Power battery health state estimation method and electronic equipment

Abstract

The invention provides a power battery health state estimation method and electronic equipment, and relates to the field of vehicle batteries, and the method comprises the steps: obtaining a plurality of groups of first battery charging data of a power battery of a target vehicle in the last charging process, and calculating the state of health of the power battery according to the battery temperature in the plurality of groups of first battery charging data; determining the average temperature of the last charging process; according to the average temperature of the last charging process and the target SOH estimated value of the previous charging process, a pre-trained regression model is adopted for prediction, and a prediction correction factor is obtained; according to SOC parameters, currents and prediction correction factors in the multiple sets of first battery charging data, the correction capacity of the last charging process is determined; and according to the corrected capacity and the rated capacity of the power battery, determining a target SOH estimated value of the last charging process. The estimation deviation is effectively eliminated by considering the average temperature of the last charging process and the target SOH estimation value of the previous charging process.

Description

Technical Field

[0001] This invention relates to the field of vehicle battery technology, and more specifically, to a method and electronic device for estimating the state of health of a power battery. Background Technology

[0002] As a core component of new energy vehicles, the State of Health (SOH) of power batteries is a crucial indicator reflecting battery performance and lifespan. Existing SOH estimation methods primarily calculate SOH by integrating the charge and discharge current to obtain the capacity and then comparing it with the rated capacity. However, these methods roughly calculate the overall capacity corresponding to the State of Charge (SOC) parameter, or assume that each 1% of SOC corresponds to the same amount of capacity, failing to consider the effects of battery aging, SOC segmentation, and temperature, leading to inaccurate estimation results. Alternatively, using deep neural networks for SOH estimation, while theoretically achieving high accuracy, often involves high computational complexity, requires large amounts of data, and faces challenges in real-time operation. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of the prior art by providing a method and electronic device for estimating the state of health (SOH) of a power battery. This method uses a pre-trained regression model to predict the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, thereby obtaining a prediction correction factor for the most recent charging process. Then, based on the prediction correction factor, multiple sets of first battery charging data from the most recent charging process, and the rated capacity of the power battery, the target SOH estimate for the most recent charging process is determined.

[0004] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a method for estimating the health status of a power battery, the method comprising: Acquire multiple sets of first battery charging data of the target vehicle's power battery during the most recent charging process. The multiple sets of first battery charging data correspond to multiple sampling times. Each set of first battery charging data includes at least: current, state of charge (SOC) parameter, and battery temperature. The average temperature of the most recent charging process is determined based on the battery temperature in the multiple sets of first battery charging data. Based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, a pre-trained regression model is used to make a prediction and obtain the prediction correction factor for the most recent charging process; wherein, the previous charging process is the charging process of the power battery before the most recent charging process in multiple target historical charging processes. Based on the SOC parameters, current, and prediction correction factor in the multiple sets of first battery charging data, the corrected capacity of the most recent charging process is determined. The target SOH estimate for the most recent charging process is determined based on the corrected capacity of the most recent charging process and the rated capacity of the power battery.

[0005] In an optional implementation, before obtaining the prediction correction factor for the most recent charging process by using a pre-trained regression model to predict based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, the method further includes: Acquire multiple sets of second battery charging data for the power battery during each target historical charging process. The multiple sets of second battery charging data correspond to multiple sampling times. Each set of second battery charging data includes at least: current, SOC parameter and battery temperature. Based on the battery temperature of the multiple sets of second battery charging data, determine the average temperature of each of the target historical charging processes; Based on the SOC parameters and current in the multiple sets of second battery charging data, the initial SOH estimate and the corresponding true correction factor for each target historical charging process are determined respectively. Multiple training samples are constructed based on the average temperature of the target historical charging process, the true correction factor, and the initial SOH estimate of the corresponding previous historical charging process. The input variables of the training samples include the average temperature of the target historical charging process and the initial SOH estimate of the corresponding previous historical charging data. The output variable of the training samples is the true correction factor of the target historical charging process. The regression model is obtained by fitting the mapping relationship between the output variable and the input variable based on multiple training samples.

[0006] In an optional implementation, determining the initial SOH estimate and corresponding true correction factor for each target historical charging process based on the SOC parameters and current in the multiple sets of second battery charging data includes: Based on the SOC parameters and current in the multiple sets of second battery charging data, determine the power information of multiple first SOC intervals involved in the target historical charging process; Based on the power information of the multiple first SOC intervals, the total power of the target historical charging process is determined; Based on the total charge of the target historical charging process, the rated capacity of the power battery, the end SOC parameter and the start SOC parameter of the target historical charging process, determine the initial SOH estimate of the target historical charging process; Based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, the capacity of the target historical charging process is predicted to obtain the historical predicted capacity of the target historical charging process. The original capacity of the target historical charging process is determined based on the total amount of electricity charged during the target historical charging process. Based on the historical predicted capacity and the original capacity of the target historical charging process, the true correction factor of the target historical charging process is determined.

[0007] In an optional implementation, the step of predicting the capacity of the target historical charging process based on the power information of each first SOC interval and the power information of the same SOC interval in the corresponding previous historical charging process, to obtain the historical predicted capacity of the target historical charging process, includes: Based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, the historical power increment of each first SOC interval is determined. Based on the historical power increment of the plurality of first SOC intervals, capacity prediction is performed for each of the target historical charging processes to obtain the historical predicted capacity of the target historical charging process.

[0008] In an optional implementation, determining the original capacity of the target historical charging process based on the total charge of the target historical charging process includes: If there is a second SOC interval that is not involved in the target historical charging process among multiple preset SOC intervals, then the predicted capacity corresponding to the second SOC interval is determined based on the historical incremental power information of the same SOC interval in the previous historical charging process among multiple target historical charging processes. The original capacity of the target historical charging process is determined based on the total charge of the target historical charging process and the predicted capacity corresponding to the second SOC interval.

[0009] In an optional implementation, the step of fitting the mapping relationship between the output variable and the input variable based on multiple training samples to obtain the regression model includes: Based on the preset input variables and preset output variables, construct an initial regression model with unknown regression coefficients; An input feature matrix is ​​constructed using the input vectors of multiple training samples; The true correction factor vector is constructed using the output vectors of multiple training samples. Based on the input feature matrix and the true correction factor vector, the regression coefficients of the initial regression model are solved using the least squares method to obtain the regression model with known regression coefficients.

[0010] In an optional implementation, determining the corrected capacity of the most recent charging process based on the SOC parameter, current, and the prediction correction factor in the plurality of sets of first battery charging data includes: Based on the SOC parameters, current and prediction correction factor in the multiple sets of first battery charging data, the corrected historical power increment of multiple preset SOC intervals corresponding to the most recent charging process is determined. Based on the corrected historical power increments of the multiple preset SOC ranges, capacity prediction is performed to obtain the corrected capacity of the most recent charging process.

[0011] In an optional implementation, the method further includes: Based on the target SOH estimates of multiple target historical charging processes, a scatter plot of the SOH of the power battery is generated, and the SOH scatter plot is linearly fitted to obtain an SOH trend line. If the rate of decline of the SOH trend line exceeds a preset threshold, an early warning message is output to indicate that protective measures should be taken for the power battery.

[0012] In an optional implementation, acquiring multiple sets of second battery charging data for the power battery during each of the target historical charging processes includes: Based on the battery charging status, the vehicle operation data of the target vehicle is sampled to obtain battery charging data from multiple historical charging processes. Based on battery charging data from multiple sampled historical charging processes, an effective charging process that meets preset effective charging conditions is determined from the multiple sampled historical charging processes as the target historical charging process.

[0013] In an optional implementation, determining the effective charging process that meets preset effective charging conditions as the target historical charging process based on battery charging data from multiple sampled historical charging processes includes: Based on the battery charging data of the sampled historical charging process, determine the initial SOC parameter, SOC change parameter, and missing sampling time of the sampled historical charging process; Determine whether the initial SOC parameter of the sampled historical charging process is less than a preset SOC threshold; Determine whether the SOC change parameter of the sampled historical charging process is greater than or equal to a preset SOC change threshold; Determine whether the missing sampling time of the historical charging process is less than or equal to a preset time threshold; If the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold, the SOC change parameter is greater than or equal to the preset SOC change threshold, and the missing sampling time is less than or equal to the preset time threshold, then the sampled historical charging process is determined to meet the preset valid charging conditions.

[0014] Secondly, embodiments of this application also provide a power battery health status estimation device, the device comprising: The acquisition module is used to acquire multiple sets of first battery charging data of the target vehicle's power battery during the most recent charging process. The multiple sets of first battery charging data correspond to multiple sampling times, and each set of first battery charging data includes at least: current, state of charge (SOC) parameter, and battery temperature. The determining module is used to determine the average temperature of the most recent charging process based on the battery temperature in the multiple sets of first battery charging data; The prediction module is used to predict the most recent charging process based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process using a pre-trained regression model, and obtain the prediction correction factor of the most recent charging process; wherein, the previous charging process is the charging process of the power battery before the most recent charging process in multiple target historical charging processes. The determining module is further configured to determine the corrected capacity of the most recent charging process based on the SOC parameter, current and the prediction correction factor in the multiple sets of first battery charging data. The determining module is further configured to determine the target SOH estimate of the most recent charging process based on the corrected capacity of the most recent charging process and the rated capacity of the power battery.

[0015] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores program instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the power battery health state estimation method as described in any of the first aspects.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the power battery health state estimation method as described in any of the first aspects.

[0017] The beneficial effects of this application are: This application provides a method and electronic device for estimating the state of health (SOH) of a power battery. The method includes: acquiring multiple sets of first battery charging data for the power battery of a target vehicle during its most recent charging process, wherein the multiple sets of first battery charging data correspond to multiple sampling times, and each set of first battery charging data includes at least: current, SOC parameter, and battery temperature; determining the average temperature of the most recent charging process based on the battery temperature in the multiple sets of first battery charging data; predicting the most recent charging process using a pre-trained regression model based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, thereby obtaining a prediction correction factor for the most recent charging process; wherein the previous charging process is the charging process prior to the most recent charging process in multiple target historical charging processes; determining the corrected capacity of the most recent charging process based on the SOC parameter, current, and prediction correction factor in the multiple sets of first battery charging data; and determining the target SOH estimate of the most recent charging process based on the corrected capacity of the most recent charging process and the rated capacity of the power battery.

[0018] The method of this application uses a pre-trained regression model to predict the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, thereby obtaining a prediction correction factor for the most recent charging process. Then, based on the prediction correction factor, multiple sets of first battery charging data from the most recent charging process, and the rated capacity of the power battery, the target SOH estimate for the most recent charging process is determined. Since the average temperature of the most recent charging process and the target SOH estimate of the previous charging process are considered when estimating SOH, the bias caused by ambient temperature and degradation effects is effectively eliminated, achieving high-precision SOH estimation and solving the problems of uneven mapping between SOC and charge and insufficient modeling of temperature and aging effects in the prior art. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 One of the flowcharts for a power battery health state estimation method provided in this application embodiment; Figure 2 A second schematic flowchart illustrating a method for estimating the health status of a power battery, provided in an embodiment of this application; Figure 3 The third flowchart illustrates a method for estimating the health status of a power battery, as provided in this application embodiment. Figure 4 The fourth flowchart illustrates a method for estimating the health status of a power battery, as provided in this application embodiment. Figure 5 Fifth flowchart illustrating a method for estimating the health status of a power battery provided in this application embodiment; Figure 6 A flowchart illustrating a method for estimating the health status of a power battery, as provided in this application embodiment, is shown in Figure 6. Figure 7 The seventh flowchart illustrates a method for estimating the health status of a power battery as provided in this application embodiment; Figure 8 This is the eighth flowchart illustrating a method for estimating the health status of a power battery, provided in an embodiment of this application. Figure 9 A scatter plot of the state of harmonics (SOH) of a power battery provided in an embodiment of this application; Figure 10 A flowchart illustrating a method for estimating the health status of a power battery, as provided in this application embodiment, is shown in Figure 9. Figure 11 This is the tenth flowchart illustrating a method for estimating the health status of a power battery, as provided in an embodiment of this application. Figure 12 This is a schematic diagram of the functional modules of a power battery health status estimation device provided in an embodiment of this application; Figure 13 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0022] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0023] In the description of this application, it should be noted that if the terms "upper", "lower", etc. appear to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship that the product of this application is usually placed in, it is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0024] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0026] To accurately determine the State of Health (SOH) of the power battery of a target vehicle, this application provides a power battery health state estimation method. By determining the average temperature of the most recent charging process and using a pre-trained regression model, the method predicts the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, obtaining a prediction correction factor for the most recent charging process. Then, based on the prediction correction factor, multiple sets of first battery charging data from the most recent charging process, and the rated capacity of the power battery, the target SOH estimate for the most recent charging process is determined. Since the average temperature of the most recent charging process and the target SOH estimate of the previous charging process are considered when estimating SOH, this method can effectively solve the problems of uneven mapping between SOC and capacity and insufficient modeling of temperature and aging effects in the prior art.

[0027] The following detailed explanation, with reference to the accompanying drawings and specific examples, illustrates the power battery health status estimation method provided in this application. Figure 1 This is one of the flowcharts illustrating a method for estimating the health status of a power battery according to an embodiment of this application; as shown below. Figure 1 As shown, the method includes: S101. Obtain multiple sets of first battery charging data of the target vehicle's power battery during the most recent charging process.

[0028] Multiple sets of first battery charging data correspond to multiple sampling times. Each set of first battery charging data includes at least: current, state of charge (SOC) parameters, and battery temperature.

[0029] In this embodiment, multiple sets of first battery charging data from the most recent charging process are collected from the target vehicle's operating data, and the sampling interval is calculated. ,in If the sampling interval is greater than or equal to 2, it is considered that there is missing sampling data. The missing data is filled in by linear interpolation of the data at both ends. This can be understood as determining the missing data at the current sampling time based on the data collected at the previous sampling time and the data collected at the next sampling time.

[0030] In addition, abnormal data points in the first battery charging data of each group are searched. Since the positive and negative signs of the charging current indicate the charging and discharging direction, and the negative current indicates the discharging, the negative currents found are removed, as are the abnormal data points of SOC jumps. Then, the removed data are supplemented by linear interpolation of the data at both ends to ensure the continuity and accuracy of the subsequent integration process.

[0031] S102. Determine the average temperature of the most recent charging process based on the battery temperature in multiple sets of first battery charging data.

[0032] In this process, probes are placed in different areas of the power battery to collect battery temperature data in different areas and determine the highest temperature. and lowest temperature The battery temperature in the first battery charging data for each group includes: the highest temperature. and lowest temperature Then based on the highest temperature and lowest temperature Determine the average temperature of the most recent charging process.

[0033] For example, probes are placed in six areas of the power battery, and six battery temperature values ​​can be collected at each sampling time to determine the highest temperature. and lowest temperature The battery temperature is used as the reference for each sampling time. Then, based on the battery temperatures from multiple sets of first battery charging data, the average temperature of the most recent charging process is determined. The calculation formula is expressed as follows:

[0034] in, This represents the average of the highest temperatures across multiple sets of first battery charging data. It represents the average of the lowest temperature among multiple sets of first battery charging data.

[0035] S103. Based on the average temperature of the most recent charging process and the estimated target SOH value of the previous charging process, a pre-trained regression model is used to make a prediction, and the prediction correction factor for the most recent charging process is obtained.

[0036] Among them, the previous charging process is the charging process before the most recent charging process in the multiple target historical charging processes of the power battery.

[0037] Specifically, a pre-trained regression model is used to predict the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, thereby determining the prediction correction factor for the most recent charging process. The calculation formula is expressed as follows:

[0038] in, , and These represent the regression coefficients of a pre-trained regression model. This represents the target SOH estimate for the previous charging process.

[0039] S104. Based on the SOC parameters, current, and prediction correction factor in multiple sets of first battery charging data, determine the corrected capacity for the most recent charging process.

[0040] S105. Based on the corrected capacity of the most recent charging process and the rated capacity of the power battery, determine the target SOH estimate for the most recent charging process.

[0041] Specifically, by predicting correction factors, the SOC parameters and current in multiple sets of first battery charging data are corrected to determine the corrected capacity of the most recent charging process. Then, based on the corrected capacity of the most recent charging process and the rated capacity of the power battery, the target SOH estimate for the most recent charging process is determined. The formula for calculating the target SOH estimate is as follows:

[0042] in, This represents the corrected capacity from the most recent charging cycle. This is expressed as the rated capacity of the power battery. This represents the target SOH estimate from the most recent charging process. Comparing the corrected actual capacity with the rated capacity yields a key indicator reflecting the degree of aging of the power battery.

[0043] In summary, this application provides a method for estimating the state of health (SOH) of a power battery. The method includes: acquiring multiple sets of first battery charging data for the target vehicle's power battery during its most recent charging process. Each set of first battery charging data corresponds to multiple sampling times, and each set of first battery charging data includes at least: current, SOC parameters, and battery temperature; determining the average temperature of the most recent charging process based on the battery temperature from the multiple sets of first battery charging data; predicting the most recent charging process using a pre-trained regression model based on the average temperature of the most recent charging process and the target SOH estimate from the previous charging process, thereby obtaining a prediction correction factor for the most recent charging process; wherein the previous charging process is the charging process preceding the most recent charging process in multiple target historical charging processes; determining the corrected capacity of the most recent charging process based on the SOC parameters, current, and prediction correction factor from the multiple sets of first battery charging data; and determining the target SOH estimate for the most recent charging process based on the corrected capacity of the most recent charging process and the rated capacity of the power battery.

[0044] The method of this application uses a pre-trained regression model to predict the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, thereby obtaining a prediction correction factor for the most recent charging process. Then, based on the prediction correction factor, multiple sets of first battery charging data from the most recent charging process, and the rated capacity of the power battery, the target SOH estimate for the most recent charging process is determined. Since the average temperature of the most recent charging process and the target SOH estimate of the previous charging process are considered when estimating SOH, the bias caused by ambient temperature and degradation effects is effectively eliminated, achieving high-precision SOH estimation and solving the problems of uneven mapping between SOC and charge and insufficient modeling of temperature and aging effects in the prior art.

[0045] This application also provides another possible implementation of the power battery health state estimation method. Figure 2 This is a second flowchart illustrating a method for estimating the health status of a power battery, as provided in an embodiment of this application. Figure 2 As shown, before obtaining the prediction correction factor for the most recent charging process using a pre-trained regression model based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, the method further includes: S201. Obtain multiple sets of second battery charging data for each target historical charging process of the power battery.

[0046] Multiple sets of second battery charging data correspond to multiple sampling times. Each set of second battery charging data includes at least: current, SOC parameters, and battery temperature.

[0047] In this embodiment, the target historical charging process refers to the historical charging records used for model training. Each set of data corresponds to a sampling time point and includes: current, SOC parameters, and battery temperature.

[0048] Similarly, calculate the sampling interval. ,in If the sampling interval is greater than or equal to 2, missing data is supplemented by linear interpolation of the data at both ends. This can be understood as determining the missing data at the current sampling time based on the data collected at the previous sampling time and the data collected at the next sampling time. Additionally, abnormal data points in each group of second battery charging data are identified, such as negative current and SOC jumps, and these abnormal data points are removed. Then, the removed data is supplemented by linear interpolation of the data at both ends to ensure the continuity and accuracy of the subsequent integration process.

[0049] S202. Based on the battery temperature of multiple sets of second battery charging data, determine the average temperature of each target historical charging process.

[0050] Since the battery temperature in each set of second battery charging data includes the highest and lowest temperatures, the average highest and lowest temperatures of each target historical charging process are determined based on the highest and lowest temperatures of multiple sets of second battery charging data. Then, the average temperature of each target historical charging process is determined based on the average highest and lowest temperatures.

[0051] S203. Based on the SOC parameters and current in multiple sets of second battery charging data, determine the initial SOH estimate and the corresponding true correction factor for each target historical charging process.

[0052] Specifically, based on the SOC parameters and currents in multiple sets of second battery charging data for each target historical charging process, the initial SOH estimate for each target historical charging process is determined, and the corresponding true correction factor is calculated. The true correction factor is used to correct the deviation of the initial SOH estimate.

[0053] S204. Based on the average temperature of multiple target historical charging processes, the true correction factor, and the initial SOH estimate of the corresponding previous historical charging process, construct multiple training samples respectively.

[0054] The input variables for the training samples include the average temperature of the target historical charging process and the initial SOH estimate of the corresponding previous historical charging data. The output variable for the training samples is the true correction factor of the target historical charging process.

[0055] S205. Fit the mapping relationship between the output variable and the input variable based on multiple training samples to obtain the regression model.

[0056] Specifically, the average temperature of multiple target historical charging processes and the initial SOH estimate of the corresponding previous historical charging process are used as input variables, and the true correction factor is used as the output variable, thereby constructing multiple training samples.

[0057] Finally, by fitting the mapping relationship between the output and input variables based on multiple training samples, a regression model is obtained. This model uses the average temperature of the most recent charging process and the target SOH estimate of the previous charging process as input variables, and then predicts the corresponding prediction correction factor as the output.

[0058] The method provided in this application involves acquiring multiple sets of second battery charging data for each target historical charging process. These multiple sets of second battery charging data correspond to multiple sampling times, and each set includes at least: current, SOC parameter, and battery temperature. Based on the battery temperature from the multiple sets of second battery charging data, the average temperature of each target historical charging process is determined. Based on the SOC parameter and current from the multiple sets of second battery charging data, the initial SOH estimate and corresponding true correction factor for each target historical charging process are determined. Multiple training samples are constructed based on the average temperature, true correction factor, and the initial SOH estimate of the corresponding previous historical charging process for each target historical charging process. The input variables of the training samples include: the average temperature of the target historical charging process and the initial SOH estimate of the corresponding previous historical charging data. The output variable of the training samples is the true correction factor for the target historical charging process. A regression model is obtained by fitting the mapping relationship between the output and input variables using the multiple training samples. By training the regression model using multiple sets of second battery charging data for each target historical charging process, the regression model can be used to predict the corrector, ensuring that the prediction result can correct the deviation of the initial SOH estimate and improve the accuracy of the SOH estimate.

[0059] This application also provides another possible implementation of the power battery health state estimation method. Figure 3 This is the third flowchart illustrating a method for estimating the health status of a power battery according to an embodiment of this application. Figure 3 As shown, based on the SOC parameters and currents from multiple sets of second battery charging data, the initial SOH estimate and corresponding true correction factor for each target historical charging process are determined, including: S301. Based on the SOC parameters and current in multiple sets of second battery charging data, determine the power information of multiple first SOC intervals involved in the target historical charging process.

[0060] In this embodiment, the target historical charging process is divided into multiple intervals, for example, with an interval of λ, from... Starting from the lower limit threshold of the parameter, set the current battery level and... The difference range of the parameters is 0-λ, λ-2λ, ..., n-1λ-nλ, thus dividing the SOC parameters of the target historical charging process into N first SOC intervals.

[0061] Then, based on the SOC parameters and current in multiple sets of second battery charging data, the power information of multiple first SOC intervals involved in the target historical charging process is determined. Taking the j-th target historical charging process as an example, the power information of multiple first SOC intervals is determined based on the SOC parameters and current in multiple sets of second battery charging data corresponding to the j-th target historical charging process.

[0062] Specifically, the formula for calculating the battery level information in the first SOC range is as follows:

[0063] in, This represents the power information of the i-th SOC interval during the j-th target historical charging process. Let SOC be the starting SOC parameter of the i-th SOC interval. This represents the end SOC parameter of the i-th SOC interval. This represents the current in the second battery charging data corresponding to the i-th SOC interval. Therefore, based on the above formula, the power information of each first SOC interval involved in the historical charging process of each target can be determined.

[0064] S302. Determine the total charge of the target historical charging process based on the charge information of multiple first SOC intervals.

[0065] Specifically, the total charge amount of the target historical charging process is determined by integrating the charge information from multiple first SOC intervals. The formula for calculating the total charge amount of the target historical charging process is as follows:

[0066] in, This represents the total amount of electricity charged during the target's historical charging process. This is represented as battery information for multiple first SOC intervals. This means that parameter k is the starting SOC interval among multiple first SOC intervals. This is represented by parameter k being the end SOC interval among multiple first SOC intervals, thus obtaining the total amount of electricity in the historical charging process of each target.

[0067] S303. Based on the total charge of the target historical charging process, the rated capacity of the power battery, the end SOC parameter and the start SOC parameter of the target historical charging process, determine the initial SOH estimate of the target historical charging process.

[0068] Specifically, the formula for calculating the initial SOH estimate is as follows:

[0069] in, This is represented as the initial SOH estimate. This represents the total amount of electricity charged during the target's historical charging process. This is expressed as the rated capacity of the power battery. In this case, in the formula for calculating the initial SOH estimate... This represents the final SOC parameter of the target historical charging process. This is represented by the initial SOC parameter of the target historical charging process, thereby determining the initial SOH estimate for each target historical charging process.

[0070] S304. Based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, perform capacity prediction for the target historical charging process to obtain the historical predicted capacity of the target historical charging process.

[0071] S305. Determine the original capacity of the target historical charging process based on the total amount of electricity generated during the target historical charging process.

[0072] S306. Based on the historical predicted capacity and original capacity of the target historical charging process, determine the true correction factor of the target historical charging process.

[0073] Specifically, by determining the historical predicted capacity and original capacity of the target historical charging process, the true correction factor of the target historical charging process is determined. The formula for calculating the true correction factor of the target historical charging process is as follows:

[0074] in, Represented as the true correction factor. Represented as the original capacity, This is represented as historical predicted capacity.

[0075] The method provided in this application embodiment involves determining the energy information of multiple first SOC intervals involved in the target historical charging process based on the SOC parameters and current in multiple sets of second battery charging data; determining the total energy of the target historical charging process based on the energy information of multiple first SOC intervals; determining the initial SOH estimate of the target historical charging process based on the total energy of the target historical charging process, the rated capacity of the power battery, the end SOC parameter and the start SOC parameter of the target historical charging process; predicting the capacity of the target historical charging process based on the energy information of each first SOC interval and the corresponding energy information of the same SOC interval in the previous historical charging process to obtain the historical predicted capacity of the target historical charging process; determining the original capacity of the target historical charging process based on the total energy of the target historical charging process; and determining the true correction factor of the target historical charging process based on the historical predicted capacity and the original capacity of the target historical charging process. By calculating the power information of multiple first SOC intervals, the total power of the target historical charging process is further calculated and determined. Then, the initial SOH estimate of the target historical charging process is calculated. In addition, the historical predicted capacity and original capacity of the target historical charging process are calculated, and the true correction factor of the target historical charging process is determined. The initial SOH and correction factor will be used as the input and output of the training samples to build a regression model to achieve the prediction of capacity deviation under different temperatures and SOH.

[0076] This application also provides another possible implementation of the power battery health state estimation method. Figure 4 This is the fourth flowchart illustrating a method for estimating the health status of a power battery, as provided in this application embodiment. Figure 4 As shown, based on the power information of each first SOC interval and the power information of the same SOC interval in the corresponding previous historical charging process, the capacity of the target historical charging process is predicted to obtain the historical predicted capacity of the target historical charging process, including: S401. Based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, determine the historical power increment of each first SOC interval.

[0077] S402. Based on the historical power increment of multiple first SOC intervals, perform capacity prediction for the target historical charging process to obtain the historical predicted capacity of the target historical charging process.

[0078] In this embodiment, the historical power increment of each first SOC interval is determined based on the power information of each first SOC interval, the power information of the same SOC interval in the previous historical charging process, and the historical power increment function.

[0079] The historical electricity increment function is expressed as:

[0080] in, Let be the historical power increment function for the i-th SOC interval during the j-th historical charging process. This represents the power information for the i-th SOC interval during the (j-1)-th historical charging process. This represents the power information for the i-th SOC interval during the j-th historical charging process. Let be the difference between the end SOC parameter and the start SOC parameter of the i-th SOC interval. The iteration parameter is in the range of 0-1, and i takes values ​​from 0 to N sequentially. This determines the historical power increment for each first SOC interval.

[0081] It should be noted that if the target historical charging process does not involve a SOC range, then the historical power increment of that SOC range is the historical power increment of the same SOC range in the previous historical charging process.

[0082] The formula for calculating historical forecast capacity is as follows:

[0083] in, This represents the historical predicted capacity for the target's historical charging process. It represents the historical power increment of the i-th SOC interval.

[0084] The method provided in this application determines the historical capacity increment of each first SOC interval based on the capacity information of each first SOC interval and the capacity information of the same SOC interval in the previous historical charging process. Based on the historical capacity increments of multiple first SOC intervals, capacity prediction is performed for each target historical charging process to obtain the historical predicted capacity of the target historical charging process. Battery capacity decay or fluctuation typically manifests differently in different SOC intervals. By comparing the capacity changes (i.e., capacity increments) in the same SOC interval during adjacent charging processes, the capacity change trend can be captured more precisely. For example, if the capacity increment of a certain interval is negative, it indicates that the capacity of that interval has decreased compared to the previous charge. Accumulating the increments of all intervals reflects the overall capacity change. Compared to directly using a single parameter to predict capacity, SOC interval-based increment analysis can more accurately consider the characteristic differences of the battery under different states, and is suitable for scenarios where the capacity distribution is uneven during battery aging.

[0085] This application also provides another possible implementation of the power battery health state estimation method. Figure 5 This is the fifth flowchart illustrating a method for estimating the health status of a power battery, as provided in the embodiments of this application. Figure 5As shown, the original capacity of the target historical charging process is determined based on the total amount of electricity charged during the target historical charging process, including: S501. If there is a second SOC interval that is not involved in the target historical charging process among multiple preset SOC intervals, then the predicted capacity corresponding to the second SOC interval is determined based on the historical incremental power information of the same SOC interval in the previous historical charging process among multiple target historical charging processes.

[0086] S502. Determine the original capacity of the target historical charging process based on the total amount of electricity generated during the target historical charging process and the predicted capacity corresponding to the second SOC interval.

[0087] In this embodiment, the original capacity calculation formula is expressed as:

[0088] in, This represents the original capacity for the target's historical charging process. This represents the total amount of electricity charged during the target's historical charging process. It is represented as the prediction capacity corresponding to m second SOC intervals.

[0089] In the method provided in this application embodiment, if there is a second SOC interval not covered in the target historical charging process among multiple preset SOC intervals, the predicted capacity corresponding to the second SOC interval is determined based on the historical incremental capacity information of the same SOC interval in previous historical charging processes among the multiple target historical charging processes; the original capacity of the target historical charging process is determined based on the total capacity of the target historical charging process and the predicted capacity corresponding to the second SOC interval. The original capacity represents the theoretical capacity that the battery can hold during a complete charging process, and it needs to cover all preset SOC intervals. Even if the current charging does not cover the second SOC interval, it needs to be supplemented by prediction using historical data to ensure the accuracy of subsequent SOH calculations.

[0090] This application also provides another possible implementation of the power battery health state estimation method. Figure 6 This is the sixth flowchart illustrating a method for estimating the health status of a power battery, as provided in this application embodiment. Figure 6 As shown, a regression model is obtained by fitting the mapping relationship between the output variable and the input variable based on multiple training samples, including: S601. Based on the preset input variables and preset output variables, construct an initial regression model with unknown regression coefficients.

[0091] S602. Construct an input feature matrix using the input vectors of multiple training samples.

[0092] S603. Construct the true correction factor vector using the output vectors of multiple training samples.

[0093] S604. Based on the input feature matrix and the true correction factor vector, the regression coefficients of the initial regression model are solved using the least squares method to obtain a regression model with known regression coefficients.

[0094] In this embodiment, the preset input variables include: the average temperature of the target historical charging process and the initial SOH estimate of the corresponding previous historical charging data, expressed as: The output variable is assumed to be the true correction factor. The initial regression model with unknown regression coefficients is represented as follows:

[0095] The input feature matrix is ​​represented as follows:

[0096] The true correction factor vector is represented as:

[0097] The solution to the normal equation is expressed as: .

[0098] Solving using the least squares method, the objective function is:

[0099] The regression coefficients are finally obtained by solving the problem. = Then, a regression model with known regression coefficients is obtained through training.

[0100] The method provided in this application involves constructing an initial regression model with unknown regression coefficients based on preset input and output variables; constructing an input feature matrix using input vectors from multiple training samples; constructing a true correction factor vector using output vectors from multiple training samples; and solving for the regression coefficients of the initial regression model using the least squares method based on the input feature matrix and the true correction factor vector to obtain a regression model with known regression coefficients. By assuming a correlation between input and output, the input and output vectors are transformed into matrix vectors to adapt to mathematical operations. Finally, the optimal parameters are found using the least squares method, enabling the model to accurately fit the mapping relationship in historical data. This allows the regression model to be used to directly predict the correction factor given the average temperature of a new charging process and the previous SOH, providing key parameters for subsequent SOH estimation.

[0101] This application also provides another possible implementation of the power battery health state estimation method. Figure 7 This is the seventh flowchart illustrating a method for estimating the health status of a power battery, as provided in this application embodiment. Figure 7As shown, based on the SOC parameters, current, and prediction correction factors in multiple sets of first battery charging data, the corrected capacity for the most recent charging process is determined, including: S701. Based on the SOC parameters, current and prediction correction factor in multiple sets of first battery charging data, determine the corrected historical power increment of multiple preset SOC intervals corresponding to the most recent charging process.

[0102] In this embodiment, the historical power increment function is determined by the SOC parameters and current in multiple sets of first battery charging data. Then, the historical power increment function is multiplied by a prediction correction factor to obtain the corrected and updated historical power increment function. This yields corrected historical power increments for multiple preset SOC intervals. Represented as:

[0103] in, Let be the historical power increment function for the i-th preset SOC interval during the j-th charging process. This is represented as the prediction correction factor.

[0104] S702. Based on the historical power increment of multiple preset SOC ranges, the capacity is predicted to obtain the corrected capacity of the most recent charging process.

[0105] The corrected capacity calculation formula is expressed as follows:

[0106] In the method provided in this application embodiment, the corrected historical power increment of multiple preset SOC intervals corresponding to the most recent charging process is determined based on the SOC parameters, current and prediction correction factor in multiple sets of first battery charging data; the capacity is predicted based on the corrected historical power increment of multiple preset SOC intervals to obtain the corrected capacity of the most recent charging process, thereby determining the corrected capacity of the most recent charging process based on the SOC parameters, current and prediction correction factor in multiple sets of first battery charging data.

[0107] This application also provides another possible implementation of the power battery health state estimation method. Figure 8 This is the eighth flowchart illustrating a method for estimating the health status of a power battery, as provided in an embodiment of this application. Figure 9 A scatter plot of the state of harmonics (SOH) of a power battery provided in an embodiment of this application is shown below. Figure 8 As shown, the method also includes: S801. Based on the target SOH estimates of multiple target historical charging processes, generate a scatter plot of the SOH of the power battery, and perform linear fitting on the SOH scatter plot to obtain the SOH trend line.

[0108] S802. If the rate of decline of the SOH trend line exceeds the preset threshold, an early warning message will be output to indicate that protective measures should be taken for the power battery.

[0109] In this embodiment, the final output is the target SOH estimate of multiple target historical charging processes, and the target SOH estimate is plotted as a scatter plot over time, as shown below. Figure 9 As shown. The trend of the SOH estimate fitted by linear regression is expressed as follows:

[0110] in, Let γ represent the rate of decrease of SOH, and γ be the ordinate of the fitted line. If the value is below a preset threshold, the system can trigger an early warning, prompting the user to take protective measures for the power battery.

[0111] In the method provided in this application embodiment, a scatter plot of the SOH of the power battery is generated based on the target SOH estimates of multiple target historical charging processes, and a linear fit is performed on the SOH scatter plot to obtain an SOH trend line. If the rate of decline of the SOH trend line exceeds a preset threshold, an early warning message is output to indicate that protective measures should be taken for the power battery. The scatter plot and trend line intuitively display the battery aging process, helping personnel to quickly judge the health status of the power battery. By monitoring the rate, potential problems can be discovered before the SOH reaches the retirement threshold, thus avoiding sudden failures.

[0112] This application also provides another possible implementation of the power battery health state estimation method. Figure 10 This is the ninth flowchart illustrating a method for estimating the health status of a power battery, as provided in this application embodiment. Figure 10 As shown, multiple sets of second battery charging data are acquired for each target historical charging process, including: S901. Based on the battery charging status, sample the vehicle operation data of the target vehicle to obtain battery charging data from multiple historical charging processes.

[0113] S902. Based on battery charging data from multiple sampled historical charging processes, determine the effective charging process that meets the preset effective charging conditions from the multiple sampled historical charging processes as the target historical charging process.

[0114] In this embodiment, the battery charging state refers to the state in which the power battery is charging, including the entire process from the start of charging to the end of charging. Vehicle operation data of the target vehicle in the charging state is sampled to obtain battery charging data from multiple historical charging processes.

[0115] However, some historical charging processes may be incomplete, such as starting charging from a SOC parameter of 30% and ending charging from a SOC parameter of 50%. Therefore, it is necessary to determine whether multiple historical charging processes meet the preset valid charging conditions and to use the valid charging processes that meet the preset valid charging conditions as the target historical charging processes.

[0116] In the method provided in this application embodiment, the vehicle operation data of the target vehicle is sampled according to the battery charging state to obtain battery charging data of multiple sampled historical charging processes; based on the battery charging data of multiple sampled historical charging processes, the effective charging process that meets the preset effective charging conditions is determined from the multiple sampled historical charging processes as the target historical charging process. The selected target historical charging process belongs to the effective charging process, which can better estimate the health state of the power battery.

[0117] This application also provides another possible implementation of the power battery health state estimation method. Figure 11 This is the tenth flowchart illustrating a method for estimating the health status of a power battery according to an embodiment of this application. Figure 11 As shown, based on battery charging data from multiple sampled historical charging processes, the effective charging process that meets preset effective charging conditions is determined as the target historical charging process, including: S1001. Based on the battery charging data of the historical charging process, determine the initial SOC parameter, SOC change parameter, and missing sampling time of the historical charging process.

[0118] S1002. Determine whether the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold.

[0119] S1003. Determine whether the SOC change parameter of the historical charging process is greater than or equal to the preset SOC change threshold.

[0120] S1004. Determine whether the missing sampling time of the historical charging process is less than or equal to the preset time threshold. S1005. If the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold, the SOC change parameter is greater than or equal to the preset SOC change threshold, and the missing sampling time is less than or equal to the preset time threshold, then the sampled historical charging process is determined to meet the preset valid charging conditions.

[0121] In this embodiment, the preset valid charging conditions are determined as follows: the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold, the SOC change parameter is greater than or equal to the preset SOC change threshold, and the missing sampling time is less than or equal to the preset time threshold. Only when the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold, the SOC change parameter is greater than or equal to the preset SOC change threshold, and the missing sampling time is less than or equal to the preset time threshold, is the sampled historical charging process determined as the target historical charging process.

[0122] For example, the preset SOC threshold is 30%, the preset SOC change threshold is 30%, and the preset time threshold is 300 seconds. This is based on the initial SOC parameter of a sampled historical charging process. SOC variation parameters If the missing sampling time is ≤300 seconds, then the sampled historical charging process is determined to be the target historical charging process.

[0123] It is necessary to use the OCV-SOC curve of the vehicle battery to avoid SOC measurement errors due to the plateau effect; Taking a larger value can reduce random errors in a single charging process; however, if the cumulative sampling time of the entire charging segment is too long, it may lead to large errors. Therefore, preset effective charging conditions are set to filter target historical charging processes. It is essential to ensure that the data used for training has sufficient information and completeness, avoiding low-quality samples such as low-charge charging and data fragmentation from interfering with the model.

[0124] The following will continue to explain the power battery health status estimation device and electronic device provided in any of the above embodiments of this application. The specific implementation process and the resulting technical effects are the same as those in the corresponding method embodiments. For the sake of brevity, the parts not mentioned in this embodiment can be referred to the corresponding content in the method embodiment.

[0125] Figure 12 This is a functional module diagram of a power battery health status estimation device provided in an embodiment of this application. Figure 12 As shown, the power battery health status estimation device 100 includes: The acquisition module 110 is used to acquire multiple sets of first battery charging data of the target vehicle's power battery during the most recent charging process. The multiple sets of first battery charging data correspond to multiple sampling times. Each set of first battery charging data includes at least: current, state of charge (SOC) parameter, and battery temperature. The determination module 120 is used to determine the average temperature of the most recent charging process based on the battery temperature in multiple sets of first battery charging data. The prediction module 130 is used to make a prediction based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process using a pre-trained regression model, and obtain the prediction correction factor for the most recent charging process; wherein, the previous charging process is the charging process of the power battery before the most recent charging process in multiple target historical charging processes. The determination module 120 is also used to determine the corrected capacity of the most recent charging process based on the SOC parameters, current and prediction correction factor in multiple sets of first battery charging data. The determination module 120 is also used to determine the target SOH estimate for the most recent charging process based on the corrected capacity of the most recent charging process and the rated capacity of the power battery.

[0126] Optionally, the device further includes: The acquisition module 110 is also used to acquire multiple sets of second battery charging data of the power battery in each target historical charging process. The multiple sets of second battery charging data correspond to multiple sampling times. Each set of second battery charging data includes at least: current, SOC parameters and battery temperature. The determination module 120 is also used to determine the average temperature of each target historical charging process based on the battery temperature of multiple sets of second battery charging data. The determination module 120 is also used to determine the initial SOH estimate and the corresponding true correction factor for each target historical charging process based on the SOC parameters and current in multiple sets of second battery charging data. The construction module is used to construct multiple training samples based on the average temperature of multiple target historical charging processes, the true correction factor, and the initial SOH estimate of the corresponding previous historical charging process. The input variables of the training samples include the average temperature of the target historical charging process and the initial SOH estimate of the corresponding previous historical charging data. The output variable of the training samples is the true correction factor of the target historical charging process. The determination module 120 is also used to fit the mapping relationship between the output variable and the input variable based on multiple training samples to obtain a regression model.

[0127] Optionally, the determining module 120 is further configured to: determine the power information of multiple first SOC intervals involved in the target historical charging process based on the SOC parameters and current in multiple sets of second battery charging data; determine the total power of the target historical charging process based on the power information of multiple first SOC intervals; determine the initial SOH estimate of the target historical charging process based on the total power of the target historical charging process, the rated capacity of the power battery, the end SOC parameter and the start SOC parameter of the target historical charging process; perform capacity prediction on the target historical charging process based on the power information of each first SOC interval and the power information of the same SOC interval in the corresponding previous historical charging process, to obtain the historical predicted capacity of the target historical charging process; determine the original capacity of the target historical charging process based on the total power of the target historical charging process; and determine the true correction factor of the target historical charging process based on the historical predicted capacity and the original capacity of the target historical charging process.

[0128] Optionally, the prediction module 130 is further configured to determine the historical power increment of each first SOC interval based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process; and to perform capacity prediction for each target historical charging process based on the historical power increments of multiple first SOC intervals to obtain the historical predicted capacity of the target historical charging process.

[0129] Optionally, the determining module 120 is further configured to, if there is a second SOC interval not covered by the target historical charging process among the multiple preset SOC intervals, determine the predicted capacity corresponding to the second SOC interval based on the historical incremental power information of the same SOC interval in the previous historical charging process among the multiple target historical charging processes; and determine the original capacity of the target historical charging process based on the total power of the target historical charging process and the predicted capacity corresponding to the second SOC interval.

[0130] Optionally, the determining module 120 is also used to construct an initial regression model with unknown regression coefficients based on preset input variables and preset output variables; construct an input feature matrix using input vectors of multiple training samples; construct a true correction factor vector using output vectors of multiple training samples; and solve for the regression coefficients of the initial regression model using the least squares method based on the input feature matrix and the true correction factor vector to obtain a regression model with known regression coefficients.

[0131] Optionally, the determining module 120 is further configured to determine the corrected historical power increment of multiple preset SOC intervals corresponding to the most recent charging process based on the SOC parameters, current and prediction correction factor in multiple sets of first battery charging data; and to perform capacity prediction based on the corrected historical power increment of multiple preset SOC intervals to obtain the corrected capacity of the most recent charging process.

[0132] Optionally, the device further includes: The generation module is used to generate a scatter plot of the SOH of the power battery based on the target SOH estimates of multiple target historical charging processes, and to perform linear fitting on the SOH scatter plot to obtain the SOH trend line. The output module is used to output a warning message if the rate of decline of the SOH trend line exceeds a preset threshold, so as to indicate that protective measures should be taken for the power battery.

[0133] Optionally, the acquisition module 110 is further configured to sample the vehicle operation data of the target vehicle according to the battery charging status to obtain battery charging data of multiple sampled historical charging processes; and to determine the effective charging process that meets the preset effective charging conditions from the multiple sampled historical charging processes as the target historical charging process based on the battery charging data of the multiple sampled historical charging processes.

[0134] Optionally, the determining module 120 is further configured to, based on the battery charging data of the sampled historical charging process, determine the initial SOC parameter, SOC change parameter, and missing sampling time of the sampled historical charging process; determine whether the initial SOC parameter of the sampled historical charging process is less than a preset SOC threshold; determine whether the SOC change parameter of the sampled historical charging process is greater than or equal to a preset SOC change threshold; determine whether the missing sampling time of the sampled historical charging process is less than or equal to a preset time threshold; if the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold, the SOC change parameter is greater than or equal to the preset SOC change threshold, and the missing sampling time is less than or equal to the preset time threshold, then it is determined that the sampled historical charging process meets the preset valid charging conditions.

[0135] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0136] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0137] Figure 13 This is a schematic diagram of an electronic device provided in an embodiment of this application. This electronic device can be used for estimating the health status of a power battery. Figure 13 As shown, the electronic device includes: a processor 210, a storage medium 220, and a bus 230.

[0138] Storage medium 220 stores machine-readable instructions executable by processor 210. When the electronic device is running, processor 210 communicates with storage medium 220 via bus 230, and processor 210 executes the machine-readable instructions to perform the steps of the above method embodiment. The specific implementation and technical effects are similar and will not be described again here.

[0139] Optionally, this application also provides a storage medium 220, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the above-described method embodiments. The specific implementation and technical effects are similar, and will not be repeated here.

[0140] In the several embodiments provided by this invention, 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 units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units 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 units may be electrical, mechanical, or other forms.

[0141] The units described as separate components may or may not be physically separate. The 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0142] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0143] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, 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 the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0144] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for estimating the health status of a power battery, characterized in that, The method includes: Acquire multiple sets of first battery charging data of the target vehicle's power battery during the most recent charging process. The multiple sets of first battery charging data correspond to multiple sampling times. Each set of first battery charging data includes at least: current, state of charge (SOC) parameter, and battery temperature. The average temperature of the most recent charging process is determined based on the battery temperature in the multiple sets of first battery charging data. Based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, a pre-trained regression model is used to make a prediction and obtain the prediction correction factor for the most recent charging process; wherein, the previous charging process is the charging process of the power battery before the most recent charging process in multiple target historical charging processes. Based on the SOC parameters, current, and prediction correction factor in the multiple sets of first battery charging data, the corrected capacity of the most recent charging process is determined. The target SOH estimate for the most recent charging process is determined based on the corrected capacity of the most recent charging process and the rated capacity of the power battery.

2. The method according to claim 1, characterized in that, Before obtaining the prediction correction factor for the most recent charging process by using a pre-trained regression model to predict based on the average temperature of the most recent charging process and the target SOH estimate of the previous charging process, the method further includes: Acquire multiple sets of second battery charging data for the power battery during each target historical charging process. The multiple sets of second battery charging data correspond to multiple sampling times. Each set of second battery charging data includes at least: current, SOC parameter and battery temperature. Based on the battery temperature of the multiple sets of second battery charging data, determine the average temperature of each of the target historical charging processes; Based on the SOC parameters and current in the multiple sets of second battery charging data, the initial SOH estimate and the corresponding true correction factor for each target historical charging process are determined respectively. Multiple training samples are constructed based on the average temperature of the target historical charging process, the true correction factor, and the initial SOH estimate of the corresponding previous historical charging process. The input variables of the training samples include the average temperature of the target historical charging process and the initial SOH estimate of the corresponding previous historical charging data. The output variable of the training samples is the true correction factor of the target historical charging process. The regression model is obtained by fitting the mapping relationship between the output variable and the input variable based on multiple training samples.

3. The method according to claim 2, characterized in that, The step of determining the initial SOH estimate and corresponding true correction factor for each target historical charging process based on the SOC parameters and current in the multiple sets of second battery charging data includes: Based on the SOC parameters and current in the multiple sets of second battery charging data, determine the power information of multiple first SOC intervals involved in the target historical charging process; Based on the power information of the multiple first SOC intervals, the total power of the target historical charging process is determined; Based on the total charge of the target historical charging process, the rated capacity of the power battery, the end SOC parameter and the start SOC parameter of the target historical charging process, determine the initial SOH estimate of the target historical charging process; Based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, the capacity of the target historical charging process is predicted to obtain the historical predicted capacity of the target historical charging process. The original capacity of the target historical charging process is determined based on the total amount of electricity charged during the target historical charging process. Based on the historical predicted capacity and the original capacity of the target historical charging process, the true correction factor of the target historical charging process is determined.

4. The method according to claim 3, characterized in that, The step of predicting the capacity of the target historical charging process based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, to obtain the historical predicted capacity of the target historical charging process, includes: Based on the power information of each first SOC interval and the power information of the same SOC interval in the previous historical charging process, the historical power increment of each first SOC interval is determined. Based on the historical power increment of the plurality of first SOC intervals, capacity prediction is performed for each of the target historical charging processes to obtain the historical predicted capacity of the target historical charging process.

5. The method according to claim 3, characterized in that, Determining the original capacity of the target historical charging process based on the total amount of electricity charged during the target historical charging process includes: If there is a second SOC interval that is not involved in the target historical charging process among multiple preset SOC intervals, then the predicted capacity corresponding to the second SOC interval is determined based on the historical incremental power information of the same SOC interval in the previous historical charging process among multiple target historical charging processes. The original capacity of the target historical charging process is determined based on the total charge of the target historical charging process and the predicted capacity corresponding to the second SOC interval.

6. The method according to claim 2, characterized in that, The step of fitting the mapping relationship between the output variable and the input variable based on multiple training samples to obtain the regression model includes: Based on the preset input variables and preset output variables, construct an initial regression model with unknown regression coefficients; An input feature matrix is ​​constructed using the input vectors of multiple training samples; The true correction factor vector is constructed using the output vectors of multiple training samples. Based on the input feature matrix and the true correction factor vector, the regression coefficients of the initial regression model are solved using the least squares method to obtain the regression model with known regression coefficients.

7. The method according to claim 1, characterized in that, The step of determining the corrected capacity of the most recent charging process based on the SOC parameter, current, and the prediction correction factor in the multiple sets of first battery charging data includes: Based on the SOC parameters, current and prediction correction factor in the multiple sets of first battery charging data, the corrected historical power increment of multiple preset SOC intervals corresponding to the most recent charging process is determined. Based on the corrected historical power increments of the multiple preset SOC ranges, capacity prediction is performed to obtain the corrected capacity of the most recent charging process.

8. The method according to claim 1, characterized in that, The method further includes: Based on the target SOH estimates of multiple target historical charging processes, a scatter plot of the SOH of the power battery is generated, and a linear fit is performed on the SOH scatter plot to obtain an SOH trend line. If the rate of decline of the SOH trend line exceeds a preset threshold, an early warning message is output to indicate that protective measures should be taken for the power battery.

9. The method according to claim 2, characterized in that, The acquisition of multiple sets of second battery charging data for the power battery in each of the target historical charging processes includes: Based on the battery charging status, the vehicle operation data of the target vehicle is sampled to obtain battery charging data from multiple historical charging processes. Based on battery charging data from multiple sampled historical charging processes, an effective charging process that meets preset effective charging conditions is determined from the multiple sampled historical charging processes as the target historical charging process.

10. The method according to claim 9, characterized in that, The step of determining the effective charging process that meets the preset effective charging conditions as the target historical charging process based on battery charging data from multiple sampled historical charging processes includes: Based on the battery charging data of the sampled historical charging process, determine the initial SOC parameter, SOC change parameter, and missing sampling time of the sampled historical charging process; Determine whether the initial SOC parameter of the sampled historical charging process is less than a preset SOC threshold; Determine whether the SOC change parameter of the sampled historical charging process is greater than or equal to a preset SOC change threshold; Determine whether the missing sampling time of the historical charging process is less than or equal to a preset time threshold; If the initial SOC parameter of the sampled historical charging process is less than the preset SOC threshold, the SOC change parameter is greater than or equal to the preset SOC change threshold, and the missing sampling time is less than or equal to the preset time threshold, then the sampled historical charging process is determined to meet the preset valid charging conditions.

11. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus. The storage medium stores program instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus. The processor executes the program instructions to perform the steps of the power battery health state estimation method as described in any one of claims 1-10.

Images