Battery product failure rate prediction method, system, device, storage medium and product

Abstract

This application relates to a method, system, device, storage medium, and product for predicting battery product failure rates. The method includes: responding to a failure rate prediction instruction from a battery product; acquiring historical failure data over the entire lifecycle of a reference battery product that matches the battery characteristic fields carried in the failure rate prediction instruction; determining a target risk function with the highest matching degree to the historical failure data from a pre-built risk function library; and determining the failure rate prediction result of the battery product over its entire lifecycle based on the matching result between the target risk function and the historical failure data. The method provided in this application can improve the accuracy of predicting battery product failure scenarios.

Description

Technical Field

[0001] This application relates to the field of new energy technology, and in particular to a method, system, device, storage medium and product for predicting battery failure rate. Background Technology

[0002] Battery products are widely used in various scenarios, such as electronic devices, new energy vehicles, and energy storage. Therefore, quality management of battery products is crucial.

[0003] To ensure battery product quality, it's common practice to predict battery failure scenarios and implement proactive quality control based on these predictions. Related technologies typically involve collecting product identification (ID) and fault information to predict battery failure.

[0004] However, the predicted failure scenarios of battery products in related technologies are not accurate enough, which affects the ability to control the quality of battery products in advance. Summary of the Invention

[0005] Based on this, this application provides a method, system, device, storage medium, and product for predicting battery product failure rates, which can improve the accuracy of predicting battery product failure rates.

[0006] In a first aspect, this application provides a method for predicting the failure rate of a battery product. The method includes: responding to a failure rate prediction instruction for a battery product, obtaining historical failure data of a reference battery product throughout its entire life cycle that matches the battery feature fields carried in the failure rate prediction instruction; determining a target risk function with the highest matching degree with the historical failure data from a pre-built risk function library; and determining the failure rate prediction result of the battery product throughout its entire life cycle based on the matching result between the target risk function and the historical failure data.

[0007] In the technical solution of this application embodiment, the historical fault data is the fault data of the reference battery product in operation. Therefore, the historical fault data is comprehensive and real data, and the failure rate prediction result of the battery product throughout its entire life cycle can accurately reflect the failure status of the battery product, thus improving the accuracy of the predicted failure status of the battery product. Furthermore, the target risk function is the risk function with the highest matching degree with the historical fault data determined from the risk function library. Therefore, based on the matching result between the target risk function and the historical fault data, the failure rate prediction result can be determined more accurately, thereby further improving the accuracy of the predicted failure status of the battery product.

[0008] In some embodiments, acquiring historical fault data of a reference battery product throughout its entire lifecycle, matching battery characteristic fields, includes: acquiring the fault time and initial operating time of the reference battery product; determining the operating time of the reference battery product based on the fault time and initial operating time; and determining the fault data of the reference battery product at each stage in multiple phases throughout its lifecycle based on the operating time. In the technical solution of this application embodiment, by determining the fault data of the reference battery product at each stage in multiple phases throughout its lifecycle, the fault data of the operating reference battery product can be divided into each stage. Therefore, by analyzing the fault data of each stage separately, the fault characteristics of each stage can be obtained, leading to a more accurate failure rate prediction result throughout the entire lifecycle and improving the accuracy of the predicted battery product failure situation.

[0009] In some embodiments, historical fault data includes fault data from each stage of a multi-stage process. Determining the target risk function with the highest matching degree to the historical fault data from a pre-built risk function library includes: determining the failure rate of the reference battery product at each stage of its entire lifecycle based on fault data from each stage; and determining the target risk function with the highest matching degree to the failure rate of the reference battery product at each stage from the pre-built risk function library. In the technical solution of this application embodiment, by determining the target risk function with the highest matching degree to the failure rate of the reference battery product at each stage, the target risk function can better reflect the changing trend of the failure rate of the reference battery product at each stage, thereby making the failure rate prediction result determined by the target risk function more accurate.

[0010] In some embodiments, determining the failure rate of a reference battery product at each stage of its entire lifecycle based on failure data at each stage includes: determining the number of multiple sub-failures corresponding to multiple product attributes at each stage based on the failure data at each stage of the reference battery product's entire lifecycle; determining multiple sub-failure rates at each stage based on the number of multiple sub-failures at each stage; and fusing the multiple sub-failure rates at each stage to obtain the failure rate of the reference battery product at each stage. In the technical solution of this application embodiment, fusing the multiple sub-failure rates corresponding to multiple product attributes at each stage to obtain the failure rate of the reference battery product at each stage can comprehensively consider the performance of the battery product under different product attributes, thereby obtaining a more accurate assessment result of the failure rate of the reference battery product, and thus improving the accuracy of the predicted failure rate of the reference battery product.

[0011] In some embodiments, multiple sub-failure rates at each stage are fused to obtain the failure rate of a reference battery product at each stage. This includes: obtaining the total number of reference battery products in operation at each stage and multiple sub-operation numbers corresponding to multiple product attributes at each stage; determining multiple proportional coefficients for the proportion of each sub-operation number to the total number of operations at each stage; and fusing the multiple sub-failure rates at each stage based on the multiple proportional coefficients at each stage to obtain the failure rate of the reference battery product at each stage. In the technical solution of this application embodiment, multiple sub-failure rates are fused based on multiple proportional coefficients. This means that if the proportion of the sub-operation number to the total number of operations is larger, the sub-failure rate has a greater impact on the failure rate of the reference battery product; conversely, if the proportion of the sub-operation number to the total number of operations is smaller, the sub-failure rate has a smaller impact on the failure rate of the reference battery product. This makes the determination of the failure rate of the reference battery product more accurate and improves the accuracy of the determined failure rate of the reference battery product.

[0012] In some embodiments, multiple sub-failure rates at each stage are fused to obtain the failure rate of the reference battery product at each stage. This includes: obtaining the number of generations a reference battery product with multiple product attributes has undergone at each stage; assigning multiple quality coefficients to multiple product attributes based on the number of generations a reference battery product has undergone; and fusing the multiple sub-failure rates at each stage based on the multiple quality coefficients at each stage to obtain the failure rate of the reference battery product at each stage. In the technical solution of this application embodiment, the more generations a reference battery product has undergone, the higher the quality of the battery product, and the greater the impact on the failure rate of the reference battery product should be. Therefore, assigning multiple quality coefficients to the number of generations a reference battery product with multiple product attributes has undergone, and fusing the multiple sub-failure rates based on the multiple quality coefficients, improves the accuracy of the determined failure rate of the reference battery product.

[0013] In some embodiments, determining the failure rate of a reference battery product at each stage of its entire lifecycle based on failure data at each stage includes: determining the failure rate of electronic components in the reference battery product at each stage based on the failure data at each stage of its entire lifecycle; and determining the failure rate of the reference battery product at each stage based on the failure rate of the electronic components in the reference battery product at each stage. In the technical solution of this application embodiment, when determining the failure rate of the reference battery product, the influence of the failure rates of different electronic components in the reference battery product on the failure rate of the reference battery product can be considered, making the determined failure rate of the reference battery product more accurate.

[0014] In some embodiments, determining the failure rate of a reference battery product at each stage based on the failure rate of electronic components in the reference battery product at each stage includes: obtaining the circuit connection method of the electronic components in the reference battery product; and determining the failure rate of the reference battery product at each stage based on the circuit connection method and the failure rate of the electronic components in the reference battery product at each stage. In the technical solution of this application embodiment, when determining the failure rate of a reference battery product, the influence of the circuit connection method of the electronic components in the reference battery product and the failure rates of different electronic components in the reference battery product on the failure rate of the reference battery product can be comprehensively considered, making the determined failure rate of the reference battery product more accurate.

[0015] In some embodiments, determining the failure rate of the reference battery product at each stage based on the circuit connection method and the failure rate of electronic components in the reference battery product at each stage includes: when the circuit connection method is a hybrid connection method, obtaining the redundancy of the parallel loops and the number of branches in the parallel loops in the hybrid circuit composed of electronic components in the reference battery product; determining the number of branch failures in the parallel loops when a fault occurs in the parallel loop based on the redundancy number; and determining the failure rate of the reference battery product at each stage based on the number of branches, the number of branch failures, and the failure rate of electronic components in the reference battery product at each stage. In the technical solution of this application embodiment, when determining the failure rate of the reference battery product, the number of branches and the number of branch failures in the parallel loops, as well as the impact of the failure rates of different electronic components in the reference battery product on the failure rate of the reference battery product, can be comprehensively considered, making the determined failure rate of the reference battery product more accurate.

[0016] In some embodiments, determining the target risk function with the highest matching degree to the failure rate of the reference battery product at each stage from a pre-built risk function library includes: dividing the entire life cycle into multiple failure periods; determining each sub-target risk function with the highest matching degree to the failure rate of the reference battery product in each failure period; each sub-target risk function is included in the target risk function. In the technical solution of this application embodiment, by determining each sub-target risk function with the highest matching degree to the failure rate of the reference battery product in each failure period, it is possible to select the optimal sub-target risk function corresponding to each failure period based on the failure rate distribution of the reference battery product in each failure period, thereby making the failure rate prediction results determined by each sub-target risk function more accurate.

[0017] In some embodiments, determining the sub-target risk functions that best match the failure rate of the reference battery product in each failure period includes: fitting the failure rate of the reference battery product in each failure period using multiple risk functions from a risk function library to obtain multiple matching results for each failure period; determining multiple accuracy parameters corresponding to the multiple matching results; and determining the risk function corresponding to the accuracy parameter with the highest accuracy among the multiple accuracy parameters in each failure period as the sub-target risk function for each failure period. In the technical solution of this application embodiment, the sub-target risk function corresponding to each failure period is the risk function corresponding to the accuracy parameter with the highest accuracy among the multiple accuracy parameters corresponding to the multiple risk functions. Therefore, the sub-target risk function corresponding to each failure period can most accurately reflect the failure rate distribution of the reference battery product in each failure period, and thus the failure rate prediction result determined based on the sub-target risk function corresponding to each failure period is more accurate.

[0018] In some embodiments, the entire lifecycle is divided into multiple failure periods, including: sequentially determining the change in failure rate of a reference battery product between every two adjacent stages; and dividing the entire lifecycle into multiple failure periods based on the change. In the technical solution of this application embodiment, the change in failure rate of the reference battery product can reflect the change pattern of failure rate of the battery product throughout its entire lifecycle, thereby accurately dividing the entire lifecycle into multiple failure periods and improving the accuracy of the divided multiple failure periods.

[0019] In some embodiments, multiple failure periods include an early failure period, an accidental failure period, and a wear-out failure period. Based on the amount of change, the entire lifecycle is divided into multiple failure periods, including: determining the first stage of two adjacent stages corresponding to the first change amount less than or equal to a preset threshold as the end stage of the early failure period; the preset threshold is greater than 0; determining the second stage of two adjacent stages corresponding to the first change amount less than or equal to a target threshold as the start stage of the wear-out failure period; the target threshold is less than 0; and dividing the entire lifecycle into an early failure period, an accidental failure period, and a wear-out failure period based on the end stage and the start stage. In the technical solution of this application embodiment, the failure rate of the reference battery product exhibits different variation patterns in the early failure period, the accidental failure period, and the wear-out failure period. By dividing the entire lifecycle into an early failure period, an accidental failure period, and a wear-out failure period, and analyzing the failure rate of the reference battery product in each of these periods, the accuracy of the predicted failure rate over the determined entire lifecycle can be improved.

[0020] In some embodiments, determining the failure rate prediction result of a battery product over its entire life cycle based on the matching result of the target risk function and historical failure data includes: determining the mapping relationship between the operating time and failure rate of the battery product over its entire life cycle based on the matching result of the target risk function and historical failure data; and determining the mapping relationship as the failure rate prediction result of the battery product over its entire life cycle. In the technical solution of this application embodiment, the mapping relationship between the operating time and failure rate of the battery product over its entire life cycle, determined based on the matching result of the target risk function and historical failure data, can reflect the change law of the failure rate of the battery product over its entire life cycle with operating time. Therefore, based on this change law, the failure rate of the battery product at any time can be accurately determined, improving the reliability of determining the failure rate of the battery product.

[0021] In some embodiments, battery feature fields are obtained by triggering target options under at least one selection item in the battery product failure rate prediction system interface; different selection items represent different features of the battery product. In the technical solution of this application embodiment, the user can trigger the options under the corresponding selection item according to needs, and the computer device determines the corresponding failure rate prediction result according to the user's selected option, so that the failure rate prediction result meets the user's needs and improves the prediction flexibility of the failure rate prediction result.

[0022] In some embodiments, the battery characteristic field includes the target manufacturer / target user to which the battery product belongs; the method further includes: obtaining the early warning failure rate corresponding to the target manufacturer / target user; displaying the failure rate prediction result of the battery product throughout its entire life cycle, and displaying the early warning line corresponding to the early warning failure rate in the target coordinate system interface. In the technical solution of this application embodiment, analyzing the historical failure data of reference battery products manufactured and put into operation by the target manufacturer or used by the target user, determining the failure rate prediction result of the battery product of the target manufacturer / target user, and displaying the failure rate prediction result and early warning line in the target coordinate system, helps to conduct quality analysis of the battery products of the target manufacturer / target user and improves the effectiveness of battery product management.

[0023] In some embodiments, the method further includes: responding to a failure number prediction instruction for the battery product within a target time period, determining an average failure rate of reference battery products within the target time period based on the failure rate prediction result; and determining the total number of failures of the battery product within the target time period based on the average failure rate and the total number of reference battery products in operation. In the technical solution of this application embodiment, by displaying the total number of failures of the battery product within the target time period on the battery product failure rate prediction system interface, users can intuitively see the total number of failures of the battery product within the target time period, which is beneficial for making failure management decisions for the battery product and improves the effectiveness of battery product management.

[0024] Secondly, this application provides a battery product failure rate prediction system, which includes: a data import module, used to respond to a failure rate prediction instruction for a battery product and, based on the battery feature fields carried in the failure rate prediction instruction, obtain historical failure data of a reference battery product throughout its entire life cycle that matches the battery feature fields; a function selection module, used to determine the target risk function with the highest matching degree to the historical failure data from a pre-built risk function library; and a data prediction module, used to determine the failure rate prediction result of the battery product throughout its entire life cycle based on the target risk function.

[0025] In some embodiments, the system further includes: a chart export module for determining a fault quantity chart based on the failure rate prediction results; the fault quantity chart includes the number of product faults of the battery product at each stage of the entire life cycle; and a data presentation module for displaying the fault quantity chart in the battery product failure rate prediction system interface.

[0026] In some embodiments, the system further includes: a data acquisition module, used to acquire historical fault data of the reference battery product and store the historical fault data of the reference battery product in a database; wherein the historical fault data of the reference battery product in the database is used by the data import module to obtain it.

[0027] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described above.

[0028] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods described above.

[0029] Fifthly, this application provides a program product including a computer program that, when executed by a processor, implements the steps of any of the methods described above. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A schematic diagram of the application system provided in some embodiments;

[0032] Figure 2 A flowchart illustrating a battery product failure rate prediction method provided for some embodiments;

[0033] Figure 3 A flowchart illustrating a method for acquiring historical fault data, provided for some embodiments;

[0034] Figure 4 A flowchart illustrating a method for determining a target risk function, provided for some embodiments;

[0035] Figure 5 A flowchart illustrating a method for determining the failure rate of a reference battery product, provided for some embodiments;

[0036] Figure 6 A flowchart illustrating a method for determining the failure rate of a reference battery product, provided for other embodiments;

[0037] Figure 7 A schematic diagram of a series circuit composed of electronic components is provided for some embodiments;

[0038] Figure 8 A schematic diagram of a parallel circuit composed of electronic components is provided for some embodiments;

[0039] Figure 9 A schematic diagram of a hybrid circuit composed of electronic components is provided for some embodiments;

[0040] Figure 10 A flowchart illustrating a process for determining the failure rate prediction of a battery product over its entire life cycle, provided for some embodiments;

[0041] Figure 11 A schematic diagram of the configuration interface of a battery product failure rate prediction system provided in some embodiments;

[0042] Figure 12 This is a schematic diagram of multiple options in the interface of a battery product failure rate prediction system provided in some embodiments;

[0043] Figure 13A schematic diagram illustrating the relationship between runtime and battery product failure rate in some embodiments;

[0044] Figure 14 A graphical representation of the number of battery products shipped and the number of defects over multiple production months for some embodiments;

[0045] Figure 15 A schematic diagram of the structure of a battery product failure rate prediction system provided in some embodiments;

[0046] Figure 16 A schematic diagram of the structure of a computer device provided for some embodiments. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0049] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0050] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0051] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0052] During operation, variations in at least one stage—design, production, logistics, or warehousing—can lead to different failure scenarios for battery products. These failure scenarios affect the overall malfunction of the battery, necessitating repair or replacement. Predicting battery failure scenarios allows for proactive quality control, facilitating battery management and improving overall quality service.

[0053] If a user encounters a battery malfunction while using the product, they can report the problem through customer service or other channels. After-sales personnel will then repair or replace the faulty battery based on the reported information. Typically, battery operators tally the number of malfunctions over a period of time to estimate battery failure rates. However, this method of estimating battery failure rates is rather subjective, leading to inaccurate predictions.

[0054] To alleviate the aforementioned problems, research revealed that there are numerous battery products on the market, each with varying failure times. Historical failure data across the entire lifecycle of these battery products was collected, and multiple functions from a risk function library were used to match this historical failure data, resulting in the target risk function with the highest matching degree. Based on the matching result between this target risk function and the historical failure data, the predicted failure rate of the battery product over its entire lifecycle was determined. Therefore, assessing battery failure does not require human intervention and is based on a large amount of failure data from operating batteries. This improves the accuracy of predicted battery failure, and since the target risk function has the highest matching degree with the historical failure data, the predicted failure rate can be determined more accurately.

[0055] Based on the above considerations, this application provides a method for predicting the failure rate of a battery product. The method includes: responding to a failure rate prediction instruction for a battery product; obtaining historical fault data throughout the entire lifecycle of a reference battery product that matches the battery characteristic fields carried in the failure rate prediction instruction; determining a target risk function with the highest matching degree to the historical fault data from a pre-built risk function library; and determining the failure rate prediction result of the battery product throughout its entire lifecycle based on the target risk function. In this way, the historical fault data is fault data from a reference battery product in operation, thus providing comprehensive and real-world data. Therefore, the determined failure rate prediction result for the battery product throughout its entire lifecycle accurately reflects the failure status of the battery product, improving the accuracy of the predicted failure status. Furthermore, the target risk function is the risk function with the highest matching degree to the historical fault data determined from the risk function library. Therefore, based on the matching result between the target risk function and the historical fault data, the failure rate prediction result can be determined more accurately, further improving the accuracy of the predicted failure status of the battery product.

[0056] The battery product failure rate prediction method in this application embodiment can be applied, for example, to a computer device on the operator side of the battery product. The operator can obtain historical failure data of the battery product in operation, that is, historical failure data of the battery product throughout its entire life cycle. For example, the operator of the battery product can be a battery product seller or manufacturer. The computer device determines the failure rate prediction result of the battery product throughout its entire life cycle based on the historical failure data of the battery product throughout its entire life cycle.

[0057] The computer equipment in this application embodiment may include one or at least two of the following interconnected devices: server, display device, mobile phone, tablet computer, computer with wireless transceiver function, handheld computer, desktop computer, personal digital assistant, digital TV, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal in self-driving, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc.

[0058] Figure 1 This is a schematic diagram of the structure of an application system provided in some embodiments, such as... Figure 1As shown, the application system includes a database device and a computer device. The database device stores historical fault data throughout the entire life cycle of the reference battery product, and the computer device can obtain historical fault data from the database device and determine the failure rate prediction result throughout the entire life cycle based on the historical fault data.

[0059] Figure 2 A flowchart illustrating a battery product failure rate prediction method provided in some embodiments, such as... Figure 2 As shown, this method is applied to a computer device, and the method includes:

[0060] S201. In response to the failure rate prediction command of the battery product, obtain historical failure data of the reference battery product throughout its entire life cycle based on the battery characteristic fields carried in the failure rate prediction command.

[0061] Failure rate refers to the probability that a product that has not failed by a certain point in time will fail after that point. In some embodiments, failure rate can be replaced by instantaneous failure rate or failure risk rate. For example, the unit of time can be a month, a day, or a week, etc.

[0062] A battery product is a product that converts chemical energy into electrical energy. For example, a battery product may include one of the following: a battery cell, a battery module, a battery system, or a battery pack.

[0063] Battery feature fields represent characteristic information of battery products, with different battery feature fields representing battery products with different characteristics. For example, battery feature fields may include at least one of the following: design information, project information, incoming material information, production information, warehousing information, logistics information, product type information, liability information, fault information, manufacturer information, faulty component information, chemical system information, shipped product information, corresponding platform information, shipped product type information, product line information, assembly part number (PN) information, customer complaint number type information, product structure information, etc. For example, if one battery feature field includes first design information and another battery feature field includes second design information, then these two battery feature fields are different. As another example, if one battery feature field includes first design information and another battery feature field includes first incoming material information, then these two battery feature fields are different.

[0064] The reference battery product can be any battery product for which the computer equipment can collect historical fault data, or in other words, the reference battery product can be any battery product in operation.

[0065] Fault data can be data related to battery product failures. For example, fault data may include at least one of the following: battery product identification (also known as product identification information), battery product fault code (also known as fault number), battery product shipping time, initial operating time, battery product failure time, battery product failure type (also known as fault type), and faulty component of the battery product.

[0066] Table 1 illustrates the contents of historical fault data for a battery product, as shown in Table 1:

[0067] Table 1

[0068]

[0069] In some embodiments, the computer device can periodically generate failure rate prediction instructions. In this way, the computer device can periodically respond to the failure rate prediction instructions and determine the failure rate prediction result of the battery product over its entire life cycle based on the failure rate prediction instructions. For example, the computer device can generate failure rate prediction instructions every day, three days, one week, or one month, and determine a failure rate prediction result accordingly based on each response to the failure rate prediction instructions.

[0070] In some embodiments, a failure rate prediction instruction may include at least one sub-failure rate prediction instruction, with different sub-failure rate prediction instructions carrying different battery characteristic fields. Thus, the computer device determines the failure rate prediction result of the battery product over its entire lifecycle based on each sub-failure rate prediction instruction. For example, the failure rate prediction instruction may include a first sub-failure rate prediction instruction and a second sub-failure rate prediction instruction. The battery characteristic field carried by the first sub-failure rate prediction instruction is a default field, and the battery characteristic field carried by the second sub-failure rate prediction instruction is the target manufacturer. For example, the default field represents all characteristics of the battery product, which can be common characteristics of battery products manufactured by the operator. For example, the default field can be NULL or ALL. For example, the target manufacturer is a manufacturer that produces battery products.

[0071] In some embodiments, the computer device may display a battery product failure rate prediction system interface, which includes a failure rate prediction button. The user can trigger the failure rate prediction button, and the computer device generates and responds to a failure rate prediction instruction based on the user's triggering of the failure rate prediction button.

[0072] In some embodiments, the computer device may display a battery product failure rate prediction system interface. This interface includes a failure rate prediction button and multiple selection items. A user can trigger the failure rate button by selecting a target option under at least one of the selection items. Based on the user's trigger, the computer device generates and responds with a failure rate prediction instruction carrying battery characteristic fields. In this case, the battery characteristic fields include at least one target option under the selection item.

[0073] S202. Determine the target risk function that best matches the historical fault data from the pre-built risk function library.

[0074] The risk function library includes multiple risk functions. For example, these risk functions include: normal distribution risk functions, log-normal distribution risk functions, exponential distribution risk functions, and Weibull distribution risk functions, etc., and this application embodiment does not limit this. In some embodiments, the target risk function can be one of the risk functions listed above, or the target risk function includes multiple sub-risk functions corresponding to multiple failure periods, each sub-risk function can be one of the risk functions listed above, and the sub-risk functions corresponding to different failure periods are different.

[0075] The computer device can match multiple risk functions with historical fault data, and select the target risk function with the highest matching degree from the multiple risk functions. In some embodiments, by matching each risk function with historical fault data, corresponding matching results can be obtained. The computer device can obtain the accuracy parameters of multiple matching results corresponding to multiple risk functions, and determine the risk function corresponding to the highest accuracy parameter among the multiple matching results as the target risk function.

[0076] S203. Based on the matching results of the objective risk function and historical failure data, determine the failure rate prediction results of the battery product throughout its entire life cycle.

[0077] For example, the matching result can be a mapping relationship between the runtime and failure rate of a battery product throughout its entire life cycle. As another example, the matching result can be a correspondence between the runtime and other parameters besides the failure rate (such as the number of failures or failure rate) of a battery product throughout its entire life cycle.

[0078] In some embodiments, the failure rate prediction results of the battery product throughout its entire life cycle can also be displayed in the battery product failure rate prediction system interface. Displaying the failure rate prediction results can guide the management of the battery product. For example, by displaying the failure rate prediction results, it can be determined whether the failure rate of the battery product in at least one previous stage is higher than a preset threshold, and whether the failure rate of the product in the stages following at least one previous stage is significantly reduced. If so, the battery product can be controlled to operate for at least one stage before it is sold, thereby reducing the failure rate of the battery product after it is sold.

[0079] In the technical solution of this application embodiment, the historical fault data is the fault data of the reference battery product in operation. Therefore, the historical fault data is comprehensive and real data, and the failure rate prediction result of the battery product throughout its entire life cycle can accurately reflect the failure status of the battery product, thus improving the accuracy of the predicted failure status of the battery product. Furthermore, the target risk function is the risk function with the highest matching degree with the historical fault data determined from the risk function library. Therefore, based on the matching result between the target risk function and the historical fault data, the failure rate prediction result can be determined more accurately, thereby further improving the accuracy of the predicted failure status of the battery product.

[0080] Figure 3 A flowchart illustrating a method for acquiring historical fault data is provided for some embodiments, such as... Figure 3 As shown, this method is applied to a computer device, and the method includes:

[0081] S301. Obtain the failure time and initial operating time of the reference battery product.

[0082] In some embodiments, the failure time and initial operating time of a reference battery product can be determined from historical failure data of the reference battery product.

[0083] S302. Determine the operating time of the reference battery product based on the failure time and initial operating time.

[0084] Runtime refers to the duration of operation of a battery product from the start of operation to the occurrence of the failure. In some embodiments, the runtime of a reference battery product can be determined by subtracting the initial runtime from the failure time.

[0085] S303. Based on the operating time of the reference battery product, determine the fault data of the reference battery product in each stage of its entire life cycle.

[0086] Multiple stages are consecutive, each corresponding to a duration. For example, a stage can represent one day, five days, seven days, one month, three months, one year, or other durations. For example, taking one month as a stage, the fault data for each stage in the multiple stages of the entire lifecycle can be the fault data for each month in the entire lifecycle.

[0087] Taking one month as an example, the fault data for each stage in the entire life cycle can be the fault data for the first month of the entire life cycle, the fault data for the second month of the entire life cycle, and so on, until the fault data for the last month of the entire life cycle.

[0088] In the technical solution of this application embodiment, by determining the fault data of each stage in the multiple stages of the entire life cycle of the reference battery product, the fault data of the reference battery product in operation can be divided into each stage. By analyzing the fault data of each stage separately, the fault characteristics of each stage can be obtained, thereby obtaining a more accurate failure rate prediction result under the entire life cycle and improving the accuracy of the predicted failure situation of the battery product.

[0089] Figure 4 A flowchart illustrating a method for determining a target risk function is provided for some embodiments, such as... Figure 4 As shown, this method is applied to a computer device, and the method includes:

[0090] S401. Based on the failure data of the reference battery product at each stage of its entire life cycle, determine the failure rate of the reference battery product at each stage of its entire life cycle.

[0091] The failure rate of reference battery products at each stage can be determined from the perspective of the battery product itself, or from the perspective of the electronic components within the battery product.

[0092] For example, the number of failures of the battery product at each stage can be determined based on the failure data of the reference battery product at each stage of its entire life cycle; and the failure rate of the reference battery product at each stage can be determined based on the number of failures of the battery product at each stage and the total number of battery products at each stage.

[0093] For example, the number of electronic component failures in each stage of the battery product can be determined based on the failure data of the reference battery product at each stage of its entire life cycle; the failure rate of the electronic components in each stage can be determined based on the number of electronic component failures in the battery product at each stage and the total number of electronic components in each stage; and the failure rate of the reference battery product in each stage can be determined based on the failure rate of the electronic components in each stage.

[0094] S402. From the pre-built risk function library, determine the target risk function that best matches the failure rate of the reference battery product at each stage.

[0095] The computer device can match multiple risk functions with the failure rates of reference battery products at each stage, and select the target risk function with the highest matching degree from the multiple risk functions. In some embodiments, by matching each risk function with the failure rates of reference battery products at each stage, the matching result is a mapping relationship between the runtime and failure rate of the battery product.

[0096] In the technical solution of this application embodiment, by determining the target risk function that has the highest matching degree with the failure rate of the reference battery product at each stage, the target risk function can better reflect the changing trend of the failure rate of the reference battery product at each stage, and thus the failure rate prediction result determined by the target risk function is more accurate.

[0097] The following explains how to determine the failure rate of reference battery products at each stage, from the perspective of battery products:

[0098] Figure 5 A flowchart illustrating a method for determining the failure rate of a reference battery product is provided for some embodiments, such as... Figure 5 As shown, this method is applied to a computer device, and the method includes:

[0099] S501. Based on the fault data of the reference battery product at each stage of its entire life cycle, determine the number of multiple sub-faults corresponding to multiple product attributes of the reference battery product at each stage.

[0100] Product attributes describe the characteristics of a battery product. In some embodiments, product attributes may include batch. For example, battery products manufactured in different batches may have different product attributes.

[0101] S502. Determine the failure rate of multiple sub-faults in each stage based on the number of multiple sub-faults in each stage.

[0102] In some embodiments, the ratio of the number of multiple sub-faults in each stage to the total number of battery products corresponding to multiple product attributes in each stage is determined as the multiple sub-fault rates in each stage.

[0103] For example, the first month's multiple product attributes include a first product attribute and a second product attribute. The ratio of the number of sub-faults of the first product attribute to the total number of the first product attribute in the first month of the entire life cycle is determined as the sub-fault rate corresponding to the first product attribute. The ratio of the number of sub-faults of the second product attribute to the total number of the second product attribute in the first month of the entire life cycle is determined as the sub-fault rate corresponding to the second product attribute. And so on, to obtain the multiple sub-fault rates corresponding to the multiple product attributes for each month.

[0104] S503. The failure rates of multiple sub-failure rates at each stage are fused to obtain the failure rate of the reference battery product at each stage.

[0105] In this way, multiple sub-failure rates at each stage are fused to obtain the failure rate of the reference battery product at each stage. There are several ways to fuse the multiple sub-failure rates at each stage. For example, a weighted fusion (e.g., weighted average or weighted summation) can be performed on the multiple sub-failure rates at each stage to obtain the failure rate of the reference battery product at each stage. Another example is to determine the maximum or minimum value of the multiple sub-failure rates at each stage as the failure rate of the reference battery product at each stage.

[0106] In the technical solution of this application embodiment, multiple sub-failure rates corresponding to multiple product attributes under each stage are fused to obtain the failure rate of the reference battery product under each stage. This can comprehensively consider the performance of the battery product under different product attributes, thereby obtaining a more accurate evaluation result of the failure rate of the reference battery product, and thus improving the accuracy of the predicted failure rate of the reference battery product.

[0107] The following describes several schemes for fusing the failure rates of multiple sub-series at each stage:

[0108] In some embodiments, the total number of reference battery products in each stage and the number of sub-operations corresponding to multiple product attributes in each stage are obtained; in each stage, the proportion of the number of sub-operations to the total number of operations is determined as multiple proportional coefficients; based on the multiple proportional coefficients in each stage, the multiple sub-failure rates in each stage are fused to obtain the failure rate of the reference battery products in each stage.

[0109] For example, multiple sub-failure rates at each stage can be weighted and fused (e.g., weighted average or weighted summation) based on multiple proportional coefficients at each stage.

[0110] In the technical solution of this application embodiment, multiple sub-failure rates are fused according to multiple proportional coefficients. In this way, if the proportion of the number of sub-operations to the total number of operations is larger, the sub-failure rate has a greater impact on the failure rate of the reference battery product. If the proportion of the number of sub-operations to the total number of operations is smaller, the sub-failure rate has a smaller impact on the failure rate of the reference battery product. This makes the determination of the failure rate of the reference battery product more accurate and improves the accuracy of the determined failure rate of the reference battery product.

[0111] In other embodiments, the number of generations of reference battery products with multiple product attributes under each stage is obtained; multiple quality coefficients are assigned to multiple product attributes based on the number of generations of reference battery products with multiple product attributes; and multiple sub-failure rates under each stage are fused based on the multiple quality coefficients under each stage to obtain the failure rate of the reference battery products under each stage.

[0112] For example, multiple sub-failure rates at each stage can be weighted and fused (e.g., weighted average or weighted summation) based on multiple quality coefficients at each stage. In some implementations, the sum of multiple quality coefficients is 1.

[0113] In the technical solution of this application embodiment, the more generations a reference battery product has undergone, the higher its quality and the greater its impact on the failure rate of the reference battery product. Therefore, multiple quality coefficients are assigned to the number of generations a reference battery product with multiple product attributes has undergone, and multiple sub-failure rates are fused based on the multiple quality coefficients, thereby improving the accuracy of the determined failure rate of the reference battery product.

[0114] In some other embodiments, the two methods described above can be combined, and the implementation is as follows: obtain the total number of reference battery products in operation at each stage; at each stage, determine the proportion of the number of multiple sub-faults to the total number of operations as multiple proportional coefficients; obtain the number of replacement cycles experienced by the reference battery products of multiple product attributes at each stage; assign multiple quality coefficients to the multiple product attributes according to the number of replacement cycles experienced by the reference battery products of multiple product attributes; and fuse the multiple sub-failure rates at each stage according to the multiple quality coefficients and the multiple proportional coefficients at each stage to obtain the failure rate of the reference battery products at each stage.

[0115] For example, multiple quality coefficients and multiple proportional coefficients for each stage can be fused to obtain multiple weight coefficients for each stage; based on the multiple weight coefficients for each stage, multiple sub-failure rates for each stage are weighted and fused (e.g., weighted average or weighted summation). In some embodiments, multiple quality coefficients and multiple proportional coefficients for each stage are multiplied or added to obtain multiple weight coefficients. In other embodiments, multiple quality coefficients and multiple proportional coefficients for each stage are multiplied or added to obtain multiple influence coefficients, and the multiple influence coefficients are normalized to obtain multiple weight coefficients.

[0116] The following explains how to determine the failure rate of reference battery products at each stage, focusing on the electronic components within the battery product:

[0117] Figure 6 A flowchart illustrating a method for determining the failure rate of a reference battery product is provided for some other embodiments, such as... Figure 6 As shown, this method is applied to a computer device, and the method includes:

[0118] S601. Based on the failure data of the reference battery product at each stage of its entire life cycle, determine the failure rate of the electronic components in the reference battery product at each stage.

[0119] For example, the electronic component may be a battery cell. In other embodiments, the electronic component may include at least one of the following: a battery cell, a circuit module, an electronic device, etc.

[0120] In some implementations, the number of electronic component failures at each stage can be determined based on failure data of a reference battery product at each stage of its entire life cycle; and the failure rate of electronic components at each stage can be determined based on the number of electronic component failures at each stage and the total number of electronic components obtained at each stage.

[0121] S602. Determine the failure rate of the reference battery product at each stage based on the failure rate of the electronic components in the reference battery product at each stage.

[0122] In some examples, S602 can be implemented in multiple ways: In some embodiments, the failure rate of the reference battery product at each stage can be determined based on the circuit connection method of the electronic components in the reference battery product and the failure rate of the electronic components at each stage. In other embodiments, the maximum, minimum, or average value of the failure rates of the electronic components in the reference battery product at each stage can be determined as the failure rate of the reference battery product at each stage.

[0123] In the technical solution of this application embodiment, when determining the failure rate of a reference battery product, the influence of the failure rate of different electronic components in the reference battery product on the failure rate of the reference battery product can be considered, so that the determined failure rate of the reference battery product is more accurate.

[0124] In some embodiments, Figure 5 and Figure 6 The embodiments can be combined, for example, by determining the failure rate of electronic components in the reference battery product at each stage of its entire life cycle based on the failure data of the reference battery product at each stage; by determining multiple sub-failure rates corresponding to multiple attributes at each stage based on the failure rate of electronic components in the reference battery product at each stage and the circuit connection methods corresponding to multiple attributes of the reference battery product; and by fusing the multiple sub-failure rates at each stage to obtain the failure rate of the reference battery product at each stage.

[0125] In some embodiments, determining the failure rate of a reference battery product at each stage based on the failure rate of electronic components in the reference battery product at each stage includes: obtaining the circuit connection method of electronic components in the reference battery product; and determining the failure rate of the reference battery product at each stage based on the circuit connection method and the failure rate of electronic components in the reference battery product at each stage.

[0126] For example, the circuit connection method of electronic components in a reference battery product may include series, parallel, or mixed connection.

[0127] In the technical solution of this application embodiment, when determining the failure rate of the reference battery product, the circuit connection method of the electronic components in the reference battery product and the failure rate of different electronic components in the reference battery product can be comprehensively considered, so that the determined failure rate of the reference battery product is more accurate.

[0128] Taking the hybrid connection method of the electronic components in the reference battery product as an example, the failure rate of the reference battery product at each stage is determined based on the circuit connection method and the failure rate of the electronic components in the reference battery product at each stage. This includes: when the circuit connection method is hybrid, obtaining the redundancy of the parallel loop and the number of branches in the parallel loop in the hybrid circuit formed by the electronic components in the reference battery product; based on the redundancy, determining the number of branch failures in the parallel loop when a fault occurs in the parallel loop; and based on the number of branches, the number of branch failures, and the failure rate of the electronic components in the reference battery product at each stage, determining the failure rate of the reference battery product at each stage.

[0129] For example, the number of branch faults can be the result of adding 1 to the number of redundancies.

[0130] In the technical solution of this application embodiment, when determining the failure rate of the reference battery product, the number of branches and the number of branch failures in the parallel circuit, as well as the failure rate of different electronic components in the reference battery product, can be comprehensively considered, so that the determined failure rate of the reference battery product is more accurate.

[0131] The following examples illustrate how to determine the failure rate of a battery product, using series, parallel, and mixed circuits of its electronic components:

[0132] Figure 7 A schematic diagram of a series circuit composed of electronic components is provided for some embodiments, such as Figure 7 As shown, N electronic components are connected in series, where N is an integer greater than or equal to 2.

[0133] Let Yi represent whether electronic component i has failed. The value of i is an integer greater than or equal to 1 and less than or equal to N. Yi = 1 indicates that electronic component i has failed, and Yi = 0 indicates that electronic component i is operating normally (not failed). Pi = P[Yi = 1] is the probability (or likelihood) of electronic component i failing. Each electronic component is independent. Then the battery product failure rate P[system failure] is: P[system failure] = 1 - p[system normal] = 1 - P[(Y1 = 0) ∩ (Y2 = 0) ∩ ... ∩ (YN = 0)]. Wherein, P[(Y1 = 0) ∩ (Y2 = 0) ∩ ... ∩ (YN = 0)] represents the probability that electronic component 1, electronic component 2, and so on, until electronic component N all operate normally at the same time.

[0134] Thus, we obtain Among them, P i This represents the probability of electronic component i failing. For example, if the failure rates of all electronic components are equal and all are P, then P[system failure] = 1 – 1 – P n .

[0135] Figure 8 A schematic diagram of a parallel circuit composed of electronic components is provided for some embodiments, such as Figure 8 As shown, N electronic components are connected in parallel in sequence, where N is an integer greater than or equal to 2.

[0136] Let Yi represent whether electronic component i has failed. The value of i is an integer greater than or equal to 1 and less than or equal to N. Yi = 1 indicates that electronic component i has failed, and Yi = 0 indicates that electronic component i is operating normally (not failed). Pi = P[Yi = 1] is the probability (or likelihood) of electronic component i failing. Each electronic component is independent. Then the battery product failure rate P[system failure] is: P[system failure] = P[(Y1 = 1) ∩ (Y2 = 1) ∩ ... ∩ (Yn = 1)]. Wherein, P[(Y1 = 1) ∩ (Y2 = 1) ∩ ... ∩ (YN = 1)] represents the probability that electronic component 1 fails, electronic component 2 fails, and so on, until electronic component N fails normally and occurs simultaneously.

[0137] Thus, we obtain Among them, P i It is the probability of electronic component i failing.

[0138] Figure 9 A schematic diagram of a hybrid circuit composed of electronic components is provided for some embodiments, such as Figure 9 As shown, the battery product has Q subsystems connected in series. Each subsystem has N electronic components connected in parallel, where Q is an integer greater than or equal to 2, and N is an integer greater than or equal to 2. Each electronic component is independent.

[0139] In a scenario where all electronic components in a subsystem fail, the battery product fails, and the battery product failure rate P[system failure] is: Among them, P ij This represents the failure rate of the j-th electronic component in the i-th subsystem.

[0140] In another scenario, if M out of N electronic components in a subsystem fail, the battery product fails. The battery product failure rate P[system failure] can then be calculated using a binomial distribution, and is: Where C(N,M)=N! / (M!×(NM)!).

[0141] Where M can be the number of branch faults mentioned above.

[0142] In other embodiments, there are also scenarios where the battery product has Q subsystems connected in parallel, and each subsystem has N electronic components connected in series. The corresponding battery product failure rate can be derived accordingly, which will not be elaborated here.

[0143] The following explains how to determine the target risk function from a pre-built risk function library.

[0144] In some embodiments, the target risk function that best matches the failure rate of the reference battery product at each stage is determined from a pre-built risk function library, including: dividing the entire life cycle into multiple failure periods; determining each sub-target risk function that best matches the failure rate of the reference battery product in each failure period; and including each sub-target risk function in the target risk function.

[0145] For example, the sub-objective risk function can be a normal distribution risk function, a log-normal distribution risk function, an exponential distribution risk function, or a Weibull distribution risk function, etc. Different sub-objective risk functions can be the same or different. In the embodiments of this application, the different sub-objective risk functions are different.

[0146] In the technical solution of this application embodiment, by determining the sub-objective risk functions that have the highest matching degree with the failure rate of the reference battery product in each failure period, it is possible to select the optimal sub-objective risk function corresponding to each failure period based on the failure rate distribution of the reference battery product in each failure period, and thus the failure rate prediction result determined by each sub-objective risk function is more accurate.

[0147] In some embodiments, determining the sub-target risk function that best matches the failure rate of the reference battery product in each failure period includes: fitting the failure rate of the reference battery product in each failure period with multiple risk functions from the risk function library to obtain multiple matching results in each failure period; determining multiple accuracy parameters corresponding to the multiple matching results; and determining the risk function corresponding to the accuracy parameter with the highest accuracy among the multiple accuracy parameters in each failure period as the sub-target risk function corresponding to each failure period.

[0148] In some embodiments, the matching result can also be called the fitting result, which can be the correspondence between the running time and failure rate of the battery product. Each matching result is obtained by fitting the failure rate of the reference battery product within each failure period according to each risk function. The matching result corresponding to a risk function can be obtained by substituting the target coefficient into the risk function, and the target coefficient is obtained through fitting.

[0149] Accuracy parameters can be used to represent the error between the matching result and the failure rate of a reference battery product. In some embodiments, accuracy parameters may also be referred to as index parameters. Exemplarily, accuracy parameters may include at least one of the following: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), goodness of fit, coefficient of determination R-squared (R²), confidence interval span, etc. For example, the closer R² is to 1, the higher the accuracy; conversely, the closer R² is to 0, the lower the accuracy. As another example, a larger 95% confidence interval span determined based on the matching result indicates lower accuracy, and vice versa.

[0150] In the technical solution of this application embodiment, the sub-target risk function corresponding to each failure period is the risk function corresponding to the highest accuracy parameter among the multiple accuracy parameters corresponding to multiple risk functions. Thus, the sub-target risk function corresponding to each failure period can most accurately reflect the failure rate distribution of the reference battery product within each failure period. Therefore, the failure rate prediction result within each sub-failure period determined based on the sub-target risk function corresponding to each failure period is more accurate.

[0151] In some embodiments, the entire life cycle is divided into multiple failure periods, including: sequentially determining the change in failure rate of a reference battery product between every two adjacent stages; and dividing the entire life cycle into multiple failure periods based on the change.

[0152] For example, the failure rate of the reference battery product in the second stage is subtracted from the failure rate of the reference battery product in the first stage to obtain the first change. The failure rate of the reference battery product in the third stage is subtracted from the failure rate of the reference battery product in the second stage to obtain the second change. This process continues until the failure rate of the reference battery product in the last stage is subtracted from the failure rate of the reference battery product in the penultimate stage to obtain the last change. Based on the first change to the last change, the entire life cycle is divided into multiple failure periods.

[0153] In some embodiments, the critical phase (also called the critical point) between each two adjacent failure periods can be determined based on the amount of change, and the entire life cycle can be divided into multiple failure periods based on the critical phase between each two adjacent failure periods.

[0154] In the technical solution of this application embodiment, the change in the failure rate of the reference battery product can reflect the change pattern of the failure rate of the battery product throughout its entire life cycle, thereby accurately dividing the entire life cycle into multiple failure periods and improving the accuracy of the division of multiple failure periods.

[0155] In some embodiments, the multiple failure periods include an early failure period, an accidental failure period, and a wear-out failure period; the entire lifecycle is divided into multiple failure periods according to the amount of change, including: determining the first stage of two adjacent stages corresponding to the first change amount that is less than or equal to a preset threshold as the end stage of the early failure period; the preset threshold is greater than 0; determining the second stage of two adjacent stages corresponding to the first change amount that is less than or equal to a target threshold as the start stage of the wear-out failure period; the target threshold is less than 0; the entire lifecycle is divided into an early failure period, an accidental failure period, and a wear-out failure period according to the end stage and the start stage.

[0156] In some embodiments, the failure rate prediction result of the battery product over the entire life cycle represents the variation law of the failure rate of the battery product with the operating time over the entire life cycle, and the curve corresponding to this variation law can be a bathtub curve. The bathtub curve is high at both ends and low in the middle, resembling the shape of a bathtub.

[0157] In the technical solution of this application embodiment, the failure rate of the reference battery product has different variation patterns in the early failure period, the accidental failure period, and the wear failure period. By dividing the entire life cycle into the early failure period, the accidental failure period, and the wear failure period, and analyzing the failure rate of the reference battery product in the early failure period, the accidental failure period, and the wear failure period respectively, the accuracy of the failure rate prediction result under the determined entire life cycle can be improved.

[0158] In some embodiments, determining the failure rate prediction result of the battery product over its entire life cycle based on the matching result of the target risk function and historical failure data includes: determining the mapping relationship between the operating time and failure rate of the battery product over its entire life cycle based on the matching result of the target risk function and historical failure data; and determining the mapping relationship as the failure rate prediction result of the battery product over its entire life cycle.

[0159] In some embodiments, the matching result is a mapping relationship between the runtime and failure rate of a battery product throughout its entire life cycle. In this case, the mapping relationship between the runtime and failure rate of a battery product throughout its entire life cycle is determined as the failure rate prediction result of the battery product throughout its entire life cycle.

[0160] In other embodiments, the matching result is the correspondence between the battery product's operating time over its entire life cycle and other parameters besides the failure rate (such as the number of failures or the failure rate). The mapping relationship can then be determined based on the correspondence, and this mapping relationship can be used as the prediction result of the battery product's failure rate over its entire life cycle.

[0161] In the technical solution of this application embodiment, the mapping relationship between the running time and failure rate of the battery product throughout its entire life cycle is determined based on the matching result of the target risk function and historical failure data. This relationship reflects the change law of the failure rate of the battery product with the running time throughout its entire life cycle. Therefore, the failure rate of the battery product at any time can be accurately determined based on this change law, thereby improving the reliability of determining the failure rate of the battery product.

[0162] In some embodiments, the battery feature field is obtained by triggering a target option under at least one selection item in the battery product failure rate prediction system interface; different selection items represent different features of the battery product.

[0163] For example, the interface of the battery product failure rate prediction system can display multiple options, such as: design information, project information, incoming material information, production information, warehousing information, logistics information, product type information, responsibility information, fault information, manufacturer information, faulty component information, chemical system information, shipped product information, corresponding platform information, shipped product type information, product line information, assembly component number information, customer complaint number type information, product structure information, etc. Each selection item has multiple options, and the user can trigger the target option under at least one selection item. Accordingly, the computer device obtains the corresponding battery characteristic fields.

[0164] For example, if the lithium iron phosphate battery option under the user's chemical system information is triggered, then the battery feature field is lithium iron phosphate battery, and the failure rate prediction result of the battery product over the entire life cycle is the failure rate prediction result of lithium iron phosphate battery over the entire life cycle.

[0165] For example, if a user triggers the target manufacturer option under the manufacturer information, then the battery feature field will be the target manufacturer, and the failure rate prediction result of the battery product over its entire life cycle will be the failure rate prediction result of the battery product manufactured by the target manufacturer over its entire life cycle.

[0166] For example, if a user triggers the lithium iron phosphate battery option under the chemical system information and the target manufacturer option under the manufacturer information, then the battery feature fields are lithium iron phosphate battery and target manufacturer. The failure rate prediction result of the battery product over the whole life cycle is the failure rate prediction result of the lithium iron phosphate battery produced by the target manufacturer over the whole life cycle.

[0167] This application does not limit the user to triggering the target options under any of the above-mentioned selection items. For example, there are other examples: For instance, the user can trigger the module option in the product type information selection item, and the computer device obtains the corresponding battery characteristic fields including module (i.e., battery module). For another example, the user can trigger all options in the manufacturer information selection item, and the computer device obtains the corresponding battery characteristic fields including all manufacturers. For yet another example, the user can trigger the target manufacturer and specified manufacturer options in the manufacturer information selection item, and the computer device obtains the corresponding battery characteristic fields including the target manufacturer and specified manufacturer. For yet another example, the user can trigger the target manufacturer option in the manufacturer information selection item and the module option in the product type information selection item, and the computer device obtains the corresponding battery characteristic fields including the target manufacturer and module. Therefore, as long as the failure rate prediction result of the battery product under the target option is generated over its entire life cycle through triggering operations on at least one of the target options under the above-listed selection items, it should be within the protection scope of this application.

[0168] In the technical solution of this application embodiment, the user can trigger the options under the corresponding selection item according to the needs, and the computer device determines the corresponding failure rate prediction result according to the user's selected option, so that the failure rate prediction result meets the user's needs and improves the prediction flexibility of the failure rate prediction result.

[0169] In some embodiments, the battery feature field includes the target manufacturer to which the battery product belongs; the method further includes: obtaining the warning failure rate corresponding to the target manufacturer / target user; displaying the failure rate prediction results of the battery product throughout its entire life cycle and the warning line corresponding to the warning failure rate in the target coordinate system interface of the battery product failure rate prediction system.

[0170] In some embodiments, the risk level corresponding to the target manufacturer / target user can be obtained, and the early warning failure rate can be determined based on the risk level.

[0171] In the technical solution of this application embodiment, historical failure data of reference battery products produced and put into operation by the target manufacturer or used by the target user are analyzed to determine the failure rate prediction result of the battery products of the target manufacturer / target user, and the failure rate prediction result and warning line are displayed in the target coordinate system. This helps to conduct quality analysis of the battery products of the target manufacturer / target user and improves the effectiveness of battery product management.

[0172] In some embodiments, the method further includes: responding to a failure number prediction instruction for the battery product within a target time period, determining an average failure rate of a reference battery product within the target time period based on the failure rate prediction result; determining the total number of failures of the battery product within the target time period based on the average failure rate and the total number of reference battery products in operation; and displaying the total number of failures in the battery product failure rate prediction system interface.

[0173] In some embodiments, the number of failures of a battery product in each stage of a target time period can be determined based on the average failure rate and the total number of reference battery products in operation, and the number of failures in each stage of the target time period can be displayed in the battery product failure rate prediction system interface.

[0174] In some embodiments, displaying the total number of failures of a battery product within a target time period in the battery product failure rate prediction system interface can guide the management of the battery product. For example, users can manage spare parts for the battery product within a target time period based on the total number of failures.

[0175] In the technical solution of this application embodiment, by displaying the total number of battery product failures within a target time period in the battery product failure rate prediction system interface, users can intuitively see the total number of battery product failures within the target time period, which is beneficial for making failure management decisions for battery products and improves the effectiveness of battery product management.

[0176] In some embodiments, the method for predicting the failure rate of a battery product throughout its entire life cycle can take into account the impact of design, production information, incoming material information, logistics information, warehousing information, and other factors on the battery failure rate.

[0177] In some embodiments, the failure rate of new energy products throughout their entire life cycle can be predicted by statistically analyzing the shipment volume of battery products and the number of failures that occur during operation, thereby effectively calculating the number of faulty parts that need to be repaired or replaced, in order to meet market demand and save on spare parts costs.

[0178] In some embodiments, by analyzing market data (i.e., the aforementioned historical failure data) and embedding failure rate analysis and prediction tools within the system, the system can predict the failure rate for various sub-dimensions of battery products. There are multiple approaches to failure rate analysis, with the optimal solution for predicting failure rates throughout the entire lifecycle utilizing several experimentally designed functions from the field of survival analysis. The reason failure analysis needs to apply knowledge and functions from the field of survival analysis is primarily because survival analysis can effectively handle data describing individual lifespan or the timing of events, which is precisely the data type required for failure analysis. In the new energy industry, the goal of failure analysis is to understand the probability and trends of battery product failures. This involves assessing the lifecycle of battery products to predict failure rates and develop corresponding maintenance and replacement strategies. Survival analysis provides an effective method for analyzing the lifespan data of vehicles or components, as well as various lifespan-related factors, such as at least one factor related to design, production, incoming materials, logistics, warehousing, and failure type.

[0179] In some embodiments, the battery product failure rate prediction method can use existing historical failure data to analyze the overall failure rate of cells, modules, battery systems, and battery packs of new energy battery products, as well as the failure rate of each component or failure type, thereby enabling the prediction of the failure rate of new energy battery products throughout their entire life cycle under various analytical dimensions.

[0180] In some embodiments, a battery product failure rate prediction system interface can be provided. Users can select target options under at least one item, such as design, project, incoming materials, production, and failure type, to obtain corresponding battery characteristic fields. The system then analyzes and predicts the full life-cycle failure rate of the battery products corresponding to these characteristic fields and visualizes the prediction results on the interface. Furthermore, by embedding risk functions as components into the system, a system capable of both screening analysis and risk modeling is achieved. Through the embedded function library containing multiple risk functions, failure rate fitting can be performed based on normal distribution risk functions, log-normal distribution risk functions, exponential distribution risk functions, or Weibull distribution risk functions.

[0181] In some embodiments, a visualization system for statistical analysis and prediction of failure rates of battery cells, modules, battery packs, or battery systems is also proposed. The system has the following functions: historical failure data acquisition, failure rate analysis, and system interface presentation. In some embodiments, it may also have a chart export function for exporting chart data of failure rates or failure counts of battery products at various stages. In some embodiments, it may also have an image export function for generating images based on failure rate prediction results and / or generating images based on chart data, and exporting the images.

[0182] In some embodiments, a method for determining the shipping time is also provided. For example, the cell manufacturing completion time is 22 / 12 / 1, the battery module manufacturing completion time is 23 / 1 / 1, and the battery pack manufacturing completion time is 23 / 2 / 1. For example, when the battery product is shipped as a battery pack, the shipping time of the battery product is determined to be 23 / 2 / 1. As another example, when the battery product is shipped as a cell, the shipping time of the battery product is 22 / 12 / 1. Yet another example, when the battery product is shipped as a battery module, the shipping time of the battery product is 23 / 1 / 1.

[0183] In some embodiments, the operating time of a battery product can be determined based on its initial operating time, or the initial operating time can be determined based on the shipping time of the battery product, and then the operating time of the battery product can be determined based on the initial operating time.

[0184] For example, the time it takes for the battery product to ship, plus the time spent in warehousing, logistics, and sales to the original equipment manufacturer (OEM), is the time it takes for the battery product to reach the sales end. Based on the time the battery product reaches the sales end, the initial operating time is determined according to the monthly sales volume of the battery product at the sales end. For example, different sales ratios can be allocated to different sales channels, and the monthly sales volume of the battery product can be determined based on these sales ratios.

[0185] In some embodiments, the number of products with different failure times can be obtained. For example, the failure time can be the time recorded on a customer complaint.

[0186] In some embodiments, the number of failures at each stage of the entire life cycle can be obtained based on at least one of the battery characteristic fields such as product design, process technology, incoming material control, project sales, and failure analysis. The failure rate of each batch is obtained by summing the failure rate of each batch within each stage with the total number of shipments. The failure rates of each batch are then fused to obtain the failure rate of the battery product at each stage. Finally, the failure rate of the battery product at each stage is fitted using an objective risk function, and the fitting result is determined as the failure rate prediction result of the battery product throughout its entire life cycle.

[0187] The following sections explain the risk functions of the normal distribution, log-normal distribution, exponential distribution, and Weibull distribution:

[0188] The probability density function of the normal distribution is The cumulative probability density function of the normal distribution is The normal distribution risk function is For example, t represents the operating time of the battery product, λ(t) represents the failure rate corresponding to the operating time, and μ and σ represent the target coefficients in the function, respectively.

[0189] The log-normal probability density function is The cumulative probability density function of the log-normal distribution is The log-normal distribution risk function is For example, t represents the operating time of the battery product, λ(t) represents the failure rate corresponding to the operating time, and μ and σ both represent the target coefficients in the function.

[0190] The exponential probability density function is f(t) = λexp(-λt); the cumulative probability density function is R(t) = exp(-λt); and the hazard function is λ(t) = λ (t>0). Here, exp() represents an exponential function with base e. For example, t represents the operating time of the battery product, λ(t) represents the failure rate corresponding to the operating time, and λ represents the target coefficient in the function.

[0191] The probability density function of the Weibull distribution is The cumulative probability density function of the Weibull distribution is The risk function of the Weibull distribution is For example, t represents the operating time of the battery product, λ(t) represents the failure rate corresponding to the operating time, and m and η both represent the target coefficients in the function.

[0192] In some embodiments, the failure rate is calculated as follows: PPM stands for Parts Per Million. 故障 N represents the number of faults. 出货 N represents the total number of items shipped. 累计故障 This represents the cumulative number of failures. In some other embodiments, the failure rate is calculated as follows: Here, PPB stands for Parts Per Billion. For example, the failure rate for the second month is calculated as: Number of failures in the second month / (Total shipments in the first and second months - Cumulative number of failures in the first and second months).

[0193] Figure 10 A flowchart illustrating the process of determining the failure rate prediction result of a battery product over its entire life cycle is provided for some embodiments, such as... Figure 10 As shown, this method is applied to a computer device, and the method includes:

[0194] S1001. Obtain the production time of the reference battery product from the database device.

[0195] In some embodiments, the reference battery product may be a battery product in an electric vehicle (EV). In other embodiments, the reference battery product may be a battery product in an energy storage system (ESS).

[0196] S1002. Determine the delivery time based on the production time.

[0197] S1003. Determine the initial running time based on the shipping time.

[0198] In other embodiments, the initial operating time of a reference battery product can be obtained from a database device. In still other embodiments, the shipping time of the reference battery product can be obtained from the database device, and the initial operating time can be determined based on the shipping time.

[0199] S1004. Based on the initial operating time and failure time of the reference battery product, determine the failure rate of multiple batches of battery products at each stage.

[0200] S1005. Weighted fusion of the failure rates of multiple batches of battery products under each stage to obtain the failure rate of battery products under each stage.

[0201] S1006. Multiple risk functions are used to fit the failure rate of battery products at each stage to obtain multiple matching results.

[0202] For example, matching results can be obtained using at least one of the following methods: maximum likelihood method, least squares method, Bayesian estimation method, etc.

[0203] S1007. Determine the accuracy parameters corresponding to multiple matching results, and determine the risk function corresponding to the accuracy parameter with the highest accuracy as the target risk function. The target matching result obtained by fitting the target risk function to the failure rate of the battery product at each stage is determined as the failure rate prediction result.

[0204] S1008. Based on the failure rate prediction results, determine the definite integral results corresponding to the target time period, and determine the average failure rate of the target time period based on the definite integral results.

[0205] In some embodiments, the integration method may include one of the following: the trapezoidal area method, the Rungebay method, the power series expansion method, etc. For example, the integration method may be the trapezoidal area method.

[0206] S1009. Determine the number of battery product failures during the target period based on the average failure rate during the target period.

[0207] S1010. Output at least one of the following on the battery product failure rate prediction system interface: number of failures, failure rate, probability density function (PDF), cumulative distribution function (CDF), and normal distribution function λ.

[0208] The failure rate is presented in PPM or PPB.

[0209] S1011. The battery product failure rate prediction system interface displays the target matching results obtained by fitting the target risk function to the failure rate of the battery product at each stage.

[0210] Figure 11 This is a schematic diagram of the configuration interface of a battery product failure rate prediction system provided in some embodiments, such as... Figure 11 As shown, the battery product failure rate prediction system has the following functions: detailed table query, data analysis, detailed table traceability, and system configuration. In the system configuration, the following items can be configured: early warning configuration, prediction coefficient configuration, conversion table, and automatic system correction, etc.

[0211] In the prediction system configuration, at least one of the coefficients, such as the maximum value, minimum value, and default value, can be configured in the normal distribution risk function, log-normal distribution risk function, exponential distribution risk function, and Weibull distribution risk function.

[0212] Figure 12 This is a schematic diagram of multiple options in the interface of a battery product failure rate prediction system provided in some embodiments, such as... Figure 12 As shown, the battery product failure rate prediction system interface includes several items such as: production time, shipped product, faulty component, chemical system, product type, corresponding platform, material group, product design drawing lookup code, shipped product type, product line, assembly component number (PN), customer complaint number, and product structure. In some other embodiments, the multiple options in the battery product failure rate prediction system interface may be only some of the options listed above.

[0213] In some embodiments, it is used to... Figure 12 The triggering operation of the target option in at least one project displays the failure rate variation pattern corresponding to that option.

[0214] Figure 13 A schematic diagram illustrating the relationship between runtime and battery product failure rate in some embodiments, such as... Figure 13 As shown, in response to a battery product's command to predict the failure rate of the battery module within a specified time period, the computer equipment displays the correspondence between runtime and battery product failure rate in the battery product failure rate prediction system interface. Figure 13 In the diagram, the solid line is obtained by connecting the calculated battery product failure rate (calculated failure rate), and the dashed line is obtained by fitting the calculated battery product failure rate (predicted failure rate) with the objective risk function. Figure 13 In the diagram, the horizontal axis represents the number of months, and the vertical axis represents PPM.

[0215] Figure 14 This is a graphical representation of the number of battery products shipped and the number of defects over multiple production months, provided for some embodiments. Figure 14 The interface may include an export button, which the user can trigger to allow the computer device to export the chart to the target storage location.

[0216] Survival analysis can explore the relationship between component failures and factors such as shipment volume and uptime, thereby predicting the life-cycle failure rate of power components. The main methods of survival analysis include descriptive methods, nonparametric methods, parametric methods, and semiparametric methods. Parametric methods estimate parameters in an assumed distribution model based on sample observations to obtain a probability distribution model of survival time. The survival time distribution includes at least one of the following: normal distribution, exponential distribution, Weibull distribution, log-normal distribution, log-logistic distribution, Gamma distribution, etc. The embodiments of this application employ parametric methods to establish models and distributions, and to calculate failure rates, thereby assisting departments such as marketing, after-sales, design, process, and incoming materials in decision-making.

[0217] Based on the same inventive concept, this application also provides a battery product failure rate prediction system for implementing the battery product failure rate prediction method described above. The solution provided by this system is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more battery product failure rate prediction system embodiments provided below can be found in the limitations of the battery product failure rate prediction method described above, and will not be repeated here.

[0218] In one exemplary embodiment, Figure 15 This is a schematic diagram of the structure of a battery product failure rate prediction system provided in some embodiments, such as... Figure 15 As shown, the battery product failure rate prediction system 1500 includes: a data import module 1501, used to respond to the failure rate prediction command of the battery product and obtain historical failure data of a reference battery product throughout its entire life cycle that matches the battery feature fields carried in the failure rate prediction command; a function selection module 1502, used to determine the target risk function with the highest matching degree with the historical failure data from a pre-built risk function library; and a data prediction module 1503, used to determine the failure rate prediction result of the battery product throughout its entire life cycle based on the target risk function.

[0219] In some embodiments, the system 1500 further includes: a chart export module for determining a fault quantity chart based on the failure rate prediction results; the fault quantity chart includes the number of product faults of the battery product at each stage of the entire life cycle; and a data presentation module for displaying the fault quantity chart in the battery product failure rate prediction system interface.

[0220] In some embodiments, the system 1500 further includes: a data acquisition module 1506, used to acquire historical fault data of a reference battery product and store the historical fault data of the reference battery product in a database; wherein the historical fault data of the reference battery product in the database is used for acquisition by the data import module.

[0221] In some embodiments, the data import module 1501 includes a time acquisition unit, a runtime determination unit, and a fault data determination unit. The time acquisition unit is used to acquire the fault time and the initial running time of the reference battery product. The runtime determination unit is used to determine the runtime of the reference battery product based on the fault time and the initial running time. The fault data determination unit is used to determine the fault data of the reference battery product in each stage of its entire life cycle based on the runtime of the reference battery product.

[0222] In some embodiments, historical fault data includes fault data for each stage in multiple phases; the function selection module 1502 includes a failure rate determination unit and a risk function determination unit. The failure rate determination unit is used to determine the failure rate of the reference battery product at each stage of the entire life cycle based on the fault data of the reference battery product at each stage. The risk function determination unit is used to determine the target risk function with the highest matching degree with the failure rate of the reference battery product at each stage from a pre-built risk function library.

[0223] In some embodiments, the failure rate determination unit includes: a sub-fault quantity determination sub-unit, a sub-failure rate determination sub-unit, and a failure rate fusion sub-unit. The sub-fault quantity determination sub-unit is used to determine the number of multiple sub-faults corresponding to multiple product attributes of the reference battery product at each stage of its entire lifecycle, based on failure data at each stage. The sub-failure rate determination sub-unit is used to determine the number of multiple sub-faults at each stage, based on the number of multiple sub-faults at each stage. The failure rate fusion sub-unit is used to fuse the multiple sub-failure rates at each stage to obtain the failure rate of the reference battery product at each stage.

[0224] In some embodiments, the failure rate fusion subunit includes an operation quantity acquisition subunit, a scaling factor determination subunit, and a failure rate determination subunit. The operation quantity acquisition subunit is used to acquire the total operation quantity of the reference battery product in each stage and the multiple sub-operation quantities corresponding to multiple product attributes in each stage. The scaling factor determination subunit is used to determine multiple scaling factors as the proportion of the sub-operation quantity to the total operation quantity in each stage. The failure rate determination subunit is used to fuse the multiple sub-failure rates in each stage according to the multiple scaling factors in each stage to obtain the failure rate of the reference battery product in each stage.

[0225] In some embodiments, the failure rate fusion subunit includes a replacement number acquisition subunit, a quality coefficient determination subunit, and a failure rate determination subunit. The replacement number acquisition subunit is used to acquire the replacement number experienced by a reference battery product with multiple product attributes at each stage. The quality coefficient determination subunit is used to assign multiple quality coefficients to multiple product attributes according to the replacement number experienced by the reference battery product with multiple product attributes. The failure rate determination subunit is used to fuse multiple sub-failure rates at each stage according to the multiple quality coefficients at each stage to obtain the failure rate of the reference battery product at each stage.

[0226] In some embodiments, the failure rate determination unit includes an electronic component failure rate determination subunit and a product failure rate determination subunit; the electronic component failure rate determination subunit is used to determine the failure rate of electronic components in the reference battery product at each stage based on failure data of the reference battery product at each stage of its entire life cycle; the product failure rate determination subunit is used to determine the failure rate of the reference battery product at each stage based on the failure rate of electronic components in the reference battery product at each stage.

[0227] In some embodiments, the product failure rate determination subunit includes a circuit connection method acquisition subunit and a product failure rate acquisition subunit. The circuit connection method acquisition subunit is used to acquire the circuit connection method of the electronic components in the reference battery product. The product failure rate acquisition subunit is used to determine the failure rate of the reference battery product at each stage based on the circuit connection method and the failure rate of the electronic components in the reference battery product at each stage.

[0228] In some embodiments, the product failure rate acquisition unit includes a branch number acquisition subunit, a branch fault number determination subunit, and a product failure rate acquisition subunit. The branch number acquisition subunit is used to acquire the redundancy of the parallel circuit and the number of branches in the parallel circuit in the hybrid circuit composed of electronic components in the reference battery product when the circuit connection method is a hybrid connection method. The branch fault number determination subunit is used to determine the number of branch faults in the parallel circuit when a fault occurs in the parallel circuit based on the redundancy number. The product failure rate acquisition subunit is used to determine the failure rate of the reference battery product at each stage based on the number of branches, the number of branch faults, and the failure rate of the electronic components in the reference battery product at each stage.

[0229] In some embodiments, the risk function determination unit includes a partitioning subunit and a risk function determination subunit, wherein the partitioning subunit is used to divide the entire life cycle into multiple failure periods; the risk function determination subunit is used to determine each sub-target risk function that has the highest matching degree with the failure rate of the reference battery product in each failure period; each sub-target risk function is included in the target risk function.

[0230] In some embodiments, the risk function determination subunit includes a fitting subunit, an accuracy parameter determination subunit, and a risk function acquisition subunit; wherein, the fitting subunit is used to fit the failure rate of the reference battery product in each failure period using multiple risk functions in the risk function library to obtain multiple matching results in each failure period; the accuracy parameter determination subunit is used to determine multiple accuracy parameters corresponding to the multiple matching results; the risk function acquisition subunit is used to determine the risk function corresponding to the accuracy parameter with the highest accuracy among the multiple accuracy parameters in each failure period as the sub-target risk function corresponding to each failure period.

[0231] In some embodiments, the division subunit includes a change determination subunit and a failure period division subunit; wherein, the change determination subunit is used to sequentially determine the change in failure rate of the reference battery product under each two adjacent stages; the failure period division subunit is used to divide the entire life cycle into multiple failure periods according to the change.

[0232] In some embodiments, the multiple failure periods include an early failure period, an accidental failure period, and a wear-out failure period. Based on the amount of change, the failure period division subunit includes an endpoint determination subunit, an initiation stage determination subunit, and a failure period determination subunit. The endpoint determination subunit is used to determine the first of two adjacent stages corresponding to the first change amount less than or equal to a preset threshold as the endpoint of the early failure period; the preset threshold is greater than 0. The initiation stage determination subunit is used to determine the second of two adjacent stages corresponding to the first change amount less than or equal to a target threshold as the initiation stage of the wear-out failure period; the target threshold is less than 0. The failure period determination subunit is used to divide the entire lifecycle into an early failure period, an accidental failure period, and a wear-out failure period based on the endpoint stage and the initiation stage.

[0233] In some embodiments, the data prediction module 1503 includes a mapping relationship determination unit and a prediction result determination unit; wherein, the mapping relationship determination unit is used to determine the mapping relationship between the running time and failure rate of the battery product throughout its entire life cycle based on the matching result of the target risk function and historical fault data; the prediction result determination unit is used to determine the mapping relationship as the failure rate prediction result of the battery product throughout its entire life cycle.

[0234] In some embodiments, the battery feature field is obtained by triggering a target option under at least one selection item in the battery product failure rate prediction system interface; different selection items represent different features of the battery product.

[0235] In some embodiments, the battery feature field includes the target manufacturer / target user to which the battery product belongs; the system 1500 also includes: a warning failure rate acquisition module and a data presentation module, the warning failure rate acquisition module is used to acquire the warning failure rate corresponding to the target manufacturer / target user; the data presentation module is used to display the failure rate prediction results of the battery product throughout its entire life cycle and the warning line corresponding to the warning failure rate in the target coordinate system interface of the battery product failure rate prediction system.

[0236] In some embodiments, the system 1500 further includes: an average failure rate determination module, a fault quantity determination module, and a data presentation module. The average failure rate determination module is used to determine the average failure rate of a reference battery product within the target time period in response to a fault quantity prediction instruction for the battery product within a target time period, based on the failure rate prediction result. The fault quantity determination module is used to determine the total number of faults of the battery product within the target time period based on the average failure rate and the total number of reference battery products in operation. The data presentation module is used to display the total number of faults in the battery product failure rate prediction system interface.

[0237] The description of the system embodiments above is similar to that of the method embodiments above, and has similar beneficial effects. For technical details not disclosed in the system embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0238] The various modules in the aforementioned battery product failure rate prediction system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0239] In one exemplary embodiment, Figure 16 This is a schematic diagram of the structure of a computer device provided for some embodiments. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be implemented through Wireless Fidelity (WIFI), mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for predicting the failure rate of a battery product. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0240] Those skilled in the art will understand that Figure 16 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0241] For example, a computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method of any of the above embodiments.

[0242] For example, in an exemplary embodiment, when the processor executes a computer program, it performs the following: in response to a failure rate prediction instruction for a battery product, it obtains historical failure data of a reference battery product throughout its entire life cycle that matches the battery feature fields carried in the failure rate prediction instruction; it determines a target risk function with the highest matching degree to the historical failure data from a pre-built risk function library; and it determines the failure rate prediction result of the battery product throughout its entire life cycle based on the matching result of the target risk function and the historical failure data.

[0243] In one embodiment, a computer-readable storage medium is provided, wherein a computer program, when executed by a processor, implements the steps of the method provided in any of the above embodiments.

[0244] For example, in one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps: in response to a failure rate prediction instruction for a battery product, obtaining historical failure data of a reference battery product throughout its entire lifecycle that matches the battery feature fields carried in the failure rate prediction instruction; determining a target risk function with the highest matching degree to the historical failure data from a pre-built risk function library; and determining the failure rate prediction result of the battery product throughout its entire lifecycle based on the matching result between the target risk function and the historical failure data.

[0245] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method provided in any of the above embodiments.

[0246] For example, in one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: in response to a failure rate prediction instruction for a battery product, obtaining historical failure data of a reference battery product throughout its entire lifecycle that matches the battery feature fields carried in the failure rate prediction instruction; determining a target risk function with the highest matching degree to the historical failure data from a pre-built risk function library; and determining a failure rate prediction result of the battery product throughout its entire lifecycle based on the matching result between the target risk function and the historical failure data.

[0247] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. 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 methods described above.

[0248] The processor, functional modules, or functional units in any embodiment of this application may include an integration of one or more of the following: a general-purpose processor, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a central processing unit (CPU), a graphics processing unit (GPU), an embedded neural network processing unit (NPU), a controller, a microcontroller, a microprocessor, a programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, a quantum computing-based data processing logic device, an artificial intelligence (AI) processor, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0249] The memory or computer-readable storage medium in any embodiment of this application may include at least one of non-volatile memory and volatile memory. Non-volatile memory includes integration of one or more of the following: Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Magnetic Surface Memory, Optical Disc, Compact Disc Read-Only Memory (CD-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, Volatile Memory, etc. Volatile memory includes one or more of the following: Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0250] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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 application.

[0251] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A battery product failure rate prediction method characterized by, The method includes: In response to a failure rate prediction instruction for a battery product, historical failure data of a reference battery product throughout its entire lifecycle is obtained based on the battery characteristic fields carried in the failure rate prediction instruction. The target risk function with the highest matching degree to the historical fault data is determined from the pre-built risk function library; Based on the matching results between the target risk function and the historical failure data, the failure rate prediction result of the battery product under the entire life cycle is determined.

2. The method of claim 1, wherein, The step of obtaining historical fault data throughout the entire lifecycle of a reference battery product that matches the battery feature fields includes: Obtain the failure time and initial operating time of the reference battery product; The operating time of the reference battery product is determined based on the fault time and the initial operating time. Based on the runtime of the reference battery product, fault data for each stage of the reference battery product in the multiple stages of the entire life cycle are determined.

3. The method according to claim 1 or 2, characterized in that, The historical fault data includes fault data from each of the multiple phases. The step of determining the target risk function with the highest matching degree to the historical fault data from the pre-built risk function library includes: Based on the failure data of the reference battery product at each stage of the entire life cycle, determine the failure rate of the reference battery product at each stage of the entire life cycle; From a pre-built library of risk functions, determine the target risk function that best matches the failure rate of the reference battery product at each stage.

4. The method of claim 3, wherein, The step of determining the failure rate of the reference battery product at each stage of its entire life cycle based on failure data from the reference battery product at each stage includes: Based on the fault data of the reference battery product at each stage of its entire life cycle, determine the number of multiple sub-faults corresponding to multiple product attributes of the reference battery product at each stage. The multiple sub-failure rates for each stage are determined based on the number of multiple sub-failures in each stage. The failure rates of the reference battery product at each stage are fused together to obtain the failure rate of the reference battery product at each stage.

5. The method of claim 4, wherein, The step of fusing the multiple sub-failure rates at each stage to obtain the failure rate of the reference battery product at each stage includes: Obtain the total number of reference battery products in each stage and the number of sub-operations corresponding to multiple product attributes in each stage; In each of the aforementioned stages, the proportion of each of the multiple sub-run quantities to the total number of runs is determined as multiple proportional coefficients; The failure rates of the reference battery product in each stage are obtained by fusing the multiple sub-failure rates in each stage according to the multiple proportional coefficients in each stage.

6. The method according to claim 4, characterized in that, The step of fusing the multiple sub-failure rates at each stage to obtain the failure rate of the reference battery product at each stage includes: Obtain the number of generations of reference battery products that have undergone the multiple product attributes under each of the aforementioned stages; Based on the number of generations a reference battery product has undergone for the multiple product attributes, multiple quality coefficients are assigned to each of the multiple product attributes. The failure rates of the reference battery product in each stage are obtained by fusing the multiple sub-failure rates in each stage based on the multiple quality coefficients in each stage.

7. The method according to claim 3, characterized in that, The step of determining the failure rate of the reference battery product at each stage of its entire life cycle based on failure data from the reference battery product at each stage includes: Based on the failure data of the reference battery product at each stage of its entire life cycle, determine the failure rate of the electronic components in the reference battery product at each stage; The failure rate of the reference battery product in each stage is determined based on the failure rate of the electronic components in the reference battery product in each stage.

8. The method according to claim 7, characterized in that, The step of determining the failure rate of the reference battery product at each stage based on the failure rate of the electronic components in the reference battery product at each stage includes: Obtain the circuit connection method of the electronic components in the reference battery product; The failure rate of the reference battery product in each stage is determined based on the circuit connection method and the failure rate of the electronic components in the reference battery product in each stage.

9. The method according to claim 8, characterized in that, The step of determining the failure rate of the reference battery product at each stage based on the circuit connection method and the failure rate of the electronic components in the reference battery product at each stage includes: When the circuit connection method is a hybrid connection method, obtain the number of redundant parallel loops and the number of branches of the parallel loops in the hybrid circuit composed of electronic components in the reference battery product. Based on the redundancy quantity, determine the number of branch faults in the parallel circuit in the event of a fault in the parallel circuit. The failure rate of the reference battery product in each stage is determined based on the number of branches, the number of branch failures, and the failure rate of electronic components in the reference battery product in each stage.

10. The method according to claim 3, characterized in that, The step of determining the target risk function that best matches the failure rate of the reference battery product at each stage from a pre-built risk function library includes: The entire lifecycle is divided into multiple failure periods; Determine the sub-target risk functions that have the highest matching degree with the failure rate of the reference battery product during each of the aforementioned failure periods; each of the sub-target risk functions is included in the target risk function.

11. The method according to claim 10, characterized in that, The determination of each sub-objective risk function that best matches the failure rate of the reference battery product within each of the aforementioned failure periods includes: Multiple risk functions from the risk function library are used to fit the failure rate of the reference battery product within each failure period to obtain multiple matching results within each failure period. Determine the multiple accuracy parameters corresponding to the multiple matching results; The risk function corresponding to the highest accuracy parameter among the multiple accuracy parameters within each failure period is determined as the risk function for each sub-objective corresponding to each failure period.

12. The method according to claim 10, characterized in that, The division of the entire lifecycle into multiple failure periods includes: The change in failure rate of the reference battery product under each two adjacent stages is determined sequentially. Based on the amount of change, the entire life cycle is divided into the multiple failure periods.

13. The method according to claim 12, characterized in that, The multiple failure periods include an early failure period, an accidental failure period, and a wear-out failure period; the division of the entire life cycle into the multiple failure periods based on the amount of change includes: The first stage of two adjacent stages corresponding to the first change amount that is less than or equal to a preset threshold is determined as the end stage of the early failure period; the preset threshold is greater than 0. The second stage of two adjacent stages corresponding to the first change amount that is less than or equal to the target threshold is determined as the starting stage of the loss failure period; the target threshold is less than 0. Based on the endpoint stage and the starting stage, the entire life cycle is divided into the early failure period, the accidental failure period, and the wear and tear failure period.

14. The method according to claim 1 or 2, characterized in that, The step of determining the predicted failure rate of the battery product over its entire life cycle based on the matching result between the target risk function and the historical failure data includes: Based on the matching results between the target risk function and the historical failure data, the mapping relationship between the operating time and failure rate of the battery product throughout its entire life cycle is determined. The mapping relationship is determined as the failure rate prediction result of the battery product throughout its entire life cycle.

15. The method according to claim 1 or 2, characterized in that, The battery feature fields are obtained by triggering the target option under at least one selection item in the battery product failure rate prediction system interface; different selection items represent different features of the battery product.

16. The method according to claim 1 or 2, characterized in that, The battery characteristic field includes the target manufacturer / target user of the battery product; the method further includes: Obtain the early warning failure rate corresponding to the target manufacturer / target user; In the target coordinate system of the battery product failure rate prediction system interface, the failure rate prediction results of the battery product under the entire life cycle are displayed, as well as the warning line corresponding to the warning failure rate are displayed.

17. The method according to claim 1 or 2, characterized in that, The method further includes: In response to a failure number prediction command for a battery product within a target time period, the average failure rate of the reference battery product within the target time period is determined based on the failure rate prediction results. The total number of failures of the battery products during the target period is determined based on the average failure rate and the total number of reference battery products in operation. The total number of failures is displayed in the battery product failure rate prediction system interface.

18. A battery product failure rate prediction system, characterized in that, The system includes: The data import module is used to respond to the failure rate prediction instruction of the battery product and, based on the battery characteristic field carried in the failure rate prediction instruction, obtain historical failure data of the reference battery product throughout its entire life cycle that matches the battery characteristic field. The function selection module is used to determine the target risk function that best matches the historical fault data from a pre-built risk function library; The data prediction module is used to determine the failure rate prediction result of the battery product under the entire life cycle based on the target risk function.

19. The system according to claim 18, characterized in that, The system also includes: The chart export module is used to determine a fault quantity chart based on the failure rate prediction results; the fault quantity chart includes the number of product faults of battery products at each stage of the entire life cycle. The data presentation module is also used to display the fault quantity chart in the battery product failure rate prediction system interface.

20. The system according to claim 18 or 19, characterized in that, The system also includes: The data acquisition module is used to collect historical fault data of the reference battery product and store the historical fault data of the reference battery product in a database; wherein, the historical fault data of the reference battery product in the database is used by the data import module to obtain the data.

21. 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, it implements the steps of the method according to any one of claims 1 to 17.

22. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 17.

23. A program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 17.

Images