Method, device and equipment for determining health state of battery
By acquiring the target aging characteristics of the battery and combining the health status prediction model and online estimation strategy, multiple sub-health status are combined to solve the problem of low accuracy in determining the battery health status, achieving higher accuracy of battery health status and extended service life .
Patent Information
- Application Number
- CN202411400364.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2024-12-06
AI Technical Summary
The accuracy of determining the health status of batteries in the prior art is mainly due to the fact that the estimation of battery aging characteristics depends on the direct online estimation strategy, and the lack of effective historical data fusion and multi-dimensional feature analysis.
By obtaining the target aging characteristics of the battery, input them into the health status prediction model, combining the online estimation strategy, multiple sub-health statuses are fused, and time-sequential two-dimensional tensor characteristics and capacity increment curve analysis are used to improve the accuracy of the battery's health status.
The accuracy of the battery health status is significantly improved. By integrating prediction models and online estimation strategies, the prediction accuracy of the battery aging degree is improved and the battery life is extended.
Smart Images

Figure CN119087236A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of vehicle technology, and in particular, relates to a method, device and apparatus for determining the health status of a battery. Background Art
[0002] With the rapid development of vehicle technology and the improvement of people's environmental awareness, electric vehicles with advantages such as zero emission, low pollution and high energy utilization are becoming more and more popular. Among them, batteries are a vital component of electric vehicles, which mainly provide energy for the drive motor of the electric vehicle so that the drive motor drives the electric vehicle to travel.
[0003] At present, in the battery management process of electric vehicles, the battery life is usually evaluated based on the battery's state of health (SOH). However, in the related art, the determination of the battery's SOH is only directly estimated through the SOH online estimation strategy, which makes the accuracy of the determined battery SOH low. Summary of the invention
[0004] The embodiments of the present application provide a method, device and apparatus for determining the health state of a battery, which can improve the accuracy of the determined battery SOH.
[0005] In a first aspect, an embodiment of the present application provides a method for determining a health status of a battery, the method comprising:
[0006] Acquire a target aging feature of the first battery, where the target aging feature is a feature related to the aging degree of the first battery;
[0007] Inputting the target aging feature into a health state prediction model to obtain a first health state output by the health state prediction model, wherein the health state prediction model is trained based on sample data, and the sample data includes a historical aging feature of the second battery and a corresponding historical health state, and the historical health state is a health state of the second battery calculated by an online health state estimation strategy when the historical aging feature is obtained;
[0008] Obtaining a second health state of the first battery by estimating the health state online estimation strategy;
[0009] The first health state and the second health state are integrated to obtain a target health state of the first battery.
[0010] In some embodiments, the health status online estimation strategy includes a first estimation strategy,
[0011] The calculating the second health state of the first battery by using the health state online estimation strategy includes:
[0012] Acquire a first state of charge of the first battery at a first time point under a target operating condition, and acquire a second state of charge of the first battery at a second time point under the target operating condition, wherein the target operating condition is a charging operating condition or a discharging operating condition, and the second time point is after the first time point;
[0013] Obtaining a capacity change value of the first battery between the first time point and the second time point;
[0014] estimating a first sub-state of health of the first battery according to the first state of charge, the second state of charge, and the capacity change value,
[0015] The second health state includes the first sub-health state.
[0016] In some embodiments, the health status online estimation strategy includes a second estimation strategy,
[0017] The calculating the second health state of the first battery by using the health state online estimation strategy includes:
[0018] Obtaining a capacity increment curve of the first battery under target operating conditions;
[0019] According to the characteristic voltage point in the capacity increment curve, the curve area corresponding to the capacity increment curve is divided to obtain a plurality of sub-areas, wherein the characteristic voltage point is a voltage point corresponding to a local minimum value in the capacity increment curve;
[0020] Determine the coverage area of each of the multiple sub-regions;
[0021] estimating a second sub-health state of the first battery according to a coverage area of each of the multiple sub-areas,
[0022] The second health state includes the second sub-health state.
[0023] In some embodiments, the characteristic voltage point includes a first voltage point and a second voltage point, the plurality of sub-regions include a first sub-region, a second sub-region, and a third sub-region, the first sub-region is located before the first voltage point, the second sub-region is located between the first voltage point and the second voltage point, and the third sub-region is located after the second voltage point.
[0024] The determining the coverage area of each of the multiple sub-areas comprises:
[0025] Performing a capacity increment analysis on the capacity increment curve to obtain a coverage area of the second sub-region and a coverage area of the third sub-region;
[0026] The coverage area of the first sub-area is determined according to the coverage area of the second sub-area.
[0027] In some implementations, determining the coverage area of the first sub-area according to the coverage area of the second sub-area includes:
[0028] The product of the target ratio and the first initial coverage area corresponding to the first sub-region is determined as the coverage area of the first sub-region, wherein the target ratio is the ratio between the coverage area of the second sub-region and the second initial coverage area, the first initial coverage area is the coverage area of the area corresponding to the first sub-region in the capacity increment curve of the first battery when aging has not occurred, and the second initial coverage area is the coverage area of the area corresponding to the second sub-region in the capacity increment curve of the first battery when aging has not occurred.
[0029] In some implementations, estimating the second sub-health state of the first battery according to the coverage area of each of the multiple sub-areas includes:
[0030] The sum of the coverage areas of the multiple sub-regions is determined as the second sub-health state of the first battery.
[0031] In some embodiments, the second health state includes a first sub-health state and a second sub-health state, the first sub-health state is estimated by a first estimation strategy, and the second sub-health state is estimated by a second estimation strategy.
[0032] The fusing the first health state and the second health state to obtain a target health state of the first battery includes:
[0033] A target health state of the first battery is calculated according to the first sub-health state, the second sub-health state, the first health state, and corresponding weights.
[0034] In some embodiments, the target aging feature includes at least one of the following:
[0035] Features of a long-period feature set, the long-period feature set comprising cumulative charge capacity and / or cumulative discharge capacity;
[0036] Features of a feature set at the end of full charge time, the feature set at the end of full charge time comprising at least one of a maximum cell voltage at the end of full charge time, a minimum cell voltage at the end of full charge time, a minimum temperature at the end of full charge time, a maximum temperature at the end of full charge time, and a continuous current at the end of full charge time;
[0037] The characteristics of the full-charge static process feature set, the full-charge static process feature set includes the voltage drop curve characteristics corresponding to the maximum voltage battery cell in the full-charge static process, the voltage drop curve characteristics corresponding to the minimum voltage battery cell and at least one of the temperature change rate, the voltage drop curve characteristics include the kurtosis, skewness, parameters identified based on the second-order resistance and capacitance equivalent circuit model and at least one of the voltage after static.
[0038] In some embodiments, obtaining a target aging characteristic of the first battery includes:
[0039] In the case where the aging characteristics of the first battery are obtained by the Nth extraction, the aging characteristics of the first battery are obtained by the first N-1 extractions, where N is an integer greater than 1;
[0040] Based on the aging features obtained for the Nth time and the aging features extracted for the first N-1 times, a time series two-dimensional tensor feature is generated.
[0041] Wherein, the target aging feature includes the time series two-dimensional tensor feature.
[0042] In a second aspect, an embodiment of the present application further provides a device for determining a health status of a battery, comprising:
[0043] an aging feature acquisition module, used to acquire a target aging feature of the first battery, wherein the target aging feature is a feature that changes due to aging of the first battery;
[0044] a health state prediction module, configured to input the target aging feature into a health state prediction model to obtain a first health state output by the health state prediction model, wherein the health state prediction model is trained based on sample data, and the sample data includes a historical aging feature of the second battery and a corresponding historical health state, wherein the historical health state is a health state of the second battery calculated by an online health state estimation strategy when the historical aging feature is obtained;
[0045] A health state estimation module, configured to estimate a second health state of the first battery by using the health state online estimation strategy;
[0046] The health state determination module is used to merge the first health state and the second health state to obtain a target health state of the first battery.
[0047] In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;
[0048] When the processor executes the computer program instructions, the method for determining the health status of a battery as described in any one of the first aspects is implemented.
[0049] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method for determining the health status of a battery as described in any one of the first aspects is implemented.
[0050] In a fifth aspect, an embodiment of the present application further provides a vehicle, comprising the electronic device as described in the third aspect.
[0051] The method, device and apparatus for determining the health state of a battery in the embodiment of the present application obtains the target aging characteristics of the first battery; inputs the target aging characteristics into the health state prediction model to obtain the first health state output by the health state prediction model, and the historical health state in the sample data used to train the health state prediction model is estimated by the online estimation strategy; the second health state of the first battery is estimated by the health state online estimation strategy; the first health state and the second health state are fused to obtain the target health state of the first battery. In this way, the health state of the battery can be determined by fusing the health state prediction model and the online estimation strategy, thereby improving the accuracy of determining the health state of the battery. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0053] Figure 1 is a flow chart of an embodiment of a method for determining a health status of a battery provided by the present application;
[0054] Figure 2 is a schematic diagram of the change of the voltage of the first battery over time at different mileages in an embodiment of the method for determining the health status of a battery provided by the present application;
[0055] Figure 3 is a schematic diagram of a curve of relationship between SOC and voltage in an embodiment of a method for determining a health state of a battery provided by the present application;
[0056] Figure 4is a schematic diagram of an IC curve in an embodiment of a method for determining a health state of a battery provided by the present application;
[0057] Figure 5 is a structural schematic diagram of an embodiment of a device for determining a health state of a battery provided by the present application;
[0058] Figure 6 It is a schematic diagram of the structure of an embodiment of the electronic device provided by the present application. DETAILED DESCRIPTION
[0059] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.
[0060] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0061] Figure 1 The flowchart of an embodiment of the method for determining the state of health of a battery provided by the present application is shown. The method for determining the state of health (SOH) of a battery provided by the present application can be applied to an electronic device, which may include a user terminal, a portable notebook or a vehicle-mounted terminal, etc. Figure 1 As shown, the method for determining the health status of a battery includes but is not limited to the following steps S101 to S104.
[0062] Step S101: Obtain target aging characteristics of a first battery.
[0063] In this step, the first battery may be any structure capable of storing electrical energy, and the present application does not limit the shape, size, structural design, material, and use of the first battery.
[0064] For example, the first battery may be a lithium iron phosphate first battery or a ternary lithium ion first battery; or, the first battery may be used to power household appliances or electric vehicles, and so on.
[0065] The target aging feature is a feature related to the aging degree of the first battery, that is, the target aging feature can be any feature that can be used to measure the aging degree of the first battery.
[0066] In some embodiments, the target aging feature includes at least one of the following:
[0067] Features of a long-period feature set, the long-period feature set comprising cumulative charge capacity and / or cumulative discharge capacity;
[0068] Features of a feature set at the end of full charge time, the feature set at the end of full charge time including at least one of a maximum cell voltage at the end of full charge time, a minimum cell voltage at the end of full charge time, a minimum temperature at the end of full charge time, a maximum temperature at the end of full charge time, and a continuous current at the end of full charge time;
[0069] The characteristics of the full-charge static process feature set include the voltage drop curve characteristics corresponding to the maximum voltage cell in the full-charge static process, the voltage drop curve characteristics corresponding to the minimum voltage cell and at least one of the temperature change rate. The voltage drop curve characteristics include the kurtosis, skewness, parameters based on the second-order resistance and capacitance equivalent circuit model and at least one of the voltage after static.
[0070] In this embodiment, the above-mentioned target aging characteristics may include at least one of the characteristics of the long-period characteristic set, the characteristics of the full-charge end-time characteristic set, and the characteristics of the full-charge static process characteristic set, thereby making the selection of the target aging characteristics more flexible and the application scenarios more extensive.
[0071] In the case where the above-mentioned target aging characteristics include characteristics of a long-period characteristic set, the target aging characteristics may include at least one of the characteristics of the long-period characteristic set including the maximum single cell voltage at full charge, the minimum single cell voltage at full charge, the minimum temperature at full charge, the maximum temperature at full charge and the continuous current at full charge.
[0072] In the case where the above-mentioned target aging characteristics include characteristics of a long-period characteristic set, the target aging characteristics may include at least one of the characteristics of the long-period characteristic set including the maximum single cell voltage at full charge, the minimum single cell voltage at full charge, the minimum temperature at full charge, the maximum temperature at full charge and the continuous current at full charge.
[0073] In the case where the above-mentioned target aging characteristics include characteristics of a full-charged static process characteristic set, the target aging characteristics may include at least one of the voltage drop curve characteristics corresponding to the maximum voltage cell during the full-charged static process, the voltage drop curve characteristics corresponding to the minimum voltage cell, and the temperature change rate in the characteristics of the full-charged static process characteristic set, and the voltage drop curve characteristics may include at least one of the kurtosis, skewness, parameters identified based on a second-order resistor-capacitor (RC) equivalent circuit model, and the voltage after static.
[0074] Specifically, in order to further improve the accuracy of the determined target SOH of the first battery, the target aging characteristics may include:
[0075] Features of the long-period feature set, which includes cumulative charge capacity and cumulative discharge capacity;
[0076] Features of the feature set at the end of full charge time, the feature set at the end of full charge time includes the maximum single cell voltage at the end of full charge time, the minimum single cell voltage at the end of full charge time, the minimum temperature at the end of full charge time, the maximum temperature at the end of full charge time, and the continuous current at the end of full charge time;
[0077] The characteristics of the full-charge static process feature set include the voltage drop curve characteristics corresponding to the maximum voltage cell, the voltage drop curve characteristics corresponding to the minimum voltage cell and the temperature change rate during the full-charge static process. The voltage drop curve characteristics include the kurtosis and skewness of the voltage drop curve, the parameters based on the second-order resistance and capacitance equivalent circuit model and the voltage after static.
[0078] The target aging characteristics of the first battery can be obtained by measuring or analyzing the first battery when the SOH of the first battery needs to be determined. Since the acquisition of the above characteristics is well known to those skilled in the art, it will not be described in detail here.
[0079] Among them, the parameters based on the second-order resistor and capacitor equivalent circuit model can be based on the voltage drop data of the fully charged static process, and the offline least squares parameter identification based on the second-order resistor and capacitor equivalent circuit principle is used to complete the corresponding characteristic parameter identification.
[0080] Specifically, the following custom equivalent circuit equation (1) can be used to identify characteristic parameters:
[0081] def func depolar(x,a,b,c,d,e):
[0082]
[0083] The custom equivalent circuit equation (1) is a nonlinear function containing 5 parameters, where x is the independent variable, a, b, c, d and e are the parameters of the function (i.e., the parameters identified based on the second-order resistor-capacitor equivalent circuit model), which describes the response of a second-order RC (Resistor Capacitor) circuit. In this function, a and b control the amplitude and time constant of the first exponential decay, c and d control the amplitude and time constant of the second exponential decay, and e is a constant offset.
[0084] The voltage reduction data based on the fully charged static process refers to data that can characterize the change of the voltage of the first battery with time at different aging degrees during the static process after the first battery is fully charged.
[0085] For example, in the case where the first battery is used to power an electric vehicle, the voltage drop data based on the fully charged static process can be used to characterize the following: Figure 2 The data of the first battery voltage changing with time under different forms of mileage are shown.
[0086] In addition, the above-mentioned target aging characteristics may be the characteristics currently extracted. For example, when the above-mentioned target aging characteristics include the characteristics of the long-period characteristic set, the characteristics of the full-charge static process characteristic set, and all the characteristics of the full-charge static process characteristic set (a total of 24 characteristics), the target aging characteristics may be the 24 characteristics currently extracted.
[0087] In some implementations, the above step 101 may include:
[0088] When the aging characteristics of the first battery are obtained by the Nth extraction, the aging characteristics of the first battery obtained by the previous N-1 extractions are obtained, where N is an integer greater than 1;
[0089] Based on the aging features obtained for the Nth time and the aging features extracted for the previous N-1 times, a time series two-dimensional tensor feature is generated.
[0090] Among them, the target aging characteristics include time series two-dimensional tensor features.
[0091] In this embodiment, when determining the current SOH of the first battery, the currently extracted aging characteristics of the first battery and the previously extracted aging characteristics are used to generate a time series two-dimensional tensor feature, and the time series two-dimensional tensor feature is used as the target aging feature, thereby making the characteristics of the target aging feature richer, further improving the accuracy of the output results of the SOH prediction model, and then improving the accuracy of determining the current SOH of the first battery.
[0092] The above N can be a value set according to actual needs. For example, assuming that the aging characteristics include the above 24 characteristics in total, and N is 5, then when the aging characteristics of the first battery are currently extracted, the aging characteristics of the first battery extracted for the previous 4 times can be obtained, and the first battery characteristics extracted for 5 consecutive times can be formed into a time series two-dimensional tensor feature set of (5, 24).
[0093] Step S102: input the target aging feature into the SOH prediction model to obtain a first SOH output by the SOH prediction model.
[0094] In this step, the SOH prediction model is trained based on sample data, and the sample data includes the historical aging characteristics of the second battery and the corresponding historical SOH. The historical SOH is the SOH of the second battery calculated by the SOH online estimation strategy when the historical aging characteristics are obtained.
[0095] That is, before the above step 102, the above method may further include:
[0096] Acquire sample data, the sample data including a historical aging feature of the second battery and a historical SOH corresponding to the historical aging feature, the historical SOH being calculated based on an SOH online estimation strategy for the SOH of the second battery when the historical aging feature is acquired;
[0097] Based on the sample data, the machine learning model is trained to obtain the above-mentioned SOH prediction model.
[0098] The second battery may be a battery different from the first battery. Specifically, the second battery may be a battery of the same type or model as the first battery, so that the SOH prediction model may predict the SOH of a certain type or model of battery more accurately.
[0099] The above-mentioned historical aging features are aging features corresponding to the above-mentioned target aging features. For example, when the above-mentioned target aging features include the above-mentioned 24 features, the historical aging features also include the 24 aging features; and when the above-mentioned target aging features are time series two-dimensional tensor features, the historical aging features are also historical time series two-dimensional tensor features.
[0100] The above-mentioned SOH prediction model is obtained by training the machine learning model based on the sample data, and the historical aging features in the sample data are input into the machine learning model to obtain the intermediate SOH output by the machine learning model; the loss between the intermediate SOH and the corresponding historical SOH is calculated; when the calculated loss does not meet the preset conditions (for example, the loss does not tend to be constant, etc.), new sample data is input into the machine learning model for retraining until the calculated loss meets the preset conditions to obtain the above-mentioned SOH prediction model.
[0101] Step S103: obtain a second SOH of the first battery by estimating through an SOH online estimation strategy.
[0102] In this step, the above-mentioned SOH online estimation strategy can be any algorithm or model that can realize online calculation of the SOH of the battery.
[0103] In some implementations, the SOH online estimation strategy includes a first estimation strategy.
[0104] The above step S103 may include:
[0105] Obtaining a first state of charge (SOC) of the first battery at a first time point under a target operating condition, and obtaining a second SOC of the first battery at a second time point under the target operating condition, wherein the target operating condition is a charging operating condition or a discharging operating condition, and the second time point is after the first time point;
[0106] Obtain a capacity change value of a first battery between a first time point and a second time point;
[0107] A first sub-SOH of the first battery is estimated according to the first SOC, the second SOC and the capacity change value, and the second SOH includes a second sub-SOH.
[0108] In this embodiment, the first sub-SOH of the first battery can be estimated by the SOC and capacity change value of the first battery at two time points under the target operating conditions (i.e., online estimation of SOH based on the "two-point method"), thereby making the method of online calculation of the SOH of the first battery simple and easy to implement.
[0109] The second SOH of the first battery is estimated based on the first SOC, the second SOC and the capacity change value, and the ratio of the capacity change value to the difference between the first SOC and the second SOC may be used as the first sub-SOC.
[0110] Specifically, for Figure 3The first battery of the SOC and voltage relationship curve shown in FIG. 1 may be in a discharge condition, and the SOH of the first battery may be estimated online by the following formula (2):
[0111] SOH_0=ΔAh / (SOC2-SOC1) (2)
[0112] Wherein, in formula (2), SOH_0 represents the estimated SOH;
[0113] SOC1 represents the first SOC at the first time point;
[0114] SOC2 represents the first SOC at the second time point;
[0115] ΔAh represents the capacity change value between the first time point and the second time point.
[0116] It should be noted that, in the case where the second SOH is the SOH estimated online based on the “two-point method”, the historical SOH is also estimated online based on the “two-point method”.
[0117] In some embodiments, the SOH online estimation strategy includes a second estimation strategy.
[0118] The above step S103 may include:
[0119] Obtaining an incremental capacity (IC) curve of the first battery under a target operating condition;
[0120] According to the characteristic voltage point in the IC curve, the curve area corresponding to the IC curve is divided to obtain multiple sub-areas, wherein the characteristic voltage point is the voltage point corresponding to the local minimum value in the IC curve;
[0121] determining a coverage area of each of the plurality of sub-regions;
[0122] The second sub-SOH of the first battery is estimated according to the coverage area of each sub-region of the multiple sub-regions, and the second SOH includes the second sub-SOH.
[0123] In this embodiment, the second sub-SOH of the first battery can be estimated according to the coverage area of each of the multiple sub-regions in the IC curve (i.e., online estimation of SOH based on the “aging characteristic mapping method”), thereby making the online calculation of SOH more diverse and accurate.
[0124] The electronic device can divide the curve area corresponding to the IC curve according to the characteristic voltage points in the IC curve to obtain multiple sub-areas. Figure 4As shown, when the IC curve of the first battery under discharge conditions has two characteristic voltage points (ie, v1 and v2), the curve area corresponding to the IC curve can be divided into three sub-areas, namely, sub-area peak_0, area peak_1 and area peak_2.
[0125] The above-mentioned determination of the coverage area of each sub-region among the multiple sub-regions can be obtained by identifying the coverage area of each region after the region is divided. For example, the image of the IC curve after the region is divided can be obtained, and the coverage area of each region can be estimated by an image recognition algorithm, and so on.
[0126] In some embodiments, the characteristic voltage point includes a first voltage point and a second voltage point, the multiple sub-regions include a first sub-region, a second sub-region, and a third sub-region, the first sub-region is located before the first voltage point, the second sub-region is located between the first voltage point and the second voltage point, and the third sub-region is located after the second voltage point.
[0127] The above-mentioned determining the coverage area of each sub-area among the multiple sub-areas may include:
[0128] Perform IC analysis on the IC curve to obtain the coverage area of the second sub-region and the coverage area of the third sub-region;
[0129] The coverage area of the first sub-region is determined according to the coverage area of the second sub-region.
[0130] In this embodiment, IC analysis is first performed on the IC curve to obtain the coverage area of the second sub-region and the coverage area of the third sub-region, and then the coverage area of the first sub-region is determined based on the coverage area of the second sub-region adjacent to the first sub-region, so that the coverage area of each sub-region is determined more accurately.
[0131] The above-mentioned determination of the coverage area of the first sub-region according to the coverage area of the second sub-region may be performed by multiplying the coverage area of the second sub-region by a preset adjustment parameter value to determine the coverage area of the first sub-region.
[0132] Among them, the above-mentioned preset adjustment parameter value can be a pre-set fixed value, or it can be an adjustment parameter value determined according to a preset corresponding relationship curve between the usage time of different batteries and the adjustment parameter value. The preset corresponding relationship curve between the usage time and the adjustment parameter value can be determined through experiments.
[0133] It should be noted that, since the above process of performing IC analysis on the IC curve is well known to those skilled in the art, it will not be described in detail here.
[0134] In some embodiments, determining the coverage area of the first sub-region according to the coverage area of the second sub-region includes:
[0135] The product of the target ratio and the first initial coverage area corresponding to the first sub-region is determined as the coverage area of the first sub-region, wherein the target ratio is the ratio of the coverage area of the second sub-region to the second initial coverage area, the first initial coverage area is the coverage area of the area corresponding to the first sub-region in the IC curve of the first battery when no aging occurs, and the second initial coverage area is the coverage area of the area corresponding to the second sub-region in the IC curve of the first battery when no aging occurs.
[0136] In this embodiment, the target ratio between the coverage area of the second sub-region and the second initial coverage area is calculated, and the product of the target ratio and the first initial coverage area corresponding to the first sub-region is determined as the coverage area of the first sub-region, thereby making the determined coverage area of the first sub-region more accurate.
[0137] For example, in the case where the curve area corresponding to the IC curve is divided into sub-area peak_0, sub-area peak_1 and sub-area peak_2, the IC curve can be first subjected to IC analysis to obtain the coverage area of sub-area peak_1 and the coverage area of sub-area peak_2, and then the coverage area of sub-area peak_0 can be calculated by the following formula (3):
[0138] peak_0_area = peak_1_area / peak_1_area_original * peak_0_area_original (3)
[0139] In the above formula (3), peak_0_area represents the coverage area of sub-region peak_0;
[0140] peak_1_area represents the coverage area of sub-region peak_1;
[0141] peak_0_area_original represents the first initial coverage area;
[0142] peak_1_area_original represents the second initial coverage area.
[0143] In some embodiments, the second sub-SOH of the first battery is estimated based on the coverage area of each of the multiple sub-areas, and the sum of the coverage areas of the multiple sub-areas is determined as the second sub-SOH of the first battery, so as to accurately calculate the second sub-SOH of the first battery.
[0144] For example, when the curve area corresponding to the IC curve is divided into sub-area peak_0, sub-area peak_1 and sub-area peak_2, the second sub-SOH can be calculated by the following formula (4):
[0145] SOH_1 = peak_0_area + peak_1_area + peak_2_area (4)
[0146] In the above formula (4), SOH_1 represents the second sub-SOH;
[0147] peak_2_area represents the coverage area of sub-region peak_2.
[0148] Furthermore, combined with the above formula (3), the above formula (4) can be transformed into the following formula (5):
[0149] SOH_1=peak_1_area / peak_1_area_original*peak_0_area_original+
[0150] peak_1_area+peak_2_area(5).
[0151] Of course, the above-mentioned estimation of the second sub-SOH of the first battery based on the coverage area of each sub-region among the multiple sub-regions can also be performed by calculating the product of the coverage area of each sub-region and the preset weight corresponding to the sub-region, and determining the sum of the products corresponding to the multiple sub-regions as the second sub-SOH of the first battery.
[0152] Step S104: merge the first SOH and the second SOH to obtain a target SOH for the first battery.
[0153] In this step, the first SOH and the second SOH are fused to obtain the target SOH of the first battery, which may be obtained by fusing the first SOH and the second SOH through a preset fusion algorithm.
[0154] Specifically, the above-mentioned fusion of the first SOH and the second SOH to obtain the target SOH of the first battery can be performed by calculating the target SOH of the first battery based on the first SOH, the second SOH and the corresponding weight, that is, the electronic device is preset with a weight corresponding to the first SOH and a weight corresponding to the second SOH, and the sum of the product between the first SOH and its corresponding weight and the product between the second SOH and its corresponding weight is taken as the target SOH.
[0155] For example, when the above-mentioned online estimation strategy only includes the strategy of estimating SOH online based on the “two-point method”, the above-mentioned target SOH is the sum of the product between the first SOH and its corresponding weight, and the product between the first sub-SOH and its corresponding weight; and when the above-mentioned online estimation strategy only includes the strategy of estimating SOH online based on the “aging characteristic mapping method”, the above-mentioned target SOH is the sum of the product between the first SOH and its corresponding weight, and the product between the second sub-SOH and its corresponding weight.
[0156] In some embodiments, the second SOH includes a first sub-SOH and a second sub-SOH, the first sub-SOH is estimated by a first estimation strategy, and the second sub-SOH is estimated by a second estimation strategy. The first SOH and the second SOH are fused to obtain the target SOH of the first battery. The target SOH of the first battery can be calculated based on the first sub-SOH, the second sub-SOH, the first SOH and the corresponding weights, so that the determined target SOH is more accurate.
[0157] For example, when SOH_0 is calculated based on the above formula (2) and SOH_0 is calculated based on the above formula (4), if the first SOH predicted by the SOH prediction model is SOH_2, the target SOH can be calculated by the following formula (6):
[0158] SOH = α* SOH_0 + β* SOH_1 + γ* SOH_2 (6)
[0159] In the above formula (6), SOH is the above target SOH;
[0160] α, β and γ are constants ranging from 0 to 1.
[0161] In the embodiment of the present application, the target aging characteristics of the first battery are obtained; the target aging characteristics are input into the SOH prediction model to obtain the first SOH output by the SOH prediction model, and the historical SOH in the sample data used to train the SOH prediction model is estimated by the online estimation strategy; the second SOH of the first battery is estimated by the SOH online estimation strategy; the first SOH and the second SOH are fused to obtain the target SOH of the first battery. In this way, the SOH prediction model and the online estimation strategy can be integrated to determine the SOH of the battery, thereby improving the accuracy of determining the SOH of the battery. In addition, since the SOH in the sample data used to train the SOH prediction model is estimated by the online estimation strategy, the efficiency of obtaining sample data can be improved.
[0162] The method for determining the health status of a battery provided in the embodiment of the present application may be performed by a device for determining the health status of a battery. In the embodiment of the present application, the method for determining the health status of a battery is performed by a device for determining the health status of a battery as an example to illustrate the device for determining the health status of a battery provided in the embodiment of the present application.
[0163] Figure 5 FIG. 1 is a schematic diagram showing a structure of a device for determining a battery health status provided by an embodiment of the present application. Figure 5 As shown, the apparatus 500 for determining the health status of a battery includes:
[0164] An aging feature acquisition module 501 is used to acquire a target aging feature of the first battery, where the target aging feature is a feature that changes due to aging of the first battery;
[0165] A health state prediction module 502 is used to input the target aging feature into a health state prediction model to obtain a first health state output by the health state prediction model, wherein the health state prediction model is trained based on sample data, and the sample data includes the historical aging feature of the second battery and the corresponding historical health state, and the historical health state is the health state of the second battery calculated by the health state online estimation strategy when the historical aging feature is obtained;
[0166] A health state estimation module 503, configured to estimate a second health state of the first battery by using an online health state estimation strategy;
[0167] The health state determination module 504 is used to merge the first health state and the second health state to obtain a target health state of the first battery.
[0168] In some embodiments, the health status online estimation strategy includes a first estimation strategy.
[0169] The health status estimation module 503 can be specifically used for:
[0170] Acquire a first state of charge of the first battery at a first time point under a target operating condition, and acquire a second state of charge of the first battery at a second time point under the target operating condition, wherein the target operating condition is a charging operating condition or a discharging operating condition, and the second time point is after the first time point;
[0171] Obtain a capacity change value of a first battery between a first time point and a second time point;
[0172] A first sub-state of health of the first battery is estimated based on the first state of charge, the second state of charge, and the capacity change value.
[0173] The second health state includes the first sub-health state.
[0174] In some embodiments, the health status online estimation strategy includes a second estimation strategy.
[0175] The health status estimation module 503 can be specifically used for:
[0176] Obtaining a capacity increment curve of the first battery under a target operating condition;
[0177] According to the characteristic voltage point in the capacity increment curve, the curve area corresponding to the capacity increment curve is divided to obtain multiple sub-areas, wherein the characteristic voltage point is a voltage point corresponding to a local minimum value in the capacity increment curve;
[0178] determining a coverage area of each of the plurality of sub-regions;
[0179] The second sub-health state of the first battery is estimated based on the coverage area of each sub-area in the multiple sub-areas,
[0180] The second health state includes a second sub-health state.
[0181] In some embodiments, the characteristic voltage point includes a first voltage point and a second voltage point, the multiple sub-regions include a first sub-region, a second sub-region, and a third sub-region, the first sub-region is located before the first voltage point, the second sub-region is located between the first voltage point and the second voltage point, and the third sub-region is located after the second voltage point.
[0182] The health status estimation module 503 can be specifically used for:
[0183] Performing capacity increment analysis on the capacity increment curve to obtain the coverage area of the second sub-region and the coverage area of the third sub-region;
[0184] The coverage area of the first sub-region is determined according to the coverage area of the second sub-region.
[0185] In some implementations, the health status estimation module 503 is specifically configured to:
[0186] The product of the target ratio and the first initial coverage area corresponding to the first sub-region is determined as the coverage area of the first sub-region, wherein the target ratio is the ratio between the coverage area of the second sub-region and the second initial coverage area, the first initial coverage area is the coverage area of the area corresponding to the first sub-region in the capacity increment curve of the first battery before aging, and the second initial coverage area is the coverage area of the area corresponding to the second sub-region in the capacity increment curve of the first battery before aging.
[0187] In some implementations, the health status estimation module 503 is specifically configured to:
[0188] The sum of the coverage areas of the multiple sub-regions is determined as the second sub-health state of the first battery.
[0189] In some embodiments, the second health state includes a first sub-health state and a second sub-health state, the first sub-health state is estimated by the first estimation strategy, and the second sub-health state is estimated by the second estimation strategy.
[0190] The health status estimation module 503 can be specifically used for:
[0191] The target health state of the first battery is calculated according to the first sub-health state, the second sub-health state, the first health state and the corresponding weights.
[0192] In some embodiments, the target aging feature includes at least one of the following:
[0193] Features of a long-period feature set, the long-period feature set comprising cumulative charge capacity and / or cumulative discharge capacity;
[0194] Features of a feature set at the end of full charge time, the feature set at the end of full charge time including at least one of a maximum cell voltage at the end of full charge time, a minimum cell voltage at the end of full charge time, a minimum temperature at the end of full charge time, a maximum temperature at the end of full charge time, and a continuous current at the end of full charge time;
[0195] The characteristics of the full-charge static process feature set include the voltage drop curve characteristics corresponding to the maximum voltage cell in the full-charge static process, the voltage drop curve characteristics corresponding to the minimum voltage cell and at least one of the temperature change rate. The voltage drop curve characteristics include the kurtosis, skewness, parameters identified based on the second-order resistance and capacitance equivalent circuit model and at least one of the voltage after static.
[0196] In some implementations, the aging feature acquisition module 501 is specifically configured to:
[0197] When the aging characteristics of the first battery are obtained by the Nth extraction, the aging characteristics of the first battery obtained by the previous N-1 extractions are obtained, where N is an integer greater than 1;
[0198] Based on the aging features obtained for the Nth time and the aging features extracted for the previous N-1 times, a time series two-dimensional tensor feature is generated.
[0199] Among them, the target aging characteristics include time series two-dimensional tensor features.
[0200] The device 500 for determining the health status of a battery provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.
[0201] Figure 6A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.
[0202] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.
[0203] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0204] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.
[0205] In some embodiments, the memory 602 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.
[0206] The processor 601 implements any one of the methods for determining the health status of a battery in the above embodiments by reading and executing computer program instructions stored in the memory 602 .
[0207] In one example, the electronic device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.
[0208] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0209] Bus 610 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.
[0210] The electronic device can execute the method for determining the health status of the battery in the embodiment of the present application, thereby realizing the combination Figures 1 to 5 Methods and apparatus for determining the state of health of a battery are described.
[0211] In addition, in combination with the method for determining the health status of a battery in the above embodiment, the embodiment of the present application also provides a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the method for determining the health status of a battery in the above embodiment is implemented.
[0212] In combination with the method for determining the health status of a battery in the above embodiment, an embodiment of the present application also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device implements the method for determining the health status of a battery in the above embodiment.
[0213] In combination with the electronic device in the above embodiment, an embodiment of the present application further provides a vehicle, which includes the electronic device in the above embodiment.
[0214] The vehicle can be a private car, such as a sedan, SUV, MPV or pickup truck. The vehicle can also be an operating vehicle, such as a van, bus, small truck or large trailer. The vehicle can be a gasoline vehicle or a new energy vehicle. When the vehicle is a new energy vehicle, it can be a hybrid vehicle or a pure electric vehicle.
[0215] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.
[0216] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0217] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.
[0218] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.
[0219] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.
Claims
1. A method for determining the health status of a battery, characterized in that: include: Acquire a target aging feature of the first battery, where the target aging feature is a feature related to the aging degree of the first battery; Inputting the target aging feature into a health state prediction model to obtain a first health state output by the health state prediction model, wherein the health state prediction model is trained based on sample data, and the sample data includes a historical aging feature of the second battery and a corresponding historical health state, and the historical health state is a health state of the second battery calculated by an online health state estimation strategy when the historical aging feature is obtained; Obtaining a second health state of the first battery by estimating the health state online estimation strategy; The first health state and the second health state are integrated to obtain a target health state of the first battery.
2. The method according to claim 1, characterized in that The health status online estimation strategy includes a first estimation strategy, The calculating the second health state of the first battery by using the health state online estimation strategy includes: Acquire a first state of charge of the first battery at a first time point under a target operating condition, and acquire a second state of charge of the first battery at a second time point under the target operating condition, wherein the target operating condition is a charging operating condition or a discharging operating condition, and the second time point is after the first time point; Obtaining a capacity change value of the first battery between the first time point and the second time point; estimating a first sub-state of health of the first battery according to the first state of charge, the second state of charge, and the capacity change value, The second health state includes the first sub-health state.
3. The method according to claim 1, characterized in that The health status online estimation strategy includes a second estimation strategy, The calculating the second health state of the first battery by using the health state online estimation strategy includes: Obtaining a capacity increment curve of the first battery under target operating conditions; According to the characteristic voltage point in the capacity increment curve, the curve area corresponding to the capacity increment curve is divided to obtain a plurality of sub-areas, wherein the characteristic voltage point is a voltage point corresponding to a local minimum value in the capacity increment curve; Determine the coverage area of each of the multiple sub-regions; estimating a second sub-health state of the first battery according to a coverage area of each of the multiple sub-areas, The second health state includes the second sub-health state.
4. The method according to claim 3, characterized in that The characteristic voltage point includes a first voltage point and a second voltage point, the multiple sub-regions include a first sub-region, a second sub-region and a third sub-region, the first sub-region is located before the first voltage point, the second sub-region is located between the first voltage point and the second voltage point, and the third sub-region is located after the second voltage point. The determining the coverage area of each of the multiple sub-areas comprises: Performing a capacity increment analysis on the capacity increment curve to obtain a coverage area of the second sub-region and a coverage area of the third sub-region; The coverage area of the first sub-area is determined according to the coverage area of the second sub-area.
5. The method according to claim 4, characterized in that The determining the coverage area of the first sub-area according to the coverage area of the second sub-area includes: The product of the target ratio and the first initial coverage area corresponding to the first sub-region is determined as the coverage area of the first sub-region, Among them, the target ratio is the ratio between the coverage area of the second sub-region and the second initial coverage area, the first initial coverage area is the coverage area of the area corresponding to the first sub-region in the capacity increment curve of the first battery before aging; the second initial coverage area is the coverage area of the area corresponding to the second sub-region in the capacity increment curve of the first battery before aging.
6. The method according to claim 3, characterized in that The estimating the second sub-health state of the first battery according to the coverage area of each of the multiple sub-areas includes: The sum of the coverage areas of the multiple sub-regions is determined as the second sub-health state of the first battery.
7. The method according to claim 1, characterized in that The second health state includes a first sub-health state and a second sub-health state, the first sub-health state is estimated by a first estimation strategy, and the second sub-health state is estimated by a second estimation strategy, The fusing the first health state and the second health state to obtain a target health state of the first battery includes: A target health state of the first battery is calculated according to the first sub-health state, the second sub-health state, the first health state, and corresponding weights.
8. The method according to claim 1, characterized in that The target aging feature includes at least one of the following: Features of a long-period feature set, the long-period feature set comprising cumulative charge capacity and / or cumulative discharge capacity; Features of a feature set at the end of full charge time, the feature set at the end of full charge time comprising at least one of a maximum cell voltage at the end of full charge time, a minimum cell voltage at the end of full charge time, a minimum temperature at the end of full charge time, a maximum temperature at the end of full charge time, and a continuous current at the end of full charge time; The characteristics of the full-charge static process feature set, the full-charge static process feature set includes the voltage drop curve characteristics corresponding to the maximum voltage battery cell in the full-charge static process, the voltage drop curve characteristics corresponding to the minimum voltage battery cell and at least one of the temperature change rate, the voltage drop curve characteristics include the kurtosis, skewness, parameters identified based on the second-order resistance and capacitance equivalent circuit model and at least one of the voltage after static.
9. The method according to claim 1, characterized in that: The obtaining of the target aging characteristic of the first battery includes: In the case where the aging characteristics of the first battery are obtained by the Nth extraction, the aging characteristics of the first battery are obtained by the first N-1 extractions, where N is an integer greater than 1; Based on the aging features obtained for the Nth time and the aging features extracted for the first N-1 times, a time series two-dimensional tensor feature is generated. Wherein, the target aging feature includes the time series two-dimensional tensor feature.
10. A device for determining the health status of a battery, characterized in that include: an aging feature acquisition module, used to acquire a target aging feature of the first battery, wherein the target aging feature is a feature that changes due to aging of the first battery; a health state prediction module, configured to input the target aging feature into a health state prediction model to obtain a first health state output by the health state prediction model, wherein the health state prediction model is trained based on sample data, and the sample data includes a historical aging feature of the second battery and a corresponding historical health state, wherein the historical health state is a health state of the second battery calculated by an online health state estimation strategy when the historical aging feature is obtained; A health state estimation module, configured to estimate a second health state of the first battery by using the health state online estimation strategy; The health state determination module is used to merge the first health state and the second health state to obtain a target health state of the first battery.
11. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining the health state of a battery as described in any one of claims 1-9 is implemented.
12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for determining the health status of a battery as described in any one of claims 1 to 9 is implemented.
13. A vehicle, characterized in that: Comprising the electronic device as claimed in claim 11.
Citation Information
Cited By
Electric quantity state information determination method, device and system, medium and program product
CN120428127A
SOH exception determination method and device, equipment and storage medium
CN120820864A
Battery health state estimation method and vehicle
CN121741514A
