AI supervision-based energy storage equipment state online operation and maintenance supervision method and system

Abstract

According to the AI supervision-based energy storage equipment state online operation and maintenance supervision method and system provided by the invention, intelligent online operation and maintenance supervision of reactive compensation of energy storage equipment is realized through cooperation of an energy storage system coordination controller and an upper computer, and state data of the energy storage equipment are monitored through the energy storage system coordination controller and uploaded to a background, so that the state of the energy storage equipment is monitored through the upper computer. A background state AI supervision model identifies a state characteristic value in the state data and outputs a reactive power compensation operation and maintenance strategy matched with the state characteristic value, and an energy storage system coordination controller executes the reactive power compensation operation and maintenance strategy on the energy storage equipment, so that intelligent and high-efficiency reactive power compensation operation and maintenance of the energy storage equipment are realized, two hands are liberated, and the energy storage efficiency is improved. Operation and maintenance management of mass energy storage equipment can be realized, the state supervision and operation and maintenance efficiency of the energy storage equipment is greatly improved, and intelligent reactive compensation of the energy storage equipment is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid operation assessment, and in particular to an online operation and maintenance supervision method and control method of energy storage device status based on AI supervision, an online operation and maintenance supervision system of energy storage device status based on AI supervision, electronic equipment and computer-readable storage medium. Background Art

[0002] The core purpose of energy storage system status monitoring is to ensure the health and safe operation of the energy storage system through regular inspections and assessments, including comprehensive monitoring of key components such as battery systems, power storage converters (PCS), and energy storage monitoring systems. Through status monitoring, the energy storage system can be ensured to operate safely and efficiently, and each component of the energy storage system can be monitored, evaluated, and maintained in real time.

[0003] The main contents of daily status supervision of energy storage systems are as follows: ‌1. Supervision of battery system‌: Batteries and battery management systems (BMS) are the core of energy storage systems. It is necessary to regularly check the clarity of equipment operation number identification and phase sequence identification, as well as the reliability of each connection point of the main circuit and secondary circuit of the battery system.

[0004] At the same time, it is necessary to monitor the health status of the battery system, including key parameters such as battery capacity, internal resistance, voltage, and environmental factors such as temperature and humidity in the battery room, to ensure that the battery operates in the best condition.

[0005] 2. Supervision of the PCS: The energy storage inverter is a key device that connects the battery system to the power grid. It is necessary to regularly check the appearance of the cabinet, the integrity of the door lock, and the working status of the temperature control device.

[0006] At the same time, it is necessary to monitor the operating parameters of the PCS, such as input / output voltage, current, power factor, etc., to ensure that it meets the design requirements and operates stably.

[0007] ‌3. Supervision of energy storage monitoring system‌: The energy storage monitoring system is responsible for data collection, processing and monitoring of the entire energy storage system. It is necessary to regularly check the operating status of the server, the switching of the functional interface, and the communication status between the monitoring system and the BMS, PCS and other systems.

[0008] Through the monitoring system, the operating status of the energy storage system can be monitored in real time, abnormal situations can be discovered and handled in a timely manner, and the safe and stable operation of the system can be ensured.

[0009] ‌4. Regular inspections and special inspections‌: In addition to daily inspections, special inspections are also required in special seasons, abnormal weather, and after abnormal equipment alarms or fault handling to ensure the safe and stable operation of the energy storage system. The inspection content should include a comprehensive inspection of key components such as the battery system, PCS, and energy storage monitoring system, as well as an inspection of the environmental conditions of the battery room or battery compartment. However, in the daily operation and maintenance of energy storage systems, system reactive power compensation is also required. The main reason for reactive power compensation in energy storage systems is to improve the stability and reliability of the power grid and to improve the power factor of the power system. This is because in the power system, reactive power is the phenomenon that the current lags or leads the voltage due to the presence of inductance and capacitance elements in the circuit. This phase difference between the lagging or leading current and voltage will cause the power factor of the power grid to decrease, which in turn affects the operating efficiency and stability of the power grid.

[0010] Therefore, through the reactive power compensation of the energy storage system, the reactive power in the power system can be effectively adjusted, the impact of reactive power on the power grid can be reduced, the overall operating efficiency of the power system can be improved, and line losses can be reduced. In addition, compared with traditional reactive power compensation equipment (such as static reactive power compensators, reactive power generators, etc.), the energy storage system is more flexible, efficient, and reliable, and can reduce dependence on traditional equipment. At the same time, reactive power is not useless power in the AC power supply system, and it has great significance for the transmission and exchange of energy. For example, the motor needs to establish and maintain a rotating magnetic field to make the rotor rotate, thereby driving mechanical movement, and reactive power is required in this process. Therefore, reactive power compensation of the energy storage system is also an important part of ensuring the normal operation of these devices.

[0011] However, during the charging and discharging process of the energy storage system, the current lags behind or leads the voltage due to the presence of inductance and capacitance elements in the circuit, so there is reactive power. This phase difference between the lagging or leading current and voltage will cause the power factor of the power grid to decrease, which in turn affects the operating efficiency and stability of the power grid. The energy storage system also needs to dynamically output or absorb reactive power, so the reactive compensation of the system energy storage equipment also needs to be considered in actual operation and maintenance. The main reason for reactive compensation of the energy storage system is to improve the stability and reliability of the power grid and improve the power factor of the power system. Through the reactive compensation of the energy storage system, the reactive power in the power system can be effectively adjusted, the impact of reactive power on the power grid can be reduced, the overall operating efficiency of the power system can be improved, and the line loss can be reduced. In addition, compared with traditional reactive compensation equipment (such as static reactive compensators, reactive generators, etc.), the energy storage system is more flexible, efficient, and reliable, and can reduce dependence on traditional equipment. At the same time, reactive power is not useless power in the AC power supply system, and it has great significance for the transmission and exchange of energy. For example, the motor needs to establish and maintain a rotating magnetic field to rotate the rotor, thereby driving mechanical movement. This process requires reactive power. Therefore, reactive power compensation of the energy storage system is also an important part of ensuring the normal operation of these devices.

[0012] The operation and maintenance supervision of existing energy storage equipment mainly focuses on routine supervision such as traditional batteries, PCS, and data collection, and lacks intelligent supervision methods for reactive power compensation. Even if reactive power compensation is actually needed, administrators usually conduct temporary offline operation and maintenance to adjust the parameters of the energy storage equipment to adjust the operating status of the energy storage equipment to achieve a charging and discharging effect that tends to the actual output. This method is only effective for individual or a small number of energy storage devices. Faced with a large number (more than dozens of) energy storage devices, the manual adjustment method is inefficient and not intelligent enough, and cannot meet the development needs of intelligent manufacturing equipment. Summary of the invention

[0013] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a method for online operation and maintenance supervision of energy storage equipment status based on AI supervision is provided. The method is implemented based on the cooperation of an energy storage system coordination controller and a host computer. The energy storage system coordination controller is used to monitor the status data of the energy storage equipment and upload it to the host computer. The host computer analyzes the status data of the energy storage equipment and performs intelligent operation and maintenance supervision and management on the energy storage equipment. The method comprises the following steps: S1, monitoring and uploading the status data of the energy storage device to the host computer through the energy storage system coordination controller; S2, the host computer inputs the state data into a preset state AI supervision model, identifies the state characteristic value in the state data through the state AI supervision model, and outputs a reactive power compensation operation and maintenance strategy matching the state characteristic value; S3, binding the reactive power compensation operation and maintenance strategy with the corresponding energy storage device, and sending it to the energy storage system coordination controller; S4. The energy storage system coordination controller executes the reactive power compensation operation and maintenance strategy on the energy storage device.

[0014] Preferably, the energy storage system coordination controller includes a communication interface, a USB interface, a plurality of sensor interfaces and a mainboard, and the mainboard is configured with a task management CPU, a coordination control CPU and a safety communication CPU, wherein: The task management CPU is used to control the sampling of the sensor interface according to the preset sampling task and send the collected charging and discharging status data of the energy storage device to the coordination control CPU, wherein the charging and discharging status data includes the charging and discharging current, voltage, power, grid frequency and temperature value of the energy storage device; The coordination control CPU is used to forward the charging and discharging status data of the energy storage device to the safety communication CPU; The secure communication CPU is used to report the charge and discharge status data of the energy storage device to the host computer through the communication interface after secure encryption processing; The task management CPU is communicatively connected with the energy storage device via the sensor interface; The safety communication CPU is connected to the host computer through the communication interface; The coordination control CPU is connected to the energy storage device through the USB interface; The task management CPU, the coordination control CPU and the safety communication CPU are communicatively connected in sequence.

[0015] Preferably, the safety communication CPU is further used to: receive and decrypt the reactive power compensation operation and maintenance strategy issued by the host computer to the corresponding energy storage device, and forward the decrypted reactive power compensation operation and maintenance strategy to the coordination control CPU; The coordination control CPU is further used to: receive and analyze the reactive compensation operation and maintenance strategy, obtain the reactive compensation control instruction therein, and issue the reactive compensation control instruction to the energy storage device through the USB interface.

[0016] Preferably, the energy storage system coordination controller further includes: Memory A, used to provide storage services for the safety communication CPU, including: storing the charging and discharging state data of the energy storage device sampled and reported each time, and the reactive compensation operation and maintenance strategy received accordingly; The memory A is communicatively connected to the safety communication CPU.

[0017] Preferably, the energy storage system coordination controller further includes: Memory B, used to provide storage services for the task management CPU, including: storing the charge and discharge state data of the energy storage device collected by each sampling; The memory B is communicatively connected to the task management CPU.

[0018] Preferably, the method for generating the state AI supervision model comprises: Collecting historical operation and maintenance supervision big data of some of the energy storage devices from the background database of the host computer, including historical status data of the energy storage devices and reactive power compensation operation and maintenance strategies issued by system operation and maintenance supervision, wherein the reactive power compensation operation and maintenance strategies include corresponding reactive power compensation control instructions; Feature engineering is performed on the historical operation and maintenance supervision big data, and a supervised learning algorithm is used to extract feature data from the historical operation and maintenance supervision big data, including the state feature values ​​in each group of the historical state data and the reactive compensation control instructions and strategy keywords corresponding to the state feature values ​​in the reactive compensation operation and maintenance strategy, and the state feature values ​​are bound to the strategy keywords to obtain the extracted features of each group: {state characteristic value, strategy keyword}; Collecting feature extraction results of each of the energy storage devices to obtain a feature set consisting of several groups of {state feature values, strategy keywords}; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into the default machine learning model, and train it according to the preset optimized iterative training conditions to construct the state AI supervision model; The performance of the state AI supervision model is verified using the validation set: If the verification is successful, the state AI supervision model is deployed and applied to the host computer; If the verification fails, repeat the above steps and retrain the model.

[0019] Preferably, S2, the host computer inputs the state data into a preset state AI supervision model, identifies the state characteristic value in the state data through the state AI supervision model and outputs a reactive power compensation operation and maintenance strategy matching the state characteristic value, including: Receive and identify the basic information of the status data reported by the energy storage system coordination controller and bind it to the device ID corresponding to the energy storage device; The state data is input into the state AI supervision model, and the state AI supervision model identifies the state feature value in the state data and determines whether there is a policy keyword matching the state feature value: If yes, extract the strategy keywords, retrieve the corresponding reactive power compensation operation and maintenance strategy according to the strategy keywords and output it; Otherwise, continue monitoring.

[0020] On the other hand, an online operation and maintenance supervision system for energy storage device status based on AI supervision is provided, and the online operation and maintenance supervision system for energy storage device status based on AI supervision is used to implement the above-mentioned online operation and maintenance supervision method for energy storage device status based on AI supervision, and the system includes: Energy storage system coordination controller, used to monitor and upload status data of energy storage equipment to the host computer; A host computer, used for inputting the state data into a preset state AI supervision model, identifying the state characteristic value in the state data through the state AI supervision model and outputting a reactive compensation operation and maintenance strategy matching the state characteristic value; and binding the reactive compensation operation and maintenance strategy with the corresponding energy storage device, and sending it to the energy storage system coordination controller, so that the energy storage system coordination controller executes the reactive compensation operation and maintenance strategy on the energy storage device; The energy storage system coordination controller is communicatively connected to the host computer.

[0021] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned methods for online operation and maintenance supervision of the energy storage device status based on AI supervision is implemented.

[0022] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned AI-supervised online operation and maintenance supervision methods for energy storage equipment status.

[0023] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention comprehensively considers the multi-dimensional indicator data of the energy storage equipment, constructs an EMS power grid operation effectiveness prediction model that identifies the performance evaluation indicator system and the corresponding effectiveness evaluation value, and performs energy storage equipment power grid effectiveness evaluation on the real-time power grid working conditions, so that the power grid control center can adjust the power grid operation parameters under the corresponding indicators based on the effectiveness evaluation value. Therefore, it is possible to use intelligent prediction technology to comprehensively consider multiple aspects of power grid operation indicators, and quickly calculate the effectiveness evaluation results through intelligent calculation methods, and use them to adjust the power grid operation parameters. Therefore, the present invention can comprehensively and effectively evaluate the operating effectiveness of energy storage equipment, and use the model to quickly and accurately predict the output of the energy storage equipment operation effectiveness evaluation value, improve work efficiency, and quickly respond to the power grid operation regulation work of the energy storage equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 It is a flow chart of an online operation and maintenance supervision method for energy storage equipment status based on AI supervision provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of an application system for online supervision of a model provided by an embodiment of the present invention; Figure 3 It is a control circuit composition structure diagram of an energy storage system coordination controller provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the training and application process of the state AI supervision model provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of an operation and maintenance monitoring control system of a plurality of energy storage devices provided by a host computer in an embodiment of the present invention; Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0027] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0028] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0029] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0030] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0031] The embodiment of the present invention provides an online operation and maintenance supervision method for energy storage device status based on AI supervision, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of the online operation and maintenance supervision method of energy storage device status based on AI supervision is shown. The method is implemented based on the cooperation of the energy storage system coordination controller and the host computer. The energy storage system coordination controller is used to monitor the status data of the energy storage device and upload it to the host computer. The host computer analyzes the status data of the energy storage device and performs intelligent operation and maintenance supervision and management on the energy storage device. The method includes the following steps: S1, monitoring and uploading the status data of the energy storage device to the host computer through the energy storage system coordination controller; S2, the host computer inputs the state data into a preset state AI supervision model, identifies the state characteristic value in the state data through the state AI supervision model, and outputs a reactive power compensation operation and maintenance strategy matching the state characteristic value; S3, binding the reactive power compensation operation and maintenance strategy with the corresponding energy storage device, and sending it to the energy storage system coordination controller; S4. The energy storage system coordination controller executes the reactive power compensation operation and maintenance strategy on the energy storage device.

[0032] In this embodiment, the energy storage system coordination controller can be referred to as the controller; the host computer can be referred to as the background; the state AI supervision model can be referred to as the supervision model or AI model or model.

[0033] like Figure 2 As shown, compared with the traditional solution of manual reactive power compensation operation and maintenance by the administrator, the present invention adopts AI technology, monitors the status data of each energy storage device through the controller and reports it to the host computer, and the status AI supervision model of the host computer performs feature recognition on the status data of the corresponding intelligent device and determines whether there is corresponding reactive power compensation feature data (identifies and matches the status feature value): if there is corresponding feature data, the AI ​​model recognizes and outputs the reactive power compensation operation and maintenance strategy that matches the current status feature value and sends it to the controller, and the controller performs reactive power compensation on the corresponding energy storage device.

[0034] In the process of historical operation and maintenance management, the reactive power compensation records implemented by the administrator can be recorded and saved several times in the background (background database deployed on the host computer). The supervision model training and application can be carried out based on historical big data. The model supervision training can be carried out on the historical reactive power compensation operation and maintenance big data to build a state AI supervision model and deploy it on the host computer for subsequent intelligent supervision of the state of each energy storage device to determine whether to perform reactive power compensation. On the host computer, the historical big data can be stored in the corresponding background database. The corresponding model training can be completed on the background.

[0035] In the present invention, a controller is used to coordinate and control the energy storage devices in each energy storage system. The controller controls the state management of each energy storage device and the reactive compensation operation and maintenance supervision. The controller communicates with the host computer, and can collect the state data of the corresponding energy storage device and upload it to the host computer. The host computer then performs AI supervision and issues corresponding reactive compensation operation and maintenance strategies. The reactive compensation operation and maintenance strategy includes reactive compensation operation and maintenance instructions for the corresponding energy storage device (including control parameters of the corresponding state characteristic values), which can be handed over to the controller to perform corresponding reactive compensation operation and maintenance control on the corresponding device. Specifically, the reactive compensation control parameters issued for the state data of the corresponding device, etc., can be combined with historical big data for corresponding recommendation and output. Therefore, by adopting the present invention, the reactive compensation of each energy storage device in the energy storage system can be realized through the energy storage system coordination controller and the host computer, and intelligent operation and maintenance supervision and management can be realized, greatly improving the operation and maintenance efficiency.

[0036] like Figure 3 As shown, preferably, the energy storage system coordination controller includes a communication interface, a USB interface, a plurality of sensor interfaces and a mainboard, and the mainboard is configured with a task management CPU, a coordination control CPU and a safety communication CPU, wherein: The task management CPU is used to control the sampling of the sensor interface according to the preset sampling task and send the collected charging and discharging status data of the energy storage device to the coordination control CPU, wherein the charging and discharging status data includes the charging and discharging current, voltage, power, grid frequency and temperature value of the energy storage device; The coordination control CPU is used to forward the charging and discharging status data of the energy storage device to the safety communication CPU; The secure communication CPU is used to report the charge and discharge status data of the energy storage device to the host computer through the communication interface after secure encryption processing; The task management CPU is communicatively connected with the energy storage device via the sensor interface; The safety communication CPU is connected to the host computer through the communication interface; The coordination control CPU is connected to the energy storage device through the USB interface; The task management CPU, the coordination control CPU and the safety communication CPU are communicatively connected in sequence.

[0037] Preferably, the safety communication CPU is further used to: receive and decrypt the reactive power compensation operation and maintenance strategy issued by the host computer to the corresponding energy storage device, and forward the decrypted reactive power compensation operation and maintenance strategy to the coordination control CPU; The coordination control CPU is further used to: receive and analyze the reactive compensation operation and maintenance strategy, obtain the reactive compensation control instruction therein, and issue the reactive compensation control instruction to the energy storage device through the USB interface.

[0038] The standby machine is equipped with corresponding data interaction interfaces, including a communication interface for communicating with the host computer, a USB interface for interactive control with the energy storage device, and several sensor interfaces for status data sensing and monitoring. These interfaces are all arranged on the main board. The main board is also equipped with a corresponding multi-CPU working system, mainly including a task management CPU, a coordination control CPU, and a safety communication CPU. Each energy storage device is pre-configured with corresponding sensors, such as temperature sensors, current / voltage sensors, etc., which can communicate with the main board through the corresponding sensor interface and perform sensor collection of corresponding types of status data under the control of the main board. The main board, that is, the PCB board, has three integrated CPUs that can respectively realize corresponding status data collection, processing, and execution of corresponding calculation control. The CPU model on the controller can be configured according to user needs.

[0039] When sampling is required, the host computer can send the corresponding sampling instructions to the controller according to the sampling frequency (task) of the corresponding energy storage device. After the security communication CPU performs security processing (generally synchronized with the encryption algorithm adopted by the host computer, such as the host computer encrypts the instruction and sends it to the controller, which is decrypted by the controller's security communication CPU and then checked for security), the instruction is forwarded, and finally the task management CPU executes the corresponding sampling task. The sampling task includes the host computer's requirements for the sampling frequency, data format, and type of status data of the corresponding energy storage device. It can be executed according to the preset sampling task.

[0040] Therefore, the task management CPU can control the corresponding sensor interface, collect the charging and discharging status data of the corresponding energy storage device, and transmit it to the coordination control CPU. After coordination by the coordination control CPU, the charging status data of the corresponding energy storage device is transmitted to the security communication CPU, which encrypts it and reports it to the host computer.

[0041] The encryption and decryption algorithms used in the secure communication CPU, such as symmetric encryption or asymmetric encryption, or hash-based encryption and decryption algorithms, can be understood by referring to the security encryption and decryption algorithms used.

[0042] The encryption and decryption processing of data signals, task instructions, etc. on the host computer and controller can be specifically referred to the selected encryption and decryption algorithm, which will not be elaborated here.

[0043] After the upper computer receives the charge and discharge status data of the corresponding energy storage device, it will decrypt and identify the signal source in the data to determine the energy storage device to which the current status data belongs. The background will generate a sampling file for the corresponding energy storage device and record and bind the charge and discharge status data sampled this time, and then perform subsequent AI supervision. The management of the corresponding energy storage device in the background and the identification of the device identity of the corresponding energy storage device based on the status data can also refer to the existing background equipment management solutions. For example, when sampling, the device code of the current energy storage device can be written into its charge and discharge status data, etc., so as to identify the identity and perform identity verification in the background.

[0044] In the coordinated control CPU, because the controller needs to collect the status of several energy storage devices and supervise the reactive compensation operation and maintenance, the coordinated control CPU can use a preset coordination management mechanism, such as a message queue, to orderly report the data of each energy storage device to the safety communication CPU. At the same time, it can also process some priority devices. For example, when the coordinated control CPU receives the charging and discharging status data of the corresponding energy storage device uploaded by the task management CPU, it can identify whether there is a corresponding priority mark in its status data. If there is a corresponding priority mark, the coordinated control CPU can perform coordinated control and report the status data with a priority mark to the host computer through the safety communication CPU first, so as to realize coordinated data reporting, prioritize uploading of important parameters, and orderly coordinate system equipment message transmission and routing.

[0045] Preferably, the energy storage system coordination controller further includes: Memory A, used to provide storage services for the safety communication CPU, including: storing the charging and discharging state data of the energy storage device sampled and reported each time, and the reactive compensation operation and maintenance strategy received accordingly; The memory A is communicatively connected to the safety communication CPU.

[0046] Preferably, the energy storage system coordination controller further includes: Memory B, used to provide storage services for the task management CPU, including: storing the charge and discharge state data of the energy storage device collected by each sampling; The memory B is communicatively connected to the task management CPU.

[0047] The memory may be, for example, a CMOS memory or a Flash memory, etc., which can store the data generated by the corresponding CPU, so as to facilitate the controller to record and back up.

[0048] like Figure 4 As shown, preferably, the method for generating the state AI supervision model includes: Collecting historical operation and maintenance supervision big data of some of the energy storage devices from the background database of the host computer, including historical status data of the energy storage devices and reactive power compensation operation and maintenance strategies issued by system operation and maintenance supervision, wherein the reactive power compensation operation and maintenance strategies include corresponding reactive power compensation control instructions; Feature engineering is performed on the historical operation and maintenance supervision big data, and a supervised learning algorithm is used to extract feature data from the historical operation and maintenance supervision big data, including the state feature values ​​in each group of the historical state data and the reactive compensation control instructions and strategy keywords corresponding to the state feature values ​​in the reactive compensation operation and maintenance strategy, and the state feature values ​​are bound to the strategy keywords to obtain the extracted features of each group: {state characteristic value, strategy keyword}; Collecting feature extraction results of each of the energy storage devices to obtain a feature set consisting of several groups of {state feature values, strategy keywords}; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into the default machine learning model, and train it according to the preset optimized iterative training conditions to construct the state AI supervision model; The performance of the state AI supervision model is verified using the validation set: If the verification is successful, the state AI supervision model is deployed and applied to the host computer; If the verification fails, repeat the above steps and retrain the model.

[0049] The data of reactive compensation operation and maintenance supervision conducted by the administrator in the past can be recorded in the system database. When training the model, the big data of historical operation and maintenance supervision can be retrieved and collected from the background database, including the analysis of the historical status data of the corresponding storage equipment and the corresponding reactive compensation operation and maintenance instructions issued. Each historical status data and the corresponding reactive compensation operation and maintenance strategy constitute a set of historical operation and maintenance supervision data; several sets of data constitute big data.

[0050] The reactive compensation operation and maintenance strategy that the administrator controls and generates based on the historical status data of the corresponding energy storage device includes the corresponding reactive compensation control instructions, which can be current compensation, voltage compensation, or compensation of the corresponding power factor. The corresponding reactive compensation control instructions are determined based on the operating parameters in the corresponding historical status data. For example, if it is found through analysis that the current is lagging or the voltage is leading, the corresponding type of reactive compensation current or reactive compensation voltage can be generated to balance the power factor, so that the charging and discharging power of the energy storage device reaches a balanced state, so that the charging and discharging is stable, the charging and discharging power grid composed of the energy storage device has the best operating efficiency, and maintains better stability.

[0051] Therefore, the reactive power compensation operation and maintenance strategy that has been set for the corresponding state in the past can be determined by the administrator according to the reactive power compensation analysis results generated by the specific analysis to determine the corresponding reactive power compensation operation and maintenance strategy.

[0052] After collecting the historical operation and maintenance supervision big data, feature engineering is required to extract the data features under each set of data. Using the supervised learning algorithm, the state feature values ​​in the historical state data in each set of data are extracted, such as the current value or voltage value with operation differences, or the power value, temperature value, etc., which may affect the operation of the system and require corresponding reactive power compensation. Therefore, the supervised learning algorithm can be used to extract the state feature values ​​in the state data of each set of data, and the reactive power compensation operation and maintenance strategy in the set of data can be analyzed to extract the corresponding strategy keywords, such as "current compensation" or "voltage compensation", etc.; at the same time, the corresponding instructions in the operation and maintenance strategy can be extracted, so as to bind the extracted strategy keywords and instructions with the corresponding state feature values, so that the subsequent model can match and output the corresponding strategy keywords and instructions according to the identified features.

[0053] The steps of using supervised learning algorithms to extract data features and their correlations in each set of data can be referred to as follows: 1. Data Collection and Preprocessing ‌Data Collection‌: Collect relevant data from various sensors, monitoring systems and other channels of the energy storage system, including the following status data: battery status, temperature, voltage, current, power factor and other parameters, as well as system operating status, alarm information (system reactive power compensation strategy or alarm instructions / information related to reactive power compensation, etc., which contain corresponding reactive power compensation control parameters), etc.

[0054] ‌Data Cleansing‌: Clean the collected data to remove duplicate, missing or abnormal data records to ensure the accuracy and completeness of the data.

[0055] ‌Data Standardization‌: Standardize data from different sources and in different formats, unify data formats and units, and facilitate subsequent data analysis and processing.

[0056] 2. Feature Selection and Extraction ‌Feature Selection‌: According to the requirements of energy storage system status monitoring, features related to the energy storage system status are selected from the preprocessed data. These features may include physical quantities such as battery temperature, voltage, current, power factor, as well as system operation time, load conditions, alarm information, etc.

[0057] ‌Feature Extraction‌: Features that are more directly related to the state of the energy storage system can be extracted from the raw data using statistical methods, mathematical transformations, or domain knowledge. For example, statistical features such as the average temperature, maximum temperature difference, and voltage fluctuation range of the battery can be calculated, or frequency domain features of the signal can be extracted using methods such as Fourier transform.

[0058] 3. Data Annotation and Training Set Construction ‌Data Annotation‌: The extracted feature data is labeled (in this embodiment, the extracted features of the group are: {state feature value, strategy keyword}, ​​and the label is on the state feature value), that is, each group of data is labeled accordingly according to the actual state of the energy storage system or expert knowledge. For example, the data can be divided into categories such as "normal", "warning", and "fault" according to the health status of the battery.

[0059] ‌Training set construction‌: The labeled data is divided into a training set and a validation set (for example, in a ratio of 8:2) for subsequent training and evaluation of the supervised learning model.

[0060] IV. Supervised Learning Model Training and Optimization ‌Model Selection‌: According to the specific needs and data characteristics of the energy storage system state supervision, select the appropriate supervised learning algorithm. For example, for classification problems, you can choose algorithms such as logistic regression, support vector machine, decision tree, random forest, etc.; for regression problems, you can choose algorithms such as linear regression and polynomial regression.

[0061] ‌Model Training‌: The selected supervised learning algorithm is trained using the training set data, and the performance of the model is optimized by adjusting the parameters and structure of the model.

[0062] ‌Model Evaluation and Optimization‌: Use the validation set data to evaluate the trained model, and evaluate the performance of the model by calculating indicators such as accuracy, recall, and F1 score. Further optimize and adjust the model based on the evaluation results.

[0063] Model validation is done by the administrator himself.

[0064] 5. Feature Correlation Analysis ‌Feature Importance Evaluation‌: Using the trained supervised learning model, evaluate the importance of each feature to the model's prediction results. This can be done by calculating the importance score of the feature or using a feature selection algorithm.

[0065] ‌Correlation Analysis‌: Based on the results of feature importance assessment, the correlation between each feature is analyzed. For example, correlation analysis, cluster analysis and other methods can be used to reveal the internal connection and mutual influence between features.

[0066] ‌Visual display‌: By drawing feature importance diagrams, correlation network diagrams, etc., the correlation relationship and importance distribution between features can be intuitively displayed, providing strong data support for energy storage system status supervision.

[0067] In summary, using supervised learning algorithms to extract data features and their correlations in each set of data in energy storage system state supervision is a complex and systematic process, which requires the comprehensive use of multiple steps and methods such as data preprocessing, feature selection and extraction, data labeling and training set construction, supervised learning model training and optimization, and feature correlation analysis.

[0068] In this aspect, by extracting data from big data through supervised learning algorithms, a feature set consisting of state feature values ​​and policy keywords can be constructed. Subsequently, a machine learning model, such as a random forest model, is used to train and learn the features in the feature set, so that the model can train and learn the relationship between policy keywords corresponding to different state feature values. The subsequent model can perform state recognition and output the matched policy keywords, and use the policy keywords to retrieve the corresponding reactive power compensation operation and maintenance strategy. The retrieval can be handed over to, for example, an LLM large language model to retrieve the reactive power compensation operation and maintenance strategy containing the corresponding policy keywords, and output it to the controller, which executes the operation and maintenance strategy on the corresponding storage device and performs reactive power compensation, so as to achieve stable operation of the power grid.

[0069] A large number of reactive power compensation operation and maintenance strategies can be pre-stored in the database, or historical operation and maintenance strategies can be used as a strategy library to provide a database retrieval basis for the output of the model.

[0070] When constructing the above features, the state feature values ​​corresponding to each strategy can also be expanded and processed, and the state feature values ​​corresponding to each strategy can be drifted up and down by a certain value to generate a state feature range value. For example, the charging current value of 40A is drifted to 37.5-42.5A. As long as the charging and discharging current values ​​meet this state feature range value, an operation and maintenance strategy will be used for processing, avoiding the drawbacks of excessive classification recognition, increased computing power share, and low recognition accuracy in the recognition of individual feature values. By identifying the range value, the model can improve the supervision range and recognition accuracy of the state data.

[0071] Preferably, S2, the host computer inputs the state data into a preset state AI supervision model, identifies the state characteristic value in the state data through the state AI supervision model and outputs a reactive power compensation operation and maintenance strategy matching the state characteristic value, including: Receive and identify the basic information of the status data reported by the energy storage system coordination controller and bind it to the device ID corresponding to the energy storage device; The state data is input into the state AI supervision model, and the state AI supervision model identifies the state feature value in the state data and determines whether there is a policy keyword matching the state feature value: If yes, extract the strategy keywords, retrieve the corresponding reactive power compensation operation and maintenance strategy according to the strategy keywords and output it; Otherwise, continue monitoring.

[0072] The model can identify whether the corresponding state characteristic value requires reactive compensation. If the state characteristic value that requires reactive compensation is extracted and identified in the state data of the current device, the AI ​​model is used to predict and match the output of the policy keywords corresponding to the state characteristic value (here, avoid directly outputting the corresponding reactive compensation operation and maintenance instructions to reduce the operating pressure of the model, and instead output the corresponding policy retrieval and send it to the policy library for execution, and find and output the reactive compensation operation and maintenance strategy containing the policy keywords).

[0073] For example, here, you can let the LLM large language model (through the backend LLM API interface, request call) perform the search, for example, you can refer to the following steps: First, it is necessary to identify the strategy keywords and prepare a relevant retrieval database or knowledge base (the original strategy stored in the background or a separate strategy library that stores a large number of reactive power compensation operation and maintenance strategies). This database or knowledge base should contain various operation and maintenance strategies and their corresponding keywords or tags.

[0074] ‌Prepare strategic keywords and database‌: Determine the strategic keywords to be searched, which should be closely related to the operation and maintenance strategy.

[0075] Establish a database or knowledge base containing various operation and maintenance strategies and their keywords or tags to ensure the accuracy and completeness of the data.

[0076] ‌Build a retrieval system‌: Utilize existing search engine technology or deep learning technology, such as keyword-based retrieval, content-based retrieval, or Transformer-based retrieval models, to build an efficient retrieval system.

[0077] This retrieval system should be able to quickly find relevant operation and maintenance strategies in the database based on strategy keywords.

[0078] ‌Combined with LLM large language model and retrieval system‌: Combine the LLM large language model with the retrieval system to achieve retrieval enhancement generation.

[0079] When a strategy keyword is entered, the retrieval system will first retrieve the operation and maintenance strategy information related to the keyword from the database.

[0080] The LLM large language model will then rearrange and combine this information to generate an operation and maintenance strategy text output that meets the requirements.

[0081] ‌Optimization and Evaluation‌: According to the needs of actual applications, the combination of LLM large language model and retrieval system is optimized to improve the accuracy and efficiency of retrieval.

[0082] Various evaluation indicators can be used to evaluate the performance of the system, such as accuracy, recall, etc., so as to continuously optimize and improve it.

[0083] Output operation and maintenance strategy: Finally, the operation and maintenance strategy text generated by the LLM large language model is output to the user for reference and use.

[0084] Through the above steps, the goal of allowing the LLM large language model to search the library based on strategy keywords and output the corresponding operation and maintenance strategy can be achieved.

[0085] like Figure 5 As shown, the host computer of the present invention can manage several energy storage devices in the energy storage power grid system through the controller, and the background can build the operation and maintenance files of the corresponding energy storage devices, and record the results of each sampling and operation and maintenance supervision to facilitate subsequent supervision and management.

[0086] Reference Figure 2 On the other hand, an online operation and maintenance supervision system for energy storage device status based on AI supervision is provided, and the online operation and maintenance supervision system for energy storage device status based on AI supervision is used to implement the above-mentioned online operation and maintenance supervision method for energy storage device status based on AI supervision, and the system includes: Energy storage system coordination controller, used to monitor and upload status data of energy storage equipment to the host computer; A host computer, used for inputting the state data into a preset state AI supervision model, identifying the state characteristic value in the state data through the state AI supervision model and outputting a reactive compensation operation and maintenance strategy matching the state characteristic value; and binding the reactive compensation operation and maintenance strategy with the corresponding energy storage device, and sending it to the energy storage system coordination controller, so that the energy storage system coordination controller executes the reactive compensation operation and maintenance strategy on the energy storage device; The energy storage system coordination controller is communicatively connected to the host computer.

[0087] The communication interaction and control between the host computer of the above-mentioned system and the energy storage system coordination controller, as well as the mode of controlling each power grid energy storage device through the energy storage system coordination controller, should be implemented in combination with the steps and principles described in the above method, and will not be repeated here.

[0088] Figure 6 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Optionally, the electronic device 410 may include a first processor 2001.

[0089] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0090] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0091] Combine the following Figure 6 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0092] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0093] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 6 CPU0 and CPU1 are shown in FIG.

[0094] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 6 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0095] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0096] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0097] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0098] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 6 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0099] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0100] It should be noted that Figure 6 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0101] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the online operation and maintenance supervision method of the energy storage device status based on AI supervision described in the above method embodiment, which will not be repeated here.

[0102] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0104] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0105] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0106] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0107] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0108] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0110] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the system or unit, which can be electrical, mechanical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0114] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An online operation and maintenance supervision method for energy storage equipment status based on AI supervision, characterized in that: Based on the coordinated implementation of the energy storage system coordination controller and the host computer, the energy storage system coordination controller is used to monitor the status data of the energy storage device and upload it to the host computer, and the host computer analyzes the status data of the energy storage device and performs intelligent operation and maintenance supervision and management of the energy storage device; the method comprises the following steps: S1, monitoring and uploading the status data of the energy storage device to the host computer through the energy storage system coordination controller; S2, the host computer inputs the state data into a preset state AI supervision model, identifies the state characteristic value in the state data through the state AI supervision model, and outputs a reactive power compensation operation and maintenance strategy matching the state characteristic value; S3, binding the reactive power compensation operation and maintenance strategy with the corresponding energy storage device, and sending it to the energy storage system coordination controller; S4. The energy storage system coordination controller executes the reactive power compensation operation and maintenance strategy on the energy storage device.

2. According to claim 1, the method for online operation and maintenance supervision of energy storage equipment status based on AI supervision is characterized in that: The energy storage system coordination controller includes a communication interface, a USB interface, several sensor interfaces and a mainboard, on which a task management CPU, a coordination control CPU and a safety communication CPU are configured, wherein: The task management CPU is used to control the sampling of the sensor interface according to the preset sampling task and send the collected charging and discharging status data of the energy storage device to the coordination control CPU, wherein the charging and discharging status data includes the charging and discharging current, voltage, power, grid frequency and temperature value of the energy storage device; The coordination control CPU is used to forward the charging and discharging status data of the energy storage device to the safety communication CPU; The secure communication CPU is used to report the charge and discharge status data of the energy storage device to the host computer through the communication interface after secure encryption processing; The task management CPU is communicatively connected with the energy storage device via the sensor interface; The safety communication CPU is connected to the host computer through the communication interface; The coordination control CPU is connected to the energy storage device through the USB interface; The task management CPU, the coordination control CPU and the safety communication CPU are communicatively connected in sequence.

3. The method for online operation and maintenance supervision of energy storage equipment status based on AI supervision according to claim 2 is characterized in that: The safety communication CPU is further used to: receive and decrypt the reactive power compensation operation and maintenance strategy issued by the host computer to the corresponding energy storage device, and forward the decrypted reactive power compensation operation and maintenance strategy to the coordination control CPU; The coordination control CPU is further used to: receive and analyze the reactive compensation operation and maintenance strategy, obtain the reactive compensation control instruction therein, and issue the reactive compensation control instruction to the energy storage device through the USB interface.

4. The method for online operation and maintenance supervision of energy storage equipment status based on AI supervision according to claim 3 is characterized in that: The energy storage system coordination controller also includes: Memory A, used to provide storage services for the safety communication CPU, including: storing the charging and discharging state data of the energy storage device sampled and reported each time, and the reactive compensation operation and maintenance strategy received accordingly; The memory A is communicatively connected to the safety communication CPU.

5. The method for online operation and maintenance supervision of energy storage equipment status based on AI supervision according to claim 3 is characterized in that: The energy storage system coordination controller also includes: Memory B, used to provide storage services for the task management CPU, including: storing the charge and discharge state data of the energy storage device collected by each sampling; The memory B is communicatively connected to the task management CPU.

6. The method for online operation and maintenance supervision of energy storage equipment status based on AI supervision according to claim 1 is characterized in that: The method for generating the state AI supervision model comprises: Collecting historical operation and maintenance supervision big data of some of the energy storage devices from the background database of the host computer, including historical status data of the energy storage devices and reactive power compensation operation and maintenance strategies issued by system operation and maintenance supervision, wherein the reactive power compensation operation and maintenance strategies include corresponding reactive power compensation control instructions; Feature engineering is performed on the historical operation and maintenance supervision big data, and a supervised learning algorithm is used to extract feature data from the historical operation and maintenance supervision big data, including the state feature values ​​in each group of the historical state data and the reactive compensation control instructions and strategy keywords corresponding to the state feature values ​​in the reactive compensation operation and maintenance strategy, and the state feature values ​​are bound to the strategy keywords to obtain the extracted features of each group: {state characteristic value, strategy keyword}; Collecting feature extraction results of each of the energy storage devices to obtain a feature set consisting of several groups of {state feature values, strategy keywords}; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into the default machine learning model, and train it according to the preset optimized iterative training conditions to construct the state AI supervision model; The performance of the state AI supervision model is verified using the validation set: If the verification is successful, the state AI supervision model is deployed and applied to the host computer; If the verification fails, repeat the above steps and retrain the model.

7. The method for online operation and maintenance supervision of energy storage equipment status based on AI supervision according to claim 6 is characterized in that: S2, the host computer inputs the state data into a preset state AI supervision model, identifies the state characteristic value in the state data through the state AI supervision model and outputs a reactive power compensation operation and maintenance strategy matching the state characteristic value, including: Receive and identify the basic information of the status data reported by the energy storage system coordination controller and bind it to the device ID corresponding to the energy storage device; The state data is input into the state AI supervision model, and the state AI supervision model identifies the state feature value in the state data and determines whether there is a policy keyword matching the state feature value: If yes, extract the strategy keywords, retrieve the corresponding reactive power compensation operation and maintenance strategy according to the strategy keywords and output it; Otherwise, continue monitoring.

8. An online operation and maintenance supervision system for energy storage device status based on AI supervision, wherein the online operation and maintenance supervision system for energy storage device status based on AI supervision is used to implement the online operation and maintenance supervision method for energy storage device status based on AI supervision as claimed in any one of claims 1 to 7, characterized in that: The system comprises: Energy storage system coordination controller, used to monitor and upload status data of energy storage equipment to the host computer; A host computer, used for inputting the state data into a preset state AI supervision model, identifying the state characteristic value in the state data through the state AI supervision model and outputting a reactive compensation operation and maintenance strategy matching the state characteristic value; and binding the reactive compensation operation and maintenance strategy with the corresponding energy storage device, and sending it to the energy storage system coordination controller, so that the energy storage system coordination controller executes the reactive compensation operation and maintenance strategy on the energy storage device; The energy storage system coordination controller is communicatively connected to the host computer.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images