Life prediction method, device and electronic equipment for new energy vehicle battery pack

Abstract

The present invention provides a method, apparatus and electronic device for predicting the lifespan of a battery pack of a new energy vehicle, including: obtaining the operating conditions characteristics and behavior characteristics of the battery pack to be predicted within a current preset interval; using a decay degree classification model to classify the decay degree of the operating conditions characteristics and behavior characteristics, so as to obtain the probabilities corresponding to the battery pack to be predicted in each decay degree category; obtaining the current vehicle data of the new energy vehicle corresponding to the battery pack to be predicted, and based on the current vehicle data and the lifespan prediction models corresponding to each decay degree category, obtaining the lifespan prediction results corresponding to the battery pack to be predicted in each decay degree category; determining the lifespan prediction result of the battery pack to be predicted according to the probabilities corresponding to the battery pack to be predicted in each decay degree category and the lifespan prediction results corresponding to the battery pack to be predicted in each decay degree category. The lifespan prediction method of the present invention can predict the lifespan of the battery pack on the premise of taking into account both the calculation amount and the prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of batteries, and in particular to a life prediction method, device and electronic equipment for a new energy vehicle battery pack. Background Art

[0002] In recent years, as the energy crisis has become more and more serious, new energy vehicles have become the focus of future vehicle industry development due to their excellent energy-saving and environmental protection characteristics. Among them, the life of the battery pack installed in new energy vehicles directly affects the performance and operation of new energy vehicles. Therefore, predicting the life of new energy vehicle battery packs has become a crucial part of new energy vehicle research.

[0003] The existing life prediction methods for new energy vehicle battery packs generally include the following two methods: One is to establish a life prediction function model for each new energy vehicle battery pack. The specific process is: first obtain the SOH (State Of Health) of a new energy vehicle battery pack at multiple historical mileage points, and then construct a life prediction function model with unknown parameters (for example, a single exponential function model, SOH = ae bx +c, where a, b and c are unknown parameters, and e is a natural constant, approximately equal to 2.71828), the values ​​of each historical point (as x in the life prediction function model) and the corresponding SOH values ​​are brought into the above life prediction function model, and the simultaneous equations can be solved to obtain the values ​​of each unknown parameter in the life prediction function model. In this way, the life prediction function model of the new energy vehicle battery pack is determined, and then the SOH is set to 0.8 (when SOH is equal to 0.8, it means that the battery pack has ended its life). The mileage value obtained by the solution is the life prediction result of the new energy vehicle battery pack, that is, the mileage value corresponding to the end of the life of the new energy vehicle battery pack. This life prediction method requires a life prediction function model to be established for each new energy vehicle battery pack, which has a large amount of calculation. In addition, when the data of a single vehicle is small, the initial attenuation trend is not obvious, and it will be impossible to accurately fit the unknown parameters; the other is to establish a unified life prediction function model for the battery packs of all new energy vehicles. The specific process is: first obtain the SOH (State Of Health) of all vehicles of the new energy vehicle battery pack at multiple historical mileage points, and then build a life prediction function model with unknown parameters (for example, a single exponential function model SOH = ae bx+c, where a, b and c are unknown parameters, and e is a natural constant, approximately equal to 2.71828), the values ​​of each historical point (as x in the life prediction function model) and the corresponding SOH values ​​are brought into the above life prediction function model, and the simultaneous equations can be solved to obtain the values ​​of each unknown parameter in the life prediction function model. In this way, the life prediction function model of the new energy vehicle battery pack is determined. In this way, when the SOH is set to 0.8 (when SOH is equal to 0.8, it means that the battery pack has reached the end of its life), the mileage value obtained is the life prediction result of all new energy vehicle battery packs. The life prediction result obtained by this life prediction method is not accurate enough, because different battery packs have different degrees of attenuation during use. If the life prediction function model obtained by the above process is directly used to predict the life of all new energy vehicle battery packs, the life prediction result obtained will have a large deviation.

[0004] In summary, how to predict the life of a battery pack while taking into account both the amount of calculation and the accuracy of prediction has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a life prediction method, device and electronic device for a new energy vehicle battery pack, so as to alleviate the technical problem that the prior art cannot predict the life of the battery pack while taking into account both the amount of calculation and the prediction accuracy.

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting the life of a battery pack of a new energy vehicle, the method comprising:

[0007] Obtaining the operating condition characteristics and behavior characteristics of the battery pack to be predicted within the current preset range;

[0008] Using an attenuation degree classification model to classify the attenuation degree of the operating condition characteristics and the behavior characteristics, and obtain the corresponding probability of the battery pack to be predicted in each attenuation degree category;

[0009] Acquire current vehicle data of the new energy vehicle to be predicted corresponding to the battery pack to be predicted, and calculate the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted based on the current vehicle data and a pre-constructed life prediction model corresponding to each attenuation degree category;

[0010] The life prediction result of the battery pack to be predicted is determined according to the probability corresponding to the battery pack to be predicted in each attenuation degree category and the life prediction result corresponding to the battery pack to be predicted in each attenuation degree category.

[0011] Further, determining the life prediction result of the battery pack to be predicted according to the probability corresponding to each attenuation degree category of the battery pack to be predicted and the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted includes:

[0012] Performing a product operation on the probability and life prediction result corresponding to the battery pack to be predicted in the same attenuation degree category to obtain the product operation result corresponding to the battery pack to be predicted in each attenuation degree category;

[0013] The product operation results corresponding to the battery pack to be predicted in each attenuation degree category are added up to obtain the life prediction result of the battery pack to be predicted.

[0014] Further, determining the life prediction result of the battery pack to be predicted according to the probability corresponding to each attenuation degree category of the battery pack to be predicted and the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted also includes:

[0015] Determining the maximum probability among the probabilities corresponding to the battery pack to be predicted in each attenuation degree category;

[0016] Taking the attenuation degree category corresponding to the maximum probability as the target attenuation degree category;

[0017] The life prediction result corresponding to the battery pack to be predicted in the target attenuation degree category is used as the life prediction result of the battery pack to be predicted.

[0018] Furthermore, the method further comprises:

[0019] Obtain historical SOH data of a battery pack of a new energy vehicle at a historical characterization point, and determine the future SOH attenuation degree of the battery pack at each target historical characterization point according to the historical SOH data of the historical characterization point, wherein the historical characterization point includes: a historical time point or a historical mileage point, and the target historical characterization point is a historical characterization point among the historical characterization points where a future SOH attenuation degree exists;

[0020] Determining the attenuation category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point;

[0021] In each attenuation degree category, a life prediction model is established according to the historical SOH data of the battery pack at each target historical characterization point, so as to obtain a life prediction model corresponding to each attenuation degree category;

[0022] Acquire the operating condition characteristics and behavior characteristics of the new energy vehicle within a preset interval of each target historical characterization point, and use the operating condition characteristics, the behavior characteristics, and the attenuation degree category of the battery pack of the new energy vehicle at each target historical characterization point as training samples;

[0023] The training samples are used to train the original attenuation degree classification model to obtain the attenuation degree classification model.

[0024] Further, determining the attenuation category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point includes:

[0025] The future SOH attenuation degree of the battery pack at each target historical characterization point is grouped according to a preset grouping strategy to obtain a future SOH attenuation degree grouping;

[0026] In each of the future SOH attenuation degree groups, the future SOH attenuation degrees are classified into attenuation degree categories to obtain the attenuation degree category of each future SOH attenuation degree at its corresponding target historical representation point;

[0027] The attenuation degree category of the battery pack at each target historical characterization point is determined according to the attenuation degree category of each future SOH attenuation degree at its corresponding target historical characterization point.

[0028] Further, determining the future SOH attenuation degree of the battery pack at each target historical characterization point according to the historical SOH data of the historical characterization point includes:

[0029] Determining, among the historical SOH data of the historical characterization points, first historical SOH data at each target historical characterization point;

[0030] Determining, from the historical SOH data of the historical characterization points, second historical SOH data of future historical characterization points after each target historical characterization point, wherein the difference between the future historical characterization point and its corresponding target historical characterization point is a preset value;

[0031] The future SOH attenuation degree of the battery pack at each target historical characterization point is calculated based on the first historical SOH data and the second historical SOH data.

[0032] Furthermore, in each attenuation degree category, a life prediction model is established according to the historical SOH data of the battery pack at each target historical characterization point, and the life prediction model corresponding to each attenuation degree category is obtained, including:

[0033] In each attenuation degree category, the unknown parameters in the preset life prediction function are calculated according to the historical SOH data of the battery pack at each target historical characterization point, thereby obtaining a preset life prediction function with known unknown parameters, wherein the preset life prediction function is a function between the SOH and the characterization point;

[0034] The preset life prediction function with known unknown parameters is used as the life prediction model, so as to obtain the life prediction model corresponding to each attenuation degree category.

[0035] Furthermore, the preset interval includes: a preset time interval or a preset mileage interval, and the current vehicle data includes: current time data or current mileage data.

[0036] In a second aspect, an embodiment of the present invention further provides a life prediction device for a battery pack of a new energy vehicle, the device comprising:

[0037] An acquisition unit, used to acquire the operating condition characteristics and behavior characteristics of the battery pack to be predicted within a current preset range;

[0038] An attenuation degree classification unit, used to classify the attenuation degree of the operating condition characteristics and the behavior characteristics using an attenuation degree classification model, and obtain the corresponding probability of the battery pack to be predicted in each attenuation degree category;

[0039] A life prediction unit, used to obtain current vehicle data of the new energy vehicle to be predicted corresponding to the battery pack to be predicted, and calculate the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted based on the current vehicle data and a pre-constructed life prediction model corresponding to each attenuation degree category;

[0040] The life prediction result determination unit is used to determine the life prediction result of the battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category.

[0041] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0042] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to execute any method described in the first aspect above.

[0043] In an embodiment of the present invention, a method for predicting the life of a battery pack of a new energy vehicle is provided, the method comprising: obtaining operating characteristics and behavioral characteristics of the battery pack to be predicted within a current preset range; using an attenuation degree classification model to classify the operating characteristics and behavioral characteristics into attenuation degrees, and obtaining the corresponding probabilities of the battery pack to be predicted in each attenuation degree category; obtaining current vehicle data of a new energy vehicle to be predicted corresponding to the battery pack to be predicted, and based on the current vehicle data and a pre-constructed life prediction model corresponding to each attenuation degree category, calculating the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category; determining the life prediction results of the battery pack to be predicted according to the corresponding probabilities of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category. From the above description, it can be seen that in the life prediction method of the present invention, only an attenuation degree classification model and a life prediction model corresponding to the number of attenuation degree categories are needed to achieve the purpose of predicting the life of the battery pack to be predicted. Compared with the method of establishing a life prediction function model for each battery pack to be predicted, the life prediction method of the present invention has a small amount of calculation. Compared with the method of establishing a unified life prediction function model for all battery packs to be predicted, the life prediction method of the present invention takes into account the attenuation degree category of the battery pack to be predicted, and then combines the attenuation degree category of the battery pack to be predicted and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category to determine the final life prediction result, so that the determined life prediction result of the battery pack to be predicted is more accurate. In other words, the life prediction method of the present invention can predict the life of the battery pack while taking into account both the amount of calculation and the prediction accuracy, thereby alleviating the technical problem that the prior art cannot predict the life of the battery pack while taking into account both the amount of calculation and the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A flow chart of a life prediction method for a new energy vehicle battery pack provided by an embodiment of the present invention;

[0046] Figure 2 A flow chart of a method for determining a life prediction result of a battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category provided by an embodiment of the present invention;

[0047] Figure 3 A flow chart of another method for determining a life prediction result of a battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category provided by an embodiment of the present invention;

[0048] Figure 4 A flow chart of a method for establishing a life prediction model and a decay degree classification model provided in an embodiment of the present invention;

[0049] Figure 5 A schematic diagram of a life prediction device for a new energy vehicle battery pack provided by an embodiment of the present invention;

[0050] Figure 6 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Among the existing life prediction methods for new energy vehicle battery packs, one is to establish a life prediction function model for each new energy vehicle battery pack. The life prediction results of the battery packs predicted by this method are accurate, but the calculation amount is large; the other is to establish a unified life prediction function model for the battery packs of all new energy vehicles. The calculation amount of this method is small, but the life prediction results obtained will have large deviations.

[0053] Based on this, in the life prediction method of the present invention, only an attenuation degree classification model and a life prediction model corresponding to the number of attenuation degree categories are needed to achieve the purpose of predicting the life of the battery pack to be predicted. Compared with the method of establishing a life prediction function model for each battery pack to be predicted, the life prediction method of the present invention has a small amount of calculation. Compared with the method of establishing a unified life prediction function model for all battery packs to be predicted, the life prediction method of the present invention takes into account the attenuation degree category of the battery pack to be predicted, and then combines the attenuation degree category of the battery pack to be predicted and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category to determine the final life prediction result, so that the determined life prediction result of the battery pack to be predicted is more accurate. In other words, the life prediction method of the present invention can predict the life of the battery pack under the premise of taking into account both the amount of calculation and the prediction accuracy.

[0054] To facilitate understanding of this embodiment, a life prediction method for a new energy vehicle battery pack disclosed in an embodiment of the present invention is first introduced in detail.

[0055] Embodiment 1:

[0056] According to an embodiment of the present invention, an embodiment of a method for predicting the life of a battery pack of a new energy vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0057] Figure 1 is a flow chart of a method for predicting the life of a battery pack for a new energy vehicle according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0058] Step S102, obtaining the operating condition characteristics and behavior characteristics of the battery pack to be predicted within the current preset interval;

[0059] In an embodiment of the present invention, the above-mentioned preset interval can be a preset time interval, and can also be a preset mileage interval; when the above-mentioned preset interval is a preset time interval, the current preset interval can be the 90 days before the current time; when the above-mentioned preset interval is a preset mileage interval, the current preset interval can be the first 10,000 miles of the current mileage. Of course, the embodiment of the present invention does not impose specific restrictions on the specific values ​​of the preset time interval and the specific values ​​of the preset mileage interval, and can also be other values.

[0060] The above-mentioned operating condition characteristics refer to the charging / discharging / stationary data related to the battery to be predicted, for example, the temperature during charging / discharging / stationary, the current during charging / discharging / stationary, the voltage during charging / discharging / stationary, etc.

[0061] The above-mentioned behavior characteristics refer to the relevant data of the user's charging / discharging / stationary behavior of the battery to be predicted, for example, the number of times of charging per week, the mileage data corresponding to the discharge (i.e., the mileage of the vehicle to which the battery to be predicted belongs), etc.

[0062] The above operating condition characteristics and behavior characteristics can be obtained by statistical analysis of the real-time monitoring data (RTM data) of the new energy vehicle.

[0063] Step S104, using the attenuation degree classification model to classify the attenuation degree of the operating condition characteristics and the behavior characteristics, and obtaining the corresponding probability of the battery pack to be predicted in each attenuation degree category;

[0064] The above-mentioned attenuation degree classification model is a pre-built model for classifying the attenuation degree of the battery. The number of attenuation degree categories divided by the attenuation degree classification model is related to the attenuation degree category division during the attenuation degree classification model training. In the embodiment of the present invention, the attenuation degree categories are divided into three categories, namely, abnormal attenuation category, normal attenuation category and slow attenuation category. Of course, the embodiment of the present invention does not specifically limit the above-mentioned attenuation degree categories.

[0065] Specifically, the operating condition characteristics and behavior characteristics obtained in step S102 are input into the attenuation classification model, and the attenuation classification model will output the probability of the battery pack to be predicted in each attenuation category, that is, the future attenuation category of the battery pack to be predicted after the current time or the current mileage can be known. For example, the probability of the battery pack to be predicted in the abnormal attenuation category is 0.2, the probability of the battery pack to be predicted in the normal attenuation category is 0.6, and the probability of the battery pack to be predicted in the slow attenuation category is 0.2.

[0066] Step S106, obtaining the current vehicle data of the new energy vehicle to be predicted corresponding to the battery pack to be predicted, and calculating the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category based on the current vehicle data and the pre-built life prediction model corresponding to each attenuation degree category;

[0067] Specifically, the above-mentioned current vehicle data can be the current mileage data, for example, the current mileage, or the current time data, for example, the current number of days of use. The specific type of vehicle data needs to be determined based on a pre-built life prediction model. If the life prediction model is a function of mileage and SOH, then the current vehicle data is the current mileage data. If the life prediction model is a function of time and SOH, then the current vehicle data is the current time data.

[0068] In an embodiment of the present invention, a life prediction model is pre-constructed for each attenuation category. For example, three life prediction models are constructed correspondingly, namely, a life prediction model corresponding to the abnormal attenuation category, a life prediction model corresponding to the normal attenuation category, and a life prediction model corresponding to the slow attenuation category. In this way, based on the current vehicle data and the pre-constructed life prediction models corresponding to each attenuation category, after corresponding calculations, the corresponding life prediction results of the battery pack to be predicted in each attenuation category will be obtained. That is to say, the present invention will use the above three life prediction models to perform a life prediction on the battery pack to be predicted, respectively, to obtain a preliminary life prediction result. The final life prediction result also needs to be determined in combination with the relevant information of the attenuation category of the battery pack to be predicted obtained in step S104.

[0069] It should be noted that the above life prediction results refer to the remaining mileage or days when the predicted battery pack ends its life (i.e. when the SOH of the predicted battery pack reaches 80%). If the life prediction model is a function of mileage and SOH, then the life prediction result is the remaining mileage of the predicted battery pack; if the life prediction model is a function of time and SOH, then the life prediction result is the remaining days of the predicted battery pack.

[0070] Specifically, if the life prediction model is a functional relationship between mileage and SOH (here the functional relationship between mileage and SOH is used as an example for explanation, and it can also be a functional relationship between time and SOH), the SOH value in the functional relationship can be set to 0.8, and the corresponding mileage can be obtained by solving, and then the current mileage data (i.e., current vehicle data) is subtracted from the solved mileage to obtain the remaining mileage of the battery pack to be predicted; if the SOH value in the functional relationship is set to 0.8 and the corresponding mileage cannot be solved, then the current mileage data can be pushed back according to the preset size interval (for example, the current mileage data is 10,000, and it is pushed back according to the interval of 1,000, which are 11,000, 12,000, 13,000...), and substituted into the functional relationship respectively to see which mileage has an SOH size of 0.8 after being substituted (if none of them are equal to 0.8, the mileage corresponding to the value before 0.8 will be taken), which is the mileage obtained by solving, and then the current mileage data is subtracted from the solved mileage to obtain the remaining mileage of the battery pack to be predicted.

[0071] The life prediction model corresponding to the above-mentioned attenuation degree categories can also be a neural network model. If it is a neural network model, then by inputting the current vehicle data into the pre-built life prediction model corresponding to each attenuation degree category, the life prediction results (remaining mileage or days) corresponding to the battery pack to be predicted in each attenuation degree category can be output.

[0072] Step S108 , determining the life prediction result of the battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category.

[0073] When predicting the life of the battery pack to be predicted, by comprehensively considering the corresponding probabilities of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category, the final life prediction results of the battery pack to be predicted are more accurate. This process is described in detail below and will not be repeated here.

[0074] In an embodiment of the present invention, a method for predicting the life of a battery pack of a new energy vehicle is provided, the method comprising: obtaining operating characteristics and behavioral characteristics of the battery pack to be predicted within a current preset range; using an attenuation degree classification model to classify the operating characteristics and behavioral characteristics into attenuation degrees, and obtaining the corresponding probabilities of the battery pack to be predicted in each attenuation degree category; obtaining current vehicle data of a new energy vehicle to be predicted corresponding to the battery pack to be predicted, and based on the current vehicle data and a pre-constructed life prediction model corresponding to each attenuation degree category, calculating the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category; determining the life prediction results of the battery pack to be predicted according to the corresponding probabilities of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category. From the above description, it can be seen that in the life prediction method of the present invention, only an attenuation degree classification model and a life prediction model corresponding to the number of attenuation degree categories are needed to achieve the purpose of predicting the life of the battery pack to be predicted. Compared with the method of establishing a life prediction function model for each battery pack to be predicted, the life prediction method of the present invention has a small amount of calculation. Compared with the method of establishing a unified life prediction function model for all battery packs to be predicted, the life prediction method of the present invention takes into account the attenuation degree category of the battery pack to be predicted, and then combines the attenuation degree category of the battery pack to be predicted and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category to determine the final life prediction result, so that the determined life prediction result of the battery pack to be predicted is more accurate. In other words, the life prediction method of the present invention can predict the life of the battery pack while taking into account both the amount of calculation and the prediction accuracy, thereby alleviating the technical problem that the prior art cannot predict the life of the battery pack while taking into account both the amount of calculation and the prediction accuracy.

[0075] In an alternative embodiment of the present invention, reference Figure 2 , determining the life prediction result of the battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category, specifically including the following steps:

[0076] Step S201, performing a product operation on the probability and life prediction result corresponding to the battery pack to be predicted in the same attenuation degree category to obtain the product operation result corresponding to each attenuation degree category of the battery pack to be predicted;

[0077] Specifically, as in the above example, the probability of the battery pack to be predicted in the abnormal attenuation category is multiplied by the life prediction result of the battery pack to be predicted in the abnormal attenuation category, and the probability of the battery pack to be predicted in the normal attenuation category is multiplied by the life prediction result of the battery pack to be predicted in the normal attenuation category, and the probability of the battery pack to be predicted in the slow attenuation category is multiplied by the life prediction result of the battery pack to be predicted in the slow attenuation category, and the product operation results of the battery pack to be predicted in the abnormal attenuation category, the normal attenuation category and the slow attenuation category can be obtained respectively.

[0078] Step S202 , performing a sum operation on the product operation results corresponding to the battery pack to be predicted in each attenuation degree category to obtain a life prediction result of the battery pack to be predicted.

[0079] It can be seen that this life prediction method integrates the results of various attenuation degree classifications and is more accurate than the traditional life prediction method that uses a unified life prediction function model.

[0080] In an alternative embodiment of the present invention, reference Figure 3 , determining the life prediction result of the battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category, further comprising the following steps:

[0081] Step S301, determining the maximum probability among the probabilities corresponding to the battery pack to be predicted in each attenuation degree category;

[0082] Specifically, as in the above example, the probability of the battery pack to be predicted being in the abnormal attenuation class is 0.2, the probability of the battery pack to be predicted being in the normal attenuation class is 0.6, and the probability of the battery pack to be predicted being in the slow attenuation class is 0.2. Then, among the probabilities corresponding to the battery pack to be predicted in each attenuation degree category, the maximum probability is 0.6.

[0083] Step S302, taking the attenuation degree category corresponding to the maximum probability as the target attenuation degree category;

[0084] As exemplified in the above step S301 , the target attenuation level category is the normal attenuation category.

[0085] Step S303 , taking the life prediction result corresponding to the target attenuation degree category of the battery pack to be predicted as the life prediction result of the battery pack to be predicted.

[0086] As exemplified in the above step S302, the life prediction result corresponding to the battery pack to be predicted in the normal attenuation class is the final life prediction result.

[0087] It can be seen that this life prediction method directly uses the life prediction result corresponding to the target attenuation degree category of the battery pack to be predicted as the final life prediction result, and also integrates the target attenuation degree category of the battery pack to be predicted. It is more accurate than the traditional life prediction method that uses a unified life prediction function model (without considering the battery attenuation degree).

[0088] The following describes the process of establishing the life prediction model and the attenuation degree classification model.

[0089] In an alternative embodiment of the present invention, reference Figure 4 ,The process of establishing the life prediction model and the attenuation degree classification model includes the following steps:

[0090] Step S401, obtaining historical SOH data of a battery pack of a new energy vehicle at a historical characterization point, and determining the future SOH attenuation degree of the battery pack at each target historical characterization point according to the historical SOH data of the historical characterization point, wherein the historical characterization point includes: a historical time point or a historical mileage point, and the target historical characterization point is a historical characterization point with a future SOH attenuation degree among the historical characterization points;

[0091] Specifically, if the historical representation point is a historical mileage point, the historical SOH data of the historical representation point include: the first historical SOH data of 10,000 miles, the second historical SOH data of 20,000 miles, the third historical SOH data of 30,000 miles, and the fourth historical SOH data of 40,000 miles. The future SOH attenuation degree represents the future SOH attenuation degree of the future 10,000 miles. Then the target historical mileage points include: 10,000 miles, 20,000 miles and 30,000 miles, because they all have future SOH attenuation degrees, and there is no fifth historical SOH data of the future 10,000 miles for 40,000 miles, so the future SOH attenuation degree of 40,000 miles cannot be determined, that is, 40,000 miles is not the target historical mileage point.

[0092] The process specifically includes:

[0093] (1) determining the first historical SOH data at each target historical representation point from the historical SOH data of the historical representation point;

[0094] (2) determining, from the historical SOH data of the historical representation points, second historical SOH data of future historical representation points after each target historical representation point, wherein the difference between the future historical representation point and its corresponding target historical representation point is a preset value;

[0095] If the historical representation point is a historical time point, the above preset value may be a preset value of days, such as 90 days, 180 days, etc.; if the historical representation point is a historical mileage point, the above preset value may be a preset value of mileage, such as 10,000 kilometers, etc.

[0096] (3) Calculate the future SOH attenuation degree of the battery pack at each target historical characterization point based on the first historical SOH data and the second historical SOH data.

[0097] Specifically, the future SOH attenuation degree of the battery pack at each target historical characterization point can be obtained by performing a difference calculation.

[0098] Step S402, determining the attenuation category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point;

[0099] The specific steps include:

[0100] (1) The future SOH attenuation degree of the battery pack at each target historical characterization point is grouped according to a preset grouping strategy to obtain a future SOH attenuation degree grouping;

[0101] The above preset grouping strategy can be 10,000 kilometers as a group (10,000 kilometers, the performance of the battery pack is relatively similar, there will not be much difference, so 10,000 kilometers is regarded as a group), and can also be 90 days as a group.

[0102] For example, 0--10,000 kilometers is one group, 10,000 kilometers--20,000 kilometers is one group, and 20,000 kilometers--30,000 kilometers is one group. If the future SOH attenuation degree of the battery pack at each target historical characterization point includes: the future SOH attenuation degree of the battery pack at 9,000 kilometers, the future SOH attenuation degree of the battery pack at 9,030 kilometers, and the future SOH attenuation degree of the battery pack at 9,230 kilometers, then the future SOH attenuation degree of the battery pack at 9,000 kilometers, the future SOH attenuation degree of the battery pack at 9,030 kilometers, and the future SOH attenuation degree of the battery pack at 9,230 kilometers are divided into the group of 0--10,000 kilometers, that is, divided into one group.

[0103] (2) In each future SOH attenuation degree group, the future SOH attenuation degrees are classified into attenuation degree categories to obtain the attenuation degree category of each future SOH attenuation degree at its corresponding target historical representation point;

[0104] Specifically, the future SOH attenuation degree is classified into attenuation degree categories using the quantile method or the box plot method.

[0105] The following is an explanation of the process of using the quantile method to classify the future SOH attenuation degree into attenuation degree categories:

[0106] The future SOH attenuation degrees in each future SOH attenuation degree group can be arranged in ascending order. The first 25% dSOH is relatively small and is defined as an abnormal attenuation class; the middle 50% (i.e., quantiles 25%-75%) are defined as a normal attenuation class; the last 25% dSOH is relatively large and is defined as a slow attenuation class. In this way, the attenuation degree category of each future SOH attenuation degree at its corresponding target historical representation point can be obtained.

[0107] (3) Determine the attenuation category of the battery pack at each target historical characterization point based on the attenuation category of each future SOH attenuation degree at its corresponding target historical characterization point.

[0108] Specifically, the attenuation category of each future SOH attenuation degree at its corresponding target historical characterization point is used as the attenuation category of the corresponding battery pack (the battery pack corresponding to each future SOH attenuation degree) at each target historical characterization point.

[0109] Step S403, in each attenuation degree category, a life prediction model is established according to the historical SOH data of the battery pack at each target historical characterization point, to obtain a life prediction model corresponding to each attenuation degree category;

[0110] The specific steps include:

[0111] (1) In each degradation degree category, the unknown parameters in the preset life prediction function are calculated according to the historical SOH data of the battery pack at each target historical characterization point, thereby obtaining a preset life prediction function with known unknown parameters, wherein the preset life prediction function is a function between the SOH and the characterization point; the characterization point includes: a time point or a mileage point;

[0112] Specifically, the historical SOH data of the battery pack at each target historical characterization point is substituted into a preset life prediction function, and a set of equations is solved to obtain the values ​​of unknown parameters in the preset life prediction function.

[0113] (2) A preset life prediction function with known unknown parameters is used as a life prediction model, and then a life prediction model corresponding to each attenuation degree category is obtained.

[0114] In addition, the life prediction model corresponding to each attenuation degree category can also be a neural network model. During training, in each attenuation degree category, it is necessary to obtain the life results (remaining mileage or days) of the battery pack at each target historical representation point, and then use each target historical representation point and the corresponding life results as training samples to train the initial life prediction model, and then obtain the life prediction model corresponding to each attenuation degree category.

[0115] Step S404, obtaining the operating condition characteristics and behavior characteristics of the new energy vehicle within a preset interval of each target historical characterization point, and using the operating condition characteristics, behavior characteristics and attenuation degree category of the battery pack of the new energy vehicle at each target historical characterization point as training samples;

[0116] The above-mentioned preset interval includes: a preset time interval or a preset mileage interval. If the above-mentioned preset value is a preset value of days, then the preset interval here is also a preset time interval. If the above-mentioned preset value is a preset value of mileage, then the preset interval here is also a preset mileage interval. However, the preset time interval here may be different from or the same as the above-mentioned preset value of days, and the preset mileage interval may be different from or the same as the above-mentioned preset value of mileage.

[0117] The above-mentioned within the preset interval of each target historical characterization point refers to within the previous preset time interval or preset mileage interval of each target historical characterization point.

[0118] Step S405: Use training samples to train the original attenuation degree classification model to obtain an attenuation degree classification model.

[0119] In the life prediction method of the present invention, only an attenuation degree classification model and a life prediction model corresponding to the number of attenuation degree categories are needed to achieve the purpose of predicting the life of the battery pack to be predicted. Compared with the method of establishing a life prediction function model for each battery pack to be predicted, the life prediction method of the present invention has a small amount of calculation. Compared with the method of establishing a unified life prediction function model for all battery packs to be predicted, the life prediction method of the present invention takes into account the attenuation degree category of the battery pack to be predicted, and then combines the attenuation degree category of the battery pack to be predicted and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category to determine the final life prediction result, so that the determined life prediction result of the battery pack to be predicted is more accurate. In other words, the life prediction method of the present invention can predict the life of the battery pack under the premise of taking into account both the amount of calculation and the prediction accuracy.

[0120] Embodiment 2:

[0121] An embodiment of the present invention also provides a life prediction device for a new energy vehicle battery pack. The life prediction device for a new energy vehicle battery pack is mainly used to execute the life prediction method for a new energy vehicle battery pack provided in Embodiment 1 of the present invention. The life prediction device for a new energy vehicle battery pack provided in the embodiment of the present invention is specifically introduced below.

[0122] Figure 5 is a schematic diagram of a life prediction device for a new energy vehicle battery pack according to an embodiment of the present invention. Figure 5As shown, the device mainly includes: an acquisition unit 10, an attenuation degree classification unit 20, a life prediction unit 30 and a life prediction result determination unit 40, wherein:

[0123] An acquisition unit, used to acquire the operating condition characteristics and behavior characteristics of the battery pack to be predicted within a current preset range;

[0124] An attenuation degree classification unit is used to classify the attenuation degree of the operating condition characteristics and the behavior characteristics using an attenuation degree classification model, and obtain the corresponding probability of the battery pack to be predicted in each attenuation degree category;

[0125] The life prediction unit is used to obtain the current vehicle data of the new energy vehicle to be predicted corresponding to the battery pack to be predicted, and calculate the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted based on the current vehicle data and the pre-built life prediction model corresponding to each attenuation degree category;

[0126] The life prediction result determination unit is used to determine the life prediction result of the battery pack to be predicted according to the corresponding probability of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction result of the battery pack to be predicted in each attenuation degree category.

[0127] In an embodiment of the present invention, a life prediction device for a battery pack of a new energy vehicle is provided, and the device includes: obtaining operating condition characteristics and behavioral characteristics of the battery pack to be predicted within a current preset range; using an attenuation degree classification model to classify the operating condition characteristics and behavioral characteristics into attenuation degrees, and obtaining the corresponding probabilities of the battery pack to be predicted in each attenuation degree category; obtaining current vehicle data of a new energy vehicle to be predicted corresponding to the battery pack to be predicted, and based on the current vehicle data and a pre-constructed life prediction model corresponding to each attenuation degree category, calculating the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category; determining the life prediction results of the battery pack to be predicted according to the corresponding probabilities of the battery pack to be predicted in each attenuation degree category and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category. From the above description, it can be seen that in the life prediction device of the present invention, only an attenuation degree classification model and a life prediction model corresponding to the number of attenuation degree categories are needed to achieve the purpose of predicting the life of the battery pack to be predicted. Compared with the method of establishing a life prediction function model for each battery pack to be predicted, the life prediction method of the present invention has a small amount of calculation. Compared with the method of establishing a unified life prediction function model for all battery packs to be predicted, the life prediction method of the present invention takes into account the attenuation degree category of the battery pack to be predicted, and then combines the attenuation degree category of the battery pack to be predicted and the corresponding life prediction results of the battery pack to be predicted in each attenuation degree category to determine the final life prediction result, so that the determined life prediction result of the battery pack to be predicted is more accurate. In other words, the life prediction device of the present invention can predict the life of the battery pack while taking into account the amount of calculation and the prediction accuracy, thereby alleviating the technical problem that the prior art cannot predict the life of the battery pack while taking into account the amount of calculation and the prediction accuracy.

[0128] Optionally, the life prediction result determination unit is also used to: perform a product operation on the probability and life prediction result corresponding to the battery pack to be predicted in the same attenuation degree category to obtain the product operation results corresponding to the battery pack to be predicted in each attenuation degree category; perform a sum operation on the product operation results corresponding to the battery pack to be predicted in each attenuation degree category to obtain the life prediction result of the battery pack to be predicted.

[0129] Optionally, the life prediction result determination unit is also used to: determine the maximum probability among the probabilities corresponding to the battery pack to be predicted in each attenuation degree category; use the attenuation degree category corresponding to the maximum probability as the target attenuation degree category; and use the life prediction result corresponding to the battery pack to be predicted in the target attenuation degree category as the life prediction result of the battery pack to be predicted.

[0130] Optionally, the device is also used to: obtain historical SOH data of the battery pack of the new energy vehicle at historical characterization points, and determine the future SOH attenuation degree of the battery pack at each target historical characterization point based on the historical SOH data of the historical characterization points, wherein the historical characterization points include: historical time points or historical mileage points, and the target historical characterization points are historical characterization points in the historical characterization points where there is a future SOH attenuation degree; determine the attenuation degree category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point; in each attenuation degree category, establish a life prediction model based on the historical SOH data of the battery pack at each target historical characterization point, and obtain a life prediction model corresponding to each attenuation degree category; obtain the operating condition characteristics and behavior characteristics of the new energy vehicle within a preset range of each target historical characterization point, and use the operating condition characteristics, behavior characteristics and attenuation degree category of the battery pack of the new energy vehicle at each target historical characterization point as training samples; use the training samples to train the original attenuation degree classification model to obtain the attenuation degree classification model.

[0131] Optionally, the device is also used to: group the future SOH attenuation degrees of the battery pack at each target historical characterization point according to a preset grouping strategy to obtain future SOH attenuation degree groups; in each future SOH attenuation degree group, divide the future SOH attenuation degrees therein into attenuation degree categories to obtain the attenuation degree categories of each future SOH attenuation degree at its corresponding target historical characterization point; determine the attenuation degree category of the battery pack at each target historical characterization point according to the attenuation degree category of each future SOH attenuation degree at its corresponding target historical characterization point.

[0132] Optionally, the device is further used to: classify the future SOH attenuation degree into attenuation degree categories by using a quantile method or a box plot method.

[0133] Optionally, the device is also used to: determine the first historical SOH data at each target historical characterization point in the historical SOH data of the historical characterization point; determine the second historical SOH data at the future historical characterization point after each target historical characterization point in the historical SOH data of the historical characterization point, wherein the difference between the future historical characterization point and its corresponding target historical characterization point is a preset value; and calculate the future SOH attenuation degree of the battery pack at each target historical characterization point based on the first historical SOH data and the second historical SOH data.

[0134] Optionally, the device is also used to: in each attenuation degree category, calculate the unknown parameters in the preset life prediction function according to the historical SOH data of the battery pack at each target historical characterization point, and then obtain the preset life prediction function with known unknown parameters, wherein the preset life prediction function is a function between SOH and the characterization point; use the preset life prediction function with known unknown parameters as the life prediction model, and then obtain the life prediction model corresponding to each attenuation degree category.

[0135] Optionally, the preset interval includes: a preset time interval or a preset mileage interval, and the current vehicle data includes: current time data or current mileage data.

[0136] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0137] like Figure 6 As shown, an electronic device 600 provided in an embodiment of the present application includes: a processor 601, a memory 602 and a bus, wherein the memory 602 stores machine-readable instructions executable by the processor 601. When the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the above-mentioned method for predicting the life of a new energy vehicle battery pack.

[0138] Specifically, the above-mentioned memory 602 and processor 601 can be general-purpose memory and processor, which are not specifically limited here. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned new energy vehicle battery pack life prediction and determination method.

[0139] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the above method in combination with its hardware.

[0140] Corresponding to the above-mentioned method for predicting and determining the life of a new energy vehicle battery pack, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned method for predicting and determining the life of a new energy vehicle battery pack.

[0141] The life prediction and determination device for the new energy vehicle battery pack provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0142] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0143] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0144] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0146] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or partly contribute to the prior art or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for an electronic device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the vehicle marking method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0147] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0148] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A life prediction method for new energy vehicle battery packs, It is characterized in that The method comprises: Obtaining the operating condition characteristics and behavior characteristics of the battery pack to be predicted within the current preset range; Using an attenuation degree classification model to classify the attenuation degree of the operating condition characteristics and the behavior characteristics, and obtain the corresponding probability of the battery pack to be predicted in each attenuation degree category; Acquire current vehicle data of the new energy vehicle to be predicted corresponding to the battery pack to be predicted, and calculate the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted based on the current vehicle data and a pre-constructed life prediction model corresponding to each attenuation degree category; Determine the life prediction result of the battery pack to be predicted according to the probability corresponding to each attenuation degree category of the battery pack to be predicted and the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted; The method further comprises: Obtain historical SOH data of a battery pack of a new energy vehicle at a historical characterization point, and determine the future SOH attenuation degree of the battery pack at each target historical characterization point according to the historical SOH data of the historical characterization point, wherein the historical characterization point includes: a historical time point or a historical mileage point, and the target historical characterization point is a historical characterization point among the historical characterization points where a future SOH attenuation degree exists; Determining the attenuation category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point; In each attenuation degree category, a life prediction model is established according to the historical SOH data of the battery pack at each target historical characterization point, so as to obtain a life prediction model corresponding to each attenuation degree category; Acquire the operating condition characteristics and behavior characteristics of the new energy vehicle within a preset interval of each target historical characterization point, and use the operating condition characteristics, the behavior characteristics, and the attenuation degree category of the battery pack of the new energy vehicle at each target historical characterization point as training samples; Using the training samples to train the original attenuation degree classification model to obtain the attenuation degree classification model; Among them, in each attenuation degree category, a life prediction model is established according to the historical SOH data of the battery pack at each target historical characterization point, and the life prediction model corresponding to each attenuation degree category is obtained, including: In each attenuation degree category, the unknown parameters in the preset life prediction function are calculated according to the historical SOH data of the battery pack at each target historical characterization point, thereby obtaining a preset life prediction function with known unknown parameters, wherein the preset life prediction function is a function between the SOH and the characterization point; The preset life prediction function with known unknown parameters is used as the life prediction model, so as to obtain the life prediction model corresponding to each attenuation degree category.

2. The method according to claim 1, It is characterized in that Determining the life prediction result of the battery pack to be predicted according to the probability corresponding to each attenuation degree category of the battery pack to be predicted and the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted, including: Performing a product operation on the probability and life prediction result corresponding to the battery pack to be predicted in the same attenuation degree category to obtain the product operation result corresponding to the battery pack to be predicted in each attenuation degree category; The product operation results corresponding to the battery pack to be predicted in each attenuation degree category are added up to obtain the life prediction result of the battery pack to be predicted.

3. The method according to claim 1, It is characterized in that Determining the life prediction result of the battery pack to be predicted according to the probability corresponding to each attenuation degree category of the battery pack to be predicted and the life prediction result corresponding to each attenuation degree category of the battery pack to be predicted, further comprising: Determining the maximum probability among the probabilities corresponding to the battery pack to be predicted in each attenuation degree category; Taking the attenuation degree category corresponding to the maximum probability as the target attenuation degree category; The life prediction result corresponding to the battery pack to be predicted in the target attenuation degree category is used as the life prediction result of the battery pack to be predicted.

4. The method according to claim 1, It is characterized in that Determining the attenuation category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point includes: The future SOH attenuation degree of the battery pack at each target historical characterization point is grouped according to a preset grouping strategy to obtain a future SOH attenuation degree grouping; In each of the future SOH attenuation degree groups, the future SOH attenuation degrees are classified into attenuation degree categories to obtain the attenuation degree category of each future SOH attenuation degree at its corresponding target historical representation point; The attenuation degree category of the battery pack at each target historical characterization point is determined according to the attenuation degree category of each future SOH attenuation degree at its corresponding target historical characterization point.

5. The method according to claim 1, It is characterized in that Determining the future SOH attenuation degree of the battery pack at each target historical characterization point according to the historical SOH data of the historical characterization point includes: Determining, among the historical SOH data of the historical characterization points, first historical SOH data at each target historical characterization point; Determining, from the historical SOH data of the historical characterization points, second historical SOH data of future historical characterization points after each target historical characterization point, wherein the difference between the future historical characterization point and its corresponding target historical characterization point is a preset value; The future SOH attenuation degree of the battery pack at each target historical characterization point is calculated based on the first historical SOH data and the second historical SOH data.

6. The method according to claim 1, It is characterized in that The preset interval includes: a preset time interval or a preset mileage interval, and the current vehicle data includes: current time data or current mileage data.

7. A life prediction device for a new energy vehicle battery pack, It is characterized in that The device comprises: An acquisition unit, used to acquire the operating condition characteristics and behavior characteristics of the battery pack to be predicted within a current preset range; An attenuation degree classification unit for classifying the working condition characteristics and the behavior characteristics by using an attenuation degree classification model to obtain the probabilities corresponding to the to-be-predicted battery pack in each attenuation degree category; A life prediction unit for obtaining the current vehicle data of the to-be-predicted new energy vehicle corresponding to the to-be-predicted battery pack, and calculating the life prediction results corresponding to the to-be-predicted battery pack in each attenuation degree category based on the current vehicle data and the pre-constructed life prediction models corresponding to each attenuation degree category; A life prediction result determination unit for determining the life prediction result of the to-be-predicted battery pack according to the probabilities corresponding to the to-be-predicted battery pack in each attenuation degree category and the life prediction results corresponding to the to-be-predicted battery pack in each attenuation degree category; The device is further configured to: obtain the historical SOH data of the battery pack of the new energy vehicle at the historical characterization points, and determine the future SOH attenuation degree of the battery pack at each target historical characterization point according to the historical SOH data of the historical characterization points, where the historical characterization points include: historical time points or historical mileage points, and the target historical characterization points are the historical characterization points with future SOH attenuation degree among the historical characterization points; determine the attenuation degree category of the battery pack at each target historical characterization point based on the future SOH attenuation degree of the battery pack at each target historical characterization point; in each attenuation degree category, establish a life prediction model according to the historical SOH data of the battery pack at each target historical characterization point in it to obtain the life prediction models corresponding to each attenuation degree category; obtain the working condition characteristics and behavior characteristics of the new energy vehicle within a preset interval at each target historical characterization point, and use the working condition characteristics, the behavior characteristics, and the attenuation degree category of the battery pack of the new energy vehicle at each target historical characterization point as training samples; train the original attenuation degree classification model by using the training samples to obtain the attenuation degree classification model; Wherein, the device is further configured to: in each attenuation degree category, calculate the unknown parameters in the preset life prediction function according to the historical SOH data of the battery pack at each target historical characterization point in it, and further obtain the preset life prediction function with known unknown parameters, where the preset life prediction function is a function between SOH and the characterization point; use the preset life prediction function with known unknown parameters as the life prediction model, and further obtain the life prediction models corresponding to each attenuation degree category.

8. An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 above are implemented.

9. A computer-readable storage medium, wherein, the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and run by the processor, the machine-executable instructions cause the processor to run the method according to any one of claims 1 to 6 above.

Images