Method and device for collecting operation information of electric power energy storage equipment and storage medium

Abstract

The invention discloses an electric power energy storage equipment operation information acquisition method and device and a storage medium, and relates to the technical field of electric power energy storage. The electric power energy storage equipment operation information acquisition method comprises the following steps: acquiring operation parameters of electric power energy storage equipment in real time through a multi-source sensor network; preprocessing the operation parameters to generate preprocessed data; inputting the preprocessed data into a state evaluation model, evaluating the current operation state of the electric power energy storage equipment, and outputting the operation state and a state index; generating a data acquisition instruction through an acquisition strategy generator according to the running state and the state index; and the multi-source sensor network performs data acquisition, transmission and storage according to the data acquisition instruction. The method effectively solves the problems caused by an existing fixed acquisition mode, and is of great significance for improving the operation efficiency, the safety and the intelligent level of the energy storage system.

Description

Technical Field

[0001] This invention relates to a method, device, and storage medium for collecting operational information of power energy storage equipment, belonging to the field of power energy storage technology. Background Technology

[0002] As a crucial component of the new power system, the safe and stable operation of power storage devices is vital to the reliability of the power grid. Currently, the collection of operational information from power storage devices typically employs a fixed-period or fixed-parameter approach. However, this method suffers from several problems. First, when the equipment is operating smoothly or under low load, a large amount of non-critical data is collected and transmitted, resulting in data redundancy, wasted storage space, and excessive communication bandwidth consumption. Second, when the equipment malfunctions or operates under high load conditions, the fixed collection frequency may fail to capture critical data changes in a timely and comprehensive manner, leading to delays in early warning of potential risks and fault diagnosis. Furthermore, existing collection methods often lack the ability to differentiate between different types and levels of importance of parameters, making it difficult to achieve refined and on-demand data acquisition and limiting further exploitation of data value. Therefore, developing a method that can intelligently adjust information collection strategies based on the actual operating status of power storage devices is of great significance for improving the operational efficiency, safety, and intelligence level of energy storage systems. Summary of the Invention

[0003] The purpose of this invention is to provide a method, device, and storage medium for collecting operational information of power energy storage equipment. This method intelligently adjusts the information collection strategy according to the actual operating status of the power energy storage equipment, thereby solving the problems of data redundancy, delayed early warning in case of anomalies, and lack of parameter differentiation and processing caused by the fixed collection mode in the prior art.

[0004] To achieve the above objectives, the present invention is implemented using the following technical solution.

[0005] On one hand, the present invention provides a method for collecting operational information of power storage devices, including: Real-time acquisition of operating parameters of power storage devices through multi-source sensor networks; The operating parameters are preprocessed to generate preprocessed data; The preprocessed data is input into the status assessment model to assess the current operating status of the power energy storage device and output the operating status and status indicators. Based on the operating status and status indicators, a data acquisition instruction is generated by the acquisition strategy generator. The data acquisition instruction includes the data acquisition frequency, the list of parameters to be acquired, and the sampling granularity. The multi-source sensor network collects, transmits, and stores data according to the data acquisition instructions.

[0006] Optionally, the operating parameters include the voltage, current, temperature, power, energy throughput, battery state of charge, battery health, and cycle count of the power storage device; these are obtained through multi-source sensors deployed in the battery cluster, battery management system, power conversion system, and energy management system.

[0007] Optionally, the preprocessing includes cleaning the collected operating parameters to remove redundant or erroneous information from the operating parameters; The cleaned operating parameters are denoised by using a moving average algorithm or a Kalman filter algorithm to eliminate noise in the operating parameters. Perform format standardization conversion on the denoised operating parameters; Synchronize the timestamps of the converted runtime parameters.

[0008] Optionally, the state assessment model combines an expert knowledge base with machine learning algorithms to assess the current operating status of the power storage device; The expert knowledge base includes preset thresholds and logical judgment rules. When the running parameters meet the thresholds or logical judgment rules, the corresponding running status warning or abnormal indication is output. Machine learning algorithms are trained using historical operating data. Long short-term memory networks are used to predict the degradation trend of battery health, or support vector machines or decision trees are used to classify the operating conditions of power storage devices, including normal, high load, or low load.

[0009] Optionally, the operating status includes normal, warning, abnormal, high load, low load, or maintenance.

[0010] Optionally, the process of generating data acquisition instructions through the acquisition strategy generator based on the operating status and status indicators includes: When the operation is normal, the command data acquisition frequency is adjusted from the first preset frequency to the second preset frequency. The second preset frequency is lower than the first preset frequency, and only core operating parameters are acquired. The core operating parameters include voltage, current, total temperature and state of charge, and the sampling granularity is appropriately reduced. When the operating status is warning or high load, the sampling frequency of relevant operating parameters is increased from the first preset frequency to the third preset frequency. The third preset frequency is higher than the first preset frequency. The number of key operating parameters collected is increased, including the voltage, current and local temperature of each individual battery cell, and the sampling granularity is improved. When the operating status is abnormal, the highest frequency of data acquisition at the millisecond level is triggered. The data acquisition includes all available electrical parameters, thermal parameters and environmental parameters, and at the same time, local alarm and remote alarm mechanisms are triggered. When the running status is maintenance or standby, only core operating parameters are collected.

[0011] Optionally, the data collection strategy generator has a built-in rule engine and is combined with a learning optimization module: The learning optimization module analyzes the performance of historical data collection strategies under different operating conditions, including data integrity, transmission latency, and timeliness of anomaly warnings. Combined with a feedback mechanism, it uses reinforcement learning algorithms to optimize the parameters of the rule engine or adjust the weights of the data collection strategies under different operating conditions, making data collection commands more accurate and efficient.

[0012] Optionally, the process of the multi-source sensor network acquiring data according to the data acquisition command includes: the data acquisition control module receiving the data acquisition command issued by the acquisition strategy generator, and communicating with the multi-source sensor network through a digital interface or an analog interface to dynamically adjust the acquisition parameters, acquisition frequency and sampling accuracy of each sensor.

[0013] In a second aspect, the present invention provides a power energy storage device operation information collection device, comprising: The data acquisition module is used to: acquire the operating parameters of the power storage device in real time through a multi-source sensor network; The operating parameters are preprocessed to generate preprocessed data; The data acquisition method generation module is used to: input the preprocessed data into the status assessment model, assess the current operating status of the power energy storage device, and output the operating status and status indicators; Based on the operating status and status indicators, a data acquisition instruction is generated by the acquisition strategy generator. The data acquisition instruction includes the data acquisition frequency, the list of parameters to be acquired, and the sampling granularity. The multi-source sensor network collects, transmits, and stores data according to the data acquisition instructions.

[0014] Thirdly, the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the steps of the method for collecting operating information of an energy storage device as described in any of the first aspects.

[0015] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: 1. This invention collects equipment operating parameters in real time through a multi-source sensor network. After preprocessing such as cleaning and noise reduction to ensure data quality, it combines an expert knowledge base and a state evaluation model based on machine learning algorithms to determine the equipment status. The acquisition strategy generator dynamically generates acquisition instructions, which effectively solves the problems of data redundancy, delayed early warning in case of anomalies, and lack of parameter differentiation caused by the existing fixed acquisition mode. It is of great significance for improving the operating efficiency, safety and intelligence level of energy storage systems. 2. The learning and optimization module of the collection strategy generator of the present invention can continuously optimize the strategy, improve the accuracy and efficiency of data collection, and ultimately improve the operating efficiency and safety of the energy storage system. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method for collecting operation information of power storage equipment according to the present invention; Figure 2 This is a flowchart of the operation parameter acquisition and preprocessing process of the present invention; Figure 3 This is a flowchart for generating acquisition instructions according to the present invention; Figure 4 This is a flowchart of the dynamic control and feedback optimization of the acquisition command in this invention. Detailed Implementation

[0017] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other. Example 1:

[0018] This embodiment describes a method for collecting operational information from power storage devices, such as... Figure 1 As shown, it includes: Real-time acquisition of operating parameters of power storage devices through multi-source sensor networks; The operating parameters are preprocessed to generate preprocessed data; The preprocessed data is input into the status assessment model to assess the current operating status of the power energy storage device and output the operating status and status indicators. Based on the operating status and status indicators, a data acquisition instruction is generated by the acquisition strategy generator. The data acquisition instruction includes the data acquisition frequency, the list of parameters to be acquired, and the sampling granularity. The multi-source sensor network collects, transmits, and stores data according to the data acquisition instructions.

[0019] I. Operation Parameter Acquisition and Preprocessing To address the diverse parameter acquisition needs, multi-source sensors are deployed. Voltage and temperature sensors are installed on each individual cell and module within the battery cluster to collect real-time data on individual cell voltage and module temperature. A dedicated acquisition module is integrated into the Battery Management System (BMS) to acquire real-time battery state of charge (SOC), state of health (SOH), and cycle count. This module communicates with the battery cluster sensors to aggregate and process the relevant data. Current and power sensors are installed at the input and output terminals of the Power Conversion System (PCS) to collect real-time input and output current and power data during equipment operation. A data acquisition unit is set up in the Energy Management System (EMS) to acquire real-time energy throughput data. This unit, through linkage with the PCS and BMS, accurately calculates the energy throughput of the equipment over a specific period. This multi-source sensor deployment enables comprehensive and accurate acquisition of various key parameters during the operation of the power storage equipment, providing a reliable data foundation for subsequent status assessment and data acquisition strategy adjustments.

[0020] like Figure 2 As shown, when preprocessing the collected operating parameters, the first step is to perform data cleaning. By using preset threshold values ​​for reasonable parameter ranges, abnormal data that exceeds the threshold is filtered out. For example, data with battery voltages exceeding the reasonable range of 2V-4.2V is identified as erroneous data and removed. At the same time, redundant data that is repeatedly transmitted is deleted to ensure the accuracy of the original data.

[0021] After data cleaning, a moving average algorithm is used to denoise the data. This algorithm calculates the average value of target data over multiple consecutive acquisition periods and uses this average value to replace the fluctuating data in the original data. Taking battery temperature data as an example, the average value is calculated by selecting temperature data from 5 consecutive acquisition periods, which can effectively eliminate noise caused by short-term random fluctuations. If the data noise interference is large, the Kalman filter algorithm can be used. This algorithm is also an existing technology. By establishing a data filtering model and combining the predicted and observed values ​​of the data for iterative updates, the influence of random noise on the data can be further eliminated, making the data more consistent with the actual operating conditions of the equipment.

[0022] Then, a format standardization conversion is performed to convert the different data output from different sensors, such as XML format and binary format, into a common data format to facilitate the unified processing and transmission of subsequent data.

[0023] Finally, timestamp synchronization is performed. Using the Precise Time Protocol (PTP), the timestamps of all sensor data are calibrated to the same time base to ensure that data collected by different sensors at the same time can correspond accurately, avoiding data analysis deviations caused by time differences, and providing time-consistent data support for the accurate analysis of subsequent state assessment models.

[0024] II. Generating Data Acquisition Commands like Figure 3 As shown, the state assessment model combines an expert knowledge base with machine learning algorithms to assess the current operating status of power storage devices.

[0025] The expert knowledge base pre-stores thresholds and logical judgment rules for various operating parameters of power storage devices. For example, it sets a voltage abnormality warning when the battery voltage is higher than 4.3V or lower than 1.8V, and a temperature abnormality warning when the battery temperature is higher than 50℃. When the pre-processed data meets these thresholds or logical rules, the model will directly output the corresponding operating status warning or abnormality indication.

[0026] Meanwhile, machine learning algorithms are trained and optimized using a large amount of historical operating data. When predicting the battery health degradation trend, a Long Short-Term Memory (LSTM) network is used. This network is good at processing time-series data. By inputting historical battery charge and discharge data, cycle count data, etc., into the network, it can capture the pattern of data changes over time and thus accurately predict the trend of battery health changes in the future. When classifying equipment operating conditions, support vector machine (SVM) or decision tree algorithms are used. SVM classifies data by finding the optimal classification hyperplane, while decision tree performs logical judgment by constructing a tree structure. By using preprocessed data such as voltage, current, and power as input features, the normal operating condition, high load condition, and low load condition of the equipment can be classified and identified.

[0027] In the actual evaluation process, the model first makes a preliminary judgment on the data through an expert knowledge base, and then combines the analysis results of machine learning algorithms to comprehensively determine the current operating status of the equipment. This not only ensures the real-time nature of the status evaluation, but also improves the accuracy of the evaluation results, providing a reliable basis for the dynamic adjustment of subsequent data collection strategies.

[0028] When the state assessment model determines, through analysis of preprocessed data, that the power storage equipment is in normal operating condition and that all operating parameters remain stable over a relatively long period without significant fluctuations, the data acquisition strategy generator will generate corresponding adjustment instructions. Regarding the data acquisition frequency, the original first preset frequency is adjusted to a second preset frequency, where the second preset frequency is lower than the first preset frequency. For example, if the first preset frequency is data acquisition every 10 seconds, the second preset frequency can be adjusted to data acquisition every 30 seconds, reducing the frequency of data acquisition.

[0029] Regarding the list of parameters to be collected, only core operating parameters are retained, including the overall voltage, total current, total temperature, and battery state of charge of the device. Other non-core auxiliary parameters, such as the voltage of individual auxiliary circuits and minor temperature and humidity changes in the local environment, are removed to reduce the amount of data collected.

[0030] At the same time, the sampling granularity can be appropriately reduced. For example, when acquiring voltage, the original sampling accuracy is 0.1V, which can be reduced to 0.5V after adjustment. When acquiring current, the sampling accuracy can be adjusted from 0.01A to 0.05A. While ensuring normal monitoring needs, data redundancy can be further reduced, the storage pressure on storage devices and the bandwidth occupation of communication links can be reduced, and the overall system operating efficiency can be improved.

[0031] After the state assessment model analyzes the preprocessed data, it outputs a mild warning state, that is, some operating parameters are close to the preset abnormal threshold but have not exceeded it, or it determines that the equipment is in a high-load discharge state, that is, when the equipment's discharge power and discharge current are continuously at a high level, the acquisition strategy generator will generate corresponding instructions to improve the acquisition capability.

[0032] Regarding the data acquisition frequency, the original first preset frequency is increased to the third preset frequency, which is higher than the first preset frequency. For example, if the first preset frequency is once every 10 seconds, the third preset frequency can be adjusted to once every 5 seconds to speed up the data acquisition speed and ensure timely capture of parameter change trends.

[0033] Regarding the parameters to be collected, the collection of key operating parameters has been added to the existing data. These key operating parameters include the voltage of each individual battery cell, the current of each individual battery cell, and the local temperature of the battery module. These parameters can more accurately reflect the internal operating status of the equipment and avoid missing local abnormal changes due to only collecting overall parameters.

[0034] At the same time, the sampling granularity is improved. For example, when collecting the voltage of a single battery cell, the sampling accuracy is increased from 0.1V to 0.05V, and when collecting the local temperature, the sampling accuracy is increased from 1℃ to 0.5℃. This makes the collected data more detailed and can more accurately reflect the subtle fluctuations in parameters, providing more precise data support for staff to promptly identify potential risks and monitor the operating status of equipment under high load conditions.

[0035] When the state assessment model determines that the power storage device is in a severely abnormal state through in-depth analysis of the preprocessed data, such as a battery voltage that sharply exceeds the safe range, a battery temperature that rises rapidly in a short period of time, or a sudden increase in current, the data acquisition strategy generator will immediately generate the highest level data acquisition command.

[0036] Regarding data acquisition frequency, the highest frequency acquisition mode at the millisecond level is activated, for example, data is collected once every 1 millisecond. This ensures that every detail of data change under abnormal device conditions can be captured at an extremely high frequency, providing a complete data chain for subsequent analysis of fault causes and tracing of fault development processes.

[0037] In terms of data acquisition scope, all available electrical, thermal, and environmental parameters are collected. Electrical parameters include input and output voltage, input and output current, power, and resistance. Thermal parameters include individual battery temperature, battery module temperature, and heat dissipation system temperature. Environmental parameters include the temperature, humidity, and air pressure of the equipment's operating environment, ensuring comprehensive coverage of all types of data related to equipment malfunctions.

[0038] Simultaneously, an alarm mechanism is triggered, which includes both local and remote alarms. Local alarms are implemented through the on-site audible and visual alarm devices, such as emitting a piercing alarm sound and illuminating a red alarm light to remind on-site personnel to handle the situation promptly. Remote alarms, on the other hand, send alarm information to the staff's mobile terminals or monitoring platforms via the network, enabling staff who are not on-site to be aware of abnormal equipment conditions in a timely manner, so as to quickly organize troubleshooting and handling, and minimize the damage caused to the equipment by abnormal conditions.

[0039] In this embodiment, the data collection strategy generator has a built-in rule engine, which is combined with a learning optimization module: like Figure 4 As shown, the rule engine built into the data acquisition strategy generator pre-stores basic acquisition rules corresponding to different operating states, such as acquisition frequency and parameter list rules under normal state. During device operation, the rule engine will call the corresponding basic rules to generate initial data acquisition instructions based on the state evaluation results.

[0040] Meanwhile, the learning and optimization module in the acquisition strategy generator will continue to play a role. This module will periodically analyze the performance of historical acquisition strategies under different operating states, specifically including the completeness of data under historical acquisition strategies, i.e., whether the key data of device operation has been fully captured; data transmission latency, i.e. whether the time from data acquisition to transmission to the storage system is within a reasonable range; and the timeliness of anomaly warnings, i.e. whether potential anomalies of the device are promptly warned through the acquired data.

[0041] Based on these analysis results, the learning optimization module uses a feedback mechanism to feed back the identified problems and optimization directions to the rule engine. Subsequently, it utilizes a reinforcement learning algorithm, an existing technology, to construct a "state-action-reward" learning framework. This algorithm adjusts behavioral strategies based on feedback from historical strategy performance, continuously optimizing the parameters in the rule engine. For example, it adjusts the specific values ​​of the collection frequency under different operating states, or adjusts the weights of different parameters in the collection list. This makes the collection instructions generated by the rule engine more closely match the actual operating needs of the equipment, further improving the accuracy and efficiency of data collection. This allows the collection strategy to be continuously optimized as the equipment's operating experience accumulates.

[0042] In this embodiment, the data acquisition control module dynamically adjusts the operating mode of the multi-source sensor network according to the data acquisition command, controlling the multi-source sensor network to acquire data according to the data acquisition command, including: Specifically, when the data acquisition and control module is working, it first receives the data acquisition command issued by the acquisition strategy generator, and then analyzes the information in the command, such as the acquisition frequency, the list of parameters to be acquired, and the sampling granularity, to determine the working parameters that need to be adjusted for each sensor.

[0043] Subsequently, the data acquisition and control module establishes a connection with the multi-source sensor network through the corresponding communication interface. If the sensor supports digital communication, it uses digital interfaces such as RS485 or Ethernet for communication; if the sensor only supports analog communication, it communicates through analog input / output interfaces. Through these interfaces, the data acquisition and control module sends adjustment commands to each sensor. For example, for a voltage sensor, if the acquisition command requires an increase in sampling accuracy, the control module will send a command to the sensor to adjust its sampling accuracy from the original 0.1V to 0.05V; for a temperature sensor, if the acquisition command requires an increase in the sampling frequency, the control module will instruct the sensor to increase the sampling frequency from once every 10 seconds to once every 5 seconds.

[0044] After the adjustment is completed, the data acquisition and control module will monitor the working status of each sensor in real time to ensure that the sensor can collect data normally according to the new acquisition instructions. If a sensor is found to be not working according to the instructions, the control module will resend the adjustment instructions or issue a fault prompt to ensure that the multi-source sensor network can accurately and stably complete the data acquisition task according to the data acquisition instructions, and provide a reliable data source for subsequent data transmission and storage.

[0045] In this embodiment, a multi-source sensor network is used to collect equipment operating parameters in real time. Data quality is ensured through preprocessing such as cleaning and noise reduction. Then, a state assessment model combining an expert knowledge base and machine learning algorithms is used to determine the equipment status. A data acquisition strategy generator dynamically generates acquisition instructions, effectively solving the problems of existing fixed acquisition modes: Under normal conditions, the acquisition frequency is reduced, and the acquisition of non-critical parameters is minimized to avoid data redundancy and waste of storage and bandwidth resources; under warning or high-load conditions, the frequency is increased, and the acquisition of critical parameters is expanded; under abnormal conditions, the highest frequency comprehensive acquisition is initiated and alarms are triggered, solving the problems of untimely data capture and delayed warnings during anomalies; during maintenance or standby, only core parameters are acquired, enabling differentiated parameter processing. Furthermore, the learning and optimization module of the acquisition strategy generator can continuously optimize the strategy, improving acquisition accuracy and efficiency, ultimately enhancing the operating efficiency and safety of the energy storage system. Example 2:

[0046] Based on the same inventive concept as Embodiment 1, this embodiment introduces a power storage device operation information collection device, including: The data acquisition module is used to: acquire the operating parameters of the power storage device in real time through a multi-source sensor network; The operating parameters are preprocessed to generate preprocessed data; The data acquisition method generation module is used to: input the preprocessed data into the status assessment model, assess the current operating status of the power energy storage device, and output the operating status and status indicators; Based on the operating status and status indicators, a data acquisition instruction is generated by the acquisition strategy generator. The data acquisition instruction includes the data acquisition frequency, the list of parameters to be acquired, and the sampling granularity. The multi-source sensor network collects, transmits, and stores data according to the data acquisition instructions.

[0047] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here. Example 3:

[0048] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the steps of the power energy storage device operation information collection method as described in any of the embodiments.

[0049] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0050] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0051] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0052] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0053] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for collecting operational information of an energy storage device, characterized in that, include: Real-time acquisition of operating parameters of power storage devices through multi-source sensor networks; The operating parameters are preprocessed to generate preprocessed data; The preprocessed data is input into the status assessment model to assess the current operating status of the power energy storage device and output the operating status and status indicators. Based on the operating status and status indicators, a data acquisition instruction is generated by the acquisition strategy generator. The data acquisition instruction includes the data acquisition frequency, the list of parameters to be acquired, and the sampling granularity. The multi-source sensor network collects, transmits, and stores data according to the data acquisition instructions.

2. The method for collecting operation information of power storage equipment according to claim 1, characterized in that, The operating parameters include the voltage, current, temperature, power, energy throughput, battery state of charge, battery health, and cycle count of the power storage device; these are obtained through multi-source sensors deployed in the battery cluster, battery management system, power conversion system, and energy management system.

3. The method for collecting operation information of power storage equipment according to claim 1, characterized in that, The preprocessing includes cleaning the collected operating parameters to remove redundant or erroneous information from the operating parameters; The cleaned operating parameters are denoised by using a moving average algorithm or a Kalman filter algorithm to eliminate noise in the operating parameters. Perform format standardization conversion on the denoised operating parameters; Synchronize the timestamps of the converted runtime parameters.

4. The method for collecting operation information of power storage equipment according to claim 1, characterized in that, The state assessment model combines an expert knowledge base with machine learning algorithms to assess the current operating status of power storage devices. The expert knowledge base includes preset thresholds and logical judgment rules. When the running parameters meet the thresholds or logical judgment rules, the corresponding running status warning or abnormal indication is output. Machine learning algorithms are trained using historical operating data. Long short-term memory networks are used to predict the degradation trend of battery health, or support vector machines or decision trees are used to classify the operating conditions of power storage devices, including normal, high load, or low load.

5. The method for collecting operation information of power storage equipment according to claim 1, characterized in that, The operating status includes normal, warning, abnormal, high load, low load, or maintenance.

6. The method for collecting operation information of power storage equipment according to claim 5, characterized in that, The process of generating data acquisition instructions through the acquisition strategy generator based on the operating status and status indicators includes: When the operation is normal, the command data acquisition frequency is adjusted from the first preset frequency to the second preset frequency. The second preset frequency is lower than the first preset frequency, and only core operating parameters are acquired. The core operating parameters include voltage, current, total temperature and state of charge, and the sampling granularity is appropriately reduced. When the operating status is warning or high load, the sampling frequency of relevant operating parameters is increased from the first preset frequency to the third preset frequency. The third preset frequency is higher than the first preset frequency. The number of key operating parameters collected is increased, including the voltage, current and local temperature of each individual battery cell, and the sampling granularity is improved. When the operating status is abnormal, the highest frequency of data acquisition at the millisecond level is triggered. The data acquisition includes all available electrical parameters, thermal parameters and environmental parameters, and at the same time, local alarm and remote alarm mechanisms are triggered. When the running status is maintenance or standby, only core operating parameters are collected.

7. The method for collecting operation information of power storage equipment according to claim 1, characterized in that, The data collection strategy generator has a built-in rule engine and is combined with a learning optimization module: The learning optimization module analyzes the performance of historical data collection strategies under different operating conditions, including data integrity, transmission latency, and timeliness of anomaly warnings. Combined with a feedback mechanism, it uses reinforcement learning algorithms to optimize the parameters of the rule engine or adjust the weights of the data collection strategies under different operating conditions.

8. The method for collecting operation information of power storage equipment according to claim 1, characterized in that, The process of the multi-source sensor network acquiring data according to the data acquisition command includes: the data acquisition control module receiving the data acquisition command issued by the acquisition strategy generator, and communicating with the multi-source sensor network through a digital interface or analog interface to dynamically adjust the acquisition parameters, acquisition frequency and sampling accuracy of each sensor.

9. A device for collecting operational information of an energy storage device, characterized in that, include: The data acquisition module is used to: acquire the operating parameters of the power storage device in real time through a multi-source sensor network; The operating parameters are preprocessed to generate preprocessed data; The data acquisition method generation module is used to: input the preprocessed data into the status assessment model, assess the current operating status of the power energy storage device, and output the operating status and status indicators; Based on the operating status and status indicators, a data acquisition instruction is generated by the acquisition strategy generator. The data acquisition instruction includes the data acquisition frequency, the list of parameters to be acquired, and the sampling granularity. The multi-source sensor network collects, transmits, and stores data according to the data acquisition instructions.

10. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the method for collecting operating information of the power storage device as described in any one of claims 1 to 8.

Images