SOH exception determination method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an SOH exception determination method and device, equipment and a storage medium. The method comprises the following steps: based on a predetermined target charging fragment set, calculating a first SOH estimated value for each target charging fragment based on a capacity increment method, and calculating a second SOH estimated value based on an ampere-hour integral method to obtain a first SOH estimated value sequence and a second SOH estimated value sequence, carrying out fusion calculation on the first SOH estimated value sequence, the second SOH estimated value sequence and historical SOH data obtained in advance, and carrying out fitting on a slope, attenuated along with time, of a full-life-cycle SOH sequence obtained through fusion calculation by adopting robust regression, and determining whether the SOH of the current battery is abnormal or not based on the attenuation slope obtained by fitting, the SOH estimated value at the current moment in the full life cycle SOH sequence, a preset SOH threshold value and an attenuation rate threshold value. According to the method, errors of a single method are counteracted through bimodal data fusion, the accuracy is improved, and the anti-noise capability is improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicles, and in particular to a method, device, equipment and storage medium for determining SOH anomaly. Background Art

[0002] With the rapid development of electric vehicles and energy storage power plants, the assessment and prediction of the state of health (SOH) of power batteries, as core components, has become increasingly important. Battery SOH directly impacts the range and safety of electric vehicles and the operational efficiency of energy storage power plants. However, batteries gradually age over time due to various factors (such as charge and discharge cycles, temperature fluctuations, and usage habits), leading to performance degradation. Therefore, accurately assessing and predicting battery SOH is crucial for ensuring battery safety, extending service life, and optimizing maintenance strategies.

[0003] In the prior art, SOH estimation is usually dominated by a single method, for example, the capacity increment method is used to calculate the peak position shift of the voltage curve.

[0004] However, the above method is relatively simple and only relies on calculation of a single charge and discharge segment, resulting in inaccurate calculation, which in turn affects the abnormal results of SOH. Summary of the Invention

[0005] The embodiments of the present application provide a method, apparatus, device, and storage medium for determining an SOH anomaly, which are used to solve the problem of how to improve the accuracy of SOH anomaly determination.

[0006] In a first aspect, an embodiment of the present application provides a method for determining an SOH anomaly, comprising:

[0007] Based on a predetermined set of target charging segments, calculating a first SOH estimation value for each target charging segment based on a capacity increment method to obtain a first SOH estimation value sequence, and calculating a second SOH estimation value for each target charging segment based on an ampere-hour integration method to obtain a second SOH estimation value sequence;

[0008] The first SOH estimation value sequence, the second SOH estimation sequence, and the previously acquired historical SOH data are integrated and calculated to obtain a full life cycle SOH sequence;

[0009] Robust regression is used to fit the slope of the full life cycle SOH series decaying over time to obtain the decay slope;

[0010] Based on the decay slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold, it is determined whether the current SOH of the battery is abnormal.

[0011] In one possible implementation, determining whether the current battery SOH is abnormal based on the decay slope, the estimated SOH value at the current moment in the full life cycle SOH sequence, a preset acquired SOH threshold, and a decay rate threshold includes:

[0012] If the SOH estimation value at the current moment is higher than the SOH threshold and / or the decay slope exceeds the decay rate threshold, it is determined that the current SOH of the battery is abnormal.

[0013] In one possible implementation, the method further includes:

[0014] Obtaining charging segment data of the battery;

[0015] Based on a preset screening condition, the target charging segment set is obtained by screening the charging segment data.

[0016] In a possible implementation, the fusing and calculating the first SOH estimation value sequence, the second SOH estimation sequence, and pre-acquired historical SOH data to obtain a full lifecycle SOH sequence includes:

[0017] The first SOH estimation value sequence, the second SOH estimation sequence, and the pre-acquired historical SOH data are fused and calculated using a pre-constructed SOH fusion function to obtain the full life cycle SOH sequence;

[0018] The SOH fusion function is used to perform weighted fusion on the first SOH estimation value sequence, the second SOH estimation sequence and the historical SOH data to obtain the full life cycle SOH sequence.

[0019] In one possible implementation, the method further includes:

[0020] Construct the initial SOH fusion function;

[0021] Optimizing the parameters of the initial SOH fusion function based on an optimization algorithm to obtain optimal parameters;

[0022] The optimal parameters are updated to the initial SOH fusion function to obtain the SOH fusion function.

[0023] In one possible implementation, the method further includes:

[0024] Obtaining the accumulated usage mileage and rest time of the battery;

[0025] According to the accumulated mileage and the rest time, the preset initial SOH threshold and initial decay rate threshold are dynamically adjusted by a table lookup method to generate the SOH threshold and the decay rate threshold.

[0026] In a possible implementation, the screening conditions include a depth of charge greater than or equal to 80%, and a charging current fluctuation less than a preset range.

[0027] In one possible implementation, dynamically adjusting a preset initial SOH threshold and an initial decay rate threshold by a table lookup method based on the accumulated mileage and the rest time to generate the SOH threshold and the decay rate threshold includes:

[0028] Based on the accumulated mileage and the rest time, searching for a target node in a preset table, wherein the table includes SOH threshold offsets and decay rate threshold offsets corresponding to different accumulated mileage and rest time combinations;

[0029] Calculate the adjustment amount by bilinear interpolation;

[0030] The initial SOH threshold and the initial decay rate threshold are dynamically adjusted based on the adjustment amount to obtain the SOH threshold and the decay rate threshold.

[0031] In a second aspect, an embodiment of the present application provides a device for determining an SOH anomaly, including:

[0032] a first calculation module, configured to calculate, based on a predetermined set of target charging segments, a first SOH estimation value for each target charging segment based on a capacity increment method to obtain a first SOH estimation value sequence, and to calculate a second SOH estimation value for each target charging segment based on an ampere-hour integration method to obtain a second SOH estimation value sequence;

[0033] A second calculation module is configured to fuse the first SOH estimation value sequence, the second SOH estimation sequence, and pre-acquired historical SOH data to obtain a full life cycle SOH sequence;

[0034] A fitting module, configured to fit the slope of the full life cycle SOH sequence attenuating over time using robust regression to obtain an attenuation slope;

[0035] A determination module is used to determine whether the SOH of the current battery is abnormal based on the decay slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold.

[0036] In a possible implementation, the determining module is specifically configured to:

[0037] If the SOH estimation value at the current moment is higher than the SOH threshold and / or the decay slope exceeds the decay rate threshold, it is determined that the current SOH of the battery is abnormal.

[0038] In a possible implementation, the device further includes:

[0039] A first acquisition module, configured to acquire charging segment data of the battery;

[0040] The screening module is configured to screen the charging segment data to obtain the target charging segment set based on a preset screening condition.

[0041] In one possible implementation, the second calculation module specifically includes:

[0042] The first SOH estimation value sequence, the second SOH estimation sequence, and the pre-acquired historical SOH data are fused and calculated using a pre-constructed SOH fusion function to obtain the full life cycle SOH sequence;

[0043] The SOH fusion function is used to perform weighted fusion on the first SOH estimation value sequence, the second SOH estimation sequence and the historical SOH data to obtain the full life cycle SOH sequence.

[0044] In a possible implementation, the device further includes:

[0045] Construction module, used to construct the initial SOH fusion function;

[0046] An optimization module, configured to optimize the parameters of the initial SOH fusion function based on an optimization algorithm to obtain optimal parameters;

[0047] An updating module is used to update the optimal parameters to the initial SOH fusion function to obtain the SOH fusion function.

[0048] In a possible implementation, the device further includes:

[0049] A second acquisition module is used to obtain the cumulative mileage and rest time of the battery;

[0050] The adjustment module is used to dynamically adjust the preset initial SOH threshold and initial decay rate threshold by a table lookup method according to the accumulated mileage and the rest time to generate the SOH threshold and the decay rate threshold.

[0051] In a possible implementation, the screening conditions include a depth of charge greater than or equal to 80%, and a charging current fluctuation less than a preset range.

[0052] In a possible implementation, the adjustment module is specifically configured to:

[0053] Based on the accumulated mileage and the rest time, searching for a target node in a preset table, wherein the table includes SOH threshold offsets and decay rate threshold offsets corresponding to different accumulated mileage and rest time combinations;

[0054] Calculate the adjustment amount by bilinear interpolation;

[0055] The initial SOH threshold and the initial decay rate threshold are dynamically adjusted based on the adjustment amount to obtain the SOH threshold and the decay rate threshold.

[0056] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0057] The memory stores computer-executable instructions;

[0058] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0059] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0060] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0061] The method, apparatus, device and storage medium for determining SOH anomaly provided in the embodiments of the present application are based on a predetermined set of target charging segments, and for each target charging segment, a first SOH estimation value is calculated based on the capacity increment method to obtain a first SOH estimation value sequence, and for each target charging segment, a second SOH estimation value is calculated based on the ampere-hour integration method to obtain a second SOH estimation value sequence, and the first SOH estimation value sequence, the second SOH estimation value sequence and the previously acquired historical SOH data are fused and calculated to obtain a full life cycle SOH sequence, and robust regression is used to fit the slope of the full life cycle SOH sequence that decays over time to obtain an attenuation slope, and based on the attenuation slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold, it is determined whether the SOH of the current battery is abnormal. The above method offsets the error of a single method through dual-modal data fusion, improves accuracy, and improves noise resistance. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0063] Figure 1 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 1 ;

[0064] Figure 2 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 2 ;

[0065] Figure 3 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 3 ;

[0066] Figure 4 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 4 ;

[0067] Figure 5 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 5 ;

[0068] Figure 6 A schematic diagram of the structure of the device for determining SOH anomaly provided by this application;

[0069] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application.

[0070] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0072] With the rapid development of electric vehicles and energy storage power stations, the assessment and prediction of the SOH of power batteries, as core components, has become particularly important. The battery's SOH directly impacts the range and safety of electric vehicles and the operating efficiency of energy storage power stations. However, batteries gradually age during use due to various factors (such as charge and discharge cycles, temperature fluctuations, and usage habits), leading to performance degradation. Therefore, accurately assessing and predicting battery SOH is crucial for ensuring battery safety, extending service life, and optimizing maintenance strategies. Existing technologies typically employ a single method for SOH estimation, such as the capacity increment method, which relies on calculating the peak offset of the voltage curve. However, these methods are relatively simplistic and rely solely on calculations of single charge and discharge cycles, resulting in inaccurate calculations and, consequently, abnormal SOH results.

[0073] To address the above-mentioned issues, the present application provides a method, apparatus, device, and storage medium for determining SOH anomalies, improving the accuracy of SOH anomaly determination. Specifically, existing techniques typically employ a single method for calculating SOH, such as calculating capacity by integrating charging current in ampere-hours and estimating SOH based on SOC changes. However, this method relies on the accuracy of the current sensor and the accuracy of SOC estimation, and is susceptible to noise and incomplete charge and discharge. Alternatively, a battery electrochemical model can be established to infer SOH through parameter identification (such as internal resistance and polarization voltage). However, this method is complex, requires frequent parameter calibration, and struggles to adapt to dynamic changes in actual operating conditions. Alternatively, fixed thresholds are set based on the peak voltage or internal resistance of the capacity increment curve. Exceeding these thresholds signals an anomaly and triggers an alarm. However, static thresholds are unsuitable for varying operating conditions (such as high mileage or long periods of inactivity) and result in a high false alarm rate. To address these issues, the inventors investigated the possibility of calculating SOH separately using the capacity increment method and the ampere-hour integration method, using the peak voltages of multiple charging segments over a year as the starting and ending points of the phase transition process. By introducing historical SOH data and designing a parameterized SOH fusion function, an optimization algorithm is used to optimally estimate the parameters of the SOH fusion function, achieving a fusion of the two. This avoids the shortcomings of relying on a single calculation result and the problem of the ampere-hour integral being overly dependent on the SOC accuracy before and after charging, thereby obtaining an accurate SOH. Finally, the SOH decay rate is calculated through robust regression, and appropriate decay rate thresholds and SOH thresholds are set to identify SOH anomalies. Based on this, the technical solution of this application is proposed.

[0074] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0075] Figure 1Schematic diagram of the process of determining SOH anomaly provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0076] S101: Based on a predetermined set of target charging segments, a first SOH estimation value is calculated for each target charging segment based on a capacity increment method to obtain a first SOH estimation value sequence, and a second SOH estimation value is calculated for each target charging segment based on an ampere-hour integration method to obtain a second SOH estimation value sequence.

[0077] In this step, to avoid the inaccuracy of SOH calculated using a single method, a multi-dimensional method can be used to calculate SOH. In order to further improve the calculation accuracy, the calculation can also be performed based on charging segments within a preset time. The first SOH estimate is calculated based on the capacity increment method, and the second SOH estimate is calculated based on the ampere-hour integration method.

[0078] The first SOH estimate represents the SOH value calculated using the capacity increment method for a single target charging segment (e.g., SOH = 85% for a specific charging segment). The first SOH estimate sequence is a chronological sequence of the first SOH estimates for all target charging segments, reflecting the changing trend of the battery's state of health over time.

[0079] Similarly, the second SOH estimate represents the SOH value calculated using the ampere-hour integration method for a single target charging segment (e.g., SOH = 83% for a particular charging segment). The second SOH estimate sequence is a sequence of the second SOH estimates of all target charging segments arranged in the same chronological order, corresponding one-to-one to the first SOH estimate sequence.

[0080] The first SOH estimation value and the second SOH estimation value at the same timestamp complement each other and reflect the aging characteristics of different dimensions respectively.

[0081] Specifically, the calculation of the first SOH estimation value is based on the capacity increment method. First, a capacity increment curve is generated for each charging segment in the target charging segment set, and the peak voltage is extracted. Then, based on the mapping relationship between the peak voltage and SOH, the first SOH estimation value is calculated.

[0082] The calculation of the first SOH estimate is based on the ampere-hour integration method. First, the current is integrated for each charging segment to calculate the actual charging capacity, and then the second SOH estimate is calculated in combination with the rated capacity.

[0083] The estimated values ​​calculated for each charging segment are processed separately to obtain a first SOH estimation value sequence and a second SOH estimation sequence.

[0084] For example, the specific calculation formula of the actual charging capacity can be expressed as:

[0085]

[0086] in, Indicates the starting time point of the charging segment, Indicates the end time point of the charging segment, t indicates time, represents the function of charging current changing with time, Indicates the state of charge at the start of charging. Indicates the state of charge at the time charging is terminated.

[0087] S102: The first SOH estimation value sequence, the second SOH estimation sequence, and the previously acquired historical SOH data are fused and calculated to obtain a full life cycle SOH sequence.

[0088] In this step, in order to improve the estimation accuracy and avoid the single method being susceptible to specific noise, the two types of estimation values ​​can be weightedly fused through a fusion function. In order to avoid the single SOH calculation result being easily disturbed by operating condition fluctuations, which in turn causes sequence jumps, the historical SOH attenuation factor can be added to the fusion function, that is, historical SOH data can be introduced to suppress short-term fluctuations. The first SOH estimation value sequence, the second SOH estimation sequence and the pre-acquired historical SOH data are fused and calculated through a pre-constructed SOH fusion function to obtain a full life cycle SOH sequence, wherein the SOH fusion function is used to weightedly fuse the first SOH estimation value sequence, the second SOH estimation sequence and the historical SOH data to obtain a full life cycle SOH sequence.

[0089] Specifically, an initial SOH fusion function is constructed in advance, and the weight parameters in the fusion function are optimized through an optimization algorithm to obtain the SOH fusion function. The first SOH estimation value sequence and the second SOH estimation sequence obtained in the above steps and the historical SOH data are input into the SOH fusion function to generate a full life cycle SOH sequence.

[0090] For example, the initial SOH fusion function can be constructed as follows:

[0091]

[0092] in, is the weight parameter of the first SOH estimation sequence, is the weight parameter of the second SOH estimation sequence, is the weight parameter of historical SOH data, represents the first SOH estimation sequence, represents the second SOH estimation sequence, Indicates historical SOH data.

[0093] S103: Use robust regression to fit the slope of the decay of the SOH series over time throughout the life cycle to obtain the decay slope.

[0094] In this step, in order to accurately capture the battery aging trend and thus suppress the interference of outliers, the slope of the full life cycle SOH sequence obtained in the above step is fitted.

[0095] Specifically, the data is first preprocessed to remove obvious outliers in the full lifecycle SOH sequence, such as SOH mutations caused by abnormal charging segments. A robust regression model is then used for fitting, using the Huber loss function to balance the sensitivity of the least squares method with the robustness of the absolute value loss. The formula is as follows:

[0096]

[0097] Among them, r is the residual, Taking 1.5 times the median of the residuals can isolate extreme outliers.

[0098] It should be noted that when the absolute value of the residual When , square loss is used to maintain efficient fitting of normal data.

[0099] when When , it switches to linear loss to reduce the weight of outliers and prevent them from dominating the fitting results.

[0100] The slope fitting model is , the fitting target is the slope k, where k reflects the battery aging rate.

[0101] Iterative fitting is performed based on the robust regression model until convergence or the preset number of iterations is reached to obtain the attenuation slope.

[0102] S104: Determine whether the current battery SOH is abnormal based on the decay slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold.

[0103] In this step, after determining the attenuation slope, it is determined whether the current battery SOH is abnormal based on the attenuation slope, the SOH estimate value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the attenuation rate threshold.

[0104] Specifically, if the SOH estimation value at the current moment is higher than the SOH threshold and / or the decay slope exceeds the decay rate threshold, it is determined that the SOH of the current battery is abnormal.

[0105] Among them, the SOH estimation value at the current moment is higher than the SOH threshold, indicating insufficient capacity, and the attenuation slope exceeds the attenuation rate threshold, indicating that the aging rate is abnormally accelerated.

[0106] Optionally, after the SOH anomaly is determined, an early warning is triggered and the early warning information is directly pushed to the cloud device.

[0107] The method for determining SOH anomalies provided in the embodiment of the present application is based on a predetermined set of target charging segments, and for each target charging segment, a first SOH estimation value is calculated based on the capacity increment method to obtain a first SOH estimation value sequence, and for each target charging segment, a second SOH estimation value is calculated based on the ampere-hour integration method to obtain a second SOH estimation value sequence. The first SOH estimation value sequence, the second SOH estimation sequence, and the previously acquired historical SOH data are fused and calculated to obtain a full life cycle SOH sequence, and robust regression is used to fit the slope of the full life cycle SOH sequence that decays over time to obtain an attenuation slope. Based on the attenuation slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold, and the decay rate threshold, it is determined whether the SOH of the current battery is abnormal. The above method offsets the error of a single method through dual-modal data fusion, improves accuracy, and improves noise resistance.

[0108] Figure 2 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 2 ,like Figure 2 As shown, based on the above embodiment, the method further includes:

[0109] S201: Obtain battery charging segment data.

[0110] In this step, in order to provide basic input for subsequent battery health status analysis and avoid the inaccuracy of a single calculation, the battery charging segment data is obtained. For example, multiple charging segments within a year can be collected.

[0111] Specifically, battery charging data can be obtained from cloud devices or on-board terminals. This data can include current, voltage, temperature, state of charge, and timestamps, where the timestamp refers to the recorded start and end times of charging and discharging.

[0112] S202: Based on pre-set screening conditions, screen the charging segment data to obtain a target charging segment set.

[0113] In this step, to select high-quality, high-information segments from the original charging segments, providing reliable input for SOH estimation and reducing noise impact, a target charging segment set is selected based on preset screening criteria. These criteria include a depth of charge greater than or equal to 80% and charging current fluctuations within a preset range.

[0114] Specifically, because slow charging current is stable, data noise is low, and the capacity increment curve features are clearer, only slow charging segments (charging current ≤ 10% of the rated value) are selected. Insufficient charge depth will increase capacity estimation errors (for example, charging only from 30% to 50% cannot effectively extract aging characteristics). Therefore, the charge depth must be greater than or equal to 80%.

[0115] Optionally, duration can also be included in the filter criteria, as too short segments may affect analysis due to incomplete data (e.g., too short segments may result in incomplete curves). Therefore, charging time can be filtered to include segments longer than 30 minutes.

[0116] Optionally, segments with sensor abnormality marks, such as current jump, temperature exceeding a limit, etc., can also be removed.

[0117] The method for determining SOH anomalies provided in the embodiments of this application obtains battery charging segment data and, based on pre-set screening conditions, filters the charging segment data to obtain a target charging segment set. This method improves the accuracy of SOH estimation, avoids SOH estimation bias, enhances the robustness of the algorithm, and reduces misjudgments caused by data quality issues.

[0118] Figure 3 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 3 ,like Figure 3 As shown, based on the above embodiment, the method further includes:

[0119] S301: Construct an initial SOH fusion function.

[0120] S302: Optimize the parameters of the initial SOH fusion function based on the optimization algorithm to obtain the optimal parameters.

[0121] S303: Update the optimal parameters to the initial SOH fusion function to obtain the SOH fusion function.

[0122] A basic function framework is designed to preliminarily integrate multi-source SOH estimation values ​​(such as the capacity increment method and the ampere-hour integration method) and historical data to provide an initial model structure for subsequent parameter optimization.

[0123] Exemplarily, the form of the initial SOH fusion function involved may be the form in step S102 in the above embodiment, and the parameters of the initial SOH fusion function are optimized based on the optimization algorithm.

[0124] Specifically, the above three weight parameters need to satisfy , you can first initialize the parameters and set the initial values ​​of the weight parameters based on experience. Through data-driven approach, the weight parameters of the fusion function are automatically adjusted to minimize the error between the fusion SOH value and the true value, thereby improving the estimation accuracy.

[0125] The particle swarm optimization algorithm can be used, so the algorithm has strong global search capabilities, can avoid local optimality, and does not require gradient calculation.

[0126] It involves the objective function, the mean square error between the minimum fused SOH value and the measured SOH value, and sets the parameter constraints, such as , .

[0127] Taking the particle swarm optimization algorithm as an example, the particle swarm is first initialized, and example positions (parameter combinations) and velocities are randomly generated. Then, an iterative update is performed, calculating the fitness (mean square error) of each particle, updating the individual and global optimal positions, and adjusting the particle velocities and positions to approach the optimal solution until the maximum number of iterations is reached or the error converges, resulting in the optimal parameters. These optimal parameters are then updated into the initial SOH fusion function, resulting in the SOH fusion parameters.

[0128] The method for determining SOH anomalies provided in the embodiments of the present application constructs an initial SOH fusion function, optimizes the parameters of the initial SOH fusion function based on an optimization algorithm to obtain optimal parameters, and updates the optimal parameters to the initial SOH fusion function to obtain the SOH fusion function. The above method integrates the capacity increment method, the ampere-hour integral method, and historical data through the initial function. The optimization algorithm ensures scientific weight distribution. Compared with a single method, it reduces errors, improves dynamic adaptability, and improves stability.

[0129] Figure 4 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 4 ,like Figure 4 As shown, based on the above embodiment, the method further includes:

[0130] S401: Obtain the accumulated usage mileage and rest time of the battery.

[0131] To improve the accuracy of SOH estimation, the threshold is dynamically adjusted based on the battery's cumulative mileage and rest time. This requires obtaining the battery's cumulative mileage and rest time in advance.

[0132] It should be noted that the accumulated mileage and rest time are key parameters that reflect the actual usage intensity of the battery.

[0133] Specifically, the cumulative mileage is the total mileage of the vehicle (unit: 10,000 kilometers), which reflects the degree of cycle aging of the battery. How to obtain:

[0134] On-board odometer data (read in real time via CAN bus).

[0135] Cloud history records (accumulate the mileage increment of each trip).

[0136] The rest time is the length of time (in days) that the battery is idle without being charged or discharged, reflecting the effects of calendar aging.

[0137] How to obtain:

[0138] The last charge and discharge timestamp recorded by the battery management system (BMS).

[0139] Cloud-synchronized static period statistics (such as GPS positioning data while the vehicle is parked).

[0140] S402: Dynamically adjust the preset initial SOH threshold and initial decay rate threshold based on the accumulated mileage and rest time by using a table lookup method to generate an SOH threshold and a decay rate threshold.

[0141] Based on the actual usage conditions of the battery (mileage and static time), the initial threshold is dynamically corrected to make the judgment boundary more consistent with the actual aging status of the battery, reducing false positives and missed negatives.

[0142] Specifically, based on the accumulated mileage and idle time, the target node is searched in a preset table, and the initial SOH threshold and initial decay rate threshold are dynamically adjusted based on the adjustment amount to obtain the SOH threshold and decay rate threshold.

[0143] The method for determining SOH anomalies provided in this embodiment obtains the battery's cumulative mileage and rest time. Based on the accumulated mileage and rest time, a table lookup method dynamically adjusts the pre-set initial SOH threshold and initial decay rate threshold to generate SOH threshold and decay rate threshold. This dynamic adjustment of the thresholds based on usage intensity improves dynamic adaptability and the accuracy of anomaly determination.

[0144] Figure 5 Schematic diagram of the process of determining SOH anomaly provided in this application Figure 5 ,like Figure 5 As shown, based on the above embodiment, step S402 specifically includes:

[0145] S501: Based on the accumulated mileage and the rest time, a target node is searched in a preset table.

[0146] Based on the battery's cumulative mileage and rest time, the nearest reference node is located in a predefined two-dimensional table, providing a benchmark for subsequent interpolation calculations. The table includes SOH threshold offsets and decay rate threshold offsets corresponding to different cumulative mileage and rest time combinations.

[0147] Exemplarily, the table structure includes:

[0148] Horizontal axis (X): cumulative mileage nodes (such as 0, 10,000, 20,000, ... kilometers).

[0149] Vertical axis (Y): static time nodes (such as 0, 30, 60, ... days).

[0150] Cell content: stores the threshold adjustment value (ΔSOH threshold, Δk threshold) corresponding to the mileage and rest time combination.

[0151] Specific table lookup process: Input the current accumulated mileage and rest time, for example, accumulated mileage M = 35,000 kilometers, rest time T = 45 days. Find the nearest mileage node on the horizontal axis, for example, M 下 =30,000 km, M 上 = 40,000 km. Find the nearest stationary time node on the vertical axis, for example, T 下 =30 days, T 上 = 60 days. Then the coordinates of the four adjacent cells, i.e. the target node, can be determined, for example (M 下 , T 下 )、(M 下 , T 上 )、(M 上 , T 上 )、(M 上 , T 下 ).

[0152] S502: Calculate the adjustment amount through bilinear interpolation.

[0153] After the target node is determined, the adjustment amount can be calculated based on the target node through bilinear interpolation.

[0154] Specifically, based on the adjustment amount of the target node, the precise adjustment amount under the current actual usage conditions is calculated through interpolation to avoid step errors caused by table discretization. First, the adjustment amounts of adjacent nodes are weighted averaged to determine the adjustment amount.

[0155] S503: Dynamically adjust the initial SOH threshold and the initial decay rate threshold based on the adjustment amount to obtain the SOH threshold and the decay rate threshold.

[0156] In this step, the interpolated adjustment amount is combined with the initial threshold to generate a dynamic decision boundary that adapts to the current usage conditions. The adjustment amount is directly added to the initial threshold to obtain the threshold.

[0157] It should be noted that the above calculation methods for the SOH threshold and the attenuation rate threshold are all calculated through the above steps, and will not be described separately here.

[0158] The method for determining SOH anomalies provided in the embodiments of this application searches for a target node in a preset table based on accumulated mileage and idle time. Bilinear interpolation is then used to dynamically adjust the initial SOH threshold and initial decay rate threshold based on the adjustment amount to obtain the SOH threshold and decay rate threshold. This method reduces computational complexity, mitigates misjudgments due to threshold jumps, and improves the accuracy of SOH anomaly determination.

[0159] Figure 6 This is a schematic diagram of the structure of the device for determining SOH anomaly provided by this application, such as Figure 6 As shown, the SOH abnormality determination device 600 specifically includes:

[0160] A first calculation module 601 is configured to calculate a first SOH estimation value and a second SOH estimation value for each target charging segment based on a predetermined target charging segment set, to obtain a first SOH estimation value sequence and a second SOH estimation value sequence, wherein the first SOH estimation value is calculated based on a capacity increment method, and the second SOH estimation value is calculated based on an ampere-hour integration method;

[0161] The second calculation module 602 is configured to input the first SOH estimation value sequence, the second SOH estimation sequence, and pre-acquired historical SOH data into a pre-built SOH fusion function to calculate a full life cycle SOH sequence;

[0162] The fitting module 603 is used to fit the slope of the decay of the full life cycle SOH sequence over time using robust regression to obtain the decay slope;

[0163] The determination module 604 is used to determine whether the current battery SOH is abnormal based on the decay slope, the SOH estimated value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold.

[0164] In a possible implementation, the determining module 604 is specifically configured to:

[0165] If the current SOH estimation value is higher than the SOH threshold and / or the decay slope exceeds the decay rate threshold, it is determined that the current battery SOH is abnormal.

[0166] In a possible implementation, the SOH abnormality determination device 600 further includes:

[0167] A first acquisition module 605 is used to acquire battery charging segment data;

[0168] The screening module 606 is configured to screen the charging segment data to obtain a target charging segment set based on a preset screening condition.

[0169] In a possible implementation, the second calculation module 602 is specifically configured to:

[0170] The first SOH estimation value sequence, the second SOH estimation sequence, and the previously acquired historical SOH data are fused and calculated using a pre-built SOH fusion function to obtain a full lifecycle SOH sequence.

[0171] The SOH fusion function is used to perform weighted fusion on the first SOH estimation value sequence, the second SOH estimation sequence and the historical SOH data to obtain the full life cycle SOH sequence.

[0172] In a possible implementation, the SOH abnormality determination device 600 further includes:

[0173] A construction module 607 is used to construct an initial SOH fusion function;

[0174] An optimization module 608 is used to optimize the parameters of the initial SOH fusion function based on an optimization algorithm to obtain optimal parameters;

[0175] The updating module 609 is configured to update the optimal parameters to the initial SOH fusion function to obtain the SOH fusion function.

[0176] In a possible implementation, the SOH abnormality determination device 600 further includes:

[0177] The second acquisition module 610 is used to obtain the accumulated mileage and rest time of the battery;

[0178] The adjustment module 611 is used to dynamically adjust the preset initial SOH threshold and initial decay rate threshold according to the accumulated mileage and rest time through a table lookup method to generate the SOH threshold and decay rate threshold.

[0179] In a possible implementation, the screening conditions include that the depth of charge is greater than or equal to 80%, and the charging current fluctuation is less than a preset range.

[0180] In a possible implementation, the adjustment module 611 is specifically configured to:

[0181] Based on the accumulated mileage and rest time, the target node is searched in a preset table. The table includes the SOH threshold offset and decay rate threshold offset corresponding to different accumulated mileage and rest time combinations.

[0182] Calculate the adjustment amount by bilinear interpolation;

[0183] The initial SOH threshold and the initial decay rate threshold are dynamically adjusted based on the adjustment amount to obtain the SOH threshold and the decay rate threshold.

[0184] The device for determining SOH anomaly provided in this embodiment can execute the SOH anomaly determination method solutions provided in the above-mentioned various method embodiments. The implementation principles and technical effects thereof are similar and will not be described in detail in this embodiment.

[0185] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 700 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the electronic device 700 further includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus 704.

[0186] During the specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that the at least one processor 701 performs the above method.

[0187] The specific implementation process of the processor 701 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0188] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0189] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0190] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0191] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0192] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0193] The readable storage medium may be implemented by any type of volatile or non-volatile memory 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 readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0194] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0195] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0196] Units described as separate components may or may not be physically separate, and components shown as units 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0197] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0198] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0199] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0200] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A method for determining SOH anomaly, characterized in that: include: Based on a predetermined set of target charging segments, calculating a first SOH estimation value for each target charging segment based on a capacity increment method to obtain a first SOH estimation value sequence, and calculating a second SOH estimation value for each target charging segment based on an ampere-hour integration method to obtain a second SOH estimation value sequence; The first SOH estimation value sequence, the second SOH estimation sequence, and the previously acquired historical SOH data are integrated and calculated to obtain a full life cycle SOH sequence; Robust regression is used to fit the slope of the full life cycle SOH series decaying over time to obtain the decay slope; Based on the decay slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold, it is determined whether the current SOH of the battery is abnormal.

2. The method according to claim 1, characterized in that The determining whether the current battery SOH is abnormal based on the decay slope, the SOH estimated value at the current moment in the full life cycle SOH sequence, a preset SOH threshold and a decay rate threshold includes: If the SOH estimation value at the current moment is higher than the SOH threshold and / or the decay slope exceeds the decay rate threshold, it is determined that the current SOH of the battery is abnormal.

3. The method according to claim 1, characterized in that The method further comprises: Obtaining charging segment data of the battery; Based on a preset screening condition, the target charging segment set is obtained by screening the charging segment data.

4. The method according to any one of claims 1 to 3, characterized in that The fusing and calculating the first SOH estimation value sequence, the second SOH estimation sequence, and the pre-acquired historical SOH data to obtain a full lifecycle SOH sequence includes: The first SOH estimation value sequence, the second SOH estimation sequence, and the pre-acquired historical SOH data are fused and calculated using a pre-constructed SOH fusion function to obtain the full life cycle SOH sequence; The SOH fusion function is used to perform weighted fusion on the first SOH estimation value sequence, the second SOH estimation sequence and the historical SOH data to obtain the full life cycle SOH sequence.

5. The method according to claim 4, characterized in that The method further comprises: Construct the initial SOH fusion function; Optimizing the parameters of the initial SOH fusion function based on an optimization algorithm to obtain optimal parameters; The optimal parameters are updated to the initial SOH fusion function to obtain the SOH fusion function.

6. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Obtaining the accumulated usage mileage and rest time of the battery; According to the accumulated mileage and the rest time, the preset initial SOH threshold and initial decay rate threshold are dynamically adjusted by a table lookup method to generate the SOH threshold and the decay rate threshold.

7. The method according to claim 3, characterized in that The screening conditions include that the depth of charge is greater than or equal to 80%, and the charging current fluctuation is less than a preset range.

8. The method according to claim 6, characterized in that The method of dynamically adjusting a preset initial SOH threshold and an initial decay rate threshold by a table lookup method based on the accumulated mileage and the rest time to generate the SOH threshold and the decay rate threshold includes: Based on the accumulated mileage and the rest time, searching for a target node in a preset table, wherein the table includes SOH threshold offsets and decay rate threshold offsets corresponding to different accumulated mileage and rest time combinations; Calculate the adjustment amount by bilinear interpolation; The initial SOH threshold and the initial decay rate threshold are dynamically adjusted based on the adjustment amount to obtain the SOH threshold and the decay rate threshold.

9. A device for determining SOH anomaly, characterized in that: include: a first calculation module, configured to calculate, based on a predetermined set of target charging segments, a first SOH estimation value for each target charging segment based on a capacity increment method to obtain a first SOH estimation value sequence, and to calculate a second SOH estimation value for each target charging segment based on an ampere-hour integration method to obtain a second SOH estimation value sequence; A second calculation module is configured to fuse the first SOH estimation value sequence, the second SOH estimation sequence, and pre-acquired historical SOH data to obtain a full life cycle SOH sequence; A fitting module, configured to fit the slope of the full life cycle SOH sequence attenuating over time using robust regression to obtain an attenuation slope; A determination module is used to determine whether the SOH of the current battery is abnormal based on the decay slope, the SOH estimation value at the current moment in the full life cycle SOH sequence, the preset SOH threshold and the decay rate threshold.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method for determining an SOH abnormality according to any one of claims 1 to 8.

11. 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 for determining an SOH anomaly according to any one of claims 1 to 8.

Images