extracts the short-term and long-term temporal dependency features of the instruction data using modules such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs). Finally, after these features are processed by a classification layer, the model outputs the recognition results, obtaining the industrial control instruction type and parameter information corresponding to the current network communication data.

[0075] In the aforementioned method for recognizing industrial control commands in energy storage power stations, firstly, the network communication data of the energy storage power station is acquired in real time. By acquiring this data, the latest commands and status changes of each device in the energy storage power station can be dynamically perceived, ensuring the real-time nature of industrial control command recognition. Next, when the network communication data meets preset conditions, the current industrial control command recognition model is updated based on the network communication data to obtain a new model. Through monitoring and conditional judgment of the network communication data, the recognition model is automatically updated under specific conditions, allowing the model to adjust its weights or structure according to the new communication data to adapt to changing factors in the scenario. This effectively improves the model's recognition accuracy and adaptability in different scenarios, avoiding recognition errors caused by data changes in traditional static models. Then, the current network communication data of the energy storage power station is acquired, and the command is processed according to a preset industrial control protocol. The current network communication data is parsed to obtain key fields of industrial control commands. Through preset parsing of the industrial control protocol, key fields of industrial control commands, such as command type, device identifier, and operating parameters, can be extracted from the raw data. This accurately parses the core information of the industrial control commands, enabling the model to recognize and understand the specific meaning of each command, improving the accuracy of data parsing and ensuring the accuracy of recognition. Finally, the key fields of the industrial control commands are used as feature information and input into a new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data. The extracted key fields of the industrial control commands, as feature information input into the model, enhance the model's understanding and recognition ability of commands, helping the model to quickly identify command types and corresponding operations, improving the model's recognition efficiency and accuracy, and enabling it to more accurately reflect the real-time command situation. In the above method, by acquiring network communication data from the energy storage power station in real time and dynamically updating the recognition model under specific conditions, it adapts to changes in the communication environment, improving the accuracy of recognition. By extracting key fields of commands through protocol parsing, feature information can be effectively extracted, and command types and parameters can be quickly identified, realizing real-time monitoring and efficient recognition of industrial control commands.

[0076] In an exemplary embodiment, step S102, where the network communication data meets preset conditions, updates the current industrial control command recognition model based on the network communication data to obtain a new industrial control command recognition model. This step further includes: determining the industrial control command transmission frequency and the number of new devices connected within a preset time window based on the network communication data; and updating the model weights and input feature weights of the current industrial control command recognition model based on the network communication data within the preset time window when the industrial control command transmission frequency and / or the number of new devices connected exceed the corresponding preset thresholds, thereby obtaining a new industrial control command recognition model.

[0077] The preset time window refers to a fixed period of time used to statistically analyze changes in network communication data characteristics. Within this period, the frequency of industrial control commands being sent and the number of new devices connecting are calculated. The frequency of industrial control commands being sent refers to the rate at which commands are sent within this time window, while the number of new devices connecting represents the number of newly connected devices during this period. Changes in these parameters reflect the dynamic nature of the network communication environment, and when they exceed a threshold, the model is triggered to update.

[0078] For example, the terminal can monitor the frequency of industrial control commands and the number of new devices connected within the energy storage power station by setting a preset time window. For instance, the terminal can periodically count the number of commands sent and the number of new devices added, generating statistical values ​​for the frequency of industrial control command transmission and the number of connected devices. When the frequency of industrial control command transmission and / or the number of new devices connected exceed a preset threshold, the terminal determines that the current communication environment may have changed significantly, thereby triggering an update operation for the recognition model. In specific implementations, the terminal updates the model weights and input feature weights of the current industrial control command recognition model based on network communication data within the time window. The model weight update ensures that the model can adapt to new communication frequencies and device access patterns, improving recognition accuracy; the input feature weight update dynamically adjusts feature priorities, such as increasing the feature weight of newly added devices, enabling the model to better recognize commands from new devices.

[0079] In this embodiment, by setting a time window and dynamically monitoring the command sending frequency and the number of connected devices, changes in the network environment can be effectively detected and the recognition model can be quickly adjusted, significantly improving the model's adaptability and recognition accuracy in complex communication environments.

[0080] In an exemplary embodiment, step S102, where the network communication data meets preset conditions, updates the current industrial control instruction recognition model based on the network communication data to obtain a new industrial control instruction recognition model. This further includes: determining the amount of network communication data and the number of industrial control instruction sending types within a preset time window based on the network communication data; when the amount of network communication data is less than a corresponding preset threshold, trimming the model structure of the current industrial control instruction recognition model based on the amount of network communication data to obtain a new industrial control instruction recognition model; and / or when the number of industrial control instruction sending types is less than a corresponding preset threshold, trimming the input features of the current industrial control instruction recognition model based on the number of industrial control instruction sending types to obtain a new industrial control instruction recognition model.

[0081] Here, network communication data volume refers to the total traffic of data packets within the time window. The number of industrial control command transmission types refers to the total number of different types of industrial control commands transmitted within the time window. By setting these thresholds, the dynamics and complexity of the current environment can be assessed, thereby determining whether to prune the model structure and features.

[0082] For example, the terminal can set a preset time window to continuously monitor the amount of network communication data and the number of industrial control command transmission types within that window. For instance, the terminal can periodically calculate the amount of communication data and the number of command types within the time window. If the amount of network communication data is lower than a preset threshold, the terminal can determine that the current environment has become simpler, and therefore can prune the industrial control command recognition model by removing redundant network layers or nodes to simplify the model structure. If the number of industrial control command transmission types is lower than a preset threshold, the terminal can prune the model's input features based on the number of command types, removing less frequently used features to reduce computational overhead and improve model efficiency. In a specific implementation, when the amount of network communication data is less than the corresponding preset threshold, the terminal will prune the recognition model's structure, removing low-weight or redundant network layers or nodes to simplify the model structure and improve resource utilization; when the number of industrial control command transmission types is less than the corresponding preset threshold, the terminal will prune the recognition model's input features, removing infrequently used features to make the model more focused on common command types in the current environment.

[0083] In this embodiment, by monitoring the amount of network communication data and the number of industrial control command transmission types, the structure and features of the identification model can be dynamically tailored according to changes in the communication environment, making the model more concise and efficient. This tailoring mechanism improves the model's operating efficiency in simplified environments and effectively reduces the consumption of computing resources.

[0084] In one exemplary embodiment, such as Figure 2 As shown, step S104 above uses key fields of industrial control commands as feature information and inputs them into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data. This can be achieved through the following steps:

[0085] Step S201: Preprocess the key fields of the industrial control instruction to obtain the preprocessed key fields of the industrial control instruction;

[0086] Step S202: Standardize the key fields of the preprocessed industrial control instructions to obtain standardized key fields of the industrial control instructions.

[0087] Step S203: Convert the standardized key fields of the industrial control instructions into feature vectors;

[0088] Step S204: Input the feature vector into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0089] Among them, the key fields of industrial control instructions refer to the fields extracted from network communication data that can describe the core content such as instruction type, target device, and parameter value, such as instruction identifier and data content. These fields constitute the key information source for the recognition model to make instruction judgments.

[0090] For example, after receiving the key fields of the industrial control instructions, the terminal can process them through the following steps to convert them into input features for the model: Preprocessing: The terminal cleans and adjusts the format of the key fields of the industrial control instructions, removing invalid characters and correcting the data format to ensure the standardization of field content. For example, the terminal can clean up whitespace characters in the key fields, unify the field format, or convert the data type of the data content. Preprocessing can eliminate data impurities and ensure the accuracy of feature information. Standardization: After preprocessing, the terminal standardizes the key fields of the industrial control instructions. Standardization can adjust the data to a uniform dimension or range, such as through normalization or Z-score standardization, to transform the data of each field to the same scale, so that the model can reasonably allocate the weights of different features. Feature Vector Conversion: The terminal converts the standardized key fields of the industrial control instructions into feature vectors to adapt to the input format of the model. Specifically, each key field can be mapped to one dimension of the feature vector. For example, the instruction identifier field is mapped to one dimension of the feature vector, and the data content is mapped to another dimension, forming a complete feature vector, which is convenient for the model to process and analyze. Finally, the terminal inputs the generated feature vector into the new industrial control instruction recognition model. The recognition model can determine the type of industrial control instruction and operation parameters corresponding to the current network communication data based on the information in the feature vector, and generate accurate recognition results.

[0091] In this embodiment, by preprocessing, standardizing, and transforming the key fields of industrial control instructions, the data format is standardized and the input features are consistent, ensuring the high quality of the input data of the recognition model, thereby improving the accuracy of industrial control instruction recognition and the stability of the model.

[0092] In an exemplary embodiment, the new industrial control instruction recognition model includes a spatial feature extraction module, a short-time temporal feature extraction module, a long-time temporal feature extraction module, and a recognition module. Step S204, which inputs the feature vector into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data, further includes: using the spatial feature extraction module to perform spatial feature extraction processing on the feature vector to obtain the spatial features corresponding to the feature vector; using the short-time temporal feature extraction module to perform short-time temporal feature extraction processing on the spatial features to obtain the short-time temporal features corresponding to the feature vector; using the long-time temporal feature extraction module to perform long-time temporal feature extraction processing on the short-time temporal features to obtain the long-time temporal features corresponding to the feature vector; and inputting the long-time temporal features into the recognition module to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0093] The spatial feature extraction module is used to extract local spatial features from the input feature vector. It can identify spatial patterns of instruction content and structure in the feature vector and is typically implemented using a convolutional neural network (CNN). The short-time and long-time feature extraction modules are responsible for identifying sequence dependencies in the feature vector over shorter and longer time periods, respectively, and are suitable for implementation using recurrent neural networks (RNNs) and long short-term memory networks (LSTMs). The recognition module is used for the final instruction type and parameter identification, outputting the industrial control instruction recognition results.

[0094] For example, the terminal first inputs the feature vector into the spatial feature extraction module. This module identifies spatial structure patterns in the feature vector through convolution operations, generating spatial features representing the instruction content and field layout. For instance, the terminal can use a convolutional neural network to extract information such as data distribution and field positions from the feature vector, thereby establishing a spatial representation of the instruction content. Next, the terminal inputs the spatial features into the short-term temporal feature extraction module. The short-term temporal feature extraction module uses methods such as recurrent neural networks or gated recurrent units (GRUs) to capture the sequence dependencies of instructions in the short term, generating short-term temporal features that reflect the short-term associations and operational continuity between instructions. This is very effective for capturing continuous operations, adjacent steps, or short-term behavioral patterns in industrial control instructions. Then, the terminal passes the short-term temporal features to the long-term temporal feature extraction module, which extracts the long-term dependencies of instructions through a Long Short-Term Memory (LSTM) network, generating long-term temporal features. This module can capture the associations of instructions over a longer time span, ensuring that the model can identify long-term dependency patterns in the industrial control process and adapt to the structured recognition needs of complex instruction sequences. Finally, the terminal inputs the long-term time-series features to the recognition module. This module performs a final comprehensive judgment on all extracted features and generates the industrial control instruction recognition result corresponding to the current network communication data through methods such as fully connected layers or Softmax, namely the type of the current instruction, the target device, and parameter information.

[0095] In this embodiment, by extracting spatial features, short-term temporal features, and long-term temporal features step by step, local patterns and temporal dependencies in industrial control instructions can be comprehensively captured, ultimately achieving accurate instruction recognition results. The modular processing approach effectively improves the model's recognition accuracy, resulting in higher adaptability and recognition stability in dynamic and complex industrial control environments.

[0096] In an exemplary embodiment, after obtaining the industrial control instruction identification result corresponding to the current network communication data in step S104, the method further includes: monitoring the status information and execution result of the target industrial control instruction; the target industrial control instruction is the industrial control instruction corresponding to the industrial control instruction identification result; analyzing the status information and execution result to obtain the execution report of the target industrial control instruction, and uploading the execution report to the blockchain network.

[0097] Among them, the target industrial control instruction refers to a specific industrial control instruction identified by the industrial control instruction recognition model. It requires further status monitoring and execution analysis to ensure the effectiveness and correct execution of the instruction. Status information includes various feedback data during instruction execution, such as execution progress and equipment response status; the execution result is the final feedback data after the instruction is completed, used to judge the execution effect of the instruction.

[0098] For example, after receiving the industrial control command recognition result, the terminal automatically monitors the status information and execution result of the target industrial control command. Specifically, the terminal interacts with the target device to collect the execution status information of the command in real time, such as whether the command was received normally, the execution progress, and the real-time status of the device. Simultaneously, the terminal records the execution result after the command is completed to determine whether the command was successfully executed or if there is an anomaly. After obtaining the status information and execution result, the terminal analyzes this data and generates an execution report. The analysis process includes evaluation of key nodes in the execution process, response latency, command completion status, and other aspects to ensure that the command execution meets expectations. For example, the terminal can determine whether the execution effect of the target command meets the requirements based on indicators such as execution success rate and response time; if an anomaly exists, detailed fault information will be recorded. Finally, the terminal uploads the generated execution report to the blockchain network. As a decentralized data storage platform, the blockchain network ensures the integrity and immutability of the execution report, thereby providing a secure and reliable basis for subsequent operational auditing and traceability. After the execution report is uploaded to the blockchain, all parties can query the execution status of the command through the blockchain network to improve the transparency and security of the industrial control system.

[0099] In this embodiment, by monitoring the status information of industrial control commands, analyzing the execution results, and uploading the reports to the blockchain, traceability and data security are ensured throughout the entire process of industrial control command execution. The introduction of blockchain ensures the authenticity and verifiability of the execution reports, providing a safer and more reliable management method for the execution of industrial control commands in energy storage power stations.

[0100] In another exemplary embodiment, such as Figure 3 As shown, this application provides a method for identifying industrial control commands in an energy storage power station, which includes the following steps:

[0101] Step S301: Initialization and traffic acquisition.

[0102] Step S302: Deep protocol parsing and instruction feature extraction.

[0103] Step S303, Intelligent Feature Recognition Model.

[0104] Step S304: Online reasoning and real-time recognition.

[0105] Step S305, auditing of industrial control behavior instructions.

[0106] The intelligent feature recognition model in step S303 can be obtained through the following steps:

[0107] Step S3031: Data preprocessing and feature extraction.

[0108] Step S3032, Model building and deep learning algorithm.

[0109] Step S3033, Model training and optimization.

[0110] Step S3034, adaptive adjustment and trimming mechanism.

[0111] For example, in step S301, a comprehensive configuration initialization is first performed to ensure that all network traffic of the energy storage power station can be captured and analyzed completely and efficiently. The system is connected to the mirror port of the switch via a bypass method to acquire the full data packet traffic. High-performance network card drivers and big data technology are used to collect and process all traffic in real time, providing basic data for subsequent protocol parsing and behavior recognition. The traffic acquisition process captures all network communication data of the energy storage power station in real time through the mirror port, ensuring comprehensive collection and high-precision data transmission. After preliminary protocol parsing, basic information such as IP address, port number, and data packet size is extracted from the traffic data, providing support for deeper command parsing.

[0112] In step S302, deep parsing based on industrial protocols is the core of the entire identification process, especially for protocols widely used in energy storage power stations such as IEC 61850 and IEC 104. Through a parsing engine, network packets are gradually disassembled, and key information is extracted. The main steps are: ① Protocol parsing: In-depth analysis of IP layer and transport layer protocols, such as TCP / UDP, ensures the integrity and validity of communication data. Then, for industrial control protocols IEC 61850 and IEC 104, specific logical nodes, data objects, remote control types, and other key information are parsed. ② Command feature extraction: During the parsing process, key fields related to industrial control behavior commands are extracted, such as invokeID, confirmedServiceRequest, itemId, Data, and confirmedServiceResponse, to ensure the correct transmission and execution of commands. ③ Feature library construction: Based on the results of long-term monitoring and parsing, a large command feature library has been built, covering various command patterns and types. This library serves as an important basis for command identification, ensuring the accuracy and effectiveness of command execution by comparing the characteristics of new commands with known patterns.

[0113] In step S3031, before executing the instruction identification, the collected energy storage power station network traffic data is first preprocessed, and feature data is extracted. The main objective of this step is to ensure data quality and extract key fields for subsequent identification.

[0114] Data cleaning: Removing redundant and irrelevant data to ensure the validity of the input data. Feature standardization: Normalizing the data to ensure that features of different ranges have a consistent scale. Common methods include Z-score standardization formula: Where X is the original feature value, μ is the mean of the feature, and σ is the standard deviation. Feature extraction: Extract key field information from the network protocol, such as invokeID, confirmedServiceRequest, itemId, and Data fields, to form a feature vector. , used as input for the model.

[0115] In step S3032, a feature recognition model is constructed using a deep learning framework combining convolutional neural networks (CNN) and recurrent neural networks (RNN). This model can capture the spatiotemporal features of industrial control commands and adapt to different business scenarios.

[0116] ① Convolutional Neural Networks (CNNs) are used for spatial feature extraction:

[0117] Input: Feature vector f of the network data stream

[0118] Convolutional layer: Local features are extracted using a convolutional kernel W, as shown in the following formula:

[0119]

[0120] in, For the output of the convolutional layer, For the k-th convolutional kernel, For input features.

[0121] Pooling layers: These downsample the output of convolutional layers, reducing the amount of data and enhancing the model's translation invariance. Max pooling is commonly used. .

[0122] ② Recurrent Neural Networks (RNNs) are used for capturing time series features:

[0123] Input: Feature sequence after convolutional layer processing .

[0124] RNN unit: Recursively processes time-series features to capture temporal dependencies in the instruction stream. The classic recursive formula for an RNN is: .in, The hidden state at the current time step. Let σ be the current input, and σ be the activation function. and Let b be the weight matrix and b be the bias.

[0125] ③ Long Short-Term Memory Network (LSTM):

[0126] To avoid the vanishing gradient problem in traditional RNNs, LSTM units are introduced, which can better remember long-term sequence information. The core structure of LSTM includes a forget gate, an input gate, and an output gate, and the calculation formula is as follows:

[0127]

[0128]

[0129]

[0130]

[0131]

[0132] Among them, f t For the Gate of Oblivion, i t For the input gate, o t For output gate, c t The state represents the unit state. W and b are the corresponding weight matrix and bias term. h is a logical activation function. t This is the final hidden state output.

[0133] In step S3033, the collected network data is divided into training set, validation set and test set to ensure the generalization ability of the model training.

[0134] Loss function: The cross-entropy loss function is used to evaluate the difference between the probability distribution of the model output and the true label.

[0135]

[0136] in, For real labels, This represents the result predicted by the model.

[0137] Optimization Algorithm: The Adam optimization algorithm is used to update the model parameters to accelerate convergence and avoid local optima. The Adam parameter update formula is:

[0138]

[0139]

[0140]

[0141] Where, θ t For model parameters, m t and v t These are the gradient momentum and squared momentum, respectively, and α is the learning rate.

[0142] In step S3034, in order to ensure that the model can still maintain efficient recognition when the business scenario changes, the model performance is actively optimized through adaptive adjustment and pruning mechanisms.

[0143] Adaptive Adjustment: ① Scene Monitoring: Real-time monitoring of traffic characteristics changes in energy storage power stations, capturing signals of business changes (such as new equipment, changes in command frequency, etc.). By setting thresholds, the adaptive adjustment module is automatically activated when an anomaly is detected. ② Model Retraining: Through the online learning module, the model is incrementally updated in small batches based on new data, ensuring the model's adaptability to new scenarios. An incremental learning method is used to prevent the model from forgetting its recognition capabilities in historical scenarios. ③ Dynamic Weight Update: Feature weights are recalculated based on the feature distribution in the new scenario. For example, some features (such as itemId or Data fields) may have different importance in different business scenarios; feature weights are dynamically adjusted using the following formula: Among them, w i For feature f i The weight, μ i Let be the characteristic mean, and α be the adjustment rate.

[0144] Pruning Mechanisms: ① Model Complexity Pruning: When the traffic volume or instruction types decrease in a scenario, model complexity can be reduced by pruning unnecessary network layers or nodes, thereby improving computational efficiency. L1 regularization is used to prune unimportant weights. Where λ is the regularization coefficient, and θ i ① Network weights. ② Redundant feature pruning: By analyzing the importance of features in real time, low-weight or redundant features are pruned to reduce the computational burden on the model and improve real-time response capabilities.

[0145] In step S304, after the model completes adaptive adjustment, it enters the online inference stage to process the newly collected data in real time. Through the optimized model, industrial control commands in the energy storage power station can be quickly and accurately identified, ensuring efficient execution and safety auditing of the commands.

[0146] In step S305, after the intelligent feature recognition algorithm identifies the instruction, the execution process of each instruction is audited and recorded in detail. The auditing function includes the following: Instruction execution time and response time: Recording the instruction's issuance time, execution time, and response time to ensure that the execution of each instruction meets expectations. Execution result analysis: By analyzing the instruction execution results, the reasons for success or failure are fed back in real time, and this information is uploaded to the blockchain network to ensure the immutability and traceability of the data.

[0147] In this embodiment, an intelligent feature recognition algorithm can efficiently and accurately identify various industrial control commands in an energy storage power station. Compared to traditional fixed-rule recognition methods, the intelligent algorithm has dynamic adjustment and self-learning capabilities, automatically updating the recognition logic according to changes in actual business scenarios, significantly improving the accuracy and efficiency of command recognition. This performance improvement ensures that the energy storage power station can accurately identify and execute each command in complex and ever-changing network environments, reducing the risk of misoperation. By integrating efficient traffic monitoring and deep protocol parsing technologies, it can analyze the data flow in the energy storage power station network in real time and perform immediate processing and auditing of key industrial control commands. When abnormal commands or unauthorized operations are detected, it can quickly respond and take corrective measures. Compared to the lag of traditional monitoring technologies, it greatly shortens the delay in command recognition and response, improving the security and stability of the energy storage power station. The adaptive learning algorithm can autonomously adapt to the access of new devices or changes in business scenarios without frequent manual intervention or readjustment of recognition rules, thereby reducing maintenance costs. In addition, this method has good scalability and can support the future expansion of the network scale and command types of the energy storage power station. Through its self-optimization mechanism, the model can be continuously updated as business develops, ensuring its long-term efficient operation. Blockchain technology ensures the security and immutability of all instruction audit data, significantly improving the operational transparency and audit reliability of energy storage power stations. The execution process, time, and results of each instruction are recorded in detail and stored on the blockchain, ensuring data integrity and traceability. This provides strong protection for the safe operation of energy storage power stations, reduces potential operational risks, and enhances the safety and stability of the power grid.

[0148] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0149] Based on the same inventive concept, this application also provides an energy storage power station industrial control command identification device for implementing the above-mentioned energy storage power station industrial control command identification method. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations in one or more embodiments of the energy storage power station industrial control command identification device provided below can be found in the limitations of the energy storage power station industrial control command identification method described above, and will not be repeated here.

[0150] In one exemplary embodiment, such as Figure 4 As shown, an industrial control command recognition device for an energy storage power station is provided, comprising: a data acquisition module 401, a model update module 402, a field parsing module 403, and a command recognition module 404, wherein:

[0151] Data acquisition module 401 is used to acquire network communication data of energy storage power station in real time;

[0152] The model update module 402 is used to update the current industrial control instruction recognition model according to the network communication data when the network communication data meets the preset conditions, so as to obtain a new industrial control instruction recognition model.

[0153] The field parsing module 403 is used to obtain the current network communication data of the energy storage power station, and to parse and process the current network communication data according to the preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data.

[0154] The instruction recognition module 404 is used to input the key fields of the industrial control instruction as feature information into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0155] In one embodiment, the model update module 402 is further configured to determine the industrial control command sending frequency and the number of new devices connected within a preset time window based on network communication data; when the industrial control command sending frequency and / or the number of new devices connected exceed the corresponding preset threshold, the model weight and input feature weight of the current industrial control command recognition model are updated based on the network communication data within the preset time window to obtain a new industrial control command recognition model.

[0156] In one embodiment, the model update module 402 is further configured to determine the amount of network communication data and the number of industrial control command sending types within a preset time window based on the network communication data; if the amount of network communication data is less than the corresponding preset threshold, trim the model structure of the current industrial control command recognition model based on the amount of network communication data to obtain a new industrial control command recognition model; and / or if the number of industrial control command sending types is less than the corresponding preset threshold, trim the input features of the current industrial control command recognition model based on the number of industrial control command sending types to obtain a new industrial control command recognition model.

[0157] In one embodiment, the instruction recognition module 404 is further configured to preprocess the key fields of the industrial control instruction to obtain preprocessed key fields of the industrial control instruction; standardize the preprocessed key fields of the industrial control instruction to obtain standardized key fields of the industrial control instruction; convert the standardized key fields of the industrial control instruction into feature vectors; and input the feature vectors into a new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0158] In one embodiment, the new industrial control instruction recognition model includes a spatial feature extraction module, a short-time temporal feature extraction module, a long-time temporal feature extraction module, and a recognition module. The instruction recognition module 404 is further configured to use the spatial feature extraction module to perform spatial feature extraction processing on the feature vector to obtain the spatial features corresponding to the feature vector; use the short-time temporal feature extraction module to perform short-time temporal feature extraction processing on the spatial features to obtain the short-time temporal features corresponding to the feature vector; use the long-time temporal feature extraction module to perform long-time temporal feature extraction processing on the short-time temporal features to obtain the long-time temporal features corresponding to the feature vector; and input the long-time temporal features to the recognition module to obtain the industrial control instruction recognition result corresponding to the current network communication data.

[0159] In one embodiment, the aforementioned energy storage power station industrial control command identification device further includes a command monitoring module, used to monitor the status information and execution results of the target industrial control command; the target industrial control command is the industrial control command corresponding to the industrial control command identification result; the status information and execution results are analyzed to obtain the execution report of the target industrial control command, and the execution report is uploaded to the blockchain network.

[0160] Each module in the aforementioned energy storage power station industrial control command recognition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0161] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for recognizing industrial control commands in an energy storage power station. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0162] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0163] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0164] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0165] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0166] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0167] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0168] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0169] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for recognizing industrial control commands in an energy storage power station, characterized in that, The method includes: Real-time acquisition of network communication data from energy storage power stations; If the network communication data meets the preset conditions, the current industrial control instruction recognition model is updated according to the network communication data to obtain a new industrial control instruction recognition model; The current network communication data of the energy storage power station is obtained, and the current network communication data is parsed and processed according to a preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data; The key fields of the industrial control command are used as feature information and input into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data.

2. The method according to claim 1, characterized in that, When the network communication data meets preset conditions, the current industrial control instruction recognition model is updated based on the network communication data to obtain a new industrial control instruction recognition model, including: Based on the network communication data, the frequency of industrial control command transmission and the number of new devices connected within the preset time window are determined; If the frequency of industrial control command transmission and / or the number of new devices connected exceed the corresponding preset threshold, the model weight and input feature weight of the current industrial control command recognition model are updated based on the network communication data within the preset time window to obtain a new industrial control command recognition model.

3. The method according to claim 1, characterized in that, When the network communication data meets preset conditions, the current industrial control instruction recognition model is updated based on the network communication data to obtain a new industrial control instruction recognition model, including: Based on the network communication data, determine the amount of network communication data and the number of industrial control command sending types within the preset time window; If the amount of network communication data is less than the corresponding preset threshold, the model structure of the current industrial control instruction recognition model is trimmed according to the amount of network communication data to obtain a new industrial control instruction recognition model. and / or If the number of industrial control command sending types is less than the corresponding preset threshold, the input features of the current industrial control command recognition model are trimmed according to the number of industrial control command sending types to obtain a new industrial control command recognition model.

4. The method according to claim 1, characterized in that, The step of inputting the key fields of the industrial control command as feature information into the new industrial control command recognition model to obtain the industrial control command recognition result corresponding to the current network communication data includes: The key fields of the industrial control instruction are preprocessed to obtain the preprocessed key fields of the industrial control instruction. The preprocessed key fields of the industrial control instruction are standardized to obtain the standardized key fields of the industrial control instruction. The standardized key fields of the industrial control instructions are converted into feature vectors; The feature vector is input into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

5. The method according to claim 4, characterized in that, The new industrial control instruction recognition model includes a spatial feature extraction module, a short-time temporal feature extraction module, a long-time temporal feature extraction module, and a recognition module. The step of inputting the feature vector into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data includes: The spatial feature extraction module is used to perform spatial feature extraction processing on the feature vector to obtain the spatial features corresponding to the feature vector; The spatial features are processed by the short-time temporal feature extraction module to obtain the short-time temporal features corresponding to the feature vector. The long-time time series feature extraction module is used to perform long-time time series feature extraction processing on the short-time time series features to obtain the long-time time series features corresponding to the feature vector; The long-term timing features are input into the recognition module to obtain the industrial control instruction recognition result corresponding to the current network communication data.

6. The method according to claim 1, characterized in that, After obtaining the industrial control instruction recognition result corresponding to the current network communication data, the method further includes: Monitor the status information and execution results of the target industrial control instruction; the target industrial control instruction is the industrial control instruction corresponding to the industrial control instruction identification result. The status information and execution results are analyzed to obtain an execution report of the target industrial control instruction, and the execution report is uploaded to the blockchain network.

7. A device for identifying industrial control commands in an energy storage power station, characterized in that, The device includes: The data acquisition module is used to acquire network communication data of the energy storage power station in real time; The model update module is used to update the current industrial control instruction recognition model according to the network communication data when the network communication data meets the preset conditions, so as to obtain a new industrial control instruction recognition model. The field parsing module is used to obtain the current network communication data of the energy storage power station, and to parse and process the current network communication data according to the preset industrial control protocol to obtain the key fields of industrial control instructions in the current network communication data. The instruction recognition module is used to input the key fields of the industrial control instruction as feature information into the new industrial control instruction recognition model to obtain the industrial control instruction recognition result corresponding to the current network communication data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images