Method for determining lifetime optimization information, computer device and vehicle

Abstract

The application discloses a kind of life optimization information determination method, computer equipment and vehicle, belong to performance evaluation technical field.It includes: the historical operation data of the i-th target component in M target components is analyzed, the motor operating characteristics, environmental operating characteristics and driving behavior operating characteristics of the i-th target component are determined;Based on the motor operating characteristics, environmental operating characteristics and driving behavior operating characteristics of M target components, the comprehensive evaluation parameters of M target components are determined, and the comprehensive evaluation parameters are used to describe the overall health status and overall service life of M target components;Based on the comprehensive evaluation parameters, the life optimization information for the target component is determined.According to the above multi-dimensional characteristics, the accurate determination of the comprehensive evaluation parameters of the target component can be realized, so that more effective life optimization suggestions can be determined based on the accurate comprehensive evaluation parameters, and the accuracy and effectiveness of the life optimization suggestion determination can be improved.

Description

Technical Field

[0001] This application relates to the field of performance evaluation technology, and in particular to a method for determining lifespan optimization information, a computer device, and a vehicle. Background Technology

[0002] The normal operation of a vehicle depends on the proper functioning of its various components. If any component malfunctions, it will negatively impact the user's driving or passenger experience. Therefore, targeted lifespan optimization is necessary during the manufacturing phase of each component to ensure the lowest possible failure rate for sold parts. Thus, providing optimization suggestions for the lifespan of specific components within a vehicle is crucial. Summary of the Invention

[0003] This application provides a method, computer device, and vehicle for determining lifespan optimization information. It can determine multi-dimensional operational characteristics of each target component. Based on these multi-dimensional characteristics, accurate comprehensive evaluation parameters for the target component can be determined. Therefore, based on accurate comprehensive evaluation parameters, more effective lifespan optimization recommendations can be derived, improving the accuracy and effectiveness of lifespan optimization recommendations. The technical solution includes the following:

[0004] Firstly, a method for determining lifetime optimization information is provided, the method comprising: Analyze the historical operating data of the i-th target component among M target components to determine the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component; Based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the M target components, comprehensive evaluation parameters for the M target components are determined. These comprehensive evaluation parameters are used to describe the overall health status and overall service life of the M target components. Based on the comprehensive evaluation parameters, lifespan optimization information for the target component is determined.

[0005] In this application, historical operational data for each of the M target components is generated by collecting data during their operation. Then, for any given target component, multi-dimensional characteristics are first determined based on its historical operational data, including motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics. Next, comprehensive evaluation parameters for the M target components are determined based on these characteristics, which assess the overall health status and overall service life of the M target components. Finally, targeted lifespan optimization information is analyzed based on these comprehensive evaluation parameters. Thus, by determining the multi-dimensional operational characteristics of each target component, accurate determination of comprehensive evaluation parameters for all target components can be achieved. Based on these accurate comprehensive evaluation parameters, more effective lifespan optimization recommendations can be derived, improving the accuracy and effectiveness of lifespan optimization recommendations.

[0006] Optionally, the historical operating data includes the timestamps of each operation of the i-th target component within the first time period, the operating current of the motor in the i-th target component, fault triggering information, false triggering information of the target function, the temperature, rainfall, and location information of the environment where the i-th target component is located during each operation, and the speed and acceleration of the vehicle during each operation, wherein the vehicle is the vehicle containing the i-th target component; the analysis of the historical operating data of the i-th target component among the M target components to determine the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component includes: The motor operating characteristics are obtained by statistically analyzing the timestamps of each operation, the current of each operation, the fault triggering information, and the false triggering information of the target function. Based on the timestamps of each operation and the temperature, rainfall, and location information of the environment in which the i-th target component is located during each operation, the environmental operation characteristics are determined. The driving behavior characteristics are determined based on the timestamps of each run, the vehicle's speed and acceleration during each run.

[0007] In the above method, by analyzing the historical operating data of the i-th target component among the M target components produced by the target supplier in various dimensions, the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component are determined. This allows the operating characteristics of the target component to be characterized through multiple dimensions, thereby achieving an accurate characterization of the operating characteristics of the target component by combining influencing factors such as environment and driving habits.

[0008] Optionally, the comprehensive evaluation parameters include the average health score and the average time between failures (MTBF). The determination of the comprehensive evaluation parameters for the M target components based on their motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics includes: Based on the motor operating characteristics of the i-th target component, the motor wear index of the i-th target component is determined, and the motor wear index is used to represent the degree of wear of the motor of the i-th target component; Based on the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component, predict the individual health score and individual fault-free time of the i-th target component; Calculate the average health score of the individual M target components to obtain the average health score of the M target components, and calculate the average time between failures (MTBF) of the individual M target components to obtain the average time between failures (MTBF) of the M target components.

[0009] In the above methods, since motor wear best reflects the performance degradation of target components, the motor wear index of each target component is determined first based on its multi-dimensional characteristics. This allows for the understanding of the performance degradation of each component, and subsequently, combining the motor wear index with the assessment of the target component's quality status can yield a more accurate evaluation. Furthermore, by first evaluating the quality status of an individual target component based on its multi-dimensional characteristics, and then calculating the average value to comprehensively evaluate the quality status of M target components, a more accurate comprehensive evaluation parameter can be obtained.

[0010] Optionally, predicting the individual health score and individual fault-free time of the i-th target component based on its motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index includes: Based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component, the failure risk probability of the i-th target component is predicted. The failure risk probability is used to represent the possibility that the i-th target component will fail in the second time period after the current moment. Based on the motor operating characteristics of the i-th target component, the failure risk probability, and the motor wear index, the individual health score is determined; The motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component are input into the life assessment model, and the individual fault-free time of the i-th target component is output through the life assessment model. Furthermore, the comprehensive evaluation parameters also include the average failure probability, and the method further includes: The average failure probability is obtained by calculating the average failure risk probability of the M target components.

[0011] In the above method, by predicting the failure risk probability of the i-th target component, the passive response after the failure occurs is transformed into active prevention before the failure occurs. Then, in the process of calculating the individual health score, the failure risk probability is integrated so that the current health status of the target component can reflect the future failure risk. For example, for target components with the same degree of wear, the target component with a lower failure risk probability is in a healthier state. In this way, by combining the motor operating characteristics, failure risk probability and motor wear index, a more accurate individual health score can be determined. Furthermore, by combining the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics and motor wear index, a more accurate individual fault-free time can be obtained.

[0012] Optionally, predicting the failure risk probability of the i-th target component based on its motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics includes: The motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component are input into the fault risk prediction model, and the fault risk prediction model outputs the fault risk probability of the i-th target component. Furthermore, the comprehensive evaluation parameters also include the target early warning frequency, and the method further includes: If the failure risk probability of the i-th target component is greater than a preset probability threshold, the failure risk prediction model outputs at least one target feature, wherein the at least one target feature is an operational feature that causes the failure risk probability to be greater than the preset probability threshold. Based on the at least one target feature, a target warning label is generated; The target warning frequency is obtained by counting the number of times the target warning label is generated.

[0013] In the above method, when the probability of failure risk is high, the failure risk prediction model outputs at least one target feature and generates a corresponding warning label accordingly. This allows the model to output why the failure will occur when it is predicted that the i-th target component is likely to fail in the future. This provides a valid basis for failure repair in specific applications.

[0014] Optionally, the comprehensive evaluation parameters also include the average health score and mean time between failures (MTBF) for different user groups, with different target components associated with different user groups. The method further includes: For any user group, calculate the average health score of the individual target components associated with the user group to obtain the average health score corresponding to the user group, and calculate the average time between failures (MTBF) of the individual target components associated with the user group to obtain the average time between failures (MTBF) corresponding to the user group.

[0015] In the above method, by also calculating the average health score and mean time between failures for different user groups under the target supplier, the quality status of the target components used by different user groups can be evaluated. This allows for targeted quality assessment of the target components from multiple dimensions, which in turn enables targeted optimization suggestions for the target components used by specific user groups.

[0016] Optionally, determining the lifespan optimization information for the target component based on the comprehensive evaluation parameters includes: Obtain the target rule base, which includes suggestion information under different health states; Based on the comprehensive evaluation parameters, the lifetime optimization information is determined from the target rule base.

[0017] In the above method, by pre-setting a target rule base, when it is necessary to determine lifespan optimization information, suggested information that matches the current health status can be directly matched from the target rule base, thus improving the efficiency of determining lifespan optimization information. Furthermore, the target rule base is set based on technical experience, and the suggested information described therein is targeted and can effectively improve the lifespan of the target component, thereby allowing for the matching of effective lifespan optimization information through the target rule base.

[0018] Optionally, the target rule base includes multiple lifetime recommendation rules, each of which includes triggering conditions and recommendation information. The step of determining the lifetime optimization information from the target rule base based on the comprehensive evaluation parameters includes: From the multiple lifetime recommendation rules, match the target recommendation rule whose triggering condition matches the comprehensive evaluation parameter; The recommendation information in the target recommendation rule is determined as the lifetime optimization information.

[0019] Secondly, a device for determining lifetime optimization information is provided, the device comprising: The data processing module is used to analyze the historical operating data of the i-th target component among M target components to determine the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component. The life assessment module is used to determine the comprehensive assessment parameters of the M target components based on their motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics. The comprehensive assessment parameters are used to describe the overall health status and overall service life of the M target components. The optimization suggestion module is used to determine lifespan optimization information for the target component based on the comprehensive evaluation parameters.

[0020] Optionally, the historical operation data includes the timestamps of each operation of the i-th target component within the first time period, the operating current of the motor in the i-th target component, fault triggering information, false triggering information of the target function, the temperature, rainfall, and location information of the environment where the i-th target component is located during each operation, and the speed and acceleration of the vehicle during each operation, wherein the vehicle is the vehicle containing the i-th target component; the data processing module is used for: The motor operating characteristics are obtained by statistically analyzing the timestamps of each operation, the current of each operation, the fault triggering information, and the false triggering information of the target function. Based on the timestamps of each operation and the temperature, rainfall, and location information of the environment in which the i-th target component is located during each operation, the environmental operation characteristics are determined. The driving behavior characteristics are determined based on the timestamps of each run, the vehicle's speed and acceleration during each run.

[0021] Optionally, the comprehensive evaluation parameters include the average health score and the average mean time between failures (MTBF), and the life assessment module is used for: Based on the motor operating characteristics of the i-th target component, the motor wear index of the i-th target component is determined, and the motor wear index is used to represent the degree of wear of the motor of the i-th target component; Based on the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component, predict the individual health score and individual fault-free time of the i-th target component; Calculate the average health score of the individual M target components to obtain the average health score of the M target components, and calculate the average time between failures (MTBF) of the individual M target components to obtain the average time between failures (MTBF) of the M target components.

[0022] Optionally, the life assessment module is specifically used for: Based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component, the failure risk probability of the i-th target component is predicted. The failure risk probability is used to represent the possibility that the i-th target component will fail in the second time period after the current moment. Based on the motor operating characteristics of the i-th target component, the failure risk probability, and the motor wear index, the individual health score is determined; The motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component are input into the life assessment model, and the individual fault-free time of the i-th target component is output through the life assessment model. Furthermore, the comprehensive evaluation parameters also include the average failure probability, and the life assessment module is further used for: The average failure probability is obtained by calculating the average failure risk probability of the M target components.

[0023] Optionally, the life assessment module is specifically used for: The motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component are input into the fault risk prediction model, and the fault risk prediction model outputs the fault risk probability of the i-th target component. Furthermore, the comprehensive evaluation parameters also include the target early warning frequency, and the lifespan assessment module is further used for: If the failure risk probability of the i-th target component is greater than a preset probability threshold, the failure risk prediction model outputs at least one target feature, wherein the at least one target feature is an operational feature that causes the failure risk probability to be greater than the preset probability threshold. Based on the at least one target feature, a target warning label is generated; The target warning frequency is obtained by counting the number of times the target warning label is generated.

[0024] Optionally, the comprehensive evaluation parameters also include the average health score and mean time between failures (MTBF) for different user groups, with different target components associated with different user groups. The lifespan assessment module is further used for: For any user group, calculate the average health score of the individual target components associated with the user group to obtain the average health score corresponding to the user group, and calculate the average time between failures (MTBF) of the individual target components associated with the user group to obtain the average time between failures (MTBF) corresponding to the user group.

[0025] Optionally, the optimization suggestion module is specifically used for: Obtain the target rule base, which includes suggestion information under different health states; Based on the comprehensive evaluation parameters, the lifetime optimization information is determined from the target rule base.

[0026] Optionally, the target rule base includes multiple lifespan suggestion rules, each of which includes triggering conditions and suggestion information. The optimization suggestion module is specifically used for: From the multiple lifetime recommendation rules, match the target recommendation rule whose triggering condition matches the comprehensive evaluation parameter; The recommendation information in the target recommendation rule is determined as the lifetime optimization information.

[0027] Thirdly, a computer device is provided, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the above-described method for determining lifetime optimization information.

[0028] Fourthly, a vehicle is provided, the vehicle including a target component equipped with a target optimization method, the target optimization method being determined based on the lifetime optimization information in the above-described method for determining lifetime optimization information.

[0029] Fifthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for determining lifetime optimization information.

[0030] In a sixth aspect, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the steps of the above-described method for determining lifetime optimization information.

[0031] It is understood that the beneficial effects of the second, third, fourth, fifth, and sixth aspects mentioned above can be found in the relevant descriptions in the first aspect above, and will not be repeated here. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram of the implementation environment of a method for determining lifetime optimization information provided in an embodiment of this application; Figure 2 This is a flowchart of a method for determining lifetime optimization information provided in an embodiment of this application; Figure 3 This is a flowchart of another method for determining lifetime optimization information provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a device for determining lifetime optimization information provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0035] It should be understood that "multiple" as mentioned in this application refers to two or more. In the description of this application, unless otherwise stated, " / " indicates "or," for example, A / B can mean A or B; "and / or" in this document 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. Furthermore, to facilitate a clear description of the technical solutions of this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or execution order, and that "first," "second," etc., do not necessarily imply differences.

[0036] First, the terms used in the embodiments of this application will be explained.

[0037] 1. Mean Time To Failure (MTTF) Mean time between failures (MTBF) refers to the average time from when a system is first used until it fails. In the embodiments of this application, MTBF refers to the average time from when a target component manufactured by the target supplier is first used until it fails.

[0038] 2. XGBoost (eXtreme Gradient Boosting) model The XGBoost model is a model that integrates many decision trees. Its core idea is to let the first tree output the prediction result, and then let the subsequent trees continuously correct the errors of the previous trees, so as to form an accurate prediction model.

[0039] 3. Cox (Cox Proportional Hazards Model) The Cox model is a statistical model for survival analysis used to study how multiple factors influence the timing of an event; that is, after considering multiple influencing factors, it determines the risk of an event occurring at a given time. In this application's embodiments, it involves the prediction of MTTF (Mean Time To Trace).

[0040] The application scenarios of the embodiments of this application are described below.

[0041] In order to ensure the service life of target components in vehicles, it is crucial to optimize the performance of target components during the production stage. Therefore, it is also very important to determine the service life optimization information for target components.

[0042] In related technologies, when a target component of a vehicle malfunctions, the user typically takes it to an after-sales service center for repair. The after-sales service center maintains a repair record for the target component, detailing the specific problem and the final solution. The vehicle manufacturer can proactively access these repair records and perform statistical analysis to propose optimization suggestions for the target component based on the results.

[0043] However, the aforementioned methods only record fault information about the target component that has already failed. Relying solely on this fault information is insufficient to accurately assess the component's overall health. Furthermore, target components manufactured by different suppliers vary, and their performance degradation rates differ depending on the climate and driving style. Given these factors, relying solely on statistical analysis of maintenance records held by after-sales service providers cannot accurately assess the cause of the fault, the component's health status, or the extent of performance degradation. Consequently, precise optimization recommendations cannot be provided.

[0044] Therefore, this application provides a method for determining lifespan optimization information. This method can be applied to the scenario where optimization suggestions are made for the performance of a target component, such as the scenario where optimization suggestions are made for the performance of a vehicle window.

[0045] Specifically, taking the vehicle window as the target component, data from M windows during operation is collected to form historical operating data for each window. Then, for any given window, based on its historical operating data, multi-dimensional characteristics are determined, including motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics. Next, based on these characteristics, comprehensive evaluation parameters for the M windows are determined, which assess the overall health status and overall lifespan of the M windows. Finally, targeted lifespan optimization information is analyzed based on these comprehensive evaluation parameters.

[0046] In this way, by determining the multi-dimensional operating characteristics of each window, the comprehensive evaluation parameters of M windows can be accurately determined based on these multi-dimensional characteristics. Thus, based on the accurate comprehensive evaluation parameters, more effective lifespan optimization suggestions can be determined, thereby improving the accuracy and effectiveness of lifespan optimization suggestions.

[0047] The implementation environment involved in the embodiments of this application will be described below.

[0048] For example, Figure 1 This is a schematic diagram illustrating the implementation environment of a method for determining lifetime optimization information provided in an embodiment of this application. See also... Figure 1 , Figure 1 It includes vehicle 101, vehicle brand owner 102 and multiple suppliers 105. Server 103 and data center screen 104 are deployed at vehicle brand owner 102.

[0049] Vehicle 101 is equipped with a target component, which can provide operational data of the target component to vehicle brand 102. Vehicle 101 can collect the operational data of the target component in real time via CAN (Controller Area Network) bus / LIN (Local Interconnect Network) bus. Taking a car window as an example, vehicle 101 can collect the current curve for each window raising and lowering, abnormal information from the Hall sensor, false triggering information for anti-pinch protection, triggering information for motor thermal protection, and the cumulative number of opening and closing operations. It can also collect temperature data from the vehicle's external temperature sensor, the vehicle's geographical location, rainfall data from the rain sensor, and acceleration data from the accelerometer. Vehicle 101 can also be equipped with a vehicle networking terminal T-BOX (TelematicsBOX). After collecting the aforementioned window operational data, vehicle 101 can upload the data to server 103 of vehicle brand 102 via the T-BOX.

[0050] Vehicle brand 102 is the leading party in proposing lifespan optimization information for the target component. Server 103 can receive the operating data of the target component collected by each vehicle 101. Then, it can analyze the operating data of the target component collected in each vehicle 101 over a period of time using the lifespan optimization information determination method provided in this application embodiment, so as to evaluate the health status and lifespan of the target component during that period and obtain comprehensive evaluation parameters. Subsequently, based on the comprehensive evaluation parameters, it can propose targeted optimization suggestions for the performance of the target component, that is, determine the lifespan optimization information for the target component.

[0051] After obtaining comprehensive evaluation parameters and determining the lifespan optimization information for the target components, it can be displayed on the large screen 104 of the data center of the vehicle brand 102, so that the technical personnel of the vehicle brand 102 can also know the performance of the target components produced by each supplier and the optimization suggestions for the target components produced by each supplier in a timely manner.

[0052] It should be understood that the determination of the comprehensive evaluation parameters and lifespan optimization information of the target components mentioned above can be obtained by analyzing the data on a supplier-by-supplier basis. In other words, it involves analyzing the operating data of each target component produced by a particular supplier to obtain the comprehensive evaluation parameters and lifespan optimization information of the target components produced by that supplier. Subsequently, the performance evaluation of the target components can be displayed on the data center's large screen 104 on a supplier-by-supplier basis.

[0053] The vehicle brand 102 can then send the lifespan optimization information of the target components produced by each supplier to the corresponding supplier via the server 103. For example, the server 103 can send the lifespan optimization information of the target components produced by supplier A to supplier A, or the server 103 can send the lifespan optimization information of the target components produced by supplier B to supplier B.

[0054] It is worth noting that the method for determining lifespan optimization information provided in this application embodiment can be executed by the server 103 in the vehicle brand 102 mentioned above.

[0055] The method for determining lifetime optimization information provided in the embodiments of this application will be explained in detail below.

[0056] Figure 2 This is a flowchart illustrating a method for determining lifetime optimization information provided in an embodiment of this application. This method can be applied to a computer device, which can be a server; the server can be a standalone server or a server cluster composed of multiple servers. See also... Figure 2 The method includes the following steps 201-203.

[0057] Step 201: Analyze the historical operating data of the i-th target component among the M target components to determine the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component.

[0058] In this embodiment, the M target components can be manufactured by a target supplier, which refers to any one of the suppliers that manufactures the target components. In other words, the purpose of this solution is to determine the corresponding lifespan optimization information for target components manufactured by a specific supplier. Here, M is an integer greater than or equal to 1, and i is an integer greater than or equal to and less than or equal to M.

[0059] The target component is a part of the vehicle that can be driven by an electric motor. For example, the target component can be any one of the following components: window, electric sunshade, electric rearview mirror, etc.

[0060] The historical operating data of the i-th target component refers to the multi-dimensional data of the i-th target component during its operation over a past period. In this embodiment, the historical operating data of the i-th target component may include the timestamps of each operation of the i-th target component in the first time period, the current of each operation of the motor in the i-th target component, fault triggering information, false triggering information of the target function, the temperature, rainfall and location information of the environment in which the i-th target component is located during each operation, and the speed and acceleration of the vehicle in which the i-th target component is located during each operation.

[0061] The first time period can be preset by technicians. For example, it can be set according to the determination cycle of lifespan optimization information. As an example, if lifespan optimization information is updated every quarter, then the first time period can be set to 90 days before the current time.

[0062] The target function can be set differently depending on the target component. For example, when the target component is a car window, the target function can be the anti-pinch function of the car window.

[0063] The vehicle can collect real-time operational data of target components via the CAN / LIN bus. Taking a car window as an example, the vehicle can record the timestamp of each window's raising and lowering (historical timestamps), collect the current changes during each raising and lowering process (historical current), Hall sensor feedback of abnormal information and motor thermal protection trigger information (fault trigger information), anti-pinch false trigger information (false trigger information of the target function), etc. Simultaneously, it can also collect temperature data from external temperature sensors, the vehicle's geographical location, rainfall data from rain sensors, acceleration data from accelerometers, and speed data from speed sensors. The vehicle sends the collected operational data of the target component to a server, which can accumulate the operational data of the i-th target component within a first time period, forming the historical operational data of the i-th target component.

[0064] Motor operating characteristics refer to the characteristics related to the motor in the target component, which are used to represent the operating state of the motor in the target component. Environmental operating characteristics refer to the operating characteristics associated with the external environment of the vehicle, which are used to represent the operating characteristics of the target component in the external environment in which the vehicle is located. Driving behavior operating characteristics refer to the operating characteristics associated with the driver's operating habits, which are used to represent the operating conditions of the target component under specific driving and operating habits.

[0065] In the above method, by analyzing the historical operating data of the i-th target component among the M target components produced by the target supplier in various dimensions, the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component are determined. This allows the operating characteristics of the target component to be characterized through multiple dimensions, thereby achieving an accurate characterization of the operating characteristics of the target component by combining influencing factors such as environment and driving habits.

[0066] The determination process of the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component is explained below.

[0067] First, motor operating characteristics One possible approach is to perform statistical analysis on the timestamps of each operation, the current of each operation, the fault triggering information, and the false triggering information of the target function for the i-th target component to obtain the motor operating characteristics.

[0068] In some embodiments, motor operating characteristics may include motor current variation characteristics, abnormal event statistical characteristics, and operation statistical characteristics.

[0069] In this case, the specific operation to obtain the motor operating characteristics by statistically analyzing the historical operating timestamps, historical operating currents, fault triggering information, and false triggering information of the target function for the i-th target component can be as follows: determine the maximum current value and average current value of the motor during each operation from the historical operating currents; determine the current change characteristics based on the historical operating currents, maximum current value, and average current value; statistically analyze the fault triggering information and false triggering information of the target function to obtain the abnormal event statistical characteristics; statistically analyze the total number of operations of the i-th target component and the single operation duration of each operation based on the historical operating timestamps; and determine the operation statistical characteristics based on the total number of operations of the i-th target component and the single operation duration of each operation.

[0070] It should be understood that current variation characteristics can characterize the current changes during motor operation, abnormal event statistical characteristics can characterize the fault conditions and the triggering of specific events during motor operation, and operation statistical characteristics can reflect the operating frequency of the motor from another perspective.

[0071] In the above method, by determining the current change characteristics, abnormal event statistical characteristics, and operation statistical characteristics, the motor operation characteristics are characterized from three aspects: current change, abnormal event triggering, and operation frequency. In this way, by characterizing the motor operation in multiple dimensions, motor operation characteristics that can more accurately characterize the motor operation can be determined.

[0072] In some embodiments, current variation characteristics may include mean peak current, current volatility, and peak current trend slope. The mean peak current refers to the average peak current of the target component during each startup within a certain time period. The current volatility refers to the standard deviation of the current during a single operation of the target component, which reflects the stability of motor operation. The peak current trend slope refers to the rate of change of the mean peak current within a certain time period.

[0073] In this case, the maximum and average current values ​​of the motor during each operation are determined from the historical operating currents. Based on the historical operating currents, maximum current values, and average current values, the operation to determine the current variation characteristics can be as follows: calculate the average of the maximum current values ​​of the target component during the last preset number of operations before the current moment to obtain the average peak current value; for any operation of the target component within the first time period, based on the current at multiple moments during that operation and the average current value during that operation, determine the current standard deviation for that operation, and calculate the average of the current standard deviations for each operation within the first time period to obtain the current fluctuation rate; based on the maximum current value of the motor during each operation, calculate the average peak current value for each day within the first time period, calculate the rate of change of the average peak current value for each day within the first time period to obtain the current peak trend slope.

[0074] The preset quantity can be set by technicians in advance; for example, the preset quantity can be set to 30.

[0075] It should be understood that the average peak current characterizes the maximum electromagnetic torque demand of the motor at startup, reflecting the magnitude of the mechanical resistance overcome during startup. Current fluctuation rate indicates the stability of the current during motor operation, reflecting the uniformity of the mechanical transmission system. The current peak trend slope characterizes the rate of change of the current peak over time, reflecting the rate of degradation of mechanical resistance. In the above method, by selecting the average peak current, current fluctuation rate, and current peak trend slope to characterize the motor's current variation characteristics, the mechanical and electrical state of the motor can be described from three dimensions: "current load level," "operational stability," and "degradation rate." These three factors comprehensively cover the reflection of major failure causes such as bearing wear, grease drying, guide rail deformation, and gear wear, thus allowing for the identification of features that more accurately characterize current variations.

[0076] In some embodiments, the statistical characteristics of abnormal events may include the cumulative number of thermal protection triggers, the number of false triggers of the target function, and the number of Hall sensor anomalies. The aforementioned fault trigger information may include a thermal protection trigger timestamp and a Hall sensor anomaly feedback timestamp. The false trigger information for the target function includes a timestamp when the target function is falsely triggered; in some embodiments, the false trigger information may also include instances of the target function being falsely triggered when the child lock is opened.

[0077] The above-mentioned statistical fault triggering information and target function triggering information can be used to obtain the statistical characteristics of abnormal events by: counting the number of timestamps when thermal protection is triggered to obtain the cumulative number of thermal protection triggers; counting the number of timestamps when Hall sensor provides abnormal feedback to obtain the number of Hall sensor abnormalities; and counting the number of timestamps when the target function is falsely triggered to obtain the number of false triggers of the target function.

[0078] Since each thermal protection trigger is a thermal shock, it can damage the insulation system and lubricant. Furthermore, false triggering of some functions may cause abnormal motor start-stop, and Hall sensor failure can prevent the motor from operating normally. Therefore, the above method, by statistically analyzing the cumulative number of thermal protection triggers, the number of Hall sensor malfunctions, and the number of false triggers of the target function, can reflect the motor's health status from three dimensions: thermal damage accumulation, abnormal motor response, and position sensing signal quality. This complements the current change characteristics and can more accurately characterize the motor's operating characteristics.

[0079] In some embodiments, operational statistical characteristics may include average daily operation frequency, percentage of days with high-frequency operations, and average time per operation. Average daily operation frequency refers to the average number of operations per day within the first time period, and percentage of days with high-frequency operations refers to the proportion of days with a high number of operations within the first time period.

[0080] In this case, the operation to determine the statistical characteristics of the operation based on the total number of runs of the i-th target component and the duration of each run can be as follows: divide the total number of runs of the i-th target component by the duration of the first time period to obtain the average daily running frequency; based on the total number of runs of the i-th target component, count the number of runs per day in the first time period, and count the total number of days in the first time period where the number of runs is greater than a preset threshold; divide the total number of days by the total number of days in the first time period to obtain the percentage of days with high-frequency operations; calculate the average duration of each run to obtain the average time consumed per run.

[0081] The preset number of times threshold can be set in advance, for example, the preset number of times threshold can be set to 15 times.

[0082] It should be understood that each operation of the target component generates mechanical wear, and the average daily operating frequency and the proportion of days with high-frequency operation are factors influencing motor wear. The average time per operation reflects the mechanical resistance overcome by the target component; for example, increased time leads to increased resistance and decreased motor performance. In the above method, by further determining the average daily operating frequency, the proportion of days with high-frequency operation, and the average time per operation, the impact on motor lifespan can be characterized through user behavior, making the characterization of motor features more accurate.

[0083] Second, environmental operating characteristics One possible approach is to determine the environmental operating characteristics based on the timestamps of each run of the i-th target component and the temperature, rainfall, and location information of the environment in which the i-th target component is located during each run.

[0084] In some embodiments, environmental operating characteristics may include temperature-related characteristics, geographic location-related characteristics, and rainfall-related characteristics. Temperature-related characteristics represent the operating status of the target component at a specific temperature, geographic location-related characteristics represent the operating status of the target component in a specific area, and rainfall-related characteristics represent the operating status of the target component under rainfall conditions.

[0085] In some embodiments, temperature-related characteristics may include the percentage of low-temperature operation, the percentage of high-temperature operation, the average external temperature, and the average daily temperature difference.

[0086] In this case, temperature-related characteristics can be determined in the following ways.

[0087] Count the number of timestamps for each run to obtain the total number of runs within the first time period; count the number of timestamps for the i-th target component when the ambient temperature is lower than the first temperature threshold to obtain the number of low-temperature runs; divide the number of low-temperature runs by the total number of runs within the first time period to obtain the percentage of low-temperature runs.

[0088] Similarly, count the number of timestamps when the temperature of the i-th target component in its environment is greater than the second temperature threshold to obtain the number of high-temperature operations; divide the number of high-temperature operations by the total number of operations in the first time period to obtain the proportion of high-temperature operations.

[0089] The first and second temperature thresholds can be preset. The first temperature threshold can be set to a smaller value, and the second temperature threshold can be set to a larger value. The first temperature threshold can be smaller than the second temperature threshold. For example, the first temperature threshold can be set to -5℃ (degrees Celsius), and the second temperature threshold can be set to 40℃.

[0090] Furthermore, in some embodiments, the average temperature of the environment in which the target component is located during the first time period can be obtained to obtain the average external temperature. More specifically, the highest and lowest temperatures of the environment in which the target component is located each day during the first time period can be obtained; the highest temperature of the environment each day is subtracted from the lowest temperature to obtain the daily temperature difference; and the average of the daily temperature differences during the first time period is determined as the daily average temperature difference.

[0091] One possible approach is to count the number of times the i-th target component operates when the rainfall in its environment is greater than or equal to a preset rainfall threshold, thus obtaining rainfall-related features; and to obtain the daily location information of the vehicle where the i-th target component is located within the first time period, and to count the number of days when the location information of the vehicle where the i-th target component is located is the target geographical area, thus obtaining geographical location-related features.

[0092] The preset rainfall threshold can be set in advance, based on the rainfall detected. The target geographical area can be a region with high salt fog, such as a coastal area.

[0093] Because the viscosity of lubricating grease increases sharply at low temperatures, and prolonged low-temperature operation can lead to abnormal wear, while the motor's heat dissipation efficiency decreases at high temperatures, thermal protection is more easily triggered in such environments. The average external temperature reflects the long-term thermal stress environment of the target component, which affects the motor's internal steady-state environment. Furthermore, drastic temperature changes cause thermal expansion and contraction of some materials, a characteristic reflected by the average daily temperature difference. Additionally, prolonged exposure to high salt spray areas can lead to metal corrosion, affecting bearings, Hall sensors, and other components of the target component; therefore, geographical location-related characteristics are also determined. During rainy weather, moisture may penetrate the motor, affecting its operation. Thus, by determining the proportion of low-temperature operation, the proportion of high-temperature operation, the average external temperature, the average daily temperature difference, rainfall-related characteristics, and geographical location-related characteristics, the main environmental factors affecting motor lifespan can be characterized from the dimensions of thermal and corrosive environments, allowing for accurate characterization of the target component's operation under specific conditions.

[0094] Third, the operational characteristics of driving behavior One possible approach is to determine the driving behavior characteristics based on the timestamps of each run of the i-th target component and the vehicle's speed and acceleration during each run.

[0095] In some embodiments, driving behavior operation characteristics may include driving habit characteristics and operating habit characteristics. Driving habit characteristics represent the operation of the target component under the driver's driving habits, while operating habit characteristics represent the operation of the target component under the user's operating habits.

[0096] In some embodiments, driving habit characteristics may include dynamic operation percentage and driving operation percentage. Operation habit characteristics may include nighttime operation frequency and frequent operation frequency. Dynamic operation percentage represents the percentage of operation of the target component when the vehicle is in a rapidly changing operating state, while driving operation percentage represents the percentage of operation of the target component while the vehicle is in motion. Nighttime operation frequency represents the frequency of operation of the target component at night, and frequent operation frequency represents the frequency of frequent operation of the target component.

[0097] In this case, the operation to determine the driving behavior operation characteristics based on the timestamps of each run of the i-th target component and the speed and acceleration of the vehicle during each run can be as follows: count the number of timestamps of the target component when the vehicle speed is greater than a preset speed threshold to obtain the number of runs during driving, and divide the number of runs during driving by the total number of runs in the first time period to obtain the proportion of runs during driving; count the number of timestamps of the target component when the vehicle acceleration is greater than a preset acceleration threshold to obtain the number of dynamic operations, and divide the number of dynamic operations by the total number of runs in the first time period to obtain the proportion of dynamic operations; count the number of timestamps of the target component that run during a preset time period each day in the first time period to obtain the nighttime operation frequency; and based on the timestamps of each run, determine the time interval between each two adjacent runs, and count the number of times the time interval between two adjacent runs is less than a preset interval threshold to obtain the frequency of frequent operations.

[0098] The preset vehicle speed threshold can be set in advance, for example, it can be set to 5 km / h. The preset acceleration threshold can also be set in advance, and the preset acceleration threshold can be set relatively high, for example, it can be set to 2.5 m / s². 2 (meters per square second). The preset time period can be a period of time during the night, such as 22:00 to 6:00 the next day. In addition, the preset interval threshold can be set to a small value, such as 3 seconds.

[0099] It should be understood that during rapid acceleration or deceleration, the vehicle's posture changes drastically, and the motor and certain components of the target part will experience superimposed loads. This will lead to a significant increase in the instantaneous load on the motor, thus affecting the operation of the target part. Similarly, while the vehicle is in motion, certain components will be subjected to wind pressure, requiring the motor to output greater torque, which will also affect the operating characteristics of the target part. From the user's perspective, whether it is nighttime operation or frequent operation, it will reflect the intensity of operation on the target part to some extent, thus affecting the operating characteristics of the motor. Therefore, by determining the proportion of dynamic operation, the proportion of operation while driving, the frequency of nighttime operation, and the frequency of frequent operation, the operating characteristics of the target part under specific driving behaviors can be accurately characterized.

[0100] It should be noted that by performing the specific implementation of step 201 above on each of the M target components, the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of each of the M target components can be obtained.

[0101] The above describes the specific implementation methods for determining the operating characteristics of the motor, the operating characteristics of the environment, and the operating characteristics of driving behavior. After the operating characteristics of each target component are characterized, the health status and service life of the target component can be analyzed by analyzing the operating characteristics of the motor, the operating characteristics of the environment, and the operating characteristics of driving behavior, so that the quality status of the target component can be quantitatively evaluated.

[0102] Step 202: Based on the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the M target components, determine the comprehensive evaluation parameters of the M target components. The comprehensive evaluation parameters are used to describe the overall health status and overall service life of the M target components.

[0103] The comprehensive evaluation parameter refers to the quantitative evaluation result obtained by comprehensively quantifying the quality status of M target components. It can describe the overall health status and overall service life of the M target components over a period of time. In some embodiments, the comprehensive evaluation parameter may include the average health score and the mean time between failures (MTBF), wherein the average health score is used to represent the overall health status of the M target components over a period of time, and the mean time between failures (MTBF) is used to represent the overall service life of the M target components.

[0104] One possible approach is that the operation of step 202 may include the following steps (1)-(3).

[0105] (1) Based on the motor operating characteristics of the i-th target component, determine the motor wear index of the i-th target component.

[0106] The motor wear index of the i-th target component is used to represent the degree of wear of the motor of the i-th target component. The larger the motor wear index, the greater the degree of wear of the motor; the smaller the motor wear index, the less the degree of wear of the motor.

[0107] It should be understood that the motor is a crucial component for the normal operation of the target part. If the motor's various indicators are normal, the operating performance of the target part can be guaranteed. If the motor's evaluation indicators are abnormal, the operating performance of the target part will be problematic. The motor wear index is an important indicator for evaluating motor performance; increased motor wear will lead to a decline in the operating performance of the target part. Therefore, in the above method, by determining the motor wear index of the i-th target part, the motor performance can be quantified, thus providing a valid basis for the subsequent quantification of the target part's performance.

[0108] It is worth noting that before determining the motor wear index of the i-th target component, the average energy consumption of a single run and the current decay slope during the motor stop phase can be obtained first within the first time period.

[0109] The average energy consumption per run within the first time period is the average energy consumption of each run within the first time period. The energy consumption of the target component per run can be calculated using W = U × I × T, where W is the energy consumption per run, U is the average voltage of the target component during a single run, I is the average current of the target component during a single run, and T is the duration of a single run. It should be understood that the operating voltage of the target component during each run can also be obtained from historical operating data.

[0110] The current decay slope during the motor's stopping phase refers to the rate of change of current after the power supply to the motor is disconnected. It reflects how quickly the current returns to zero under the combined effects of mechanical load and electrical characteristics after power is cut off. Because the motor rotor continues to rotate due to inertia after the power supply is cut off, the electronic windings cut the magnetic field, generating an induced electromotive force that drives the current to continue flowing. Therefore, the current in the motor does not immediately return to zero. The greater the mechanical resistance the motor has to overcome, the faster the inertial rotation decelerates, resulting in a greater rate of change of current. In other words, the current decay slope during the motor's stopping phase can, to some extent, reflect the dynamic friction and mechanical losses during operation.

[0111] Since the operating characteristics of a motor reflect its properties during energized operation, in this case, by also determining the current decay slope during the motor's stopping phase, the mechanical and electrical characteristics of the motor after power failure can also be reflected. This complements the motor's operating characteristics and together they can characterize the complete dynamic characteristics of the motor from start to stop.

[0112] In this case, step (1) can be performed as follows: linear regression is performed on the mean peak current, current fluctuation rate, average energy consumption during a single run in the first time period and the current decay slope during the motor stop phase of the i-th target component to obtain the motor wear index of the i-th target component.

[0113] In the above method, the complete dynamic characteristics of the motor from start to stop are characterized by combining the current characteristics when the motor starts, the current changes during operation, the energy consumption, and the current changes after power failure. These characteristic parameters all reflect the wear of the motor to a certain extent. Thus, by combining these characteristic parameters, the motor wear index can be accurately determined.

[0114] One possible approach is to perform linear regression on the mean peak current, current fluctuation rate, average energy consumption during a single run in the first time period, and current decay slope during the motor stop phase of the i-th target component to obtain the motor wear index of the i-th target component. This can be achieved by the following formula (1).

[0115] (1) in, Let be the motor wear index of the i-th target component. The average peak current of the i-th target component Let be the current fluctuation rate of the i-th target component. Let be the average energy consumption of the i-th target component during a single operation in the first time period. Let be the current decay slope of the i-th target component during the motor stop phase. The weighting coefficient is the average value of the peak current. The weighting coefficients corresponding to the current volatility are: The weighting coefficient corresponding to the average energy consumption. This is the weighting coefficient corresponding to the current decay slope. , , , It can be pre-calibrated, or in some embodiments, it can be obtained by fitting historical operating data of a target component that has failed.

[0116] It is worth noting that by setting i to 1, 2, 3, ..., M in sequence, the motor wear index of each of the M target components can be determined.

[0117] (2) Based on the motor operation characteristics, environmental operation characteristics, driving behavior operation characteristics and motor wear index of the i-th target component, predict the individual health score and individual fault-free time of the i-th target component.

[0118] Individual health score, or health score for a single target component, is used to represent the health status of that single target component. Individual mean time between failures (MTBF), or mean time between failures (MTBF) for a single target component, is used to represent the service life of that single target component.

[0119] The process of determining the individual health score of the i-th target component will be explained below.

[0120] One possible approach is to predict the failure risk probability of the i-th target component based on its motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics; and to determine an individual health score based on the motor operating characteristics, failure risk probability, and motor wear index of the i-th target component.

[0121] Here, the failure risk probability of the i-th target component represents the likelihood of the i-th target component failing within a second time period after the current moment; that is, the probability that the i-th target component will fail within a future period under the current operating state. The second time period can be preset, for example, it can be set to 90 days.

[0122] In the above method, by predicting the failure risk probability of the i-th target component, the passive response after the failure occurs is transformed into active prevention before the failure occurs. Then, in the process of calculating the individual health score, the failure risk probability is integrated so that the current health status of the target component can reflect the future failure risk. For example, for target components with the same degree of wear, the target component with a lower failure risk probability is healthier. In this way, by combining the motor operating characteristics, failure risk probability and motor wear index, a more accurate individual health score can be determined.

[0123] It is worth noting that, in some embodiments, the comprehensive evaluation parameters may also include the average failure probability, which reflects the average probability that the M target components will fail over a future period of time. In this case, after determining the failure risk probability of each of the M target components, the average failure risk probability of the M target components can be calculated to obtain the average failure probability, providing additional analytical basis for determining subsequent lifespan optimization information.

[0124] The operation of predicting the failure risk probability of the i-th target component based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component can be as follows: input the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component into the failure risk prediction model, and output the failure risk probability of the i-th target component through the failure risk prediction model.

[0125] This failure risk prediction model is used to predict the failure probability of a target component. This model can be trained using historical operating data of a target component that has already failed. This historical operating data can be all operating data of the target component from the start of operation to the occurrence of failure. When creating training samples, operating data of the target component within a third time period can be processed. For example, the third time period could be from the start of operation to five months. The specific time period can be set by technical personnel, and this application does not limit this. The purpose of limiting the time is mainly to avoid using operating data throughout the entire lifecycle, which would prevent the acquisition of sample labels indicating whether future failures will occur.

[0126] Before training the fault risk prediction model, the operating data of the target component during the third time period can be processed using step 201 to obtain the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of each target component that has experienced a fault. The motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of one target component are then used as training sample data. If the target component experiences a motor overload fault or performance fault in the second time period following the third time period, the sample label of this training sample can be set to 1; otherwise, the sample label can be set to 0.

[0127] During training, the server can acquire multiple training samples and use these multiple training samples to train the initial prediction model, thereby obtaining the fault risk prediction model.

[0128] These multiple training samples can be pre-set. Each training sample includes sample data and sample labels. The sample data is the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of a target component, and the sample label is 1 or 0. In other words, the input data of a training sample is the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of a target component.

[0129] It is worth noting that the initial prediction model can be a neural network model, a tree model, etc. For example, in some embodiments, XGBoost can be used as the initial prediction model.

[0130] When the server trains the initial prediction model using multiple training samples, for each training sample, the input data from that training sample is fed into the initial prediction model to obtain output data. A loss function is then used to determine the loss value between the output data and the sample labels in that training sample. The parameters of the initial prediction model are adjusted based on this loss value. After adjusting the parameters of the initial prediction model based on each of the multiple training samples, the adjusted initial prediction model becomes the fault risk prediction model.

[0131] During model training, K-fold cross-validation (such as 5-fold cross-validation) can be used to optimize model hyperparameters. Model parameters can include learning rate, maximum depth, subsampling rate, etc.

[0132] After training the fault risk prediction model, it can be deployed to the application scenario to output the fault risk probability of the i-th target component.

[0133] It is worth noting that if the failure risk probability of the i-th target component is greater than a preset probability threshold, at least one target feature can be output by the failure risk prediction model. Then, a target warning label can be generated based on this at least one target feature. After the failure risk probabilities of all M target components are predicted, the number of times the target warning labels are generated can be counted to obtain the target warning frequency.

[0134] The preset probability threshold can be set in advance, for example, the preset probability threshold can be set to 0.7.

[0135] At least one target feature is an operating feature of the i-th target component whose multi-dimensional features (including average peak current, current fluctuation rate, current peak trend slope, cumulative number of thermal protection triggers, number of false triggers of target functions, number of Hall sensor anomalies, average daily operating frequency, proportion of high-frequency operation days, average time of single operation, proportion of low-temperature operation, proportion of high-temperature operation, average external temperature, average daily temperature difference, geographical location correlation features, rainfall correlation features, proportion of dynamic operation, proportion of operation while driving, frequency of operation at night, and frequency of frequent operation) cause the failure risk probability of the i-th target component to be greater than a preset probability threshold.

[0136] A target warning label is a warning label corresponding to a target feature. In this embodiment, different operating features can correspond to different warning labels. For example, when the target feature is the average peak current, the corresponding warning label can be "low-temperature starting torque decay". Low-temperature starting torque decay describes the motor's starting performance. By generating this "low-temperature starting torque decay" label, a corresponding warning can be triggered when the motor's starting performance gradually deteriorates. The target warning frequency refers to the frequency at which a specific warning is triggered, that is, the number of times a specific warning label is generated, such as the number of times the "low-temperature starting torque decay" warning is triggered.

[0137] It should be understood that during the training of the fault risk prediction model, the fault risk prediction model will learn the importance of each operational feature to the fault risk probability, such as which features will lead to a higher fault risk probability. After the training is completed, the fault risk prediction model will analyze each operational feature after inputting it into the model to determine which operational features will lead to a higher fault risk probability, and output the corresponding fault risk probability accordingly. At the same time, in the above method, at least one target feature that leads to a higher fault risk probability can also be output.

[0138] In addition, in some embodiments, the comprehensive evaluation parameters may also include the target warning frequency. Therefore, after predicting the failure risk probability of M target components, the number of times a specific warning label is generated can be counted to obtain the target warning frequency.

[0139] In the above method, at least one target feature is output through the fault risk prediction model, and a corresponding early warning label is generated accordingly. This allows the model to output why the fault will occur when it is predicted that the i-th target component is likely to fail in the future. In other words, the cause of the fault can be output. This can provide a valid basis for fault repair in specific applications.

[0140] In some embodiments, the operation of determining an individual health score based on the motor operating characteristics, fault risk probability, and motor wear index of the i-th target component can be as follows: the individual health score is determined by the following formula (2) based on the motor operating characteristics, fault risk probability, and motor wear index of the i-th target component.

[0141] (2) in, For the i-th target component, the individual health score is... The 5th percentile of the motor wear index for all target components that have failed. The 95th percentile of the motor wear index for all target components that have failed. Let be the failure risk probability of the i-th target component. This represents the number of Hall sensor malfunctions or the number of false triggers of the target function in the motor operation characteristics of the i-th target component. The total number of times an abnormal event is triggered for the i-th target component. The importance of the motor wear index can be preset by technicians, for example, it can be set to 0.5. The degree of importance used to indicate the probability of failure risk can be preset by technicians, for example, it can be set to 0.3. The indicator used to represent the importance of the current operating status can be preset by technicians, for example, it can be set to 0.2.

[0142] In the above method, the motor wear index refers to the degree of physical wear that has occurred in the motor from the past to the present, representing the physical wear dimension. The failure risk probability reflects the short-term failure risk in the future, representing the future risk dimension. The number of Hall sensor anomalies or the number of false triggers of the target function reflects the frequency of recent abnormal events, representing the recent motor condition. Therefore, by using the motor wear index, failure risk probability, and the number of Hall sensor anomalies or the number of false triggers of the target function to jointly reflect the health status of the motor from the individual dimensions of physical wear, future risk, and recent operating status, a more accurate individual health score can be determined.

[0143] It is worth noting that if the individual health score of a target component is less than a preset score threshold, the target component can be marked as a high-risk component. This information can then be displayed on the data center dashboard or sent to the vehicle where the target component is located, allowing users to be aware that the target component in that vehicle may have a failure risk.

[0144] The process of determining the individual health score of the i-th target component has been explained above. The process of determining the individual fault-free time of the i-th target component will be explained below.

[0145] One possible approach is to input the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component into a life assessment model, and then output the individual fault-free time of the i-th target component through the life assessment model.

[0146] Specifically, the instantaneous failure risk of the i-th target component at different time points can be obtained by processing the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component through a life assessment model; the instantaneous failure risk of the i-th target component at different time points can be obtained by integrating the instantaneous failure risk of the i-th target component at different time points through the life assessment model; the cumulative risk of the i-th target component at different time points can be obtained by exponentially transforming the cumulative risk of the i-th target component at different time points through the life assessment model; and the individual fault-free time of the i-th target component can be obtained by integrating the survival probability of the i-th target component at different time points through the life assessment model.

[0147] In the above method, by first analyzing the current operating status and motor wear of the i-th target component, the instantaneous failure risk of the i-th target component at different time points is determined. Then, based on this, the service life of the i-th target component under the current operating status and motor wear conditions can be accurately derived through operations such as integration and exponential transformation, which means that a relatively accurate individual fault-free time can be obtained.

[0148] Before establishing the service life assessment model, this model can be trained. In some embodiments, the service life assessment model can employ a Cox proportional hazards model. Similar to the failure risk prediction model, this service life assessment model can be trained using historical operating data of target components that have already failed.

[0149] In this embodiment of the application, the transient failure risk can be represented by the following function model (1).

[0150] (1) in, For the instantaneous risks of the target component at different points in time, It is the basic risk function, which is used to represent the inherent failure tendency of a standard product without any abnormal characteristics over time. These are used to represent the multi-dimensional characteristics of the i-th target component (including average peak current, current fluctuation rate, current peak trend slope, cumulative number of thermal protection triggers, number of false triggers of the target function, number of Hall sensor anomalies, average daily operating frequency, daily proportion of high-frequency operation, average time per operation, proportion of low-temperature operation, proportion of high-temperature operation, average external temperature, average daily temperature difference, geographical location correlation characteristics, rainfall correlation characteristics, proportion of dynamic operation, proportion of operation while driving, nighttime operation frequency, and frequent operation frequency). Used to indicate the importance of the motor wear index These are used to represent the importance of each multi-dimensional feature. , , It can be fitted during the training process of the life assessment model.

[0151] Before training the life assessment model, the historical operating data of the target component that has already failed can be processed to obtain multiple training samples. The sample data in each of these training samples are the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of a target component. The sample label is the actual lifespan of this target component.

[0152] During the training of the life assessment model, for any one of the multiple training samples, the sample data of the training sample can be input into the life assessment model. First, the initial instantaneous risk at different time points is obtained through the function model (1). Then, the initial instantaneous risk at different time points is integrated to obtain the initial cumulative risk at different time points. Then, the initial cumulative risk at different time points is exponentially transformed to obtain the initial survival probability at different time points. Finally, the initial survival probability at different time points is integrated to obtain the output data of the life assessment model. The loss value between the output data and the sample label in this training sample is determined through the loss function. The model is then adjusted according to the loss value. , , After adjusting the parameter based on each of the multiple training samples, the trained lifetime assessment model can be obtained.

[0153] It is worth noting that by performing the above step (2) on each of the M target components, the individual health score and individual fault-free time of each target component can be obtained. Then, the average health score and average fault-free time of the M target components can be calculated accordingly.

[0154] (3) Based on the average of the individual health scores of the M target components, the average health score of the M target components is obtained, and the average individual fault-free time of the M target components is calculated to obtain the average fault-free time of the M target components.

[0155] In steps (1) to (3) above, since the degree of motor wear best reflects the performance degradation of the target component, the motor wear index of each target component is determined based on its multi-dimensional characteristics. This allows us to understand the performance degradation of each target component, and subsequently, by combining the motor wear index, we can more accurately assess the quality of the target component. Furthermore, by first assessing the quality of a single target component based on its multi-dimensional characteristics, and then comprehensively assessing the quality of M target components by calculating the average value, we can achieve an accurate assessment of the quality of M target components and obtain more precise comprehensive assessment parameters.

[0156] It's worth noting that the aforementioned M target components are manufactured by the target supplier. Therefore, steps 201-202 assess the quality of the target components manufactured by the target supplier on a per-supplier basis. In other words, the average health score represents the current health status of the target component manufactured by the target supplier, and the mean time between failures (MTBF) represents the overall service life of the target component manufactured by the target supplier. Furthermore, the target components manufactured by the target supplier may be used by different user groups, meaning different user groups are associated with different target components. For example, the target components manufactured by the target supplier may be used in different climate zones, and the vehicles may be driven by drivers with different driving styles. These factors will all affect the quality of the target components. Therefore, for the target supplier, it is also possible to assess the quality of the target components used by different user groups.

[0157] It is worth noting that, before this, the M target components can be divided into a first set of components and a second set of components based on the environmental operation characteristics of the M target components, so as to obtain the target components associated with the first user group and the target components associated with the second user group; based on the driving behavior operation characteristics of the M target components, the M target components can be divided into a third set of components and a fourth set of components, so as to obtain the target components associated with the third user group and the target components associated with the fourth user group.

[0158] The first set of components includes target components used in a first climate zone. These target components are associated with a first user group, meaning the first user group consists of users who use the target components in the first climate zone. The first climate zone can be a southern geographical region. In some embodiments, the climate zone of the target component can be determined based on the average external temperature in the environmental operating characteristics; for example, a higher average external temperature indicates the target component is located in the first climate zone. The second set of components includes target components used in a second climate zone. These target components are associated with a second user group, meaning the second user group consists of users who use the target components in the second climate zone. The second climate zone can be a northern geographical region; for example, a lower average external temperature indicates the target component is located in the second climate zone.

[0159] The target components in the third component set are installed on vehicles corresponding to the first driving style, which is aggressive. This means the vehicles containing the target components in the third component set are driven by drivers with an aggressive driving style. The target components in the third component set are associated with a third user group, meaning the third user group uses an aggressive driving style, and the target components associated with this user group are installed on vehicles corresponding to the aggressive driving style. The target components in the fourth component set are installed on vehicles corresponding to the second driving style, which is mild. This means the vehicles containing the target components in the fourth component set are driven by drivers with a mild driving style, and the target components associated with this user group are associated with a fourth user group, meaning the fourth user group uses a mild driving style, and the target components associated with this user group are installed on vehicles corresponding to the mild driving style.

[0160] In this case, the comprehensive evaluation parameters can also include the average health score and mean time between failures (MTBF) for different user groups. Specifically, the average health score and MTBF for different user groups can include those corresponding to user groups in different climate zones, and those employing different driving styles.

[0161] One possible approach is to calculate the average health score and mean time between failures for each user group in the following way.

[0162] For any user group, calculate the average health score of the individual target components associated with this user group to obtain the average health score of this user group; and calculate the average mean time between failures (MTBF) of the individual target components associated with this user group to obtain the mean time between failures (MTBF) of this user group.

[0163] In the above method, by also calculating the average health score and mean time between failures for different user groups under the target supplier, the quality status of the target components used by different user groups can be evaluated, so that targeted optimization suggestions can be made for the target components used by specific user groups.

[0164] Specifically, for the average health score and mean time between failures (MTBF) of user groups in different climate regions, for any climate region, the average health score of individual target components (target components in the first component set / second component set) associated with the user group in this climate region is calculated to obtain the average health score of the user group (first user group / second user group) in this climate region; and the average MTBF of individual target components associated with the user group in this climate region is calculated to obtain the average MTBF of the user group in this climate region.

[0165] For user groups with different driving styles, the average health score and mean time between failures (MTBF) are calculated as follows: For any driving style, the average health score of the target components (target components in the third component set / fourth component set) associated with the user group of this driving style is calculated to obtain the average health score of the user group (third user group / fourth user group) for this driving style; and the average MTBF of the target components associated with the user group of this driving style is calculated to obtain the mean time between failures (MTBF) for the user group of this driving style.

[0166] In the above method, by calculating the average health score and mean time between failures (MTBF) for user groups in different climate zones (first user group and second user group), and the average health score and MTBF for user groups with different driving styles (third user group and fourth user group), the quality status of the target components can be evaluated by climate zone and by driving style. This allows for multi-dimensional quality assessment of the target components, enabling targeted optimization suggestions for the target components under specific climate zones and driving styles.

[0167] After obtaining the comprehensive evaluation parameters of the M target components through the above step 202, the comprehensive evaluation parameters can be analyzed to propose targeted optimization suggestions.

[0168] Step 203: Based on the comprehensive evaluation parameters, determine the lifespan optimization information for the target component.

[0169] In this embodiment of the application, lifespan optimization information for the target component can be determined by using rule base matching.

[0170] One possible approach is to perform step 203 as follows: obtain the target rule base; and determine lifetime optimization information from the target rule base based on comprehensive evaluation parameters.

[0171] The target rule base includes suggested information for different health states. In this embodiment, the target rule base includes multiple lifespan suggestion rules, each of which includes triggering conditions and suggested information. The target rule base supports both manual updates and machine learning updates.

[0172] For example, Table 1 below is an example of a target rule base. Referring to Table 1, it includes multiple triggering conditions and multiple suggestion messages, with each triggering condition and suggestion message corresponding one-to-one.

[0173] Table 1

[0174] Of course, the above is only an example to illustrate the target rule base provided in the embodiments of this application. The specific triggering conditions and suggested information can be set by technicians based on experience, and the embodiments of this application do not limit this.

[0175] In the above method, by pre-setting a target rule base, when it is necessary to determine lifespan optimization information, suggested information that matches the current health status can be directly matched from the target rule base, thus improving the efficiency of determining lifespan optimization information. Furthermore, the target rule base is set based on technical experience, and the suggested information described therein is targeted and can effectively improve the lifespan of the target component, thereby allowing for the matching of effective lifespan optimization information through the target rule base.

[0176] In this case, the operation of determining lifetime optimization information from the target rule base based on comprehensive evaluation parameters can be as follows: matching the target recommendation rules whose trigger conditions match the comprehensive evaluation parameters from multiple lifetime recommendation rules; and determining the recommendation information in the target recommendation rules as lifetime optimization information.

[0177] It is worth noting that in the method for determining lifespan optimization information provided in this application embodiment, by correlating the microsecond-level current curve characteristics of the motor, macro-climate data, and driving behavior, a comprehensive profile feature for evaluating motor load and wear can be constructed, enabling a comprehensive characterization of the target component's operating characteristics. Furthermore, by determining multi-dimensional comprehensive evaluation parameters, quality comparisons can be achieved across multiple dimensions, including suppliers, climate regions, and driving styles, accurately pinpointing the root causes of common problems and providing quantitative basis for OEM supply chain management and regional product design improvements.

[0178] To facilitate understanding, we will now combine... Figure 3The overall flow of the method for determining lifetime optimization information provided in the embodiments of this application is described. Figure 3 This is a flowchart of another method for determining lifetime optimization information provided in an embodiment of this application.

[0179] like Figure 3 As shown, historical operating data for each of the M target components can be obtained first. Then, for the i-th target component, its historical operating data can be analyzed to obtain its motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics. Finally, based on the motor operating characteristics of the i-th target component, its motor wear index can be determined.

[0180] Next, based on the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component, the failure risk probability of the i-th target component is predicted. Then, combining the failure risk probability, motor operating characteristics, and motor wear index, the individual health score of the i-th target component is determined. Then, combining the individual health scores of each of the M target components, the average health score of the M target components is obtained. Simultaneously, the average failure probability of the M target components can be determined by combining the failure risk probability of each of the M target components.

[0181] Meanwhile, based on the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component, the individual fault-free time of the i-th target component can be predicted. Then, by combining the individual fault-free time of each of the M target components, the average fault-free time of the M target components can be obtained.

[0182] After obtaining comprehensive evaluation parameters such as average health score, mean time between failures (MTBF), and mean failure probability, these parameters can be analyzed to determine lifespan optimization information that aligns with the current health status from the target rule base.

[0183] In this embodiment, data from the operation of M target components is collected to form historical operating data for each component. Then, for any given target component, the computer device first determines its multi-dimensional characteristics based on its historical operating data, including motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics. Next, based on these characteristics, the computer determines comprehensive evaluation parameters for the M target components, assessing their overall health and lifespan. Finally, it analyzes these comprehensive evaluation parameters to generate targeted lifespan optimization information. Thus, by determining the multi-dimensional operating characteristics of each target component, accurate comprehensive evaluation parameters for all target components can be determined. Based on these accurate comprehensive evaluation parameters, more effective lifespan optimization suggestions can be derived, improving the accuracy and effectiveness of the lifespan optimization recommendations.

[0184] Figure 4 This is a schematic diagram of a lifespan optimization information determination device provided in an embodiment of this application. This lifespan optimization information determination device can be implemented as part or all of a computer device by software, hardware, or a combination of both. This computer device can be as described below. Figure 5 The computer equipment shown. See also Figure 4 The device includes: a data processing module 401, a life assessment module 402, and an optimization suggestion module 403.

[0185] The data processing module 401 is used to analyze the historical operating data of the i-th target component among M target components to determine the motor operating characteristics, environmental operating characteristics and driving behavior operating characteristics of the i-th target component; The life assessment module 402 is used to determine the comprehensive assessment parameters of the M target components based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the M target components. The comprehensive assessment parameters are used to describe the overall health status and overall service life of the M target components. The optimization suggestion module 403 is used to determine life optimization information for the target component based on comprehensive evaluation parameters.

[0186] Optionally, the historical operation data includes the timestamps of each operation of the i-th target component within the first time period, the operating current of the motor in the i-th target component each time, fault triggering information, false triggering information of the target function, the temperature, rainfall, and location information of the environment where the i-th target component is located during each operation, and the speed and acceleration of the vehicle during each operation, where the vehicle is the vehicle containing the i-th target component; the data processing module 401 is used for: By statistically analyzing the timestamps of each operation, the current of each operation, the fault triggering information, and the false triggering information of the target function, the operating characteristics of the motor are obtained. Based on the timestamps of each operation and the temperature, rainfall, and location information of the environment in which the i-th target component is located during each operation, the operational characteristics of the environment are determined. Based on the timestamps of each run, the vehicle's speed and acceleration during each run, the operational characteristics of this driving behavior are determined.

[0187] Optionally, the comprehensive evaluation parameters include the mean health score and mean time between failures (MTBF), and the life assessment module 402 is used for: Based on the motor operating characteristics of the i-th target component, the motor wear index of the i-th target component is determined, which is used to represent the degree of wear of the motor of the i-th target component. Based on the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component, predict the individual health score and individual fault-free time of the i-th target component; Calculate the average health score of each of the M target components to obtain the average health score of the M target components, and calculate the average time between failures (MTBF) of each of the M target components to obtain the average time between failures (MTBF) of the M target components.

[0188] Optionally, the life assessment module 402 is specifically used for: Based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component, the failure risk probability of the i-th target component is predicted. The failure risk probability is used to represent the possibility that the i-th target component will fail in the second time period after the current time. Based on the motor operating characteristics, failure risk probability, and motor wear index of the i-th target component, an individual health score is determined; Input the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component into the life assessment model, and output the individual fault-free time of the i-th target component through the life assessment model; In addition, the comprehensive evaluation parameters also include the average failure probability, and the life assessment module 402 is also used for: Calculate the average failure probability of M target components to obtain the average failure probability.

[0189] Optionally, the life assessment module 402 is specifically used for: Input the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component into the fault risk prediction model, and output the fault risk probability of the i-th target component through the fault risk prediction model; In addition, the comprehensive evaluation parameters also include the target early warning frequency, and the life assessment module 402 is also used for: If the failure risk probability of the i-th target component is greater than the preset probability threshold, at least one target feature is output by the failure risk prediction model. The at least one target feature is an operational feature that causes the failure risk probability to be greater than the preset probability threshold. Generate target warning labels based on at least one target feature; The frequency of target warnings is obtained by counting the number of times target warning labels are generated.

[0190] Optionally, the comprehensive evaluation parameters also include the average health score and mean time between failures (MTBF) for different user groups, with different target components associated with different user groups. The lifespan assessment module 402 is also used for: For any user group, calculate the average health score of the individual target components associated with that user group to obtain the average health score of that user group, and calculate the average mean time between failures (MTBF) of the individual target components associated with that user group to obtain the mean time between failures (MTBF) of that user group.

[0191] Optionally, the optimization suggestion module 403 is specifically used for: Obtain the target rule base, which includes suggestion information for different health states; Based on comprehensive evaluation parameters, lifetime optimization information is determined from the target rule base.

[0192] Optionally, the target rule base includes multiple lifetime recommendation rules, each of which includes triggering conditions and recommendation information. The optimization recommendation module 403 is specifically used for: Match the target recommendation rule that matches the triggering conditions and comprehensive evaluation parameters from multiple lifetime recommendation rules; The recommendation information in the target recommendation rule is identified as lifetime optimization information.

[0193] In this embodiment, data from M target components during operation is collected to form historical operational data for each component. Then, for any given target component, its multi-dimensional characteristics are first determined based on its historical operational data, including motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics. Next, based on these characteristics, comprehensive evaluation parameters for the M target components are determined, which assess the overall health status and overall service life of the M target components. Finally, targeted lifespan optimization information is analyzed based on these comprehensive evaluation parameters. Thus, by determining the multi-dimensional operational characteristics of each target component, accurate determination of comprehensive evaluation parameters for all target components can be achieved. Based on these accurate comprehensive evaluation parameters, more effective lifespan optimization suggestions can be determined, improving the accuracy and effectiveness of lifespan optimization suggestions.

[0194] It should be noted that the above-described lifespan optimization information determination device only uses the above-described division of functional modules as an example when determining lifespan optimization information for a target component. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0195] The functional units and modules in the above embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of the embodiments of this application.

[0196] The apparatus for determining lifetime optimization information and the method for determining lifetime optimization information provided in the above embodiments belong to the same concept. The specific working process and technical effects of the units and modules in the above embodiments can be found in the method embodiments section, and will not be repeated here.

[0197] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 5 As shown, the computer device 500 includes: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, it implements the steps in the lifespan optimization information determination method in the above embodiments.

[0198] Computer device 500 can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, computer device 500 can be a network server. Those skilled in the art will understand that... Figure 5 This is merely an example of computer device 500 and does not constitute a limitation on computer device 500. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0199] Processor 50 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0200] In some embodiments, memory 51 may be an internal storage unit of computer device 500, such as a hard disk or memory of computer device 500. In other embodiments, memory 51 may be an external storage device of computer device 500, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on computer device 500. Furthermore, memory 51 may include both internal and external storage units of computer device 500. Memory 51 is used to store operating system, application programs, boot loader, data, and other programs. Memory 51 may also be used to temporarily store data that has been output or will be output.

[0201] This application also provides a vehicle that includes a target component equipped with a target optimization method, the target optimization method being determined based on the lifetime optimization information in the above-described lifetime optimization information determination method.

[0202] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the various method embodiments described above.

[0203] This application provides a computer program product that, when run on a computer, causes the computer to perform the steps described in the various method embodiments above.

[0204] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above method embodiments of this application can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage devices. The computer-readable storage medium mentioned in this application can be a non-volatile storage medium; in other words, it can be a non-transient storage medium.

[0205] It should be understood that all or part of the steps of the above embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented in whole or in part as a computer program product. The computer program product includes one or more computer instructions. The computer instructions can be stored in the above-described computer-readable storage medium.

[0206] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0207] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0208] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0209] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0210] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining lifetime optimization information, characterized in that, The method includes: Analyze the historical operating data of the i-th target component among M target components to determine the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component; Based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the M target components, comprehensive evaluation parameters for the M target components are determined. These comprehensive evaluation parameters are used to describe the overall health status and overall service life of the M target components. Based on the comprehensive evaluation parameters, lifespan optimization information for the target component is determined.

2. The method as described in claim 1, characterized in that, The historical operating data includes the timestamps of each operation of the i-th target component within the first time period, the operating current of the motor in the i-th target component, fault triggering information, false triggering information of the target function, the temperature, rainfall, and location information of the environment in which the i-th target component is located during each operation, and the speed and acceleration of the vehicle during each operation, wherein the vehicle is the vehicle in which the i-th target component is located; the analysis of the historical operating data of the i-th target component among the M target components to determine the motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics of the i-th target component includes: The motor operating characteristics are obtained by statistically analyzing the timestamps of each operation, the current of each operation, the fault triggering information, and the false triggering information of the target function. Based on the timestamps of each operation and the temperature, rainfall, and location information of the environment in which the i-th target component is located during each operation, the environmental operation characteristics are determined. The driving behavior characteristics are determined based on the timestamps of each run, the vehicle's speed and acceleration during each run.

3. The method as described in claim 1, characterized in that, The comprehensive evaluation parameters include the average health score and the average time between failures (MTBF). The determination of the comprehensive evaluation parameters for the M target components based on their motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics includes: Based on the motor operating characteristics of the i-th target component, the motor wear index of the i-th target component is determined, and the motor wear index is used to represent the degree of wear of the motor of the i-th target component; Based on the motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component, predict the individual health score and individual fault-free time of the i-th target component; Calculate the average health score of the individual M target components to obtain the average health score of the M target components, and calculate the average time between failures (MTBF) of the individual M target components to obtain the average time between failures (MTBF) of the M target components.

4. The method as described in claim 3, characterized in that, The prediction of the individual health score and individual fault-free time of the i-th target component based on its motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index includes: Based on the motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component, the failure risk probability of the i-th target component is predicted. The failure risk probability is used to represent the possibility that the i-th target component will fail in the second time period after the current moment. Based on the motor operating characteristics of the i-th target component, the failure risk probability, and the motor wear index, the individual health score is determined; The motor operating characteristics, environmental operating characteristics, driving behavior operating characteristics, and motor wear index of the i-th target component are input into the life assessment model, and the individual fault-free time of the i-th target component is output through the life assessment model. Furthermore, the comprehensive evaluation parameters also include the average failure probability, and the method further includes: The average failure probability is obtained by calculating the average failure risk probability of the M target components.

5. The method as described in claim 4, characterized in that, The prediction of the failure risk probability of the i-th target component based on its motor operating characteristics, environmental operating characteristics, and driving behavior operating characteristics includes: The motor operation characteristics, environmental operation characteristics, and driving behavior operation characteristics of the i-th target component are input into the fault risk prediction model, and the fault risk prediction model outputs the fault risk probability of the i-th target component. Furthermore, the comprehensive evaluation parameters also include the target early warning frequency, and the method further includes: If the failure risk probability of the i-th target component is greater than a preset probability threshold, the failure risk prediction model outputs at least one target feature, wherein the at least one target feature is an operational feature that causes the failure risk probability to be greater than the preset probability threshold. Based on the at least one target feature, a target warning label is generated; The target warning frequency is obtained by counting the number of times the target warning label is generated.

6. The method as described in claim 3, characterized in that, The comprehensive evaluation parameters also include the average health score and mean time between failures (MTBF) for different user groups, with different target components associated with different user groups. The method further includes: For any user group, calculate the average health score of the individual target components associated with the user group to obtain the average health score corresponding to the user group, and calculate the average time between failures (MTBF) of the individual target components associated with the user group to obtain the average time between failures (MTBF) corresponding to the user group.

7. The method according to any one of claims 1-6, characterized in that, The determination of lifespan optimization information for the target component based on the comprehensive evaluation parameters includes: Obtain the target rule base, which includes suggestion information under different health states; Based on the comprehensive evaluation parameters, the lifetime optimization information is determined from the target rule base.

8. The method as described in claim 7, characterized in that, The target rule base includes multiple lifetime recommendation rules. Each lifetime recommendation rule includes triggering conditions and recommendation information. The determination of the lifetime optimization information from the target rule base based on the comprehensive evaluation parameters includes: From the multiple lifetime recommendation rules, match the target recommendation rule whose triggering condition matches the comprehensive evaluation parameter; The recommendation information in the target recommendation rule is determined as the lifetime optimization information.

9. A computer device, characterized in that, The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that, The vehicle includes a target component equipped with a target optimization method, the target optimization method being determined based on lifetime optimization information as described in any one of claims 1 to 8.

Images