Battery health state estimation method, device and equipment and readable storage medium

By constructing an energy consumption distribution model and estimating the battery health status, the problem of low accuracy caused by differences in battery attenuation parameters in the power battery health status estimation is solved, and a more accurate evaluation of the battery health status is achieved, and the battery management system is enhanced Validity.

CN119024205APending Publication Date: 2024-11-26RADAR NEW ENERGY AUTOMOBILE (ZHEJIANG) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310602593.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-25
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In the prior art, the estimation method of the health status of the power battery is low due to the difference in battery attenuation parameters.

Method used

By obtaining the historical itinerary information of the target vehicle, the energy consumption distribution model is constructed, the mileage energy consumption corresponding to the target usage time is estimated, and the battery health status is calculated based on the preset initial mileage energy consumption, so as to improve the accuracy of the estimation.

Benefits of technology

It improves the accuracy of battery health status estimation, matches it with the actual mileage and energy consumption of the vehicle, is more in line with the user's intuitive feeling, and enhances the effectiveness of the battery management system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119024205A_ABST
    Figure CN119024205A_ABST
Patent Text Reader

Abstract

The invention discloses a battery health state estimation method, device and equipment and a readable storage medium, and relates to the technical field of vehicles. The battery health state estimation method comprises the following steps: acquiring an energy consumption distribution model and target use duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time sequence in historical travel information of the target vehicle; inputting the target use duration into the energy consumption distribution model to obtain estimated mileage energy consumption corresponding to the target use duration; and according to the estimated mileage energy consumption and preset initial mileage energy consumption, calculating to obtain a battery health state corresponding to the target use duration. According to the method, the accuracy of the estimated SOH is improved, and the accuracy is matched with the visual feeling of a user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a battery health status estimation method, device, equipment and readable storage medium. Background Art

[0002] As new energy vehicles are increasingly recognized in terms of technology and market, power batteries as the core components of pure electric vehicles are also receiving much attention. The health status (SOH) of power batteries will affect the endurance of pure electric vehicles. Therefore, it is of great significance to introduce battery health status (SOH) estimation into the battery management system (BMS) of pure electric vehicles.

[0003] At present, the traditional estimation methods for SOH estimation include electrochemical modeling, or the ampere-hour integration method to estimate the battery's state of charge (SOC), and then indirectly estimate SOH from SOC. The current estimation of the health state (SOH) of power batteries usually uses technical features such as "cumulative factor, number of cycles, and cycle attenuation". However, even for the same power battery, there will be differences in battery attenuation parameters such as cumulative factor and cycle attenuation, resulting in low accuracy of the estimated SOH. Summary of the invention

[0004] The main purpose of this application is to provide a battery health state estimation method, aiming to solve the current technical problem that there are differences in battery attenuation parameters of power batteries, resulting in low accuracy of estimated SOH.

[0005] To achieve the above objectives, in a first aspect, the present application provides a battery health state estimation method, the battery health state estimation method comprising:

[0006] Obtaining an energy consumption distribution model and a target usage duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time series in historical travel information of the target vehicle;

[0007] Inputting the target usage time into the energy consumption distribution model to obtain the estimated mileage energy consumption corresponding to the target usage time;

[0008] The battery health status corresponding to the target usage time is calculated based on the estimated mileage energy consumption and the preset initial mileage energy consumption.

[0009] According to the first aspect, before the step of obtaining the energy consumption distribution model and target usage time of the target vehicle, the method includes:

[0010] Obtain historical travel information of the target vehicle;

[0011] Filtering a reference path from the historical travel information, and acquiring a first energy consumption time series of the reference path;

[0012] A preset initial model is trained based on the first energy consumption time series to obtain an energy consumption distribution model of the target vehicle.

[0013] According to the first aspect, or any implementation of the first aspect above, the step of filtering out a reference path from the historical travel information includes:

[0014] Acquire each historical travel route of the target vehicle from the historical travel information, and determine a common road section set of each historical travel route;

[0015] Obtaining the travel frequency of each public road section in the public road section set, and selecting at least two high-frequency road sections from each public road section according to the travel frequency;

[0016] A second energy consumption time series of each of the high-frequency sections is obtained, and a reference path in the high-frequency section is determined according to the second energy consumption time series.

[0017] According to the first aspect, or any implementation of the first aspect above, the step of determining the reference path in the high-frequency section according to the second energy consumption time series includes:

[0018] Calculating the energy consumption standard deviation of each of the high-frequency sections according to the second energy consumption time series;

[0019] The high-frequency section with the smallest energy consumption standard deviation is used as a reference path.

[0020] According to the first aspect, or any implementation of the first aspect above, before the step of obtaining the travel frequency of each public road section in the public road section set, the step includes:

[0021] Obtaining the section length of each public section in the public section set;

[0022] The public road sections whose road section lengths are lower than a preset length threshold are deleted from the public road section set to obtain a new public road section set.

[0023] According to the first aspect, or any implementation of the first aspect above, the preset initial model is a polynomial exponential distribution model, and the step of training the preset initial model based on the first energy consumption time series to obtain the energy consumption distribution model of the target vehicle includes:

[0024] Substituting each accumulated usage time in the first energy consumption time series and the mileage energy consumption corresponding to each accumulated usage time into the polynomial exponential distribution model to obtain a relationship between a weight coefficient and a scaling factor in the polynomial exponential distribution model;

[0025] The relationship is solved to obtain the values ​​of the weight coefficient and the scaling factor, and the energy consumption distribution model of the target vehicle is determined.

[0026] According to the first aspect, or any implementation of the first aspect above, before the step of calculating the battery health state corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption, the step includes:

[0027] Inputting the preset initial duration into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial duration;

[0028] The step of calculating the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption includes:

[0029] The ratio of the preset initial mileage energy consumption to the estimated mileage energy consumption is used as the battery health status corresponding to the target usage time.

[0030] In a second aspect, the present application provides a battery health state estimation device, the battery health state estimation device comprising:

[0031] An acquisition module, used to acquire an energy consumption distribution model and a target usage duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time series in historical travel information of the target vehicle;

[0032] An estimation module, used for inputting the target usage time into the energy consumption distribution model to obtain an estimated mileage energy consumption corresponding to the target usage time;

[0033] The calculation module is used to calculate the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption.

[0034] According to the second aspect, the battery health state estimation device further includes a model training module, which is used to:

[0035] Obtain historical travel information of the target vehicle;

[0036] Filtering a reference path from the historical travel information, and acquiring a first energy consumption time series of the reference path;

[0037] A preset initial model is trained based on the first energy consumption time series to obtain an energy consumption distribution model of the target vehicle.

[0038] According to the second aspect, or any implementation of the second aspect above, the model training module is further used to:

[0039] Acquire each historical travel route of the target vehicle from the historical travel information, and determine a common road section set of each historical travel route;

[0040] Obtaining the travel frequency of each public road section in the public road section set, and selecting at least two high-frequency road sections from each public road section according to the travel frequency;

[0041] A second energy consumption time series of each of the high-frequency sections is obtained, and a reference path in the high-frequency section is determined according to the second energy consumption time series.

[0042] According to the second aspect, or any implementation of the second aspect above, the model training module is further used to:

[0043] Calculating the energy consumption standard deviation of each of the high-frequency sections according to the second energy consumption time series;

[0044] The high-frequency section with the smallest energy consumption standard deviation is used as a reference path.

[0045] According to the second aspect, or any implementation of the second aspect above, the model training module is further used to:

[0046] Obtaining the section length of each public section in the public section set;

[0047] The public road sections whose road section lengths are lower than a preset length threshold are deleted from the public road section set to obtain a new public road section set.

[0048] According to the second aspect, or any implementation of the second aspect above, the preset initial model is a multinomial exponential distribution model, and the model training module is further used to:

[0049] Substituting each accumulated usage time in the first energy consumption time series and the mileage energy consumption corresponding to each accumulated usage time into the polynomial exponential distribution model to obtain a relationship between a weight coefficient and a scaling factor in the polynomial exponential distribution model;

[0050] The relationship is solved to obtain the values ​​of the weight coefficient and the scaling factor, and the energy consumption distribution model of the target vehicle is determined.

[0051] According to the second aspect, or any implementation of the second aspect, the computing module is further configured to:

[0052] Inputting the preset initial duration into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial duration;

[0053] The ratio of the preset initial mileage energy consumption to the estimated mileage energy consumption is used as the battery health status corresponding to the target usage time.

[0054] In a third aspect, the present application provides a battery health status estimation device, which includes: a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and the computer program is configured to implement the steps of the battery health status estimation method as described above.

[0055] The third aspect and any implementation of the third aspect correspond to the first aspect and any implementation of the first aspect, respectively. The technical effects corresponding to the third aspect and any implementation of the third aspect can refer to the technical effects corresponding to the first aspect and any implementation of the first aspect, which will not be repeated here.

[0056] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor executes a battery health status estimation method as described in any one of the first aspect or possible implementations of the first aspect.

[0057] The fourth aspect and any implementation of the fourth aspect correspond to the first aspect and any implementation of the first aspect, respectively. The technical effects corresponding to the fourth aspect and any implementation of the fourth aspect can refer to the technical effects corresponding to the above-mentioned first aspect and any implementation of the first aspect, which will not be repeated here.

[0058] In a fifth aspect, an embodiment of the present application provides a computer program, which includes instructions for executing the battery health status estimation method in the first aspect and any possible implementation of the first aspect.

[0059] The fifth aspect and any implementation of the fifth aspect correspond to the first aspect and any implementation of the first aspect, respectively. The technical effects corresponding to the fifth aspect and any implementation of the fifth aspect can refer to the technical effects corresponding to the first aspect and any implementation of the first aspect, which will not be repeated here.

[0060] The present application proposes a battery health status estimation method, device, equipment and readable storage medium, by obtaining the energy consumption distribution model and target usage time of the target vehicle, wherein the energy consumption distribution model is constructed by the first energy consumption time series in the historical travel information of the target vehicle. Thus, the energy consumption distribution model can be used to estimate the mileage energy consumption (energy consumption per kilometer or energy consumption per 100 kilometers) corresponding to the target vehicle at different times based on the first energy consumption time series in the historical travel information. The target usage time is input into the energy consumption distribution model to obtain the estimated mileage energy consumption corresponding to the target usage time. Then, based on the estimated mileage energy consumption and the preset initial mileage energy consumption, the change in mileage energy consumption between the initial time and the target usage time can be determined, and the battery health status corresponding to the target usage time can be calculated. Since the battery health status will directly affect the cruising range of pure electric vehicles, this application indirectly solves the changes in the battery health status of the target vehicle through the changes in the mileage energy consumption of the target vehicle. Compared with the current method of estimating SOH by technical features such as "cumulative factor, number of cycles, and cycle attenuation", the battery health status estimated by this application matches the mileage energy consumption of the target vehicle, effectively improving the accuracy of the estimated SOH and being more in line with the user's intuitive feelings. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a flow chart of the first embodiment of the battery health status estimation method of the present application;

[0062] Figure 2 This is a flow chart of a second embodiment of a method for estimating a battery health state of the present application;

[0063] Figure 3 This is an index distribution diagram involved in the embodiment of the present application;

[0064] Figure 4 This is a schematic diagram of the structure of the battery health status estimation device of this application;

[0065] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application.

[0066] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0068] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0069] The terms "first" and "second" in the description and claims of the embodiments of the present application are used to distinguish different objects rather than to describe a specific order of objects. For example, a first target object and a second target object are used to distinguish different target objects rather than to describe a specific order of target objects.

[0070] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0071] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0072] The following is an explanation of the battery health status estimation method of the present application in combination with some prior art:

[0073] As new energy vehicles are increasingly recognized in terms of technology and market, power batteries as the core components of pure electric vehicles are also receiving much attention. The health status (SOH) of power batteries will affect the endurance of pure electric vehicles. Therefore, it is of great significance to introduce battery health status (SOH) estimation into the battery management system (BMS) of pure electric vehicles.

[0074] At present, the traditional estimation methods for SOH estimation include electrochemical modeling, or the ampere-hour integration method to estimate the battery's state of charge (SOC), and then indirectly estimate SOH from SOC. Currently, technical features such as "cumulative factor" or "number of cycles, cycle attenuation" are usually selected to estimate the health state (SOH) of power batteries. However, even for the same power battery, there will be differences in battery attenuation parameters such as cumulative factor and cycle attenuation, resulting in low accuracy of the estimated SOH.

[0075] Since the battery health status will directly affect the endurance of pure electric vehicles, the present application obtains the change of the battery health status of the target vehicle by the change of the mileage energy consumption of the target vehicle. In one embodiment of the present application, the energy consumption distribution model and the target usage time of the target vehicle are obtained, wherein the energy consumption distribution model is constructed by the first energy consumption time series in the historical travel information of the target vehicle. Thus, the energy consumption distribution model can be used to estimate the mileage energy consumption of the target vehicle at different times based on the first energy consumption time series in the historical travel information. The target usage time is input into the energy consumption distribution model to obtain the estimated mileage energy consumption corresponding to the target usage time. Then, according to the estimated mileage energy consumption and the preset initial mileage energy consumption, the change of the mileage energy consumption between the initial time and the target usage time can be determined, and the battery health status corresponding to the target usage time can be calculated. Therefore, the battery health status estimated by the present application matches the mileage energy consumption of the target vehicle, effectively improving the accuracy of the estimated SOH, and more in line with the user's intuitive feelings.

[0076] Please refer to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the battery health status estimation method of the present application. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.

[0077] A first embodiment of the present application provides a method for estimating a battery health state, the method comprising the following steps:

[0078] Step S100, obtaining an energy consumption distribution model and a target usage duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time series in historical travel information of the target vehicle;

[0079] In this embodiment, it should be noted that the energy consumption distribution model is constructed by the first energy consumption time series in the historical travel information of the target vehicle. The first energy consumption time series includes the energy consumption time series of the benchmark path in the historical travel information. The energy consumption time series includes the cumulative usage time and the corresponding mileage energy consumption. The mileage energy consumption can be in the form of energy consumption per hundred kilometers or energy consumption per kilometer, such as 30% / hundred kilometers, 0.3% / kilometer. Exemplarily, the energy consumption distribution model can adopt models such as exponential distribution models, neural network models, and Kalman filter models to estimate the estimated mileage energy consumption corresponding to the target usage time through the first energy consumption time series in the historical travel information of the target vehicle. The first energy consumption time series can be in the form of

[0080]

[0081] , t1, t2...t n To accumulate usage time, The mileage energy consumption corresponding to each cumulative usage time. The cumulative usage time is the cumulative sum of the usage time of the power batteries loaded on the target vehicle. The energy consumption distribution model of the target vehicle can be trained in advance or in real time.

[0082] In addition, it should be noted that the target usage time may be the cumulative usage time of the power battery corresponding to the current moment, or may be the cumulative usage time corresponding to the target usage time for which other users expect to estimate the battery health status.

[0083] Step S200, inputting the target usage time into the energy consumption distribution model to obtain the estimated mileage energy consumption corresponding to the target usage time;

[0084] Exemplarily, by inputting the target usage time into the energy consumption distribution model, the estimated mileage energy consumption corresponding to the target usage time output by the energy consumption distribution model can be obtained.

[0085] Step S300, calculating the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption.

[0086] In this embodiment, it should be noted that the preset initial mileage energy consumption is the energy consumption of the power battery of the target vehicle in an undecayed state. It is understandable that there may be a slight difference between the actual initial mileage energy consumption (i.e., the energy consumption of the power battery of the target vehicle in an undecayed state) and the theoretical initial mileage energy consumption in the energy consumption distribution model. Therefore, in order to more accurately estimate the battery health status corresponding to the target usage time, the preset initial usage time can be input into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial usage time. Among them, the preset initial usage time is the usage time corresponding to the undecayed state of the power battery of the target vehicle, which can be 0 days. Of course, since the decay of the power battery is not obvious in a short time, a slightly larger value, such as 1 day or 2 days, can also be used. The preset initial mileage energy consumption can be calculated in advance or in real time.

[0087] In this embodiment, the estimated mileage energy consumption is the energy consumption corresponding to the target usage time, and the preset initial mileage energy consumption is the energy consumption when the power battery is not attenuated. Therefore, the ratio of the preset initial mileage energy consumption and the estimated mileage energy consumption can be directly used as the battery health status corresponding to the target vehicle at the target usage time. Of course, in another embodiment, the full-charge range corresponding to the target vehicle at the target usage time can also be determined based on the estimated mileage energy consumption. According to the preset initial mileage energy consumption, determine the initial range corresponding to the target vehicle when the power battery is not attenuated. The ratio of the full-charge range to the initial range is used as the battery health status corresponding to the target vehicle at the target usage time.

[0088] Before the step of calculating the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption in step S300, the following steps are included:

[0089] Step S310, inputting the preset initial duration into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial duration;

[0090] Since the actual initial mileage energy consumption may be slightly different from the theoretical initial mileage energy consumption in the energy consumption distribution model, in order to more accurately estimate the battery health status corresponding to the target usage time, the preset initial usage time can be input into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial usage time. This can improve the accuracy of the battery health status and avoid the situation where the battery health status exceeds 100%.

[0091] The step of calculating the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption in step S300 includes:

[0092] Step S320: taking the ratio of the preset initial mileage energy consumption to the estimated mileage energy consumption as the battery health status corresponding to the target usage time.

[0093] As the usage time increases, the power battery also decays and the mileage energy consumption increases. The preset initial mileage energy consumption is less than the estimated mileage energy consumption. Therefore, the ratio of the preset initial mileage energy consumption to the estimated mileage energy consumption can be used as the battery health status corresponding to the target usage time. The target usage time t n of for:

[0094]

[0095] in, To preset the initial mileage energy consumption, The estimated mileage energy consumption corresponding to the target usage duration.

[0096] In the first embodiment of the present application, the energy consumption distribution model and the target usage time of the target vehicle are obtained, wherein the energy consumption distribution model is constructed by the first energy consumption time series in the historical travel information of the target vehicle. Thus, the energy consumption distribution model can be used to estimate the mileage energy consumption corresponding to the target vehicle at different times based on the first energy consumption time series in the historical travel information. The target usage time is input into the energy consumption distribution model to obtain the estimated mileage energy consumption corresponding to the target usage time. Then, the change between the initial time and the mileage energy consumption of the target usage time can be determined according to the estimated mileage energy consumption and the preset initial mileage energy consumption, and the battery health state corresponding to the target usage time can be calculated. Since the battery health state will directly affect the endurance of the pure electric vehicle, this embodiment obtains the change of the battery health state of the target vehicle by the change of the mileage energy consumption of the target vehicle. Compared with the current method of estimating the SOH by selecting technical features such as "cumulative factor, number of cycles, and cycle attenuation", the battery health state estimated in this embodiment matches the mileage energy consumption of the target vehicle, effectively improving the accuracy of the estimated SOH and being more in line with the user's intuitive feelings.

[0097] Reference Figure 2 , Figure 2 This is a flow chart of a second embodiment of a battery health status estimation method of the present application.

[0098] The second embodiment of the present application provides a battery health status estimation method, which includes:

[0099] Step A10, obtaining historical travel information of the target vehicle;

[0100] Step A20, selecting a reference route from the historical travel information, and obtaining a first energy consumption time series of the reference route;

[0101] Step A30: training a preset initial model based on the first energy consumption time series to obtain an energy consumption distribution model of the target vehicle.

[0102] In this embodiment, it should be noted that the historical travel information may include the historical travel route and the corresponding historical usage time and mileage energy consumption. The reference path is a path with stable mileage energy consumption changes. For example, the standard deviation of mileage energy consumption can be used to evaluate whether the mileage energy consumption change is stable. Of course, the range, average difference, etc. can also be used.

[0103] As an example, the historical travel information of the target vehicle can be obtained. Based on the mileage energy consumption corresponding to the historical travel routes of the historical travel information, a reference path can be screened out from the historical travel routes. In another example, in order to further avoid the interference of other noise factors such as different road conditions, driving habits, and accidental events. The historical travel routes of the target vehicle can be obtained from the historical travel information, and the common section set of each historical travel route can be determined. Then, the travel frequency of each common section in the common section set is obtained, and at least two high-frequency sections are selected from each of the common sections based on the travel frequency. The second energy consumption time series of each high-frequency section is obtained, and the reference path in the high-frequency section is determined based on the second energy consumption time series. In this way, the first energy consumption time series of the reference path can be obtained, and the preset initial model can be trained based on the first energy consumption time series to obtain the energy consumption distribution model of the target vehicle.

[0104] The step of selecting a reference path from the historical travel information in step A20 includes:

[0105] Step B10, obtaining each historical travel route of the target vehicle from the historical travel information, and determining a common road section set of each historical travel route;

[0106] Step B20, obtaining the travel frequency of each public road section in the public road section set, and selecting at least two high-frequency road sections from each public road section according to the travel frequency;

[0107] Step B30, obtaining a second energy consumption time series of each of the high-frequency sections, and determining a reference path in the high-frequency section according to the second energy consumption time series.

[0108] In this embodiment, in order to avoid interference from different road conditions between different historical travel routes, each historical travel route of the target vehicle can be obtained from the historical travel information, and a common road segment set of each historical travel route can be determined. The common road segment set is a set of common road segments that each historical travel route will travel. For example, assuming that the historical travel information s list The path from segment S1 to segment Sn can be drawn on the same plane map, and the overlapping sections from segment S1 to segment Sn are taken as common sections, thereby obtaining a common section set si set The above process can be expressed in the form of:

[0109] si set =line intersection (s list ).

[0110] Then, the passing frequency of each public road section in the public road section set (i.e., the number of times the target vehicle passes through the public road section) can be counted to obtain the passing frequency of each public road section. The above process is formally expressed as:

[0111] si count = count(si set ,s list ).

[0112] According to the law of large numbers, the more samples there are, the closer the frequency is to probability. Therefore, at least two high-frequency sections can be selected from each of the common sections based on the travel frequency to ensure that there are enough sample data in the first energy consumption time series used to train the model. It is understandable that since other noise factors such as ambient temperature, driving habits, and accidental events will interfere with mileage energy consumption, at least two high-frequency sections are required for subsequent screening, and the number of high-frequency sections can be selected according to specific needs, such as 3 or 4. Then, the second energy consumption time series of each high-frequency section can be obtained, and the second energy consumption time series includes the cumulative usage time and the corresponding mileage energy consumption corresponding to the high-frequency section. Then, according to the standard deviation of each mileage energy consumption in the second energy consumption time series, a reference path can be selected from the high-frequency section. Of course, the range, average difference, etc. can also be used to filter out the reference path from the high-frequency section.

[0113] Wherein, the step of determining the reference path in the high-frequency section according to the second energy consumption time series in step B30 includes:

[0114] Step C10, calculating the energy consumption standard deviation of each of the high-frequency sections according to the second energy consumption time series;

[0115] Step C20: taking the high-frequency section with the smallest energy consumption standard deviation as a reference path.

[0116] After obtaining the second energy consumption time series of each high-frequency section, this embodiment can calculate the energy consumption standard deviation of each high-frequency section (i.e., the standard deviation of each mileage energy consumption in the second energy consumption time series) based on the second energy consumption time series. Then, the high-frequency section with the smallest energy consumption standard deviation can be used as the reference path, and the high-frequency section with the most stable mileage energy consumption change among the high-frequency sections can be used as the reference path. As an example, the number of high-frequency sections is 3, and the above process is formulated as follows:

[0117] i top3efficiency std =std(si top3efficiency}=[std(si efficiency1 ),std(si efficiency2 ),std(siefficiency3 )];

[0118] s baseline =si top3 [argmin(si top3efficiency std )].

[0119] Among them, i top3efficiency std is the set of standard deviations of energy consumption of three high-frequency sections, std() is the standard deviation, si top3efficiency is the set of energy consumption of each mileage of the three high-frequency sections, std(si efficiency1 )、std(si efficiency2 )、std(si efficiency3 ) are the standard deviations of energy consumption of the three high-frequency sections. argmin is the label for taking the minimum value in the set. top3 [] takes the value of the label from the array in the brackets.

[0120] Before the step of obtaining the travel frequency of each public road section in the public road section set in step B20, the following steps are included:

[0121] Step D10, obtaining the section length of each public section in the public section set;

[0122] Step D20, deleting the public road sections whose lengths are lower than a preset length threshold from the public road section set to obtain a new public road section set.

[0123] In this embodiment, it is considered that there are public sections that are too short and it is difficult to characterize the accurate mileage energy consumption under the accumulated usage time. Therefore, by obtaining the section length of each public section in the public section set; deleting the public sections whose section length is lower than the preset length threshold (such as 1000m, 1500m, 2000m, etc.) from the public section set, a new public section set is obtained. In this way, the estimated accuracy of the energy consumption distribution model obtained by training based on the first energy consumption time series of the reference path can be further improved.

[0124] Wherein, the preset initial model is a polynomial exponential distribution model, and the step of training the preset initial model based on the first energy consumption time series to obtain the energy consumption distribution model of the target vehicle in step A30 includes:

[0125] Step E10, substituting each accumulated usage time in the first energy consumption time series and the mileage energy consumption corresponding to each accumulated usage time into the polynomial exponential distribution model to obtain a relationship between a weight coefficient and a scaling factor in the polynomial exponential distribution model;

[0126] Step E20, solving the relationship, obtaining the values ​​of the weight coefficient and the scaling factor, and determining the energy consumption distribution model of the target vehicle.

[0127] Considering the large computing power requirements of the neural network model, the slow offline execution speed and poor effect, this embodiment uses a polynomial exponential distribution model as a preset initial model for training the energy consumption distribution model. The polynomial exponential distribution model is an exponential distribution model with a polynomial as an exponential distribution parameter. Taking the third-order polynomial as an example, the exponential distribution parameter λ i for

[0128]

[0129] The exponential distribution parameter λ i Substituting into the exponential distribution, we get

[0130]

[0131] where t i >0, i represents the i-th moment, and the cumulative usage time of the power battery at the i-th moment is t i , a1, a2, a3 are weight coefficients of the polynomial exponential distribution model; k is a scaling factor used to adjust the dimensional difference between the exponential distribution and the mileage energy consumption (percentage of energy consumption per kilometer). It is understandable that the polynomial is not limited to a third-order polynomial and can be selected according to specific needs. The purpose of using a polynomial in this embodiment is to fit the complex electrochemical properties and usage scenarios of the power battery, because the actual battery is not a theoretical battery, and time and SOH are not necessarily strictly negatively correlated, and there are some nonlinear changes in the middle. Reference Figure 3 , Figure 3 This is an exponential distribution diagram involved in the embodiment of the present application. Figure 3 where λ is the exponential distribution parameter of the exponential distribution, Figure 3 The exponential distribution curves are shown for the cases of λ = 0.5, λ = 1 and λ = 1. The purpose of using the exponential distribution in this embodiment is that the memoryless property of the exponential distribution can better describe the life trend of electrical products, such as the SOH of a battery.

[0132] Therefore, this embodiment can substitute each accumulated usage time in the first energy consumption time series and the mileage energy consumption corresponding to each accumulated usage time into the polynomial exponential distribution model to obtain the relationship between the weight coefficient and the scaling factor in the polynomial exponential distribution model. Then, the relationship is solved to obtain the values ​​of the weight coefficient and the scaling factor, and the energy consumption distribution model of the target vehicle is determined.

[0133] This embodiment uses a polynomial exponential distribution model as a preset initial model for training the energy consumption distribution model. The energy consumption distribution model obtained by such training has a small amount of calculation and runs quickly. Compared with the method using a neural network model, it greatly reduces the computing power requirements, and can also ensure a relatively accurate battery health status estimation when the vehicle is offline and running at low computing power. Even the training process of the energy consumption distribution model can be implemented under the condition of offline low computing power on the vehicle. This embodiment is suitable for offline low computing power scenarios, which effectively broadens the application scenarios of battery health status estimation.

[0134] In the second embodiment of the present application, by obtaining the historical travel information of the target vehicle, a reference path is screened out from the historical travel information, and a first energy consumption time series of the reference path is obtained. Then, a preset initial model is trained based on the first energy consumption time series to obtain an energy consumption distribution model of the target vehicle. Thus, based on the historical travel information of the target vehicle, a first energy consumption time series is determined that characterizes the change in mileage energy consumption of the target vehicle with the accumulated usage time. The energy consumption distribution model obtained by training the first energy consumption time series can be used to accurately estimate the estimated mileage energy consumption corresponding to different usage times.

[0135] Reference Figure 4 , Figure 4 This is a schematic diagram of the structure of the battery health status estimation device of the present application.

[0136] The present application also provides a battery health status estimation device, the battery health status estimation device comprising:

[0137] An acquisition module 10 is used to acquire an energy consumption distribution model and a target usage duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time series in historical travel information of the target vehicle;

[0138] An estimation module 20 is used to input the target usage time into the energy consumption distribution model to obtain an estimated mileage energy consumption corresponding to the target usage time;

[0139] The calculation module 30 is used to calculate the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption.

[0140] Optionally, the battery health status estimation device further includes a model training module, which is used to:

[0141] Obtain historical travel information of the target vehicle;

[0142] Filtering a reference path from the historical travel information, and acquiring a first energy consumption time series of the reference path;

[0143] A preset initial model is trained based on the first energy consumption time series to obtain an energy consumption distribution model of the target vehicle.

[0144] Optionally, the model training module is also used to:

[0145] Acquire each historical travel route of the target vehicle from the historical travel information, and determine a common road section set of each historical travel route;

[0146] Obtaining the travel frequency of each public road section in the public road section set, and selecting at least two high-frequency road sections from each public road section according to the travel frequency;

[0147] A second energy consumption time series of each of the high-frequency sections is obtained, and a reference path in the high-frequency section is determined according to the second energy consumption time series.

[0148] Optionally, the model training module is also used to:

[0149] Calculating the energy consumption standard deviation of each of the high-frequency sections according to the second energy consumption time series;

[0150] The high-frequency section with the smallest energy consumption standard deviation is used as a reference path.

[0151] Optionally, the model training module is also used to:

[0152] Obtaining the section length of each public section in the public section set;

[0153] The public road sections whose road section lengths are lower than a preset length threshold are deleted from the public road section set to obtain a new public road section set.

[0154] Optionally, the preset initial model is a multinomial exponential distribution model, and the model training module is further used to:

[0155] Substituting each accumulated usage time in the first energy consumption time series and the mileage energy consumption corresponding to each accumulated usage time into the polynomial exponential distribution model to obtain a relationship between a weight coefficient and a scaling factor in the polynomial exponential distribution model;

[0156] The relationship is solved to obtain the values ​​of the weight coefficient and the scaling factor, and the energy consumption distribution model of the target vehicle is determined.

[0157] Optionally, the calculation module 30 is further configured to:

[0158] Inputting the preset initial duration into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial duration;

[0159] The ratio of the preset initial mileage energy consumption to the estimated mileage energy consumption is used as the battery health status corresponding to the target usage time.

[0160] like Figure 5 As shown, Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application.

[0161] Specifically, the battery health status estimation device can be a VCU (Vehicle Control Unit), a PC (Personal Computer), a tablet computer, a portable computer or a server.

[0162] like Figure 5 As shown, the battery health status estimation device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0163] Those skilled in the art will understand that Figure 5 The device structure shown in the figure does not constitute a limitation on the battery health status estimation device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0164] like Figure 5 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a battery health status estimation application.

[0165] exist Figure 5In the device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client and communicate data with the client; and the processor 1001 can be used to call the battery health status estimation program stored in the memory 1005 to implement the operations in the battery health status estimation method provided in the above embodiment.

[0166] In addition, the embodiment of the present application also provides a vehicle, the vehicle including the above-mentioned battery health status estimation device. Of course, it is understandable that the vehicle also includes other devices such as energy storage devices and drive devices to ensure the normal operation of the vehicle.

[0167] In addition, an embodiment of the present application also proposes a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the operations in the battery health status estimation method provided in the above embodiment are implemented. The specific steps will not be repeated here.

[0168] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such actual relationship or order between these entities / operations / objects; the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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 system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0169] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, and the units described as separate components may or may not be physically separated. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0170] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0171] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, including a number of instructions for a terminal device (which can be a mobile phone, computer, server, vehicle, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0172] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for estimating a battery health state, characterized in that: The battery health status estimation method comprises the following steps: Obtaining an energy consumption distribution model and a target usage duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time series in historical travel information of the target vehicle; Inputting the target usage time into the energy consumption distribution model to obtain the estimated mileage energy consumption corresponding to the target usage time; The battery health status corresponding to the target usage time is calculated based on the estimated mileage energy consumption and the preset initial mileage energy consumption.

2. The battery health status estimation method according to claim 1, characterized in that: Before the step of obtaining the energy consumption distribution model and target usage time of the target vehicle, the following steps are included: Obtain historical travel information of the target vehicle; Filtering a reference path from the historical travel information, and acquiring a first energy consumption time series of the reference path; A preset initial model is trained based on the first energy consumption time series to obtain an energy consumption distribution model of the target vehicle.

3. The battery health status estimation method according to claim 2, characterized in that: The step of selecting a reference path from the historical travel information includes: Acquire each historical travel route of the target vehicle from the historical travel information, and determine a common road section set of each historical travel route; Obtaining the travel frequency of each public road section in the public road section set, and selecting at least two high-frequency road sections from each public road section according to the travel frequency; A second energy consumption time series of each of the high-frequency sections is obtained, and a reference path in the high-frequency section is determined according to the second energy consumption time series.

4. The battery health status estimation method according to claim 3, characterized in that: The step of determining the reference path in the high-frequency section according to the second energy consumption time series comprises: Calculating the energy consumption standard deviation of each of the high-frequency sections according to the second energy consumption time series; The high-frequency section with the smallest energy consumption standard deviation is used as a reference path.

5. The battery health status estimation method according to claim 3, characterized in that: Before the step of obtaining the travel frequency of each public road section in the public road section set, the method includes: Obtaining the section length of each public section in the public section set; The public road sections whose road section lengths are lower than a preset length threshold are deleted from the public road section set to obtain a new public road section set.

6. The battery health status estimation method according to claim 2, characterized in that: The preset initial model is a polynomial exponential distribution model, and the step of training the preset initial model based on the first energy consumption time series to obtain the energy consumption distribution model of the target vehicle includes: Substituting each accumulated usage time in the first energy consumption time series and the mileage energy consumption corresponding to each accumulated usage time into the polynomial exponential distribution model to obtain a relationship between a weight coefficient and a scaling factor in the polynomial exponential distribution model; The relationship is solved to obtain the values ​​of the weight coefficient and the scaling factor, and the energy consumption distribution model of the target vehicle is determined.

7. The battery health status estimation method according to claim 1, characterized in that: Before the step of calculating the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption, the method includes: Inputting the preset initial duration into the energy consumption distribution model to obtain the preset initial mileage energy consumption corresponding to the preset initial duration; The step of calculating the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption includes: The ratio of the preset initial mileage energy consumption to the estimated mileage energy consumption is used as the battery health status corresponding to the target usage time.

8. A battery health status estimation device, characterized in that: The battery health status estimation device comprises: An acquisition module, used to acquire an energy consumption distribution model and a target usage duration of a target vehicle, wherein the energy consumption distribution model is constructed by a first energy consumption time series in historical travel information of the target vehicle; An estimation module, used to input the target usage time into the energy consumption distribution model to obtain an estimated mileage energy consumption corresponding to the target usage time; The calculation module is used to calculate the battery health status corresponding to the target usage time according to the estimated mileage energy consumption and the preset initial mileage energy consumption.

9. A battery health status estimation device, characterized in that: The battery health state estimation device includes: a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the computer program is executed by the processor, the steps of the battery health state estimation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a battery health state estimation program, and when the battery health state estimation program is executed by a processor, the steps of the battery health state estimation method according to any one of claims 1 to 7 are implemented.