Battery spare part prediction method and device, computer equipment and storage medium

Abstract

The invention relates to a battery spare part prediction method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring various data of a plurality of in-use battery packs to obtain total data; wherein the plurality of in-use battery packs are arranged in different electric equipment; determining a failure change relationship according to the total data; the failure change relationship comprises a relationship that the failure probability of the battery pack changes along with the first survival duration; according to the failure change relationship, predicting the failure number of the plurality of in-use battery packs in a preset future time period; and determining the number of battery pack spare parts required in the preset future time period according to the failure number. According to the invention, the accuracy of battery spare part prediction can be improved, so that spare parts can be better supplied.

Description

Technical Field

[0001] The present application relates to the technical field of spare parts prediction, and in particular to a battery spare parts prediction method, device, computer equipment and storage medium. Background Art

[0002] In the automotive industry, spare parts forecasting is not only a core tool for supply chain management, but also a strategic means to improve customer experience and enhance brand competitiveness. Through scientific spare parts forecasting, companies can achieve efficient operations, reduce costs, and better respond to changes in market demand, especially in the new energy and intelligent wave, its importance is even more significant.

[0003] At present, the spare parts prediction results are relatively accurate for components with clear failure mechanisms such as bearings; however, there is an issue of inaccurate prediction for spare parts of battery packs. Summary of the invention

[0004] Based on the above problems, the present application provides a battery spare parts prediction method, apparatus, computer equipment and storage medium, which can improve the accuracy of battery spare parts prediction and thus better supply spare parts.

[0005] In a first aspect, the present application provides a battery spare parts prediction method, the method comprising: obtaining various data of multiple battery packs in use to obtain full data; wherein the multiple battery packs in use are arranged in different electrical equipment; determining a failure change relationship based on the full data; the failure change relationship includes a relationship between a failure probability of a battery pack and a change in a first survival time; based on the failure change relationship, predicting the number of failures of multiple battery packs in use within a preset future time period; and determining the number of battery pack spare parts required within the preset future time period based on the number of failures.

[0006] In the technical solution of the embodiment of the present application, a corresponding failure change relationship is determined for the battery pack, and the failure change relationship can more accurately reflect the change of the failure probability of the battery pack with the first survival time. Therefore, battery spare parts prediction based on the failure change relationship can improve the prediction accuracy, thereby better supplying spare parts.

[0007] In some embodiments, the failure change relationship is determined based on the full data, including: analyzing the failure causes of the battery pack based on the historical consumption data, coupling multiple factors that affect the battery pack survival time based on the analysis results, and obtaining the corresponding relationship between the first survival time and multiple influencing factors; calculating based on the corresponding relationship and the full data to obtain the sample survival time of multiple sample battery packs and the sample failure probability corresponding to each sample survival time; fitting the multiple sample survival times and the multiple sample failure probabilities to obtain the failure change relationship. In the technical solution of the embodiment of the present application, the failure change relationship is established based on the first survival time, and the first survival time takes into account the failure mode of the sample battery pack, and has the characteristics of high fitting accuracy and strong interpretability. Therefore, the failure change relationship can more accurately reflect the corresponding relationship between the first survival time of the battery pack and the failure probability, which provides help for the subsequent accurate prediction of the number of spare parts.

[0008] In some embodiments, calculations are performed based on the corresponding relationship and the full amount of data to obtain sample survival times of multiple sample battery packs and sample failure probabilities corresponding to each sample survival time, including: determining the data of each influencing factor corresponding to each sample battery pack based on the full amount of data; optimizing the importance weights of each influencing factor within a preset weight range; determining multiple optimized sample survival times based on the optimized importance weights, sorting the multiple optimized sample survival times, and calculating the sample failure probabilities corresponding to each optimized sample survival time based on the sorting results. In the technical solution of the embodiment of the present application, based on the corresponding relationship between the first survival time and the influencing factor, the sample survival time and sample failure probability corresponding to multiple sample battery packs can be calculated, providing a data basis for the subsequent fitting of the failure change relationship.

[0009] In some embodiments, the importance weights of each influencing factor are optimized within a preset weight range, including: performing multiple rounds of assignment of the importance weights of each influencing factor within a preset weight range; after each round of assignment, calculating the sample survival time corresponding to each sample battery pack and the sample failure probability corresponding to each sample survival time according to the assigned importance weights, the data of each influencing factor and the corresponding relationship; performing fitting processing on multiple sample survival times and multiple sample failure probabilities; determining the fitting error according to the fitting results and the sample failure probability of the sample battery pack; and determining the optimized importance weights according to the multiple fitting errors calculated after multiple rounds of assignment. In the technical scheme of the embodiment of the present application, the importance weights of each influencing factor are optimized to obtain importance weights that are more in line with the actual situation, thereby improving the accuracy of the first survival time, and then improving the subsequent prediction of the failure probability of the battery pack in use, as well as the accuracy of determining the failure number of the battery pack in use and the number of spare parts of the battery pack.

[0010] In some embodiments, multiple sample survival times and multiple sample failure probabilities are fitted, including: transforming a pre-established survival analysis model to obtain a linear relationship; the linear relationship uses the first logarithm of the sample failure probability as an independent variable and the second logarithm of the sample failure probability as a dependent variable; calculating the second logarithm and first logarithm of each sample failure probability; fitting based on the calculated second logarithm and first logarithm, and determining the linear coefficient and constant in the linear relationship based on the fitting result; obtaining the model parameters in the survival analysis model based on the linear coefficient and constant in the linear relationship. In the technical solution of the embodiment of the present application, fitting based on the second logarithm and first logarithm of the sample failure probability can reduce the difficulty of fitting and improve the accuracy of fitting, thereby obtaining a more accurate failure change relationship and improving the accuracy of battery spare parts prediction.

[0011] In some embodiments, based on the failure variation relationship, the number of failures of multiple battery packs in use within a preset future time period is predicted, including: predicting the failure probability of each battery pack in use within the preset future time period based on the failure variation relationship; statistically analyzing the failure probability of multiple battery packs in use to obtain a total failure probability; and determining the number of failures based on the total failure probability and the total number of battery packs in use. In the technical solution of the embodiment of the present application, the failure probability of all battery packs in use within a preset future time period can be determined based on the failure variation relationship, thereby accurately predicting the number of failures, providing an accurate basis for the subsequent determination of the number of spare parts.

[0012] In some embodiments, the number of failures is determined based on the total failure probability and the total number of battery packs in use, including: determining a failure probability range based on a preset confidence interval and the total failure probability; determining the number of failures based on the failure probability range and the total number of battery packs in use. In the technical solution of the embodiment of the present application, the preset confidence interval can expand the range of the number of failures, making the number of spare parts more flexible, thereby better supplying spare parts and improving user experience.

[0013] In some embodiments, the number of battery pack spare parts required in a preset future period is determined based on the number of failures, including: correcting the number of failures based on the battery pack business information to obtain the number of battery pack spare parts required in the preset future period. In the technical solution of the embodiment of the present application, the number of spare parts is determined by comprehensively considering the failure and business scenarios, and a margin is reserved for the supply of spare parts, which can reduce the risk of insufficient spare parts, thereby better supplying spare parts and improving user experience.

[0014] In a second aspect, the present application also provides a battery spare parts prediction device, the device comprising:

[0015] A data acquisition module, used to acquire various data of a plurality of battery packs in use to obtain full data; wherein the plurality of battery packs in use are arranged in different power-consuming devices;

[0016] A relationship determination module, used to determine a failure change relationship based on the full amount of data; the failure change relationship includes a relationship between the failure probability of the battery pack and the first survival time;

[0017] A failure prediction module is used to predict the number of failures of multiple battery packs in use within a preset future period based on the failure change relationship;

[0018] The spare parts determination module is used to determine the number of battery pack spare parts required in a preset future period based on the number of failures.

[0019] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the methods in the first aspect when executing the computer program.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method of any one of the first aspects is implemented.

[0021] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the optional embodiments below. The accompanying drawings are only used for the purpose of illustrating the optional embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0023] Figure 1 is a schematic diagram of an application environment of a battery spare parts prediction method according to an embodiment of the present application;

[0024] Figure 2 is a flowchart of a battery spare parts prediction method according to an embodiment of the present application;

[0025] Figure 3 It is a flowchart of the step of determining the failure change relationship in one embodiment of the present application;

[0026] Figure 4 is a curve diagram of the failure change relationship of an embodiment of the present application;

[0027] Figure 5 It is a flowchart of the steps of calculating the sample survival time and the sample failure probability in one embodiment of the present application;

[0028] Figure 6It is a flowchart of the importance weight optimization step of an embodiment of the present application;

[0029] Figure 7 is a flow chart of the fitting processing steps of an embodiment of the present application;

[0030] Figure 8 is a schematic diagram of a fitting result of an embodiment of the present application;

[0031] Fig. 9 It is a flowchart of the step of predicting the number of failures in one embodiment of the present application;

[0032] Fig.10 It is a flowchart of the step of determining the number of failures in one embodiment of the present application;

[0033] Fig.11 is a structural block diagram of a battery spare parts prediction device according to an embodiment of the present application;

[0034] Fig.12 It is a diagram of the internal structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0037] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0038] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0039] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0040] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0041] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0042] In the automotive industry, spare parts forecasting is not only a core tool for supply chain management, but also a strategic means to improve customer experience and enhance brand competitiveness. Through scientific spare parts forecasting, companies can achieve efficient operations, reduce costs, and better respond to changes in market demand, especially under the wave of new energy and intelligence, its importance is even more significant. At present, for components such as bearings with clear failure mechanisms, the spare parts forecasting results are relatively accurate; however, for spare parts of battery packs, there is a problem of inaccurate forecasting.

[0043] In response to the above problems, an embodiment of the present application provides a battery spare parts prediction method, which obtains various data of multiple battery packs in use to obtain full data; determines a failure change relationship based on the full data; the failure change relationship includes the relationship between the failure probability of the battery pack and the change of the first survival time; predicts the number of failures of multiple battery packs in use within a preset future time period based on the failure change relationship; and determines the number of battery pack spare parts required within the preset future time period based on the failure number. In the technical solution of the embodiment of the present application, a corresponding failure change relationship is determined for the battery pack, and the failure change relationship can more accurately reflect the change of the failure probability of the battery pack with the first survival time. Therefore, battery spare parts prediction based on the failure change relationship can improve the prediction accuracy, thereby better supplying spare parts.

[0044] The battery spare parts prediction method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the application environment includes multiple terminals 102 and servers 104, and the terminals 102 and the servers 104 can communicate through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 can upload relevant data to the server 104 through the network, such as mileage, battery charge times, battery health (State Of Health, SOH), battery power throughput, battery pack offline time, consumption time, consumption quantity, and geographical location at the time of consumption, etc. The server 104 collects data, analyzes and processes the data to obtain the failure change relationship of the battery pack, and then predicts battery spare parts based on the failure change relationship.

[0045] The battery pack may be a component of various devices, including but not limited to vehicles, intelligent robots, drones, medical imaging equipment, communication equipment, etc. The terminal 102 may be, but not limited to, various personal computers, laptops, smart phones, tablet computers, controllers in devices, such as vehicle controllers, battery management systems, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0046] According to some embodiments of the present application, referring to Figure 2 , a battery spare parts prediction method is provided, which can be applied to Figure 1 Taking the server in as an example, the following steps may be included:

[0047] Step 201, obtaining various data of multiple battery packs in use to obtain full data.

[0048] Among them, the in-use battery pack refers to the battery pack in use, and the full data includes various data of the battery pack, such as the number of battery charging times, battery health, battery power throughput, battery pack offline time, usage time, etc. Multiple in-use battery packs are set in different power-consuming devices. For example, the power-consuming device is a new energy vehicle, and each new energy vehicle is equipped with one or more battery packs.

[0049] In actual applications, the server can communicate with each vehicle and obtain various data of the battery pack in use from each vehicle, thereby obtaining full data. The server can also communicate with terminals such as smartphones and personal computers. Users enter data in the terminal, and the server obtains full data from the terminal.

[0050] Step 202: determine the failure change relationship based on the full amount of data.

[0051] The first survival time represents the absolute size of a physical quantity accumulated from the time the battery pack is manufactured off the production line to the time when the failure occurs; for example, the first survival time represents the number of charging times, throughput, and the combination of the number of charging times and throughput from the time the battery pack is manufactured off the production line to the time when the failure occurs. The second survival time represents the absolute length of time from the time the battery pack is manufactured off the production line to the time when the failure occurs.

[0052] The above failure variation relationship includes the relationship between the failure probability of the battery pack and the first survival time. For example, the first generation time is the number of charging times, and the failure variation relationship of the battery pack may include that the failure probability corresponding to the battery pack being charged 30 times is 0.05%; and the failure probability corresponding to the battery pack being charged 500 times is 71%.

[0053] After obtaining the full data, the server can couple the different data in the full data according to the failure mode of the battery pack to obtain the first survival time corresponding to the battery pack. Then, the failure probability of each battery pack is calculated according to the first survival time of different battery packs; and the failure change relationship of the battery pack is fitted according to the calculated multiple first survival times and multiple failure probabilities.

[0054] Step 203 , predicting the number of failures of multiple battery packs in use within a preset future period based on the failure variation relationship.

[0055] The preset future time period is a preset time period to be predicted, such as next month, next week, etc.

[0056] The failure probability of each battery pack in use within a preset future time period can be predicted based on the failure variation relationship, and then the number of failures of multiple battery packs in use within the preset future time period can be determined based on the failure probability of all battery packs in use.

[0057] For example, based on the failure change relationship, the failure probability of each battery pack in use next month can be determined; based on the failure probability of all battery packs in use, the failure number of battery packs in use next month can be determined.

[0058] Step 204, determining the number of battery pack spare parts required within a preset future time period based on the number of failures.

[0059] Determine the number of failures of multiple battery packs in use within a preset future period, and the number of failures can be determined as the number of battery pack spares required within the preset future period. For example, the number of failures of M battery packs in use next month is N, where M and N are natural numbers and M≥N, then the number of spare battery packs required to be provided next month is N.

[0060] In the above embodiment, various data of multiple battery packs in use are obtained to obtain full data; the failure change relationship is determined based on the full data; the failure change relationship includes the relationship between the failure probability of the battery pack and the first survival time; based on the failure change relationship, the number of failures of multiple battery packs in use within a preset future time period is predicted; based on the number of failures, the number of battery pack spare parts required within the preset future time period is determined. In the technical solution of the embodiment of the present application, a corresponding failure change relationship is determined for the battery pack, and the failure change relationship can more accurately reflect the change of the failure probability of the battery pack with the first survival time. Therefore, battery spare parts prediction based on the failure change relationship can improve the prediction accuracy, thereby better supplying spare parts.

[0061] According to some embodiments of the present application, referring to Figure 3 In the above embodiment, “determining the failure change relationship based on the full amount of data” may include the following steps:

[0062] Step 301 , analyzing the failure causes of the battery pack according to the historical consumption data, coupling multiple factors affecting the battery pack life span based on the analysis results, and obtaining a corresponding relationship between the first life span and multiple influencing factors.

[0063] The historical consumption data refers to the consumption data of the battery packs in the historical period. The historical consumption data may include the type, identification, consumption quantity, consumption time, geographical location of the battery packs consumed in the historical period, etc. For example, the number of battery packs consumed in the historical period is a, where a is a natural number; the consumption time of battery pack i is a certain year, month, and day, where i is the identification of the battery pack, which can be a number, a letter, or a combination of numbers and letters; the geographical location is Pi, where Pi includes longitude and latitude.

[0064] It is understandable that the reasons why the battery pack is consumed are different, that is, the reasons for failure are different. Based on the historical consumption data, the various reasons for failure of the battery pack can be summarized, thereby analyzing the various factors affecting the battery pack life span and determining the failure mode of the battery pack.

[0065] The server can establish a correspondence between the first survival time and multiple influencing factors according to the failure mode of the battery pack. For example, T=F1*X1+F2*X2+F3*X3, where T is the first survival time corresponding to the battery pack, F1, F2, and F3 are factors affecting the survival time of the battery pack obtained by performing failure analysis on the battery pack, and X1, X2, and X3 are the importance weights corresponding to each influencing factor.

[0066] Step 302 , performing calculations based on the corresponding relationship and the full amount of data to obtain sample survival times of multiple sample battery packs and sample failure probabilities corresponding to each sample survival time.

[0067] Based on the full data, multiple sample battery packs can be selected from multiple battery packs in use, and the data of each influencing factor corresponding to each sample battery pack can be determined. For each sample battery pack, the data of each influencing factor is substituted into the above correspondence, and the sample survival time corresponding to the sample battery pack can be calculated. After that, the sample survival times of multiple sample battery packs are normalized, and the normalized result corresponding to each sample battery pack can be determined as the sample failure probability corresponding to the sample battery pack.

[0068] Step 303 , performing fitting processing on multiple sample survival times and multiple sample failure probabilities to obtain a failure variation relationship.

[0069] The server can use a preset fitting algorithm to fit multiple sample survival times and multiple sample failure probabilities. For example, the sample survival time and the corresponding sample failure probability are used as a coordinate point, so that multiple sample survival times and multiple sample failure probabilities can determine multiple coordinate points; a curve can be fitted based on the multiple coordinate points, and the curve can represent the failure change relationship.

[0070] Reference Figure 4 In the coordinate system of the fitting curve, the x-axis is the sample survival time, the y-axis is the sample failure probability, the curve in the figure is the fitted failure change relationship, the small dots in the figure are the coordinate points determined by the sample survival time and sample failure probability used in the fitting, and the large dots in the figure are typical coordinate points.

[0071] In the above embodiment, the failure causes of the battery pack are analyzed based on the historical consumption data, and based on the analysis results, multiple factors affecting the survival time of the battery pack are coupled to obtain the corresponding relationship between the first survival time and the multiple influencing factors; calculations are performed based on the corresponding relationship and the full amount of data to obtain the sample survival times of multiple sample battery packs and the sample failure probabilities corresponding to each sample survival time; multiple sample survival times and multiple sample failure probabilities are fitted to obtain the failure change relationship. In the technical solution of the embodiment of the present application, the failure change relationship is established based on the first survival time, and the first survival time takes into account the failure mode of the sample battery pack, and has the characteristics of high fitting accuracy and strong interpretability. Therefore, the failure change relationship can more accurately reflect the corresponding relationship between the first survival time of the battery pack and the failure probability, which provides help for the subsequent accurate prediction of the number of spare parts.

[0072] According to some embodiments of the present application, referring to Figure 5 In the above embodiment, "calculating according to the corresponding relationship and the full amount of data to obtain the sample survival time of multiple sample battery packs and the sample failure probability corresponding to each sample survival time" may include the following steps:

[0073] Step 401 : determining data of each influencing factor corresponding to each sample battery pack based on the full data.

[0074] For example, 20 sample battery packs are selected based on the full data, and the factors that affect the battery pack life span include battery health, number of charges, and battery power throughput. Based on the full data, the battery health, number of charges, and throughput of the first sample battery pack, the battery health, number of charges, and throughput of the second sample battery pack, and so on, the battery health, number of charges, and throughput of the 20th sample battery pack can be determined.

[0075] Step 402: Optimize the importance weight of each influencing factor within a preset weight range.

[0076] In order to reduce the amount of calculation, the importance weight can be set to change between 0 and 1, that is, the preset weight range is 0-1. In the optimization process, the importance weight corresponding to each influencing factor can be changed in steps of 0.05. In order to further reduce the amount of calculation, X1+X2+X3=1 can be set.

[0077] Within the preset weight range, adjust the importance weight of each influencing factor, and calculate the sample survival time and sample failure probability corresponding to each sample battery pack based on the adjusted importance weight, the data of each influencing factor and the corresponding relationship. If the calculated sample survival time and sample failure probability do not match the actual survival time and failure probability, continue to adjust the importance weight of each influencing factor. End the optimization search when the calculated sample survival time and sample failure probability match the actual survival time and failure probability, and determine the importance weight of the calculated sample survival time and sample failure probability as the importance weight after optimization.

[0078] For example, for sample battery pack 1, its battery health F1, charging times F2 and throughput F3 are determined based on the full data, and the importance weights X1, X2 and X3 are set to 0.05, 0.10 and 0.85, and then the sample survival time T1 and sample failure probability F1 are calculated based on the above correspondence T=F1*X1+F2*X2+F3*X3. If the sample survival time T1 and the sample failure probability F1 match the actual situation, X1 is 0.05, X2 is 0.10 and X3 is 0.85 as the importance weights after optimization. If the sample survival time T1 and the sample failure probability F1 do not match the actual situation, X1 is adjusted to 0.10, X2 is 0.15 and X3 is 0.75, and the sample survival time T2 and the sample failure probability F2 are recalculated based on the corresponding relationship. By analogy, the importance weights after optimization can be determined. By analogy, the importance weights after optimization corresponding to other sample battery packs can be calculated.

[0079] Step 403, determining multiple optimized sample survival times according to the optimized importance weights, sorting the multiple optimized sample survival times, and calculating the sample failure probability corresponding to each optimized sample survival time according to the sorting result.

[0080] The sample survival time corresponding to the importance weight after optimization is determined as the sample survival time after optimization, and the sample survival time after optimization is calculated for each sample battery pack. Then, the multiple sample survival times after optimization are sorted in order from small to large, and the sample failure probability corresponding to each sample battery pack is calculated according to the sorting result and the failure probability calculation formula. Among them, the failure probability calculation formula is F=i / (n+1), F is the sample failure probability, i is the sorted number, and n is the number of sample battery packs. See the data of 6 sample battery packs in Table 1.

[0081] Table 1

[0082]

[0083] In the above embodiment, the data of each influencing factor corresponding to each sample battery pack is determined based on the full amount of data; the importance weight of each influencing factor is optimized within the preset weight range; multiple optimized sample survival times are determined based on the optimized importance weights, the multiple optimized sample survival times are sorted, and the sample failure probability corresponding to each optimized sample survival time is calculated based on the sorting results. In the technical solution of the embodiment of the present application, based on the corresponding relationship between the first survival time and the influencing factor, the sample survival time and sample failure probability corresponding to multiple sample battery packs can be calculated, providing a data basis for the subsequent fitting of the failure change relationship.

[0084] According to some embodiments of the present application, referring to Figure 6 In the above embodiment, “optimizing the importance weight of each influencing factor within a preset weight range” may include the following steps:

[0085] Step 501 : performing multiple rounds of assignment of importance weights of various influencing factors within a preset weight range.

[0086] Among them, the preset weight range can be 0-1, that is, the importance weights X1, X2, and X3 are assigned multiple rounds between 0-1, and X1+X2+X3=1.

[0087] For example, in the first round of assignment, X1 is assigned 0.05, X2 is assigned 0.10, and X3 is assigned 0.85. In the second round of assignment, X1 is assigned 0.10, X2 is assigned 0.15, and X3 is assigned 0.75. In the third round of assignment, X1 is assigned 0.15, X2 is assigned 0.20, and X3 is assigned 0.65. And so on, the importance weights after multiple rounds of assignment are obtained.

[0088] Step 502, after each round of assignment, the sample survival time corresponding to each sample battery pack and the sample failure probability corresponding to each sample survival time are calculated based on the assigned importance weights, the data of each influencing factor and the corresponding relationship.

[0089] After each round of assignment, the sample survival time and sample failure probability are calculated based on the assigned importance weights, the data of each influencing factor and the above corresponding relationship T=F1*X1+F2*X2+F3*X3.

[0090] For example, after the first round of assignment, the sample survival time T1 and the sample failure probability F1 are calculated based on X1 being 0.05, X2 being 0.10, and X3 being 0.85, the battery health F1, the number of charges F2, and the battery power throughput F3. After the second round of assignment, the sample survival time T2 and the sample failure probability F2 are calculated based on X1 being 0.10, X2 being 0.15, and X3 being 0.75, the battery health F1, the number of charges F2, and the battery power throughput F3. By analogy, multiple sample survival times and multiple sample failure probabilities are calculated.

[0091] Step 503: Fitting the survival time of multiple samples and the failure probabilities of multiple samples.

[0092] The sample survival time and the corresponding sample failure probability are taken as a coordinate point, and multiple coordinate points can be determined according to multiple sample survival times and multiple sample failure probabilities. The multiple coordinate points are fitted to obtain a fitting result, which can be represented by a fitting curve.

[0093] Step 504 , determining a fitting error based on the fitting result and the sample failure probability of the sample battery pack.

[0094] The root mean square error can be used to calculate the fitting error, as shown in formula (1):

[0095] -------------------------------(1)

[0096] Where, e is the fitting error; i is the number of the sample battery pack, and n is the number of sample battery packs; is the sample failure probability before the sample battery pack is fitted; is the sample failure probability determined in the fitting curve according to the sample survival time of the sample battery pack.

[0097] Step 505, determining the importance weight after optimization according to the multiple fitting errors calculated after multiple rounds of assignment.

[0098] For the sample survival time and sample failure probability calculated after each round of assignment, a fitting result can be obtained; the fitting error can also be calculated based on the fitting result. In this way, multiple fitting errors can be calculated after multiple rounds of assignment, and the smallest fitting error among the multiple fitting errors is determined as the target fitting error, and the importance weight corresponding to the target fitting error is determined as the importance weight after optimization.

[0099] In the above embodiment, multiple rounds of assignments are performed on the importance weights of each influencing factor within a preset weight range; after each round of assignments, the sample survival time corresponding to each sample battery pack and the sample failure probability corresponding to each sample survival time are calculated based on the assigned importance weights, the data of each influencing factor and the corresponding relationship; multiple sample survival times and multiple sample failure probabilities are fitted; the fitting error is determined based on the fitting results and the sample failure probability of the sample battery pack; the importance weight after optimization is determined based on the multiple fitting errors calculated after multiple rounds of assignments. In the technical solution of the embodiment of the present application, the importance weights of each influencing factor are optimized to obtain importance weights that are more in line with the actual situation, thereby improving the accuracy of the first survival time, and then improving the accuracy of the failure probability of the battery pack in use, as well as the accuracy of the failure number and the number of spare parts of the battery pack in use.

[0100] According to some embodiments of the present application, referring to Figure 7 In the above embodiment, “fitting the survival time of multiple samples and the failure probability of multiple samples” may include the following steps:

[0101] Step 601, transform the pre-established survival analysis model to obtain a linear relationship.

[0102] Among them, the linear relationship uses the first logarithm of the sample failure probability as the independent variable and the second logarithm of the sample failure probability as the dependent variable.

[0103] A survival analysis model is established in advance, and the Weibull distribution is used as an example, as shown in formula (2):

[0104] ----------------------- (2)

[0105] Among them, N represents the life span, that is, the survival time; F (N) represents the failure probability when the life span is N, N0 represents the minimum life parameter, which is generally taken as 0; Na is a constant, representing the characteristic life parameter, when N = Na, F (Na) = 0.632.

[0106] The survival analysis model is transformed as shown in formula (3):

[0107] ----------------------(3)

[0108] Taking the quadratic logarithm of formula (3) yields formula (4):

[0109] ----------(4)

[0110] Let N0 = 0, then we get formula (5):

[0111] -----------------(5)

[0112] in, is the constant c, b is the linear coefficient, As the independent variable x, As the dependent variable y, then , We can get formula (6):

[0113] ---------------------------------(6)

[0114] Step 602, calculating the quadratic logarithm and the linear logarithm of the failure probability of each sample.

[0115] According to Table 1 and the above formula, the quadratic logarithm lg(lg(1 / (1-F(N)) and the linear logarithm lg(F(N)) of the failure probability F(N) of each sample can be calculated to obtain Table 2.

[0116] Table 2

[0117]

[0118] Step 603, performing fitting processing according to the calculated quadratic logarithm and linear logarithm, and determining the linear coefficient and constant in the linear relationship equation according to the fitting result.

[0119] Determine the coordinate points according to the x and y in Table 2, and then fit the relationship between the failure probability and the sample survival time by function fitting. Figure 8According to the fitting results, the linear coefficient b=1.323 and the constant c=0.057 in the linear relationship.

[0120] Step 604, obtaining model parameters in the survival analysis model according to the linear coefficients and constants in the linear relationship.

[0121] Substituting the linear coefficients and constants in the linear relationship into formula (6) and inversely deducing, we can obtain the model parameter N in formula (2): a =0.4823. The model parameter N a Substituting into formula (2), the failure change relationship can be obtained.

[0122] In the above embodiment, the pre-established survival analysis model is transformed to obtain a linear relationship; the quadratic logarithm and the linear logarithm of the failure probability of each sample are calculated; fitting is performed based on the calculated quadratic logarithm and the linear logarithm, and the linear coefficients and constants in the linear relationship are determined based on the fitting results; the model parameters in the survival analysis model are obtained based on the linear coefficients and constants in the linear relationship. In the technical solution of the embodiment of the present application, fitting is performed based on the quadratic logarithm and the linear logarithm of the sample failure probability, which can reduce the difficulty of fitting and improve the accuracy of fitting, thereby obtaining a more accurate failure change relationship and improving the accuracy of battery spare parts prediction.

[0123] According to some embodiments of the present application, referring to Fig. 9 In the above embodiment, “predicting the number of failures of multiple battery packs in use within a preset future period according to the failure change relationship” may include the following steps:

[0124] Step 701 , predicting the failure probability of each battery pack in use within a preset future period based on the failure variation relationship.

[0125] For each battery pack in use, the failure probability can be determined in the failure change relationship based on its current survival time and the preset future time period.

[0126] For example, the preset future period is the next month, and the preset future period is equivalent to 100; the current survival time of the first battery pack in use is 100, and the failure probability corresponding to the survival time of 200 can be determined in the failure change relationship. The current survival time of the second battery pack in use is 150, and the failure probability corresponding to the survival time of 250 can be determined in the failure change relationship. And so on, the failure probability corresponding to each battery pack in use is determined.

[0127] Step 702 , statistically analyzing the failure probabilities of multiple battery packs in use to obtain a total failure probability.

[0128] The failure probabilities of multiple battery packs in use are summed to obtain the total failure probability. For example, the failure probability of the first battery pack in use is f1, the failure probability of the second battery pack in use is f2... the failure probability of the jth battery pack in use is fj, then the total failure probability f0=f1+f2...+fj.

[0129] Step 703, determining the number of failures based on the total failure probability and the total number of battery packs in use.

[0130] The total failure probability is calculated by multiplying the total number of battery packs in use to obtain the number of failures. For example, the number of failures , where f0 is the total failure probability and j is the total number of battery packs in use.

[0131] In the above embodiment, the failure probability of each in-use battery pack in a preset future period is predicted based on the failure change relationship; the failure probabilities of multiple in-use battery packs are counted to obtain the total failure probability; and the number of failures is determined based on the total failure probability and the total number of in-use battery packs. In the technical solution of the embodiment of the present application, the failure probability of all in-use battery packs in a preset future period can be determined based on the failure change relationship, thereby accurately predicting the number of failures, providing an accurate basis for the subsequent determination of the number of battery pack spare parts.

[0132] According to some embodiments of the present application, referring to Fig.10 In the above embodiment, “determining the number of failures according to the total failure probability and the total number of battery packs in use” may include the following steps:

[0133] Step 801, determining a failure probability range according to a preset confidence interval and a total failure probability.

[0134] In practical applications, in order to improve the accuracy of prediction, a confidence interval can be set in advance. After the total failure probability is determined, the total failure probability is expanded to a failure probability range according to the preset confidence interval.

[0135] For example, if the preset confidence interval is 95% and the total failure probability is f0, the failure probability range can be 95%*f0~f0 or 95%*f0~105%*f0.

[0136] It should be noted that the preset confidence interval is not limited to the above example, and the method for determining the failure probability range is not limited to the above example, and can be set according to actual conditions.

[0137] Step 802, determining the number of failures based on the failure probability range and the total number of battery packs in use.

[0138] Based on the failure probability range and the total number of battery packs in use, the range of the failure quantity can be calculated. For example, if the failure probability range is 95%*f0~f0 and the total number of battery packs in use is j, then the minimum failure quantity is The maximum number of failures is .

[0139] It should be noted that different confidence intervals will result in different failure probability ranges, and the minimum and maximum values ​​of the calculated failure numbers will also be different.

[0140] In the above embodiment, the failure probability range is determined based on the preset confidence interval and the total failure probability; the failure quantity is determined based on the failure probability range and the total number of battery packs in use. In the technical solution of the embodiment of the present application, the preset confidence interval can expand the range of the failure quantity, making the number of spare parts more flexible, thereby better supplying spare parts and improving user experience.

[0141] According to some embodiments of the present application, in the above-mentioned embodiment, "determining the number of battery pack spare parts required in a preset future time period based on the number of failures" may include: correcting the number of failures based on the battery pack business information to obtain the number of battery pack spare parts required in the preset future time period.

[0142] Among them, the battery pack business information includes at least one of the battery pack's raw material procurement, production scheduling cycle, transportation cycle, and delivery time.

[0143] When predicting battery spare parts, we need to consider not only the number of failures, but also the actual business scenarios. For example, we need to consider the time for raw material procurement, the time for production scheduling, etc. Taking all the above factors into consideration, we can correct the number of failures and get the number of battery pack spare parts required in the preset future period.

[0144] For example, it is predicted that the number of failures of battery packs in use next month will be N. Taking into account the procurement time of raw materials for battery packs, the production cycle of battery packs, the transportation cycle of battery packs, etc., a certain number of additional spare parts are needed. In this way, the failure number N is corrected and the number of spare parts for battery packs next month is B, and B is greater than N.

[0145] In the above embodiment, the number of failures is corrected according to the battery pack business information to obtain the number of battery pack spare parts required in the preset future period. In the technical solution of the embodiment of the present application, the number of spare parts is determined by comprehensively considering the failure and business scenarios, and a margin is reserved for the supply of spare parts, which can reduce the risk of insufficient spare parts, thereby better supplying spare parts and improving user experience.

[0146] According to some embodiments of the present application, a battery spare parts prediction method is provided, which is applied to Figure 1Taking the computer device in the example as an example, the following steps may be included:

[0147] Step 1: Obtain various data of multiple battery packs in use to obtain full data.

[0148] Step 2: Analyze the failure causes of the battery pack according to the historical consumption data, couple multiple factors affecting the battery pack life span based on the analysis results, and obtain the corresponding relationship between the first life span and the multiple influencing factors.

[0149] Step 3: Determine the data of each influencing factor corresponding to each sample battery pack based on the full data.

[0150] Step 4, perform multiple rounds of assignment of importance weights of each influencing factor within a preset weight range; after each round of assignment, calculate the sample survival time corresponding to each sample battery pack and the sample failure probability corresponding to each sample survival time based on the assigned importance weights, the data of each influencing factor and the corresponding relationship; perform fitting processing on the sample survival time and the sample failure probability; determine the fitting error based on the fitting results and the sample failure probability of the sample battery pack; determine the importance weight after optimization based on the multiple fitting errors calculated after multiple rounds of assignment.

[0151] Step 5: Determine the survival times of multiple optimized samples according to the importance weights after optimization, sort the survival times of multiple optimized samples, and calculate the sample failure probability corresponding to each optimized sample survival time according to the sorting result.

[0152] Step 6, transform the pre-established survival analysis model to obtain a linear relationship; the linear relationship uses the first logarithm of the sample failure probability as the independent variable and the second logarithm of the sample failure probability as the dependent variable; calculates the second logarithm and first logarithm of the failure probability of each sample; performs fitting processing based on the calculated second logarithm and first logarithm, and determines the linear coefficients and constants in the linear relationship based on the fitting results; obtains the model parameters in the survival analysis model based on the linear coefficients and constants in the linear relationship, substitutes the model parameters into the survival analysis model, and obtains the failure change relationship.

[0153] Step 7, predict the failure probability of each battery pack in use within a preset future time period based on the failure change relationship; statistically analyze the failure probabilities of multiple battery packs in use to obtain a total failure probability; determine the failure probability range based on a preset confidence interval and the total failure probability; determine the number of failures based on the failure probability range and the total number of battery packs in use.

[0154] Step 8: Correct the failure quantity according to the battery pack business information to obtain the number of battery pack spare parts required in a preset future period.

[0155] In the above embodiment, a corresponding failure variation relationship is determined for the battery pack, and the failure variation relationship can more accurately reflect the change of the failure probability of the battery pack with the first survival time. Therefore, battery spare parts prediction based on the failure variation relationship can improve the prediction accuracy, thereby better supplying spare parts.

[0156] It should be understood that, although the various steps in the above flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowchart may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0157] Based on the same inventive concept, the embodiment of the present application also provides a battery spare parts prediction device for implementing the battery spare parts prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more battery spare parts prediction device embodiments provided below can refer to the limitations of the battery spare parts prediction method above, and will not be repeated here.

[0158] According to some embodiments of the present application, referring to Fig.11 The present application provides a battery spare parts prediction device, the device comprising:

[0159] The data acquisition module 901 is used to acquire various data of multiple battery packs in use to obtain full data; wherein the multiple battery packs in use are set in different power-consuming devices;

[0160] A relationship determination module 902 is used to determine a failure change relationship based on the full amount of data; the failure change relationship includes a relationship between the failure probability of the battery pack and the first survival time;

[0161] A failure prediction module 903 is used to predict the number of failures of multiple battery packs in use within a preset future period according to the failure change relationship;

[0162] The spare parts determination module 904 is used to predict the number of failures of multiple battery packs in use within a preset future time period based on the number of failures.

[0163] In some embodiments, the relationship determination module 902 is specifically used to analyze the failure causes of the battery pack according to the historical consumption data, couple multiple factors affecting the survival time of the battery pack based on the analysis results, and obtain the corresponding relationship between the first survival time and multiple influencing factors; calculate according to the corresponding relationship and the full amount of data to obtain the sample survival time of multiple sample battery packs and the sample failure probability corresponding to each sample survival time; fit multiple sample survival times and multiple sample failure probabilities to obtain the failure change relationship.

[0164] In some embodiments, the relationship determination module 902 is specifically used to determine the data of each influencing factor corresponding to each sample battery pack based on the full data; optimize the importance weight of each influencing factor within a preset weight range; determine multiple optimized sample survival times based on the optimized importance weights, sort the multiple optimized sample survival times, and calculate the sample failure probability corresponding to each optimized sample survival time based on the sorting results.

[0165] In some embodiments, the relationship determination module 902 is specifically used to perform multiple rounds of assignment of importance weights of each influencing factor within a preset weight range; after each round of assignment, the sample survival time corresponding to each sample battery pack and the sample failure probability corresponding to each sample survival time are calculated based on the assigned importance weights, the data of each influencing factor and the corresponding relationship; multiple sample survival times and multiple sample failure probabilities are fitted; the fitting error is determined based on the fitting results and the sample failure probability of the sample battery pack; and the importance weight after optimization is determined based on the multiple fitting errors calculated after multiple rounds of assignment.

[0166] In some embodiments, the relationship determination module 902 is specifically used to transform the pre-established survival analysis model to obtain a linear relationship; the linear relationship uses the first logarithm of the sample failure probability as an independent variable and the second logarithm of the sample failure probability as a dependent variable; calculates the second logarithm and the first logarithm of each sample failure probability; performs fitting processing based on the calculated second logarithm and first logarithm, and determines the linear coefficients and constants in the linear relationship based on the fitting results; obtains the model parameters in the survival analysis model based on the linear coefficients and constants in the linear relationship.

[0167] In some embodiments, the failure prediction module 903 is specifically used to predict the failure probability of each battery pack in use within a preset future time period based on the failure change relationship; to count the failure probabilities of multiple battery packs in use to obtain a total failure probability; and to determine the number of failures based on the total failure probability and the total number of battery packs in use.

[0168] In some embodiments, the failure prediction module 903 is specifically used to determine the failure probability range according to a preset confidence interval and the total failure probability; and determine the failure quantity according to the failure probability range and the total number of battery packs in use.

[0169] In some embodiments, the spare parts determination module 904 is specifically used to correct the failure quantity according to the battery pack business information to obtain the number of battery pack spare parts required in a preset future time period.

[0170] Each module in the above battery spare parts prediction device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in an electronic device in the form of hardware, or can be stored in a memory in the electronic device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0171] According to some embodiments of the present application, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication) or other technologies. When the computer program is executed by the processor, a battery spare parts prediction method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0172] Those skilled in the art will understand that Fig.12The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] According to some embodiments of the present application, there is also provided a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, and the above instructions can be executed by a processor of an electronic device to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0174] According to some embodiments of the present application, a computer program product is also provided, and when the computer program is executed by a processor, the above method can be implemented. The computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, part or all of the above method can be implemented in whole or in part according to the process or function described in the embodiment of the present application.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0176] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The above-described embodiments only express several implementation methods of the present application, which is convenient for understanding the technical solutions of the present application in detail, but cannot be understood as limiting the scope of protection of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. It should be understood that the technical solutions obtained by those skilled in the art through logical analysis, reasoning or limited experiments on the basis of the technical solutions provided in the present application are all within the protection scope of the attached claims described in the present application. Therefore, the protection scope of the patent of this application shall be based on the contents of the attached claims, and the description and drawings can be used to explain the contents of the claims.

Claims

1. A battery spare parts prediction method, characterized in that: The method comprises: Acquire various data of multiple battery packs in use to obtain full data; wherein the multiple battery packs in use are arranged in different power-consuming devices; Determine a failure change relationship according to the full amount of data; the failure change relationship includes a relationship between a failure probability of the battery pack and a first survival time; Predicting the number of failures of the plurality of battery packs in use within a preset future period according to the failure variation relationship; Based on the number of failures, the number of battery pack spare parts required within the preset future time period is determined.

2. The method according to claim 1, characterized in that: The determining the failure change relationship according to the full amount of data includes: Analyzing the failure cause of the battery pack according to the historical consumption data, coupling multiple factors affecting the battery pack life span based on the analysis result, and obtaining a corresponding relationship between the first life span and multiple influencing factors; Calculating according to the corresponding relationship and the full amount of data to obtain sample survival times of multiple sample battery packs and sample failure probabilities corresponding to the sample survival times; Fitting is performed on multiple sample survival times and multiple sample failure probabilities to obtain the failure change relationship.

3. The method according to claim 2, characterized in that The calculation is performed according to the corresponding relationship and the full amount of data to obtain the sample survival time of multiple sample battery packs and the sample failure probability corresponding to each of the sample survival time, including: Determine data of each influencing factor corresponding to each of the sample battery packs according to the full amount of data; Optimizing the importance weight of each of the influencing factors within a preset weight range; The survival times of multiple optimized samples are determined according to the importance weights after optimization, the survival times of the multiple optimized samples are sorted, and the sample failure probability corresponding to each of the optimized sample survival times is calculated according to the sorting result.

4. The method according to claim 3, characterized in that The optimizing the importance weight of each of the influencing factors within a preset weight range includes: Perform multiple rounds of assigning importance weights of each of the influencing factors within the preset weight range; After each round of assignment, the sample survival time corresponding to each sample battery pack and the sample failure probability corresponding to each sample survival time are calculated according to the assigned importance weight, the data of each influencing factor and the corresponding relationship; Performing fitting processing on the survival time of the plurality of samples and the failure probability of the plurality of samples; Determine a fitting error according to the fitting result and the sample failure probability of the sample battery pack; The importance weight after the optimization is determined according to the multiple fitting errors calculated after multiple rounds of assignment.

5. The method according to any one of claims 2 to 4, characterized in that: The fitting process of the survival time of the plurality of samples and the failure probability of the plurality of samples comprises: Transforming the pre-established survival analysis model to obtain a linear relationship; the linear relationship uses the first logarithm of the sample failure probability as an independent variable and the second logarithm of the sample failure probability as a dependent variable; Calculating the quadratic logarithm and the linear logarithm of the failure probability of each of the samples; Performing fitting processing according to the calculated quadratic logarithm and linear logarithm, and determining the linear coefficient and constant in the linear relationship equation according to the fitting result; The model parameters in the survival analysis model are obtained according to the linear coefficients and constants in the linear relationship.

6. The method according to claim 1, characterized in that The predicting, based on the failure variation relationship, the number of failures of the plurality of battery packs in use within a preset future period of time includes: Predicting the failure probability of each of the in-use battery packs within the preset future period according to the failure change relationship; Counting the failure probabilities corresponding to the multiple battery packs in use to obtain a total failure probability; The failure quantity is determined based on the total failure probability and the total quantity of the battery packs in use.

7. The method according to claim 6, characterized in that The determining the failure quantity according to the total failure probability and the total quantity of the battery packs in use includes: Determining a failure probability range according to a preset confidence interval and the total failure probability; The failure quantity is determined based on the failure probability range and the total quantity of the battery packs in use.

8. The method according to claim 1, characterized in that The determining, based on the number of failures, the number of battery pack spare parts required in the preset future period includes: The failure quantity is corrected according to the battery pack business information to obtain the required number of battery pack spare parts in the preset future time period.

9. A battery spare parts prediction device, characterized in that: The device comprises: A data acquisition module, used to acquire various data of a plurality of battery packs in use to obtain full data; wherein the plurality of battery packs in use are arranged in different electrical devices; A relationship determination module, configured to determine a failure change relationship based on the full amount of data; the failure change relationship includes a relationship between a failure probability of a battery pack and a first survival time; A failure prediction module, used to predict the number of failures of the plurality of battery packs in use within a preset future period according to the failure change relationship; The spare parts determination module is used to determine the number of battery pack spare parts required within the preset future time period based on the number of failures.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images