Energy storage power station battery SOC real-time calibration method and system

Through neural network model and dynamic calibration technology, the error problem of battery management system in SOC estimation is solved, the accuracy and reliability of battery status monitoring are improved, and the safe and efficient operation of the power station is ensured.

CN119024171APending Publication Date: 2024-11-26NANJING GUODIAN NANZI POWER GRID AUTOMATION CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410893723.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

When estimating the SOC of the energy storage battery, it is difficult for the existing battery management system to accurately obtain the initial value, and it is affected by factors such as noise and temperature fluctuations, resulting in large errors in SOC estimation, which makes it difficult to meet the needs of high-precision monitoring and management.

Method used

By obtaining battery data, including rated capacity, calibration capacity and historical information, using neural network model algorithm for SOC estimation, and combining BMS power for real-time calibration, different neural network models (LSTM or RNN) are selected to predict according to the power range, and through Specific calibration formulas adjust weights and perform dynamic calibration.

Benefits of technology

The calculation accuracy of SOC is significantly improved, the cumulative errors caused by the A/Time Integration method are overcome, and the battery capacity attenuation error is corrected by regularly expiring and filling, and more accurate battery status monitoring is achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119024171A_ABST
    Figure CN119024171A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of battery management, in particular to an energy storage power station battery SOC real-time calibration method and system, and the method comprises the following steps: obtaining battery data; during the normal operation state of the battery, a neural network model algorithm is adopted to obtain a battery SOC estimated value based on the battery data; and carrying out real-time correction and calibration on the SOC estimated value of the battery based on the battery electric quantity calculated by the current battery management system BMS to obtain a calibrated SOC estimated value of the battery. According to the method, the SOC of the battery is estimated and calibrated in real time by comprehensively utilizing various data of the battery of the energy storage power station and the real-time electric quantity calculation of the battery management system (BMS) in combination with the neural network model algorithm, and the accuracy and reliability of SOC estimation are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and in particular to a method and system for real-time calibration of SOC of a battery in an energy storage power station. Background Art

[0002] The state of charge (SOC) of the energy storage battery is the ratio of the current remaining power to the total battery capacity, which directly reveals the current energy reserve state of the battery. This parameter plays a vital role in the battery management system (BMS). It is not only used to monitor the performance status of the battery, but also a key basis for ensuring the efficient use of the battery pack, extending its life, and ensuring the reliability and safety of power station operation.

[0003] At present, battery management systems mainly rely on the open circuit voltage method combined with the ampere-hour integration method when estimating SOC. Although this method is simple to calculate and easy to implement, it faces a series of challenges in practical applications. First, the initial value of SOC is often difficult to obtain accurately, which directly affects the accuracy of subsequent estimates. Secondly, the battery is affected by multiple factors such as noise, temperature fluctuations, and current changes during operation. These interference factors continue to accumulate, causing the estimation error of SOC to gradually increase. According to statistics, the estimation error of this method usually exceeds 7%, which is difficult to meet the needs of high-precision monitoring and management. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for real-time calibration of SOC of batteries in an energy storage power station in order to solve at least one of the above technical problems.

[0005] The present invention achieves the above-mentioned purpose through the following technical solutions:

[0006] A method for real-time calibration of SOC of a battery in an energy storage power station comprises the following steps:

[0007] Obtaining battery data, the battery data including the rated capacity of the battery, the calibrated capacity of the battery, the battery history information stored in the energy management system EMS, and the battery power calculated by the current battery management system BMS;

[0008] During the normal operation of the battery, a battery SOC estimation value is obtained based on the battery data using a neural network model algorithm;

[0009] The battery SOC estimation value is corrected and calibrated in real time based on the battery power calculated by the current battery management system BMS to obtain a calibrated battery SOC estimation value.

[0010] Furthermore, the rated capacity of the battery is the rated capacity of the battery when it leaves the factory;

[0011] The rated capacity of the battery is the full charge capacity calculated by the ampere-hour integration method during the most recent full charge and discharge of the battery;

[0012] The battery history information stored in the energy management system EMS includes information such as battery voltage, current, and temperature.

[0013] Furthermore, the input of the neural network model algorithm includes the battery history information stored in the energy management system EMS within a preset time before the current moment, as well as the time difference between the current moment and the last time the battery was fully charged and discharged, and the battery life SOH.

[0014] Furthermore, the battery life SOH is determined according to the ratio of the rated capacity of the battery to the calibrated capacity of the battery.

[0015] Further, a battery SOC estimation value is obtained based on the battery data using a neural network model algorithm, including:

[0016] According to the battery power value calculated by the current battery management system BMS, different neural network model algorithms are used to obtain the battery SOC estimation value.

[0017] Furthermore, when 15% ≤ SOC BMS When ≤85%, a long short-term memory neural network LSTM model is used to predict the battery SOC estimation value;

[0018] When SOC BMS <15% or SOC BMS When the battery SOC is greater than 85%, a recurrent neural network (RNN) model is used to predict the battery SOC estimation value;

[0019] Among them, SOC BMS Indicates the battery capacity calculated by the current battery management system BMS.

[0020] Furthermore, the battery SOC is calibrated by the following algorithm:

[0021] When SOC BMS ≥95% or SOC BMS When ≤5%, SOC 校准 =SOC BMS *0.7+SOC 估算 *0.3;

[0022] When 20%≤SOC BMS When ≤80%, SOC 校准 =SOC BMS *0.5+SOC 估算 *0.5;

[0023] When SOCBMS For other values, SOC 校准 =SOC BMS *0.6+SOC 估算 *0.4;

[0024] Among them, SOC BMS Indicates the battery capacity calculated by the current battery management system BMS; SOC 估算 Indicates the estimated battery SOC value.

[0025] A real-time SOC calibration system for batteries in energy storage power stations, characterized in that:

[0026] An acquisition module is used to acquire battery data, wherein the battery data includes the rated capacity of the battery, the calibrated capacity of the battery, the battery history information stored in the energy management system EMS, and the battery power calculated by the current battery management system BMS;

[0027] An estimation module, used for obtaining a battery SOC estimation value by using a neural network model algorithm based on the battery data during a normal battery operation state;

[0028] The calibration module is used to perform real-time correction and calibration on the battery SOC estimation value based on the battery power calculated by the current battery management system BMS to obtain a calibrated battery SOC estimation value.

[0029] An electronic device comprises: a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the above-mentioned method for real-time calibration of SOC of a battery in an energy storage power station.

[0030] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for real-time calibration of the SOC of a battery in an energy storage power station as described above is implemented.

[0031] The beneficial effects of the present invention are:

[0032] The present invention corrects the SOC value calculated by the BMS in real time, thus overcoming the cumulative error caused by the ampere-hour integration method. At the same time, the calculation error caused by battery capacity attenuation is corrected by regularly charging and discharging the battery. The method is easy to operate and improves the calculation accuracy of the battery SOC. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of a method for implementing SOC calibration of a battery in an energy storage power station according to Embodiment 1 of the present invention;

[0034] Figure 2 This is a flow chart of a method for implementing SOC calibration of a battery in an energy storage power station according to Embodiment 2 of the present invention;

[0035] Figure 3 This is a structural diagram of a battery SOC calibration system for an energy storage power station according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The content of the present invention will now be discussed with reference to exemplary embodiments. It should be understood that the embodiments discussed are only to enable those skilled in the art to better understand and thus implement the content of the present invention, rather than implying any limitation on the scope of the present invention.

[0037] As used herein, the term “including” and variations thereof are to be interpreted as open-ended terms meaning “including, but not limited to.” The term “based on” is to be interpreted as “based, at least in part, on.” The terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment.”

[0038] Embodiment 1

[0039] Figure 1 This is a flow chart of the SOC calibration method for the energy storage power station battery according to the first embodiment of the present invention. Figure 1 As shown, according to one embodiment of the present invention, a real-time calibration method for SOC of a battery in an energy storage power station comprises the following steps:

[0040] Step S102: Obtain battery data; the battery data includes the rated capacity of the battery, the calibrated capacity of the battery, the battery history information stored in the energy management system EMS, and the battery power calculated by the current battery management system BMS; wherein,

[0041] The rated capacity of the battery is the rated capacity of the battery when it leaves the factory;

[0042] The rated capacity of a battery is the full charge capacity calculated by the ampere-hour integration method during the most recent full charge and discharge of the battery.

[0043] The battery history information stored in the energy management system EMS includes battery voltage, current, temperature and other information.

[0044] The rated capacity of a battery is the actual full charge capacity calculated by regularly charging and discharging the battery and using the ampere-hour integration method; the rated capacity of a battery reflects the actual current capacity of the battery, which may change due to usage, aging, and other factors. The battery history information stored in the energy management system EMS includes the battery's voltage, current, temperature, etc., which are a direct reflection of the battery's current state and historical operating conditions, and are essential for accurately estimating SOC. The battery capacity calculated by the current battery management system BMS is the current battery capacity obtained by the BMS through real-time measurement and calculation, which can be used as a reference for SOC estimation.

[0045] Step S104: During the normal operation of the battery, a battery SOC estimation value is obtained using a neural network model algorithm based on battery data;

[0046] The neural network model algorithm is a powerful machine learning tool that can handle complex nonlinear relationships. In this step, the previously acquired battery data is used as input, and the trained neural network model is used for inference to obtain the battery's SOC estimate, which can take into account multiple factors and provide a more accurate and comprehensive SOC estimate.

[0047] Step S106: performing real-time correction and calibration on the battery SOC estimation value based on the battery power currently calculated by the battery management system BMS to obtain a calibrated battery SOC estimation value.

[0048] The battery power calculated by the BMS is compared with the SOC estimated value obtained by the neural network model, and the SOC estimated value is corrected and calibrated in real time to make the SOC estimated value closer to the actual value.

[0049] In this embodiment, the rated capacity of the battery when it leaves the factory is marked as C 额定 The battery is fully charged and discharged regularly, and the full charge capacity C is calculated by the ampere-hour integration method. 标定 During the normal operation of the battery, the voltage, current, temperature and other historical information stored in the EMS energy management system and the C 额定 and C 标定 , the battery SOC is obtained through the neural network model algorithm 估算 The battery capacity calculated by the current BMS battery management system is recorded as SOC BMS , according to SOC BMS Different value ranges of SOC 估算 Perform real-time correction calibration.

[0050] The present invention realizes real-time estimation and calibration of battery SOC by comprehensively utilizing various data of energy storage power station batteries and real-time power calculation of battery management system BMS, combined with neural network model algorithm. The present invention not only takes into account the actual use and aging factors of the battery, but also provides a more accurate and comprehensive SOC estimation through the neural network model, and corrects the estimated value through BMS real-time data, thereby ensuring the accuracy and reliability of SOC estimation.

[0051] According to one embodiment of the present invention, in step S104, the input of the neural network model algorithm includes the battery history information stored in the energy management system EMS within a preset time before the current moment, as well as the time difference between the current moment and the last time the battery was fully charged and discharged, and the battery life SOH; wherein,

[0052] The battery life SOH is determined based on the ratio of the rated capacity of the battery to the calibrated capacity of the battery.

[0053] In this embodiment, the input of the neural network model algorithm includes the time series of battery voltage, current, and temperature in the period before the current moment provided by the EMS, as well as the time difference between the current moment and the last time the battery was fully charged and discharged regularly, and the battery life SOH; the battery life SOH is calculated based on C 标定 and C 额定 The ratio is determined.

[0054] The historical information of the battery, such as voltage, current, temperature, etc., is the key data for evaluating the current state of the battery. Selecting the data within the preset time before the current moment can capture the dynamic changes of the battery over a period of time, including charging and discharging patterns, temperature fluctuations, etc.; the time difference between the current moment and the last time the battery was fully charged and discharged reflects the time the battery has experienced since the last full charge and discharge. The performance and capacity of the battery will change with time and use. Therefore, this time difference can be used as an important input in the neural network model algorithm to help the model better understand the aging degree and current state of the battery. Battery life (State of Health) is an indicator that reflects the health status and aging degree of the battery. The battery life SOH is determined based on the ratio of the rated capacity to the calibrated capacity of the battery; the closer this ratio is to 1, the better the health status of the battery; otherwise, it means that the battery has aged significantly. Using SOH as the input of the neural network model algorithm can help the model more accurately evaluate the performance and remaining capacity of the battery, thereby improving the accuracy of SOC estimation.

[0055] The present invention introduces rich input parameters into the neural network model algorithm to achieve accurate estimation of the SOC of the energy storage power station battery; these parameters comprehensively reflect the dynamic changes, aging degree and health status of the battery, which helps the neural network model to more accurately evaluate the performance and remaining capacity of the battery, thereby significantly improving the SOC 估算 The accuracy provides strong support for the safe and efficient operation of energy storage power stations.

[0056] According to an embodiment of the present invention, step S104 includes:

[0057] According to the battery power value calculated by the current battery management system BMS, different neural network model algorithms are used to obtain the battery SOC estimation value; specifically:

[0058] When 15%≤SOC BMS When ≤85%, the long short-term memory neural network LSTM model is used to predict the battery SOC estimation value;

[0059] When SOC BMS<15% or SOC BMS When the battery SOC is >85%, the recurrent neural network (RNN) model is used to predict the battery SOC estimation value;

[0060] Among them, SOC BMS Indicates the battery capacity calculated by the current battery management system BMS.

[0061] The characteristics of the battery will be different under different power states: when the battery power is in the range of 15% to 85%, the battery usually exhibits relatively stable electrochemical characteristics, and the relationship between parameters such as voltage and current and SOC is relatively linear; when the power is lower (SOCBMS <15%) or higher (SOCBMS>85%), the electrochemical characteristics of the battery may change, such as enhanced polarization effect, nonlinear voltage change, etc.

[0062] The long short-term memory neural network model (LSTM) can learn long-term dependencies and effectively solve the gradient vanishing or gradient exploding problems that may occur when RNN processes long sequences. When the battery power is in the range of 15% to 85%, LSTM is better able to capture the stable pattern of battery characteristics and predict SOC accordingly. When the power is low or high, due to changes in battery characteristics, it may be more appropriate to use a simple RNN model because it can quickly adapt to these changes.

[0063] The present invention selects different neural network models to perform SOC prediction according to the battery power value calculated by the BMS, which can more effectively utilize the characteristics of different neural network models and improve the accuracy and reliability of SOC prediction; the accuracy of SOC prediction is improved, and it is also helpful to better manage the battery resources of the energy storage power station, extend the service life of the battery, and improve the operating efficiency and safety of the energy storage power station.

[0064] According to an embodiment of the present invention, in step S106, the battery SOC is calibrated by the following algorithm:

[0065] When SOC BMS ≥95% or SOC BMS When ≤5%, SOC 校准 =SOC BMS *0.7+SOC 估算 *0.3;

[0066] When 20%≤SOC BMS When ≤80%, SOC 校准 =SOC BMS *0.5+SOC 估算 *0.5;

[0067] When SOC BMS For other values, SOC校准 =SOC BMS *0.6+SOC 估算 *0.4;

[0068] Among them, SOC BMS Indicates the battery capacity calculated by the current battery management system BMS; SOC 估算 Indicates the estimated battery SOC value.

[0069] When the battery SOC is in the lower and higher ranges, the voltage, current and other characteristic quantities will have small-scale mutations and fluctuations, resulting in the average error and standard deviation of the SOC estimation value obtained by the neural network model algorithm in this range being larger than the estimated values ​​in other ranges. Therefore, in the battery SOC calibration formula in this range, SOC 估算 When SOC is in other ranges, the average error and standard deviation of the SOC estimation value obtained by the neural network model algorithm are relatively smaller, and its weight in the calibration formula is higher, and the weight coefficient is manually determined by actual experience.

[0070] The present invention effectively improves the calculation accuracy of the battery SOC by dynamically adjusting the weight coefficient in the battery SOC calibration formula; this calibration method not only overcomes the cumulative error caused by the ampere-hour integration method of the BMS system, but also corrects the calculation error caused by battery capacity attenuation by regular full charging and discharging, thereby significantly improving the overall calculation accuracy of the battery SOC.

[0071] Embodiment 2

[0072] Figure 2 This is a flow chart of the SOC calibration method for the energy storage power station battery according to the second embodiment of the present invention. Figure 2 As shown, according to an embodiment of the present invention, a method for calibrating the SOC of a battery in an energy storage power station comprises the following steps:

[0073] The rated capacity of the battery when it leaves the factory is marked as C 额定 , which value can be obtained from the battery supplier;

[0074] The battery is fully charged and discharged regularly (the cycle is set to about 10 days), and the full charge capacity C is calculated by the ampere-hour integration method during this period. 标定 ,

[0075] During normal battery operation, the voltage, current, temperature and other historical information stored in the EMS energy management system and the C 额定 and C 标定 , the battery SOC is obtained through the neural network model algorithm 估算 ,

[0076] The battery capacity calculated by the current BMS battery management system is recorded as SOC BMS ,

[0077] The neural network model algorithm can adopt a hybrid model of recurrent neural network RNN ​​combined with long short-term memory neural network LSTM. The input of the training model includes the time series of battery voltage, current, and temperature in the period before the current moment provided by EMS, as well as the time difference between the current moment and the last time the battery was fully charged and discharged regularly, and the battery life SOH. The battery life SOH is calculated based on C 标定 and C 额定 The actual predicted SOC 估算 When, according to the current SOC BMS Different prediction models are used for the range of values. When 15% ≤ SOC BMS When SOC is ≤85%, the long short-term memory neural network LSTM model is used for prediction. BMS <15% or SOC BMS When the value is >85%, the recurrent neural network (RNN) model is used for prediction.

[0078] Among them, the BMS battery management system calculates the battery power SOC BMS The method is set by the battery management system manufacturer and generally adopts the ampere-hour integration method.

[0079] According to SOC BMS Different value ranges of SOC are used to perform real-time correction and calibration.

[0080] Among them, according to the current SOC BMS Different value ranges of SOC 估算 Perform real-time correction calibration. The specific calibration method is as follows:

[0081] When SOC BMS ≥95% or SOC BMS When ≤5%, SOC 校准 =SOC BMS *0.7+SOC 估算 *0.3;

[0082] When 20%≤SOC BMS When ≤80%, SOC 校准 =SOC BMS *0.5+SOC 估算 *0.5;

[0083] When SOC BMS For other values, SOC 校准 =SOC BMS *0.6+SOC 估算 *0.4;

[0084] When the battery SOC is in the lower and higher ranges, the voltage, current and other characteristic quantities will have a small range of mutations and fluctuations, resulting in the SOC obtained by the neural network model algorithm within this range. 估算 The average error and standard deviation of the value are larger than those of other ranges. Therefore, in the battery SOC calibration formula within this range, SOC 估算 The weight is lower; when SOC is in other ranges, the SOC obtained by the neural network model algorithm 估算 The average error and standard deviation of the value are relatively smaller, and its weight in the calibration formula is higher, and the weight coefficient is manually determined by actual experience.

[0085] This calibration method is based on the SOC in different ranges of SOC 估算 The characteristics of the battery overcome the cumulative error caused by the BMS system only using the ampere-hour integration method. At the same time, the calculation error caused by the battery capacity attenuation is corrected by regularly charging and discharging the battery, thereby improving the calculation accuracy of the battery SOC.

[0086] Embodiment 3

[0087] Figure 3 This is a structural diagram of a battery SOC calibration system for an energy storage power station according to an embodiment of the present invention.

[0088] like Figure 3 As shown, a real-time SOC calibration system for a battery in an energy storage power station includes:

[0089] The acquisition module is used to acquire battery data, including the rated capacity of the battery, the calibrated capacity of the battery, the battery history information stored in the energy management system EMS, and the battery power calculated by the current battery management system BMS;

[0090] An estimation module, used to obtain a battery SOC estimation value using a neural network model algorithm based on battery data during normal battery operation;

[0091] The calibration module is used to perform real-time correction and calibration on the battery SOC estimation value based on the battery power calculated by the current battery management system BMS to obtain a calibrated battery SOC estimation value.

[0092] An electronic device comprises a processor, a memory and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, a real-time calibration method for the SOC of a battery in any energy storage power station is implemented.

[0093] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a real-time calibration method for the SOC of a battery in any energy storage power station is implemented.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices and media can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0095] The present invention provides a method, system, electronic device and storage medium for real-time calibration of SOC of batteries in energy storage power stations, which integrates multiple key data of batteries and uses a neural network model algorithm to estimate SOC. The present invention selects different neural network models according to the power value calculated by the BMS to improve the accuracy of the estimation. At the same time, the present invention further optimizes the accuracy of SOC estimation through a real-time calibration mechanism, combining the BMS power and the neural network estimation value. The present invention provides an efficient and accurate SOC estimation solution for battery management in energy storage power stations, ensuring the safe and stable operation of the power station.

[0096] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0097] It should be understood that the size of the serial numbers of each step in the content of the invention and the embodiments of the present invention does not absolutely 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.

Claims

1. A real-time calibration method for SOC of a battery in an energy storage power station, characterized in that: The steps include: Obtaining battery data, the battery data including the rated capacity of the battery, the calibrated capacity of the battery, the battery history information stored in the energy management system EMS, and the battery power calculated by the current battery management system BMS; During the normal operation of the battery, a battery SOC estimation value is obtained based on the battery data using a neural network model algorithm; The battery SOC estimation value is corrected and calibrated in real time based on the battery power calculated by the current battery management system BMS to obtain a calibrated battery SOC estimation value.

2. The method for real-time calibration of battery SOC of an energy storage power station according to claim 1, characterized in that: The rated capacity of the battery is the rated capacity of the battery when it leaves the factory; The rated capacity of the battery is the full charge capacity calculated by the ampere-hour integration method during the most recent full charge and discharge of the battery; The battery history information stored in the energy management system EMS includes information such as battery voltage, current, and temperature.

3. The method for real-time calibration of SOC of a battery in an energy storage power station according to claim 1, characterized in that: The input of the neural network model algorithm includes the battery history information stored in the energy management system EMS within a preset time before the current moment, as well as the time difference between the current moment and the last time the battery was fully charged and discharged, and the battery life SOH.

4. The method for real-time calibration of SOC of a battery in an energy storage power station according to claim 3, characterized in that: The battery life SOH is determined according to the ratio of the rated capacity of the battery to the calibrated capacity of the battery.

5. The method for real-time calibration of battery SOC of energy storage power station according to claim 1, characterized in that: Obtaining a battery SOC estimation value based on the battery data using a neural network model algorithm includes: According to the battery power value calculated by the current battery management system BMS, different neural network model algorithms are used to obtain the battery SOC estimation value.

6. The method for real-time calibration of SOC of a battery in an energy storage power station according to claim 5, characterized in that: When 15%≤SOC BMS When ≤85%, a long short-term memory neural network LSTM model is used to predict the battery SOC estimation value; When SOC BMS <15% or SOC BMS When the battery SOC is greater than 85%, a recurrent neural network (RNN) model is used to predict the battery SOC estimation value; Among them, SOC BMS Indicates the battery capacity calculated by the current battery management system BMS.

7. The method for real-time calibration of battery SOC of energy storage power station according to claim 1, characterized in that: The battery SOC is calibrated using the following algorithm: When SOC BMS ≥95% or SOC BMS When ≤5%, SOC 校准 =SOC BMS *0.7+SOC 估算 *0.3; When 20%≤SOC BMS When ≤80%, SOC 校准 =SOC BMS *0.5+SOC 估算 *0.5; When SOC BMS For other values, SOC 校准 =SOC BMS *0.6+SOC 估算 *0.4; Among them, SOC BMS Indicates the battery capacity calculated by the current battery management system BMS; SOC 估算 Indicates the estimated battery SOC value.

8. A real-time SOC calibration system for a battery in an energy storage power station, characterized in that: include: An acquisition module is used to acquire battery data, wherein the battery data includes the rated capacity of the battery, the calibrated capacity of the battery, the battery history information stored in the energy management system EMS, and the battery power calculated by the current battery management system BMS; An estimation module, used for obtaining a battery SOC estimation value by using a neural network model algorithm based on the battery data during a normal battery operation state; The calibration module is used to perform real-time correction and calibration on the battery SOC estimation value based on the battery power calculated by the current battery management system BMS to obtain a calibrated battery SOC estimation value.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method for real-time calibration of the SOC of a battery in an energy storage power station as claimed in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the real-time SOC calibration method for a battery in an energy storage power station according to any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Electric vehicle battery control method and device

    CN120816959A

  • Ship battery SOC estimation method and system based on energy reference dynamic reconstruction

    CN122449394A