Battery polarization anomaly detection method and device, electronic equipment, medium and product

Abstract

The application provides a battery polarization anomaly detection method and device, electronic equipment, medium and product, and relates to the technical field of batteries. The method comprises the following steps: obtaining working condition data of an energy storage system and battery parameters determined based on an equivalent circuit model; determining a working condition state based on the working condition data, processing the battery parameters based on the working condition state, determining target parameters of a target state; constructing a target function based on the target parameters to determine RC parameters in multiple dimensions; the target function is used to minimize the error between the measured voltage of the energy storage system and the model output voltage; performing outlier analysis on the RC parameters in multiple dimensions to determine outlier data points, and detecting whether the energy storage system has a polarization anomaly based on the confidence of the outlier data points. In this way, by optimizing the RC parameters, the model can more accurately reflect the dynamic behavior of the energy storage system, and the outlier analysis helps to identify abnormal behavior in the energy storage system, thereby accurately diagnosing the polarization anomaly and improving the reliability and safety of the energy storage system.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a method, apparatus, electronic device, medium and product for detecting abnormal battery polarization. Background Technology

[0002] In battery energy storage systems, lithium-ion batteries are an ideal choice for grid regulation and renewable energy storage due to their superior performance characteristics, such as high energy density, long cycle life, and efficient charge-discharge performance. However, abnormal changes in polarization voltage during the operation of lithium-ion batteries are a significant issue that can be ignored, as they have a substantial impact on battery performance and lifespan.

[0003] In existing technologies, vehicle data of the lithium battery system can be acquired, including total current and voltage monitoring data of each individual cell. Based on this vehicle data, the change value of voltage and the change value of current ratio of each cell can be calculated. Furthermore, preset conditions for the change of current ratio can be set. When the change value of current ratio meets the preset conditions, the polarization characteristic value at a single time point can be calculated based on the change value of individual cell voltage. Based on the polarization characteristic value, it can be determined whether there is a polarization abnormality in the lithium battery system and a warning signal can be issued.

[0004] However, since preset thresholds may not be able to adapt to all operating conditions and changes in battery state, judging polarization anomalies based on comparisons of preset thresholds may result in low accuracy of polarization anomaly detection. Summary of the Invention

[0005] This application provides a battery polarization anomaly detection method, apparatus, electronic device, medium, and product to solve the problem that existing polarization anomaly detection methods based on preset threshold comparisons have low accuracy.

[0006] In a first aspect, this application provides a method for detecting abnormal battery polarization, the method comprising:

[0007] Acquire operating data of the energy storage system and battery parameters determined based on the equivalent circuit model;

[0008] The operating condition of the energy storage system is determined based on the operating condition data, and the battery parameters are processed based on the operating condition to determine the target parameters of the target state.

[0009] An objective function is constructed based on the target parameters, and RC parameters in multiple dimensions are determined based on the objective function; the objective function is used to minimize the error between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model.

[0010] Outlier analysis is performed on the RC parameters of the multiple dimensions to identify outlier data points, and the confidence level of the outlier data points is used to detect whether the energy storage system has polarization anomalies.

[0011] Optionally, the energy storage system includes multiple battery cells, and the operating condition data includes current data of the multiple battery cells in different frames; determining the operating condition state of the energy storage system based on the operating condition data includes:

[0012] The operating status of the energy storage system is determined based on the current data of the current frame and the current data of the previous frame; the operating status includes the charging start state, the discharging start state, the charging end state, the discharging end state, the post-charging resting state, and the post-discharging resting state; the current data includes the current magnitude and the current direction.

[0013] Optionally, the equivalent circuit model is a second-order RC equivalent circuit model; the target parameters include open-circuit voltage, terminal voltage, battery current, first branch voltage, and second branch voltage; the target parameters satisfy Kirchhoff's voltage law; and an objective function is constructed based on the target parameters, including:

[0014] Determine the state equation corresponding to the target parameter, and based on the Hough voltage law and the state equation, determine the time-domain solution functions of the first branch voltage and the second branch voltage;

[0015] The time-domain solution function is discretized to obtain a discretized time-domain function;

[0016] Based on the first branch voltage and the second branch voltage, the objective function is constructed using the discretized time-domain function.

[0017] Optionally, the RC parameters include: electrochemical resistance, electrochemical capacitance, polarization resistance, and polarization capacitance; outlier analysis is performed on the multiple dimensions of the RC parameters to identify outlier data points, including:

[0018] The RC parameters of the multiple dimensions are reduced in dimensionality to obtain feature data;

[0019] Outlier data points are identified by performing outlier analysis on the feature data using a preset method.

[0020] Optionally, the energy storage system includes multiple battery cells, each battery cell corresponding to its own outlier data point; detecting whether the energy storage system exhibits polarization anomalies based on the confidence level of the outlier data point includes:

[0021] Calculate the deviation value of the outlier data point corresponding to each battery cell, and use the cumulative distribution function to calculate the confidence level of the deviation value;

[0022] The confidence level is compared with a preset threshold to detect whether the energy storage system has battery cells with abnormal polarization.

[0023] Optionally, the method further includes:

[0024] After determining that the energy storage system has a polarization anomaly, an early warning message is generated and the early warning message is displayed visually; the early warning message is used to indicate the battery cell that has a polarization anomaly.

[0025] Secondly, this application provides a battery polarization anomaly detection device, the device comprising:

[0026] The acquisition module is used to acquire the operating condition data of the energy storage system and the battery parameters determined based on the equivalent circuit model;

[0027] The determination module is used to determine the operating status of the energy storage system based on the operating data, and to process the battery parameters based on the operating status to determine the target parameters of the target status.

[0028] A construction module is used to construct an objective function based on the target parameters, and to determine RC parameters in multiple dimensions based on the objective function; the objective function is used to minimize the error between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model;

[0029] The detection module is used to perform outlier analysis on the RC parameters of the multiple dimensions, identify outlier data points, and detect whether the energy storage system has polarization anomalies based on the confidence level of the outlier data points.

[0030] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0031] The memory stores computer-executed instructions;

[0032] The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects.

[0033] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method as described in any one of the first aspects.

[0034] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method as described in any one of the first aspects.

[0035] In summary, this application provides a battery polarization anomaly detection method, apparatus, electronic device, medium, and product. It acquires operating condition data of the energy storage system and battery parameters determined based on an equivalent circuit model. These battery parameters describe the dynamic changes of the battery. Furthermore, the operating condition data is used to evaluate the current operating state of the energy storage system. Based on this operating state, the battery parameters are adjusted and processed to obtain target parameters that can be used for subsequent processing. An objective function is then constructed to minimize the error between the actually measured voltage of the energy storage system and the output voltage of the equivalent circuit model. Based on the objective function, multiple RC parameters are determined. Outlier analysis is then performed on these multiple RC parameters to identify potential polarization anomaly data points. Furthermore, based on the confidence level of these potential polarization anomaly data points, the presence of polarization anomalies in the energy storage system is detected. By optimizing the RC parameters, the equivalent circuit model more accurately reflects the dynamic behavior of the actual energy storage system, thereby improving the accuracy of prediction and control. Outlier analysis also helps identify abnormal behaviors in the energy storage system. Therefore, this application can accurately diagnose polarization anomalies and significantly improve the reliability and safety of the energy storage system. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0037] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0038] Figure 2 This is a schematic flowchart of a battery polarization anomaly detection method provided in an embodiment of this application;

[0039] Figure 3 A schematic diagram of the charge and discharge voltage curves of all battery cells in an energy storage system provided for an embodiment of this application;

[0040] Figure 4 A schematic diagram of a 2RC equivalent circuit model provided in an embodiment of this application;

[0041] Figure 5 A schematic diagram of the voltage curve of a battery cell with abnormal polarization provided for an embodiment of this application;

[0042] Figure 6 This is an overall flowchart of a battery polarization anomaly detection method provided in an embodiment of this application;

[0043] Figure 7 This is a schematic diagram of the structure of a battery polarization anomaly detection device provided in an embodiment of this application;

[0044] Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0045] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0046] To facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and purpose. For example, "first device" and "second device" are merely used to distinguish different devices and do not limit their order of execution. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0047] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0048] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single 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.

[0049] The following is an explanation of the technical terms used in this application.

[0050] An equivalent circuit model (ECM) is a mathematical model that uses circuit elements to simulate the electrochemical characteristics of a lithium-ion battery. The ECM uses components such as resistors, capacitors, and inductors to represent the battery's internal ohmic impedance, polarization effects, and dynamic characteristics. Common ECMs include first-order RC models, second-order RC models (2RC), and the Thevenin model. ECM models allow for the analysis of the battery's dynamic response, such as voltage, current, and temperature changes during charging and discharging, and are widely used in battery energy storage system modeling.

[0051] Ohmic impedance: refers to the voltage drop caused by the resistance of a conductor in a circuit.

[0052] Polarization effect: refers to the voltage deviation from the equilibrium potential caused by various processes occurring on the electrode surface during electrochemical reactions, such as charge transfer, electrochemical reactions, and diffusion.

[0053] Dynamic characteristics refer to the system's response to time-varying inputs, such as the system's response to changes in current or voltage.

[0054] The RC (Resistor-Capacitor Circuit Model) is an important form of ECM used to simulate the impedance and polarization behavior in batteries. This RC circuit model consists of resistors and capacitors connected in series or parallel, approximating the ohmic impedance and electrochemical polarization effect of the battery, respectively. In lithium-ion battery modeling, the RC circuit model simulates the dynamic characteristics of voltage changes with current by capturing the battery's transient response, and is particularly suitable for describing the change of polarization voltage over time.

[0055] Polarization voltage refers to the additional voltage drop that occurs in a lithium-ion battery during charging and discharging due to the battery's internal resistance and concentration gradient. Polarization voltage can be divided into ohmic polarization and concentration gradient polarization. Ohmic polarization is caused by the battery's internal resistance, while concentration gradient polarization is caused by the lithium-ion concentration gradient in the electrolyte.

[0056] Ohmic polarization refers to the voltage drop in an electrochemical system caused by the current flowing through the internal resistance (ohmic resistance) of the battery. This voltage drop is linear and proportional to the current flowing through the battery.

[0057] Concentration gradient polarization refers to the voltage drop in an electrochemical system caused by the concentration gradient between reactants and products. This polarization phenomenon occurs in the electrolyte near the electrode surface because the electrochemical reaction rate exceeds the mass transfer rate, resulting in a concentration difference between the electrode surface and the bulk electrolyte.

[0058] Additional voltage drop: refers to the extra voltage loss in a battery or energy storage system caused by various factors.

[0059] State of Health (SOH): This refers to a quantitative indicator that assesses the current performance of an energy storage system compared to its initial performance, reflecting the overall health of the energy storage device. SOH is typically determined by comparing the device's current capacity with its rated capacity (or initial capacity), or it can be comprehensively evaluated in conjunction with other parameters such as internal resistance and cycle efficiency. The SOH value generally ranges from 0% to 100%, with higher values ​​indicating better device health and performance closer to the initial state. In this application, SOH specifically refers to the percentage of the device's current capacity to its rated capacity.

[0060] State of Charge (SOC): This represents the ratio of a battery's current remaining charge to its rated capacity. It is a key parameter for measuring the degree of battery charging and is usually expressed as a percentage. SOC ranges from 0% (battery completely discharged) to 100% (battery fully charged).

[0061] The second-order RC model (2RC model): also known as the second-order RC equivalent circuit model, is an equivalent circuit model used to describe the dynamic behavior of a battery. This second-order RC model simulates the electrochemical characteristics of a battery, especially its transient response, through a combination of resistors and capacitors. The second-order RC model describes the ohmic polarization, electrochemical polarization, and concentration polarization processes of the battery through five components, which are used to reflect the dynamic response characteristics of the battery. These five components are R0 (ohmic resistor), R1 (electrochemical resistor 1), C1 (electrochemical capacitor 1), R2 (polarization resistor 2), and C2 (polarization capacitor 2).

[0062] R0 (ohm resistance): Represents the internal resistance of the battery, including contact resistance, wire resistance, and the ohmic resistance of electrode materials. R0 reflects the resistance in the electronic conduction path inside the battery and is mainly related to the battery's materials and structure, affecting the instantaneous rise and fall of the battery voltage during charging and discharging.

[0063] R1 (electrochemical resistance 1): Represents the electrochemical resistance of the battery, usually related to battery activation polarization. R1 reflects the resistance caused by incomplete or slow electrochemical reactions.

[0064] C1 (electrochemical capacitance 1): Corresponding to R1, it represents the electrochemical reaction capacitance, reflecting the ability of charge to accumulate and release at the electrode / electrolyte interface, and is often used to describe the dynamic behavior of electrochemical reactions. The time constant formed by R1 and C1 together is relatively small.

[0065] R2 (Polarization Resistance 2): Primarily related to the concentration difference polarization of the battery, it reflects the resistance to lithium ion diffusion in the electrolyte. As the battery discharges or charges, the difference in lithium ion concentration causes a potential difference, and R2 is used to describe the hindrance to this process.

[0066] C2 (Polarization Capacitance 2): Corresponding to R2, it represents the diffusion effect caused by the concentration gradient, reflecting the capacitive effect generated during the diffusion of lithium ions in the electrolyte. It typically operates over a relatively long time constant, describing the slow concentration polarization behavior of the battery. The time constant formed by R2 and C2 is relatively large.

[0067] Time constant: Used to describe the response speed of a circuit to changes in the input signal.

[0068] Abnormal battery polarization: refers to abnormal polarization phenomena that occur during battery operation, that is, changes in electrode potential that exceed the expected range or behavior pattern.

[0069] In battery energy storage systems, abnormal changes in polarization voltage are a significant issue that cannot be ignored in lithium battery operation. Polarization voltage not only affects the battery's usable capacity but also has a substantial impact on its lifespan and health status. For example, a high polarization resistance usually reflects changes in the battery's internal electrochemical environment, such as the accumulation of localized side reactions leading to obstructed conductive paths, or uneven electrolyte distribution causing concentration gradient polarization. Batteries with abnormal polarization will experience accelerated degradation if used for extended periods. Therefore, detecting and providing early warnings for abnormal polarization faults in lithium batteries can effectively prevent inconsistency deterioration and even safety risks caused by abnormal polarization, significantly improving the energy efficiency and reliability of lithium battery systems.

[0070] The polarization voltage in lithium-ion batteries can be divided into electrochemical polarization voltage and concentration gradient polarization voltage. Both polarization phenomena are caused by the uneven ion concentration inside the battery due to the movement of lithium ions between the positive and negative electrodes, resulting in a potential difference on the electrodes. As the charging and discharging current increases, the temperature decreases, and the amount of active material inside the battery decreases, the accumulation of polarization voltage becomes significant, leading to a substantial reduction in the usable capacity of the lithium battery.

[0071] However, significant progress has been made in the identification of polarization anomalies in lithium-ion batteries. One possible approach is to calculate the polarization characteristic value at a single time point by monitoring changes in current rate and cell voltage, and then determine whether a polarization anomaly has occurred based on a set threshold. Another possible approach is to use the Local Outlier Factor (LOF) algorithm to detect abnormal polarization voltage in the battery system. This LOF algorithm is particularly suitable for situations where voltage anomalies are caused by battery aging or abuse.

[0072] However, most of the above methods are still limited to describing polarization anomalies by constructing local voltage characteristics. They rarely start from the equivalent circuit model of the battery to establish dynamic response equations for voltage and current, so as to obtain relevant characteristic parameters through system identification and achieve more accurate diagnosis of polarization anomalies.

[0073] For example, vehicle data of the lithium battery system can be acquired, including total current and voltage monitoring data of each individual cell. Then, based on this vehicle data, the change value of the voltage of each cell and the change value of the current ratio can be calculated. Furthermore, preset conditions for the change of current ratio can be set. When the change value of the current ratio meets the preset conditions, the polarization characteristic value at a single time point can be calculated based on the change value of the individual cell voltage. Based on the polarization characteristic value, it can be determined whether there is a polarization abnormality in the lithium battery system and a warning signal can be issued.

[0074] Although the above method (Example 1) performs polarization analysis by monitoring the current and voltage data of the lithium battery and provides early warnings based on the comparison of preset thresholds, the accuracy of polarization anomaly detection may be low because the preset thresholds may not be adaptable to all operating conditions and changes in battery state.

[0075] In some embodiments, by acquiring the voltage and current data of the battery during the charging process in real time, the dynamic impedance of the battery is calculated using an equivalent circuit model. Then, by monitoring the impedance change trend over time, an impedance curve is generated and compared with a preset normal impedance range. If the impedance value exceeds the normal range, it is determined that the battery is abnormal.

[0076] Although the above method (Example 2) combines data analysis and fault diagnosis algorithms to provide early warning of potential battery faults, such as increased internal resistance or electrolyte failure, the above method mainly focuses on judging whether the battery is faulty by the impedance change during charging, focusing on analyzing the battery's impedance change curve, and does not pay attention to polarization anomalies.

[0077] In other embodiments, self-discharge anomalies are identified by monitoring resistance changes between adjacent cells. First, a first resistance value between each cell and its adjacent cells is obtained. If an abnormal resistance value is detected, the cell group is marked as abnormal. Subsequently, after removing the aluminum busbar, a second resistance value of these abnormal cell groups is measured again. The specific cause of the anomaly is determined by comparing and analyzing the second resistance values, such as insulation film failure or internal short circuit within the cell.

[0078] Although the above method (Example 3) can quickly locate cells with self-discharge abnormalities, significantly shorten the detection time, and improve the quality and efficiency of cell assembly, the above method is mainly aimed at self-discharge abnormalities of lithium-ion batteries. The method focuses on the resistance detection between cells, and pays special attention to the investigation of abnormalities caused by insulation film failure.

[0079] In summary, existing technologies typically rely on single-point-of-time characteristic values ​​of current and voltage for judgment, which has limited accuracy and is difficult to fully reflect the polarization anomalies of the battery during dynamic operation.

[0080] To address the aforementioned issues, this application provides a battery polarization anomaly detection method. This method acquires operating condition data of the energy storage system and battery parameters determined based on an equivalent circuit model. These battery parameters describe the dynamic changes of the battery. Furthermore, the operating condition data is used to assess the current operating state of the energy storage system. Based on this operating state, the battery parameters are adjusted and processed to obtain target parameters that can be used for subsequent processing. An objective function is then constructed to minimize the error between the actually measured voltage of the energy storage system and the output voltage of the equivalent circuit model. Based on the objective function, multiple RC parameters are determined. Outlier analysis is then performed on these multiple RC parameters to identify potential polarization anomaly data points. Furthermore, based on the confidence level of these potential polarization anomaly data points, the presence of polarization anomalies in the energy storage system is detected. By optimizing the RC parameters, the equivalent circuit model more accurately reflects the dynamic behavior of the actual energy storage system, thereby improving the accuracy of prediction and control. Outlier analysis also helps identify abnormal behaviors in the energy storage system. Therefore, this application can accurately diagnose polarization anomalies, significantly improving the reliability and safety of the energy storage system.

[0081] It should be noted that RC parameters in the battery equivalent circuit model usually refer to the resistance and capacitance parameters.

[0082] For example, Figure 1 This is a schematic diagram of an application scenario provided in an embodiment of this application, such as... Figure 1 As shown, this application scenario can be applied to the detection of abnormal cell polarization in energy storage systems, where the cell is a battery unit. This application scenario includes an energy storage system 101, a battery management system 102, and a terminal device 103. The energy storage system 101 includes battery units 1-16. In this application embodiment, the number of battery units in the energy storage system 101 is not specifically limited, but can be determined based on the actual application scenario.

[0083] During the charging and discharging process of the energy storage system 101, there are corresponding operating condition data, such as the voltage, SOC, SOH, temperature of each battery cell, and the total current of the energy storage system 101. This application embodiment does not limit the specific content of the operating condition data. Furthermore, the battery management system 102 can acquire the operating condition data of the energy storage system 101 and the battery parameters determined based on the equivalent circuit model, and then use the operating condition data to evaluate the current operating condition of the energy storage system 101. Then, the battery parameters are adjusted and processed according to the operating condition to obtain target parameters that can be used for subsequent processing. Furthermore, the battery management system 102 also needs to construct an objective function to determine RC parameters of multiple dimensions based on the objective function. The objective function is constructed based on the target parameters. Furthermore, outlier analysis is performed on the RC parameters of multiple dimensions to identify potential polarization anomaly data points. Then, based on the confidence level of the potential polarization anomaly data points, it is detected whether there is polarization anomaly in the battery cells of the energy storage system 101.

[0084] Optionally, when the confidence level of a potential polarization anomaly data point corresponding to a certain battery cell is higher than a preset threshold, it can be determined that the battery cell has a polarization anomaly. Then, the polarization anomaly result can be sent to the user's terminal device 103 for visualization display, so that the user can view the polarization anomaly result of the energy storage system 101. The polarization anomaly result can be a voltage curve diagram corresponding to the battery cell. In this embodiment of the application, the display content of the polarization anomaly result is not specifically limited.

[0085] It is understood that the terminal device 103 can also be a display device corresponding to the battery management system 102. This application embodiment does not specifically limit the device used for visualization; optionally, the terminal device can also be referred to as user equipment (UE), mobile station (MS), mobile terminal, terminal, etc. In practical applications, terminal devices include, for example, desktop computers, laptops, personal digital assistants (PDAs), smartphones, tablets, in-vehicle devices, wearable devices (such as smartwatches and smart bracelets), and smart home devices (such as smart display devices).

[0086] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0087] Figure 2This is a flowchart illustrating a battery polarization anomaly detection method provided in an embodiment of this application. This method can be applied to a battery management system, such as... Figure 2 As shown, the battery polarization anomaly detection method includes the following steps:

[0088] S201. Obtain the operating condition data of the energy storage system and the battery parameters determined based on the equivalent circuit model.

[0089] In this application, various sensors and measuring devices can be installed in the energy storage system to monitor the operating status of the energy storage system in real time. These sensors may include voltage sensors, current sensors, temperature sensors, etc. Through these sensors, the operating data of the energy storage system under different times and operating conditions, i.e., operating condition data, can be continuously collected. This operating condition data includes the voltage, SOC, SOH, temperature of each battery cell, and the total current of the energy storage system.

[0090] It should be noted that during the operation of the battery energy storage system, the operating condition data generated by the system can be stored in a local database. When it is necessary to retrieve operating condition data from a previous moment, it can be obtained from the local database. Optionally, the operating condition data can also be uploaded and stored in the cloud to save local storage space, and can be retrieved directly from the cloud when data is needed.

[0091] In this embodiment, a suitable equivalent circuit model can be selected to describe the electrochemical behavior of the battery. The equivalent circuit model may include the RC equivalent circuit model, the Thevenin model, etc. This embodiment does not limit the specific type of the equivalent circuit model.

[0092] Optionally, using the collected operating condition data, mathematical and computational methods, such as least squares method and Kalman filtering, can be used to identify and determine the battery parameters in the equivalent circuit model. Taking the 2RC model as an example, the battery parameter can be the open-circuit voltage V. oc (t), terminal voltage V(t), current I(t), branch voltage V RC1 (t) and V RC2 (t) etc., the embodiments of this application do not specifically limit the type and number of battery parameters, as long as they can reflect the dynamic changes of the battery.

[0093] Alternatively, a simple model such as 1RC or a more complex high-order RC equivalent circuit model, such as the 3RC model, can be used to more accurately capture various dynamic behaviors inside the battery. Due to the addition of RC branches, the accuracy of polarization anomaly detection can be further improved.

[0094] S202. Determine the operating condition of the energy storage system based on the operating condition data, and process the battery parameters based on the operating condition to determine the target parameters of the target state.

[0095] In this step, by analyzing the operating data, the operating state of the battery in the energy storage system is identified and classified. For example, different operating states can be classified according to the direction, magnitude, and rate of change of the current data. This application embodiment does not specifically limit the type of operating state.

[0096] Optionally, the operating conditions include charging start state, discharging start state, charging end state, discharging end state, post-charging resting state, and post-discharging resting state.

[0097] S203. Construct an objective function based on the objective parameters, and determine RC parameters in multiple dimensions based on the objective function; the objective function is used to minimize the error between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model.

[0098] In this application, error is defined as the difference between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model. This error can be expressed in the form of mean square error (MSE) or absolute error, etc., and the embodiments of this application do not specifically limit it.

[0099] For example, an objective function can be constructed with error as the core. This objective function can be a cumulative or averaged form of error, and the optimization goal of the objective function is to minimize the error, thereby improving the accuracy of the model.

[0100] It should be noted that by optimizing the objective function, the RC parameters of each battery cell can be identified. For example, by minimizing the error between the measured voltage and the model output voltage, the R0, R1, C1, R2 and C2 parameters in the model can be accurately estimated. This process can dynamically adapt to the specific electrochemical characteristics of each battery cell, ensuring that the model input and output can accurately describe the internal resistance and polarization characteristics of each battery cell, which is a key input for subsequent polarization anomaly identification.

[0101] Optionally, different types of optimization algorithms can be used to minimize the objective function and obtain the parameters R0, R1, C1, R2, and C2. This application does not specifically limit the type of optimization algorithm. For example, the optimization algorithm can be gradient descent, genetic algorithm, simulated annealing, etc.

[0102] For example, a suitable optimization algorithm is selected to adjust the RC parameters in order to minimize the objective function. During the optimization process, the RC parameters are adjusted through multiple iterations to gradually reduce the value of the objective function until a preset error threshold or optimization stopping condition is reached, thereby determining the RC parameters in multiple dimensions.

[0103] The embodiments of this application do not specifically limit the dimensions of RC parameters. For example, the RC parameters of a battery cell in multiple dimensions are R1, C1, R2 and C2 parameters.

[0104] S204. Perform outlier analysis on the RC parameters of the multiple dimensions to identify outlier data points, and detect whether the energy storage system has polarization anomalies based on the confidence level of the outlier data points.

[0105] In some embodiments, statistical methods, such as Z-scores or interquartile range (IQR) methods, can be used to identify outlier data points, which are parameter values ​​that deviate significantly from other data points.

[0106] In other embodiments, machine learning algorithms, such as isolated forests or support vector machines for outlier detection, can be used to identify outlier data points in multidimensional data.

[0107] In this application, outlier analysis can be performed simultaneously across multiple dimensions to identify combinations of parameters that are significantly anomalous across one or more dimensions.

[0108] It should be noted that the methods used for outlier analysis in this application are not specifically limited; the above are merely illustrative examples.

[0109] For example, a confidence assessment is performed on the detected outlier data points to determine whether there are any anomalies. The confidence level can be calculated based on statistical significance or model prediction probability. This application does not specifically limit the method used to calculate the confidence level.

[0110] Optionally, a preset threshold is set. Outlier data points exceeding the preset threshold will be marked as potential anomalies. Then, the patterns and distribution of outlier data points with potential anomalies are analyzed to identify possible polarization anomalies, such as by identifying specific parameter combinations or trends.

[0111] Optionally, if an abnormal polarization is detected, the system can trigger an alarm and take appropriate response measures, such as adjusting the charging and discharging strategy or performing a system check.

[0112] In this way, by acquiring the operating condition data of the energy storage system and the battery parameters determined based on the equivalent circuit model, the actual state of the battery can be reflected more accurately. This accuracy helps improve the accuracy of energy storage system detection. Furthermore, by processing the battery parameters based on the operating condition, the performance of the battery under different states can be determined, thus identifying the parameters required for subsequent analysis and processing. Moreover, by constructing an objective function to minimize the error between the measured energy storage system voltage and the output voltage of the equivalent circuit model, the accuracy and reliability of the model can be improved. By determining RC parameters in multiple dimensions through the objective function, a more comprehensive analysis of the battery's dynamic behavior can be conducted. This multi-dimensional analysis helps to better understand the complex characteristics of the battery. Furthermore, outlier analysis and confidence detection based on outlier data points can effectively identify polarization anomalies in the energy storage system. This detection helps to discover potential problems in advance and improve the accuracy of polarization anomaly detection.

[0113] Optionally, the energy storage system includes multiple battery cells, and the operating condition data includes current data of the multiple battery cells in different frames; determining the operating condition state of the energy storage system based on the operating condition data includes:

[0114] The operating status of the energy storage system is determined based on the current data of the current frame and the current data of the previous frame; the operating status includes the charging start state, the discharging start state, the charging end state, the discharging end state, the post-charging resting state, and the post-discharging resting state; the current data includes the current magnitude and the current direction.

[0115] In this embodiment of the application, current data is collected from multiple battery cells. The current data includes the magnitude and direction of the current. The sign of the current direction indicates charging or discharging. For example, it is negative when charging and positive when discharging. For example, I(t)>0 indicates that the battery is in a discharging state, I(t)<0 indicates that the battery is in a charging state, and I(t)≈0 indicates that the battery is in a resting state. I(t) represents the current data.

[0116] In this step, the current data is divided into different frames according to time sequence. Each frame represents a time segment. By comparing the current data of the current frame with that of the previous frame, the trend and pattern of current change are identified, thereby determining the operating status of the energy storage system.

[0117] The charging start state indicates that charging has started if the current data in the current frame changes from negative (or 0) to positive. The discharging start state indicates that discharging has started if the current data in the current frame changes from positive (or 0) to negative. The charging end state indicates that charging has ended if the current data in the current frame decreases from positive to close to zero. The discharging end state indicates that discharging may end if the current data in the current frame decreases from negative to close to zero. The post-charging rest state indicates that the current remains near zero after charging has ended. The post-discharging rest state indicates that the current remains near zero after discharging has ended.

[0118] Understandably, by identifying the charging start state, discharging start state, charging end state, discharging end state, post-charging rest state, and post-discharging rest state, the operating condition switching point can be determined, thereby determining the charging duration, discharging duration, and rest duration. This provides effective data filtering for the subsequent parameter identification process.

[0119] Optionally, the battery parameters can be segmented based on the operating conditions to obtain the battery parameters corresponding to the charging state and / or discharging state, i.e., the target parameters of the target state.

[0120] For example, Figure 3 A schematic diagram of the charge and discharge voltage curves of all battery cells in an energy storage system provided in this application embodiment is shown below. Figure 3 As shown, the smooth line segment represents the battery cell in a static state, and the curved line segment represents the battery cell in a charging or discharging state. It can be understood that the battery parameters are segmented based on the operating conditions to obtain the battery parameters corresponding to the charging state and / or discharging state. That is, the battery parameters corresponding to the smooth line segment are removed, leaving the battery parameters corresponding to the curved line segment.

[0121] It should be noted that the embodiments of this application do not specifically limit the process of processing battery parameters using operating conditions. For example, numerical identification methods can also be used to determine the target parameters of the target state.

[0122] Optionally, data from multiple frames can be combined to confirm whether the identified state is continuous, in order to avoid misjudgment due to brief current fluctuations.

[0123] Therefore, the embodiments of this application accurately identify different operating conditions by using current data from different frames, which helps to understand the battery's operating status in real time. This allows for more precise determination of battery parameters corresponding to the operating conditions. By recording and analyzing battery parameters under different operating conditions, data support can be provided for subsequent optimization and polarization anomaly detection.

[0124] Optionally, the equivalent circuit model is a second-order RC equivalent circuit model; the target parameters include open-circuit voltage, terminal voltage, battery current, first branch voltage, and second branch voltage; the target parameters satisfy Kirchhoff's voltage law; and an objective function is constructed based on the target parameters, including:

[0125] Determine the state equation corresponding to the target parameter, and based on the Hough voltage law and the state equation, determine the time-domain solution functions of the first branch voltage and the second branch voltage;

[0126] The time-domain solution function is discretized to obtain a discretized time-domain function;

[0127] Based on the first branch voltage and the second branch voltage, the objective function is constructed using the discretized time-domain function.

[0128] In this embodiment, the second-order RC equivalent circuit model consists of a voltage source (representing the open-circuit voltage) and two RC branches. Each RC branch is composed of a resistor and a capacitor connected in series, used to simulate the dynamic behavior of the battery.

[0129] For example, Figure 4 This is a schematic diagram of a 2RC equivalent circuit model provided in an embodiment of this application, such as... Figure 4 As shown, the 2RC equivalent circuit model includes a series resistor R0 and two parallel RC branches (R1, C1 and R2, C2). This 2RC equivalent circuit model is used to describe the dynamic voltage response of the battery, covering the battery's ohmic resistance, polarization resistance and its associated capacitance effects.

[0130] In this step, the open-circuit voltage V of the second-order RC equivalent circuit model oc (t), terminal voltage V(t), current I(t), voltage of the first branch V RC1 (t) and the voltage of the second branch V RC2 (t) satisfies the following Kirchhoff's voltage law:

[0131] V(t)=V oc (t)-I(t)·R0-V RC1 (t)-V RC2 (t)

[0132] Where I(t) represents the current data, which is negative during charging and positive during discharging; V RC1 (t) and V RC2 (t) represent the voltages of the two RC branches, respectively, and satisfy the state equations:

[0133]

[0134] Thus, according to Kirchhoff's Voltage Law (KVL), in any closed loop of a circuit, the sum of the voltages of all components is zero. When applied to a second-order RC equivalent circuit model, the open-circuit voltage is equal to the terminal voltage plus the drop in voltage of each branch.

[0135] Furthermore, based on the above state equations and Kirchhoff's voltage law, V can be derived. RC1 (t) and V RC2 The time-domain solution function of (t) is given by the time-domain solution functions of the first branch voltage and the second branch voltage, respectively:

[0136]

[0137] Furthermore, the time-domain solution function is discretized for use in numerical computation. This discretization involves converting the continuous-time function into a discrete-time series, i.e., V RC1 (t) and V RC2 The continuous time-domain solution of (t) is approximately discretized into an exponentially decaying summation form by time step. During the discretization process, the exponential decay characteristic can be approximated by the cumulative summation form.

[0138] The preset step size refers to selecting a suitable time step for discretization. In this application embodiment, the size of the preset step size is not specifically limited. It can be fixed (such as per second or per millisecond) or variable, depending on the application scenario and the required accuracy.

[0139] Furthermore, using the discretized time-domain function, an objective function is constructed, namely V. RC1 (k) and V RC2 (k) Substitute the discretized time-domain function to obtain the objective function. The optimization objective of this objective function is to minimize the error in order to accurately estimate the parameters R0, R1, C1, R2 and C2 in the model. This objective function can also be understood as the voltage response function.

[0140] It should also be noted that, in Figure 4 In the middle, V bat The voltage of the energy storage system is represented by V(t), the terminal voltage by R0 is represented by the voltage across the resistor R0, and the current I(t) corresponds to I0. bat Thus, the second-order RC equivalent circuit model can be based on the current I. bat The input signal is used to derive the dynamic voltage response equation of the battery, and the battery parameters are discretized based on the sampling frequency for subsequent data processing and parameter identification.

[0141] Since the second-order RC equivalent circuit model can more accurately capture the dynamic behavior of the battery, especially the voltage changes and transient response during rapid charging and discharging, this application can reflect the polarization effect and electrochemical process of the battery by using the second-order RC equivalent circuit model, providing higher accuracy than the first-order model. Furthermore, this application also converts the continuous-time state equation into a discrete-time form through discretization transformation, enabling the model to be simulated and analyzed on a digital computing platform, and making it easy to integrate with other digital systems and algorithms. In addition, by constructing the objective function through discretization of the time-domain function and optimizing it, the error between the model prediction and the actual data can be effectively reduced, and the reliability of the model can be improved.

[0142] Optionally, the RC parameters include: electrochemical resistance, electrochemical capacitance, polarization resistance, and polarization capacitance; outlier analysis is performed on the multiple dimensions of the RC parameters to identify outlier data points, including:

[0143] The RC parameters of the multiple dimensions are reduced in dimensionality to obtain feature data;

[0144] Outlier data points are identified by performing outlier analysis on the feature data using a preset method.

[0145] In this application, the RC parameters of multiple dimensions may lead to the complexity and computational burden of data analysis. Therefore, the data structure can be simplified by dimensionality reduction. The dimensionality reduction method may include Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), etc. The embodiments of this application do not specifically limit the dimensionality reduction method. It can extract the main features of the data, transform high-dimensional data into low-dimensional feature data, and retain as much information as possible.

[0146] In this step, outlier analysis can be performed on the dimensionality-reduced feature data using a preset method. This preset method can be a statistical method (such as Z-score, IQR) or a machine learning method (such as isolated forest). By analyzing the distribution and bias of the feature data, that is, analyzing the degree of deviation of each battery cell from the overall distribution, outlier data points that significantly deviate from the normal pattern can be identified. Furthermore, an outlier determination threshold is set, and data points that exceed the threshold are marked as outlier data points.

[0147] For example, assuming the RC parameters of each battery cell in the energy storage system are obtained, a data matrix X is constructed based on these parameters. Each row of data matrix X represents the multi-dimensional parameters of a battery cell, and each column represents a single parameter (such as R1, C1, R2, and C2). The data matrix X has an n×m dimension, where n is the number of battery cells and m is the dimension of the parameters. The data matrix X is as follows:

[0148]

[0149] Furthermore, different types of dimensionality reduction methods can be used to reduce the dimensionality of the data matrix X and extract the feature data Z. Then, outlier analysis can be performed on the dimensionality-reduced data Z using a preset method to identify outlier data points.

[0150] Thus, this application reduces the complexity of the data through dimensionality reduction, making outlier analysis more efficient and intuitive. Furthermore, by extracting key features, dimensionality reduction helps improve the accuracy of outlier analysis, reducing interference from noise and redundant information. Moreover, outlier analysis can effectively identify abnormal combinations of RC parameters, which is of great significance for detecting abnormal battery behavior or faults. Therefore, this application can reduce the consumption of computing resources and improve the efficiency of data processing through dimensionality reduction and outlier analysis, which is especially important in large-scale energy storage systems.

[0151] Optionally, the energy storage system includes multiple battery cells, each battery cell corresponding to its own outlier data point; detecting whether the energy storage system exhibits polarization anomalies based on the confidence level of the outlier data point includes:

[0152] Calculate the deviation value of the outlier data point corresponding to each battery cell, and use the cumulative distribution function to calculate the confidence level of the deviation value;

[0153] The confidence level is compared with a preset threshold to detect whether the energy storage system has battery cells with abnormal polarization.

[0154] In this embodiment, the deviation value is the degree of deviation of outlier data points from the normal data distribution. It can be represented by calculating the distance between the outlier point and the center of the dataset (such as the mean or median). The corresponding calculation method can use statistical methods (such as Z-scores) to quantify the deviation value, or use machine learning models to evaluate the degree of anomaly of the data points. This embodiment does not specifically limit the method for calculating the deviation value. It can refer to existing calculation methods or redefine new calculation methods.

[0155] In this application, outlier data points represent abnormal behavior of battery cells under certain conditions, which can predict potential polarization anomalies or other problems. Since the energy storage system consists of multiple battery cells, each battery cell may exhibit different electrical characteristics and behaviors. Therefore, outlier data points are identified by performing outlier analysis on the RC parameters of each battery cell.

[0156] In this step, the confidence level of the deviation value is calculated using the cumulative distribution function. The confidence level can be determined by the absolute value of the Z-score. The larger the Z-score, the greater the deviation of the outlier data point from the overall distribution, and the higher the confidence level of the anomaly. Furthermore, the calculated confidence level is compared with a preset threshold. If the confidence level exceeds the preset threshold, it is considered that the battery cell may have a polarization anomaly.

[0157] The preset threshold can be determined based on experience or historical data, representing the probability limit for considering an outlier data point as abnormal. This application does not specifically limit the size of the preset threshold. For a given Z-score value |z|, the confidence level can be calculated using the cumulative distribution function Φ(z) of the standard normal distribution. This cumulative distribution function provides a probability value representing the position of an outlier data point within the normal distribution. The specific formula is as follows:

[0158] Confidence percentage = (1 - 2 × (1 - Φ(|z|))) × 100%

[0159] Therefore, by calculating deviation values ​​and confidence levels, this application can more accurately identify abnormal behaviors in battery cells, especially polarization anomalies. Moreover, each battery cell is analyzed individually, ensuring that even in multi-cell systems, specific abnormal cells can be identified, improving the granularity of detection. In polarization anomaly detection, confidence levels are used to determine the battery cells with polarization anomalies. These confidence levels provide a quantitative indicator, making polarization anomaly detection more reliable.

[0160] Alternatively, other machine learning or deep learning methods can be used for battery anomaly detection, such as neural network-based predictive models, which can learn autonomously from historical data and predict anomalies with strong adaptability.

[0161] Optionally, the method further includes:

[0162] After determining that the energy storage system has a polarization anomaly, an early warning message is generated and the early warning message is displayed visually; the early warning message is used to indicate the battery cell that has a polarization anomaly.

[0163] For example, through the aforementioned outlier analysis and confidence level calculation, it can be determined whether there are battery cells with polarization anomalies in the energy storage system. After determining that a polarization anomaly has occurred, an early warning message is generated. This early warning message may include the identifier of the abnormal battery cell (such as cell number), the anomaly type (polarization anomaly), the confidence level value, the detection time, etc. This application embodiment does not specifically limit the content of the early warning message. Furthermore, the early warning message can be visualized and can be sent to the user's terminal device via email, SMS, or other communication means, or it can be directly displayed on the corresponding display device of the battery management system. This application embodiment does not specifically limit the form of sending the early warning message or the display content. For example, charts, color codes, or other visual elements can be used to highlight the battery cells with polarization anomalies, or the voltage curve of the battery cells with polarization anomalies can be directly displayed. Figure 5 A schematic diagram of the voltage curve of a battery cell with abnormal polarization provided in an embodiment of this application, as shown below. Figure 5 As shown, the content within the dashed box represents a polarization anomaly.

[0164] In this way, by generating and displaying early warning information, relevant personnel can be quickly notified when polarization anomalies occur, ensuring timely measures are taken. Moreover, the visual display makes complex anomaly information more intuitive and easy to understand, helping relevant personnel to quickly locate and understand the problem. Therefore, by accurately identifying and indicating abnormal units, targeted maintenance and repair can be carried out, reducing downtime and maintenance costs. This timely early warning and response mechanism helps prevent system failures or safety accidents caused by polarization anomalies.

[0165] In conjunction with the above embodiments, Figure 6 This is an overall flowchart of a battery polarization anomaly detection method provided in an embodiment of this application, as shown below. Figure 6 As shown, the battery polarization anomaly detection method includes the following five main steps: model establishment, data acquisition, operating condition judgment, parameter identification, and anomaly identification.

[0166] Among them, model establishment refers to establishing a 2RC equivalent circuit model of a lithium-ion battery, such as... Figure 4 As shown; data acquisition refers to acquiring real-time operating data of the energy storage system, including cell voltage, total current, etc.; operating condition judgment refers to identifying charging, discharging, post-charging resting, and post-discharging resting periods based on the total system current, including the charging start state, discharging start state, charging end state, discharging end state, post-charging resting state, and post-discharging resting state. The charging start state and charging end state determine the charging period, and the discharging start state and discharging end state determine the discharging period; parameter identification and anomaly identification refers to identifying the RC parameters of all cells, identifying cells with outlier parameters based on dimensionality reduction analysis and preset methods, thereby detecting polarization anomalies.

[0167] It should be noted that other optimization methods can be used for parameter identification, dimensionality reduction analysis, statistical testing, and outlier analysis, and the embodiments of this application do not specifically limit these methods.

[0168] In this application, a second-order RC equivalent circuit model is constructed, and real-time monitoring data (such as total current and voltage of each individual cell) is combined to continuously monitor the dynamic changes in voltage during battery operation. When the direction, magnitude, and duration of the current meet set conditions, the time series of voltage and current are fitted by optimizing the objective function to identify the RC parameters of the equivalent circuit model. Furthermore, outlier analysis is performed using the RC parameters to identify polarization anomalies. Therefore, based on this model-based analysis method, this application can accurately diagnose polarization anomalies and achieve early warning of battery faults, significantly improving the reliability and safety of the energy storage system.

[0169] Understandably, this application, by introducing a 2RC equivalent circuit model and combining parameter identification, dimensionality reduction analysis, and statistical testing methods, can effectively identify battery polarization anomalies. This application achieves a precise description of various battery polarization phenomena, covering ohmic polarization, electrochemical polarization, and concentration polarization. Furthermore, by optimizing the objective function corresponding to the prediction error and dynamically identifying the battery RC parameters, the accuracy of the model is improved, enabling the battery management system to predict abnormal states more quickly, reducing the risk of battery failure. Moreover, through data dimensionality reduction and statistical testing, high-precision identification of cell anomalies can be achieved, and anomaly confidence assessment can be provided, offering strong data support for battery health management.

[0170] Based on the above findings, compared to Example 1 which only calculates the polarization characteristic value at a single time point through current ratio and voltage change, this application uses a second-order RC model to more accurately describe the dynamic behavior of polarization voltage. In addition, it focuses more on time series data analysis and combines outlier analysis to identify polarization anomalies. Therefore, the accuracy of polarization anomaly detection in this application is improved. Furthermore, this application also identifies equivalent circuit parameters by optimizing the objective function and combines anomaly detection technology to provide more comprehensive early warning.

[0171] Compared to Example 2, which mainly focuses on judging whether the battery is faulty by the impedance change during charging, and emphasizes the analysis of the battery impedance change curve and fault detection in impedance monitoring, this application uses a second-order RC model to describe the dynamic change of polarization voltage, focuses on the identification of polarization voltage anomalies, and identifies the model parameters by optimizing the objective function. In addition, this application pays more attention to polarization anomalies, and combines outlier analysis of current rate and battery voltage to detect polarization anomalies.

[0172] Compared to Example 3, which mainly targets the self-discharge anomaly of lithium-ion batteries and focuses on the resistance detection between cells and the troubleshooting of anomalies caused by insulation film failure, this application focuses on polarization anomalies and uses a more complex second-order RC model to simulate the dynamic behavior of the battery. It also identifies the anomalies of battery polarization voltage by identifying equivalent circuit parameters, rather than simply detecting cells.

[0173] In the foregoing embodiments, the battery polarization anomaly detection method provided by the embodiments of this application has been described. To implement the functions of the methods provided by the embodiments of this application, the electronic device serving as the execution subject may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0174] For example, Figure 7 This is a schematic diagram of the structure of a battery polarization anomaly detection device provided in an embodiment of this application, as shown below. Figure 7 As shown, the device 700 includes: an acquisition module 701, used to acquire the operating condition data of the energy storage system and battery parameters determined based on the equivalent circuit model;

[0175] The determination module 702 is used to determine the operating state of the energy storage system based on the operating condition data, and to process the battery parameters based on the operating state to determine the target parameters of the target state.

[0176] The construction module 703 is used to construct an objective function based on the target parameters, and to determine RC parameters in multiple dimensions based on the objective function; the objective function is used to minimize the error between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model;

[0177] The detection module 704 is used to perform outlier analysis on the RC parameters of the multiple dimensions, identify outlier data points, and detect whether the energy storage system has polarization anomalies based on the confidence level of the outlier data points.

[0178] Optionally, the energy storage system includes multiple battery cells, and the operating condition data includes current data of the multiple battery cells in different frames; the determining module 702 is specifically used for:

[0179] The operating status of the energy storage system is determined based on the current data of the current frame and the current data of the previous frame; the operating status includes the charging start state, the discharging start state, the charging end state, the discharging end state, the post-charging resting state, and the post-discharging resting state; the current data includes the current magnitude and the current direction.

[0180] Optionally, the equivalent circuit model is a second-order RC equivalent circuit model; the target parameters include open-circuit voltage, terminal voltage, battery current, first branch voltage, and second branch voltage; the target parameters satisfy Kirchhoff's voltage law; the construction module 703 is specifically used for:

[0181] Determine the state equation corresponding to the target parameter, and based on the Hough voltage law and the state equation, determine the time-domain solution functions of the first branch voltage and the second branch voltage;

[0182] The time-domain solution function is discretized to obtain a discretized time-domain function;

[0183] Based on the first branch voltage and the second branch voltage, the objective function is constructed using the discretized time-domain function.

[0184] Optionally, the RC parameters include: electrochemical resistance, electrochemical capacitance, polarization resistance, and polarization capacitance; the detection module 704 includes a determination unit and a detection unit; the determination unit is used for:

[0185] The RC parameters of the multiple dimensions are reduced in dimensionality to obtain feature data;

[0186] Outlier data points are identified by performing outlier analysis on the feature data using a preset method.

[0187] Optionally, the energy storage system includes multiple battery cells, each battery cell corresponding to its own outlier data point; the detection unit is used for:

[0188] Calculate the deviation value of the outlier data point corresponding to each battery cell, and use the cumulative distribution function to calculate the confidence level of the deviation value;

[0189] The confidence level is compared with a preset threshold to detect whether the energy storage system has battery cells with abnormal polarization.

[0190] Optionally, the device 700 further includes a generation module, the generation module being used for:

[0191] After determining that the energy storage system has a polarization anomaly, an early warning message is generated and the early warning message is displayed visually; the early warning message is used to indicate the battery cell that has a polarization anomaly.

[0192] It should be noted that the specific implementation principle and effect of the above-mentioned battery polarization anomaly detection device can be found in the relevant descriptions and effects of the above embodiments, and will not be elaborated further here.

[0193] This application also provides a schematic diagram of the structure of an electronic device. Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8 As shown, the electronic device may include: a processor 801 and a memory 802 communicatively connected to the processor 801; the memory 802 stores a computer program; the processor 801 executes the computer program stored in the memory 802, causing the processor 801 to perform the method described in any of the above embodiments.

[0194] The memory 802 and the processor 801 can be connected via bus 803.

[0195] This application also provides a computer-readable storage medium storing computer program execution instructions, which, when executed by a processor, are used to implement the methods described in any of the foregoing embodiments of this application.

[0196] This application also provides a chip for executing instructions, which is used to perform the methods described in any of the foregoing embodiments executed by an electronic device as described in any of the foregoing embodiments of this application.

[0197] This application also provides a computer program product, which includes a computer program that, when executed by a processor, can implement the methods described in any of the foregoing embodiments executed by an electronic device as described in any of the foregoing embodiments of this application.

[0198] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0199] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0200] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0201] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application.

[0202] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0203] The memory may include high-speed random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0204] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0205] The aforementioned storage media can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage media can be any available medium accessible to general-purpose or special-purpose computers.

[0206] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0207] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0208] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0209] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0210] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0211] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the claims.

Claims

1. A method for detecting abnormal battery polarization, characterized in that, The method includes: Acquire operating data of the energy storage system and battery parameters determined based on the equivalent circuit model; The operating condition of the energy storage system is determined based on the operating condition data, and the battery parameters are processed based on the operating condition to determine the target parameters of the target state. An objective function is constructed based on the target parameters, and RC parameters in multiple dimensions are determined based on the objective function; the objective function is used to minimize the error between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model. Outlier analysis is performed on the RC parameters of the multiple dimensions to identify outlier data points, and the confidence level of the outlier data points is used to detect whether the energy storage system has polarization anomalies.

2. The method according to claim 1, characterized in that, The energy storage system includes multiple battery cells, and the operating data includes current data of the multiple battery cells in different frames; Determining the operating status of the energy storage system based on the operating data includes: The operating status of the energy storage system is determined based on the current data of the current frame and the current data of the previous frame. The operating conditions include charging start state, discharging start state, charging end state, discharging end state, post-charging rest state, and post-discharging rest state; the current data includes current magnitude and current direction.

3. The method according to claim 1, characterized in that, The equivalent circuit model is a second-order RC equivalent circuit model; the target parameters include open-circuit voltage, terminal voltage, battery current, first branch voltage, and second branch voltage; the target parameters satisfy Kirchhoff's voltage law; Constructing an objective function based on the target parameters includes: Determine the state equation corresponding to the target parameter, and based on the Hough voltage law and the state equation, determine the time-domain solution functions of the first branch voltage and the second branch voltage; The time-domain solution function is discretized to obtain a discretized time-domain function; Based on the first branch voltage and the second branch voltage, the objective function is constructed using the discretized time-domain function.

4. The method according to claim 1, characterized in that, The RC parameters include: electrochemical resistance, electrochemical capacitance, polarization resistance, and polarization capacitance; outlier analysis is performed on the RC parameters across these multiple dimensions to identify outlier data points, including: The RC parameters of the multiple dimensions are reduced in dimensionality to obtain feature data; Outlier data points are identified by performing outlier analysis on the feature data using a preset method.

5. The method according to claim 1, characterized in that, The energy storage system includes multiple battery cells, each battery cell corresponding to its own outlier data point; Detecting whether the energy storage system exhibits polarization anomalies based on the confidence level of the outlier data points includes: Calculate the deviation value of the outlier data point corresponding to each battery cell, and use the cumulative distribution function to calculate the confidence level of the deviation value; The confidence level is compared with a preset threshold to detect whether the energy storage system has battery cells with abnormal polarization.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: After determining that the energy storage system has a polarization anomaly, an early warning message is generated and the early warning message is displayed visually; the early warning message is used to indicate the battery cell that has a polarization anomaly.

7. A battery polarization anomaly detection device, characterized in that, The device includes: The acquisition module is used to acquire the operating condition data of the energy storage system and the battery parameters determined based on the equivalent circuit model; The determination module is used to determine the operating status of the energy storage system based on the operating data, and to process the battery parameters based on the operating status to determine the target parameters of the target status. A construction module is used to construct an objective function based on the target parameters, and to determine RC parameters in multiple dimensions based on the objective function; the objective function is used to minimize the error between the measured voltage of the energy storage system and the output voltage of the equivalent circuit model; The detection module is used to perform outlier analysis on the RC parameters of the multiple dimensions, identify outlier data points, and detect whether the energy storage system has polarization anomalies based on the confidence level of the outlier data points.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.

Images