Method, device, equipment and medium for predicting life of vehicle corner module

Abstract

The application provides a life prediction method, device, equipment and medium of a vehicle corner module. The method constructs a life sample data set of an electronic component for each type of electronic component, determines a target life distribution model matched with the type of electronic component, and performs parameter estimation on the target life distribution model based on the life sample data set to construct a target life distribution model containing estimated parameter information. Based on a preset life distribution correlation model, the target life distribution models of various types of electronic components are correlated to construct a component joint life distribution model. Life sampling is performed on the component joint life distribution model to obtain a joint life sample set. Based on the joint life sample set and the internal connection logic of the corner module, a corner module life sample set is generated. The life of the vehicle corner module is predicted based on the corner module life sample set. The application embodiment can improve the prediction accuracy of the life of the corner module.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically, to a method, apparatus, device, and storage medium for predicting the lifespan of a vehicle corner module. Background Technology

[0002] With the continuous development of drive-by-wire chassis technology, vehicle chassis systems are gradually evolving from traditional mechanical structures to drive-by-wire architectures centered around electric motors. Drive, braking, steering, and suspension systems no longer rely on mechanical transmission but instead transmit control commands via electrical signals, with the motor handling the control. Based on this, the corner module, as a core execution unit integrating drive, braking, steering, and suspension systems, has emerged.

[0003] The electronic components in a corner module need to operate collaboratively, and their lifespans are significantly correlated. In related technologies, predictions of corner module lifespan are mostly based on the assumption of component independence, which is difficult to apply in scenarios where components are highly correlated and coupled. For example, corner modules are subjected to the combined effects of temperature, vibration, and electromagnetic fields over long periods, and there are often correlations between electronic components such as motors, sensors, and controllers. Therefore, how to accurately assess the lifespan of corner modules is one of the urgent problems to be solved. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, device and storage medium for predicting the lifespan of a vehicle corner module, in order to at least solve the problems existing in the related art.

[0005] Specifically, this application is implemented through the following technical solution: This application provides a method for predicting the lifespan of a vehicle corner module, wherein the vehicle corner module includes multiple vehicle subsystems, and each vehicle subsystem includes various electronic components; the method includes: For each type of electronic component, obtain a lifetime sample dataset of the electronic component; A target lifetime distribution model matching the type of electronic component is determined, and parameters of the target lifetime distribution model are estimated based on the lifetime sample dataset to obtain a target lifetime distribution model containing estimated parameter information. Based on a pre-defined lifetime distribution correlation model, the target lifetime distribution models of various electronic components are correlated to construct a joint lifetime distribution model for the components; the joint lifetime distribution model for the components is used to characterize the correlation between the lifetimes of various electronic components. The joint lifetime distribution model of the components is sampled to obtain a joint lifetime sample set. Based on the joint lifetime sample set and the internal connection logic of the corner module, a corner module lifetime sample set is generated. The lifetime of the vehicle corner module is predicted based on the corner module lifetime sample set.

[0006] This application also provides a life prediction device for a vehicle corner module, wherein the vehicle corner module includes multiple vehicle subsystems, and each vehicle subsystem includes various electronic components; the device includes: A lifetime sample dataset construction module is used to obtain a lifetime sample dataset for each type of electronic component. The component lifetime distribution model construction module is used to determine the target lifetime distribution model that matches the type of electronic component, and to perform parameter estimation on the target lifetime distribution model based on the lifetime sample dataset to obtain the target lifetime distribution model containing the estimated parameter information. The joint lifetime distribution model construction module is used to associate the target lifetime distribution models of various electronic components based on a preset lifetime distribution correlation model to construct a joint lifetime distribution model of the components; the joint lifetime distribution model of the components is used to characterize the correlation between the lifetimes of various electronic components. The corner module life prediction module is used to perform life sampling on the joint life distribution model to obtain a joint life sample set, and generate a corner module life sample set based on the joint life sample set and the internal connection logic of the corner module, and predict the life of the vehicle corner module based on the corner module life sample set.

[0007] This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the life prediction method for the vehicle corner module described in any of the foregoing embodiments.

[0008] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the life prediction method for the vehicle corner module described in any of the foregoing embodiments.

[0009] This application also provides a computer program product, including a computer program that, when run by a processor, performs the steps of any of the possible vehicle corner module life prediction methods described above.

[0010] The technical solutions provided by the embodiments of this application may include the following beneficial effects: In this embodiment, considering the complex structural characteristics of corner modules with multiple systems and multiple electronic components, a mapping from the lifetime distribution of electronic components to the system-level lifetime is achieved by using a preset lifetime distribution correlation model. This provides a descriptive framework for the lifetime dependency of multiple electronic components, thereby enabling the acquisition of corner module reliability and lifetime under complex system structures and improving the applicability of corner module lifetime prediction methods under complex structures.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present application of a method for predicting the lifespan of a vehicle corner module; Figure 2 This is a flowchart illustrating an exemplary embodiment of the present application of constructing a joint lifetime distribution model for components; Figure 3 This is a flowchart illustrating an exemplary embodiment of the present application of generating a corner module lifetime sample set; Figure 4 This is a schematic diagram of the structure of a life prediction device for a vehicle corner module according to an exemplary embodiment of this application; Figure 5 This is a schematic diagram of the structure of another vehicle corner module life prediction device shown in an exemplary embodiment of this application; Figure 6 This is a hardware structure diagram of a computer device illustrated in an exemplary embodiment of this application. Detailed Implementation

[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0014] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0015] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0016] With the continuous development of drive-by-wire chassis technology, vehicle chassis systems are gradually evolving from traditional mechanical structures to drive-by-wire architectures centered around electric motors. Drive, braking, steering, and suspension systems no longer rely on mechanical transmission but instead transmit control commands via electrical signals, with the motor handling the control. Based on this, the corner module, as a core execution unit integrating drive, braking, steering, and suspension systems, has emerged.

[0017] The electronic components in a corner module need to operate collaboratively, and their lifespans are significantly correlated. In related technologies, predictions of corner module lifespan are mostly based on the assumption of component independence, which is difficult to apply in scenarios where components are highly correlated and coupled. For example, corner modules are subjected to the combined effects of temperature, vibration, and electromagnetic fields over long periods, and there are often correlations between electronic components such as motors, sensors, and controllers. Therefore, how to accurately assess the lifespan of corner modules is one of the urgent problems to be solved.

[0018] Based on the above research, this disclosure provides a method for predicting the lifespan of a vehicle corner module. The vehicle corner module includes multiple vehicle subsystems, and each vehicle subsystem includes various electronic components. The method first obtains a lifespan sample dataset for each type of electronic component, determines a target lifespan distribution model matching the electronic component type, and estimates the parameters of the target lifespan distribution model based on the lifespan sample dataset to obtain a target lifespan distribution model containing estimated parameter information. Then, based on a preset lifespan distribution association model, the target lifespan distribution models of various electronic components are associated to construct a joint component lifespan distribution model. The joint component lifespan distribution model is used to characterize the correlation between the lifespans of various electronic components. Finally, lifespan sampling is performed on the joint lifespan distribution model to obtain a joint lifespan sample set. Based on the joint lifespan sample set and the internal connection logic of the corner module, a corner module lifespan sample set is generated, and the lifespan of the vehicle corner module is predicted based on the corner module lifespan sample set.

[0019] In this embodiment, considering the complex structural characteristics of corner modules with multiple systems and multiple electronic components, a mapping from the lifetime distribution of electronic components to the system-level lifetime is achieved by using a preset lifetime distribution correlation model. This provides a descriptive framework for the lifetime dependency of multiple electronic components, thereby enabling the acquisition of corner module reliability and lifetime under complex system structures and improving the applicability of corner module lifetime prediction methods under complex structures.

[0020] To facilitate understanding of this embodiment, a detailed description of the lifespan prediction method for a vehicle corner module disclosed in this disclosure is provided first. The execution entity of the lifespan prediction method for a vehicle corner module provided in this disclosure is generally a computer device. This computer device can be a server, which can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms. In other embodiments, the computer device can also be a terminal device, which can be a mobile device, terminal, handheld device, computing device, vehicle-mounted device, etc.

[0021] In other embodiments, the method can also be applied to an implementation environment consisting of computer equipment and servers, or an implementation environment consisting of terminal equipment and servers. Furthermore, the lifespan prediction method for the vehicle corner module can also be implemented by a processor calling computer-readable instructions stored in memory.

[0022] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0023] The following is a conceptual introduction to the corner module, which comprises multiple vehicle subsystems. These subsystems typically consist of four parts: a drive system, a braking system, a steering system, and a suspension system. Each system shares a basic structural consistency, primarily consisting of three types of electronic components: actuators, sensors, and controllers. The actuators translate control commands into actual mechanical outputs, the sensors acquire real-time vehicle operating status and environmental information, and the controllers process the information collected by the sensors and generate corresponding control commands. All systems are connected in series, and the electronic components within each system are also connected in series.

[0024] Please see the appendix Figure 1 The above is a flowchart illustrating a method for predicting the lifespan of a vehicle corner module, as shown in an exemplary embodiment of this application. Figure 1 As shown, the life prediction method for the vehicle corner module in this embodiment includes the following steps S101~S103: S101: For each type of electronic component, construct a lifetime sample dataset of the electronic component.

[0025] In this step, when constructing a lifetime sample dataset for each type of electronic component, the specific steps (A) to (B) are included: (A) For each type of electronic component, based on the degradation influencing factors corresponding to the electronic component, determine the stochastic process mathematical model corresponding to the degradation influencing factors, and construct an electronic component lifetime degradation model based on the stochastic process mathematical model.

[0026] Here, for each type of electronic component, a mathematical model corresponding to its degradation characteristics is established to mathematically describe the actual degradation process of the electronic component, thereby improving the ability of the electronic component lifetime degradation model to represent the actual operating state.

[0027] As mentioned above, each system includes motor components, sensor components, and controller components. Therefore, the following section will introduce the construction of electronic component life degradation models for the above three types of electronic components.

[0028] (1) For motor components.

[0029] For motor components, the main sources of factors affecting their lifespan degradation are temperature and the decrease in motor output torque. Therefore, the process of constructing the electronic component lifespan degradation model for motor components includes the following steps (1.1) to (1.3): (1.1) For the motor component, based on the temperature factor, the stochastic process mathematical model matching the temperature factor is determined to be the Wiener process, and based on the Wiener process, a first motor degradation model characterizing temperature rise degradation is constructed.

[0030] It is understandable that the motor temperature exhibits both continuous change and random fluctuation during operation, and the Wiener process can simultaneously describe the characteristics of continuous change and random disturbance of the electronic component state, as shown in formula (1), which is the expression for the Wiener process: (1) in, Indicates time The degenerate state quantity, This is the initial degenerate state. This is the drift coefficient, used to describe the average rate of degradation. The diffusion coefficient is used to characterize the intensity of random fluctuations during the degradation process. This is the standard Wiener process.

[0031] (1.2) Based on the motor output torque factor, the stochastic process mathematical model matching the motor output torque factor is determined to be a gamma process, and based on the gamma process, a second motor degradation model characterizing the attenuation of motor output torque is constructed.

[0032] It is easy to understand that the output torque of the motor gradually decreases over time, exhibiting a monotonically decreasing and irreversible degradation characteristic. Therefore, a gamma process can be used to simulate and describe the monotonically cumulative degradation behavior of the motor, as shown in formula (2), which is the expression of the gamma process: (2) in, Indicates the time interval Increment of degradation state within, This is a shape function that monotonically increases with time and is used to describe the rate of degradation accumulation. is a scale parameter used to characterize the dispersion of the degradation increment. This represents the gamma distribution.

[0033] (1.3) Based on the first motor degradation model and the second motor degradation model, determine the motor component life degradation model.

[0034] Thus, after obtaining the first motor degradation model and the second motor degradation model, the life degradation model of motor components can be determined.

[0035] (B) Simulate the life degradation model of the electronic component to obtain a life sample dataset of the electronic component.

[0036] (2) For sensor components.

[0037] For sensor components, the main sources of lifespan degradation are zero-point drift and noise. Therefore, the process of constructing the electronic component lifespan degradation model for sensor components includes the following steps (2.1) to (2.3): (2.1) For the sensor element, based on the zero-point drift factor, the stochastic process mathematical model matching the zero-point drift factor is determined to be the Wiener process, and based on the Wiener process, a first sensor degradation model is constructed.

[0038] The zero-point drift process is characterized by random walks, upward and downward movement, and continuous change. Therefore, the Wiener process is used for modeling.

[0039] Here, please refer to formula (1) above for the expression of the Wiener process, which will not be repeated here.

[0040] (2.2) Based on the noise factors, determine the random process mathematical model that matches the noise factors as an inverse Gaussian process, and construct a second sensor degradation model based on the inverse Gaussian process.

[0041] It is understandable that the sensor noise amplitude gradually increases over time, which is a non-negative, cumulative degradation process. The degradation process can be mathematically modeled using an inverse Gaussian process, which can be expressed by formula (3): (3) in, Here, represents the drift parameter, indicating the average degradation rate. These are shape parameters used to control the intensity of random fluctuations in the degradation path. This indicates an inverse Gaussian distribution.

[0042] (2.3) Based on the first sensor degradation model and the second sensor degradation model, determine the sensor element lifetime degradation model.

[0043] Thus, after constructing the first sensor degradation model and the second sensor degradation model, the sensor element lifetime degradation model can be obtained.

[0044] (3) For controller components.

[0045] For controller components, the main sources of their lifespan degradation are the increase in control delay and the fluctuation of control error. Therefore, the process of constructing the electronic component lifespan degradation model for controller components includes the following steps (3.1) to (3.3): (3.1) For the controller element, based on the control delay factor, determine the stochastic process mathematical model that matches the control delay factor as a gamma process, and construct a first controller degradation model based on the gamma process; or based on the control delay factor, determine the stochastic process mathematical model that matches the control delay factor as an inverse Gaussian process, and construct a first controller degradation model based on the inverse Gaussian process.

[0046] Here, since the control delay usually shows an overall increasing trend with the running time and may be accompanied by abrupt changes, its matching stochastic process mathematical model can be a gamma process or an inverse Gaussian process.

[0047] The gamma process is shown in formula (2), and will not be elaborated here; the inverse Gaussian process is shown in formula (3), and will not be elaborated here.

[0048] (3.2) Based on the control error factors, determine the stochastic process mathematical model that matches the control error factors as the Wiener process, and construct a second controller degradation model based on the Wiener process.

[0049] It is understandable that control errors typically fluctuate within a certain range; therefore, the Wiener process can be used as the matching stochastic process mathematical model.

[0050] (3.3) Based on the first controller degradation model and the second controller degradation model, determine the controller component lifetime degradation model.

[0051] Thus, after constructing the first controller degradation model and the second controller degradation model, the lifetime degradation model of the controller components can be determined.

[0052] In this embodiment of the application, by selecting a stochastic process mathematical model that matches the degradation mechanism of each type of electronic component and its corresponding degradation mechanism, the degradation process of the electronic component is simulated, which can reflect the actual degradation process of the electronic component.

[0053] Furthermore, for each type of electronic component, after obtaining the electronic component lifespan degradation model, the electronic component lifespan degradation model can be simulated to obtain the electronic component lifespan sample dataset. Specifically, the lifespan degradation model can be simulated within a preset lifespan time interval to obtain the degradation state trajectory of the electronic component. The degradation state trajectory includes the degradation state corresponding to each lifespan time point of the electronic component within the preset lifespan time interval. Then, based on the lifespan time points corresponding to degradation states greater than a preset degradation state threshold, the electronic component lifespan sample dataset is generated.

[0054] The preset lifespan time interval can be set according to actual needs, such as one month, one year, ten years, etc., without limitation. Within the preset lifespan time interval, the lifespan degradation model is simulated to obtain the degradation state trajectory of the electronic component. Here, the preset lifespan time interval includes multiple lifespan times, and the degradation state trajectory includes the degradation state corresponding to each lifespan time.

[0055] Furthermore, for each lifetime corresponding to the degradation state, it is determined whether the degradation state is not greater than the degradation state threshold. When the degradation state of the electronic component is equal to or greater than the degradation state threshold for the first time, the corresponding lifetime is taken as the lifetime of the electronic component.

[0056] As shown in formula (4), this is the expression for the degenerate state function: (4) in, This is the degradation state threshold, used to characterize the state threshold of electronic component failure.

[0057] It should be noted that the degenerate state function in formula (4) This is a unified representation of the target lifetime degradation model for various electronic components mentioned above, and the corresponding degradation state thresholds are different for different types of electronic components.

[0058] In this way, by performing multiple simulations on the life degradation models of various electronic components, we can obtain life sample datasets for motor components, sensor components, and controller components.

[0059] In some implementations, by changing the random perturbation terms or initial conditions, the generated lifetime sample datasets for various electronic components can cover a wide range of degradation states, thereby enhancing the richness of the lifetime sample datasets.

[0060] S102: Determine a target lifetime distribution model that matches the type of electronic component, and perform parameter estimation on the target lifetime distribution model based on the lifetime sample dataset to obtain a target lifetime distribution model containing estimated parameter information.

[0061] After obtaining the lifetime sample dataset of electronic components such as motors, sensors, and controllers using the above method, if the lifetime samples are used only as discrete data, it is difficult to characterize the randomness and uncertainty of the electronic component lifetime, and it cannot provide a continuous probabilistic description for corner module lifetime prediction. In addition, the lifetime distribution of different types of electronic components is different. If there is a lack of unified probability distribution modeling, it will limit the accuracy of subsequent system lifetime prediction. Therefore, in this embodiment of the application, for step S101, after obtaining the lifetime sample dataset of electronic components, a target lifetime distribution model matching the type of electronic component is first determined, and based on the lifetime sample dataset, the parameters of the target lifetime distribution model are estimated to obtain a target component lifetime distribution model containing estimated parameter information.

[0062] In other words, based on the lifetime sample datasets of various electronic components, the lifetime distribution of different types of electronic components can be modeled by probability statistics, and the corresponding distribution parameters can be estimated, thereby obtaining the lifetime distribution model of various electronic components.

[0063] For example, the lifetime sample dataset of a certain type of electronic component is shown in formula (5): (5) in, Indicates the first One lifetime sample.

[0064] Target lifetime distribution model for each type of electronic component The maximum likelihood estimation method is used to evaluate its parameters. Solve for it. The likelihood function is used. Defined as formula (6): (6) By taking the logarithm of the likelihood function, we obtain the log-likelihood function. As shown in formula (7): (7) Equation (7) is transformed into Equation (8) and solved to obtain the parameter estimates of the target lifetime distribution model of the component. : (8) Based on the parameter estimation process of the above formulas (5)-(8), the following section introduces the construction process of the target lifetime distribution model for motor components, sensor components and controller components.

[0065] (I) For motor components.

[0066] As mentioned above, motor components are mainly affected by insulation aging caused by temperature rise and the decay of maximum output torque over time. This results in a characteristic of continuous accumulation of degradation over time and a gradual increase in failure rate. The Weibull distribution can flexibly characterize the law of failure rate change over time under the combined effect of temperature and load. It is suitable for describing the lifetime distribution characteristics dominated by thermo-mechanical coupling degradation. Therefore, the lifetime distribution model for matching motor components is the Weibull distribution model.

[0067] When fitting the parameters of the lifespan distribution model to construct the target lifespan distribution model of the electronic component based on the lifespan sample dataset of the electronic component, the parameters of the Weibull distribution model can be estimated based on the lifespan sample dataset corresponding to the motor component to obtain the first model parameters, and the target lifespan distribution model of the motor component can be generated based on the first model parameters and the Weibull distribution model.

[0068] The expression for the Weibull distribution model is shown in equation (9): (9) in, , For proportional parameters, For shape parameters.

[0069] Specifically, the probability density function of the Weibull distribution shown in formula (9) is shown in formula (10): (10) in, Let be the probability density function of the Weibull distribution. For shape parameters, For proportional parameters, For position parameters.

[0070] Based on the above probability density function, a log-likelihood function is constructed, and the parameters are solved by the maximum likelihood estimation method, as shown in formula (11): (11) in, These are estimated values ​​for the shape parameters. This is an estimated value for the proportional parameter. These are estimated values ​​for the location parameters.

[0071] Optionally, to conform to practical meaning, the position parameters can be adjusted. Apply constraints that do not exceed a certain percentage of the minimum lifetime sample value to avoid unreasonable minimum lifetime offsets.

[0072] (II) For sensor elements and controller elements.

[0073] Since the lifespan of sensor and controller components is affected by a variety of environmental factors, most electronic components fail within a relatively short or medium time. However, a small number of electronic components can continue to operate for a longer period of time. Therefore, a log-normal distribution model can be used to model their lifespan distribution.

[0074] The log-normal distribution function is shown in formula (12): (12) in, It is the standard normal distribution function. It is the mean parameter of the logarithmic lifetime. It is the standard deviation of the logarithmic lifetime. For position parameters.

[0075] Specifically, for a sensor element, the parameters of the log-normal distribution model can be estimated based on the lifetime sample dataset corresponding to the sensor element to obtain second model parameters, and the target lifetime distribution model of the sensor element can be generated based on the second model parameters and the log-normal distribution model.

[0076] Here, based on the lifetime sample dataset corresponding to the sensor element, the parameters of the log-normal distribution model are estimated to obtain the second model parameters. The second model parameters are then substituted into the log-normal distribution model to obtain the target lifetime distribution model of the sensor element.

[0077] Similarly, for a controller element, the parameters of the log-normal distribution model can be estimated based on the lifetime sample dataset corresponding to the controller element to obtain the third model parameters, and the target lifetime distribution model of the controller element can be generated based on the third model parameters and the log-normal distribution model.

[0078] Here, based on the lifetime sample dataset corresponding to the controller element, the parameters of the log-normal distribution model are estimated to obtain the third model parameters. The third model parameters are then substituted into the log-normal distribution model to obtain the target lifetime distribution model of the controller element.

[0079] For the log-normal distribution model, its probability density function is shown in formula (13): (13) in, The mean parameter of the logarithmic lifetime. The standard deviation of the logarithmic lifetime. For position parameters.

[0080] Based on this distribution, the corresponding log-likelihood function is constructed, and the parameters are solved using the maximum likelihood estimation method, as shown in formula (14): (14) in, This is an estimate of the mean parameter. This is the estimate of the standard deviation. These are estimated values ​​for the location parameters.

[0081] Optionally, a constraint not exceeding a certain proportion of the minimum lifetime sample value can be imposed on the position parameter in formula (14) to avoid unreasonable minimum lifetime offset.

[0082] Based on the target lifetime distribution model construction and model parameter estimation of the components described in the above embodiments, the complete lifetime distribution of the motor, sensor and controller are obtained respectively, laying a mathematical foundation for the subsequent step of electronic component correlation modeling based on Coupla function.

[0083] S103: Based on a preset lifetime distribution correlation model, the target lifetime distribution models of various electronic components are correlated to construct a joint lifetime distribution model of components; the joint lifetime distribution model of components is used to characterize the correlation between the lifetimes of various electronic components.

[0084] The preset lifetime distribution correlation model is the Coupla function.

[0085] Here, in the corner module, electronic components such as motors, sensors, and controllers operate under the same conditions and multi-physics coupling, and their life evolution is often correlated. Traditional system life prediction methods usually assume that the life of each electronic component is independent, ignoring the degradation effects caused by environmental factors and the correlation between electronic components. This can easily lead to deviations in system reliability and life assessment results, making it difficult to meet the accuracy requirements of life analysis for complex systems.

[0086] Therefore, in this embodiment, based on the existing target lifetime distribution models, the Copula mathematical modeling method is introduced to model the correlation between the lifetimes of different electronic components. By constructing a multivariate joint lifetime distribution, a unified characterization of the non-independent lifetime characteristics of electronic components is achieved, thereby providing a more realistic and reliable probabilistic model basis for system-level lifetime prediction.

[0087] Specifically, regarding step S103, when constructing a joint lifetime distribution model by associating the target lifetime distribution models of various electronic components based on a preset lifetime distribution correlation model, please refer to [link to relevant documentation]. Figure 2 The flowchart provided for constructing a component joint lifetime distribution model is an exemplary embodiment of this application. Figure 2 As shown, the process includes the following steps S1031~S1033: S1031: Substitute the samples from the lifetime sample datasets of various electronic components into the corresponding target lifetime distribution models for probability integral transformation to generate a set of joint lifetime observations.

[0088] In this step, based on the target lifetime distribution model of each component constructed in the aforementioned embodiments, the lifetime random variables of the motor, sensor, and controller are respectively... , and Their corresponding lifetime distribution functions are respectively , and The lifetime samples of electronic components are transformed using their corresponding lifetime distribution functions and mapped to... Intervals, constructing pseudo-observations Based on the pseudo-observations As joint lifetime observations, as shown in formulas (15) to (17): (15) (16) (17) in, , where is the sample size.

[0089] S1032: Based on the lifetime distribution correlation model and each of the target lifetime distribution models, determine the initial component joint lifetime distribution model.

[0090] Among them, the lifetime distribution correlation model follows Sklar's theorem: Let H Two-dimensional random variable The joint distribution function, and Let each be a marginal distribution function. Then there exists a Copula function.C This makes it possible for all ,have .like and If continuous, then the Copula function It is unique.

[0091] Therefore, according to Sklar's theorem, the initial component joint lifetime distribution model can be expressed as a combination of the component's target lifetime distribution model and the lifetime distribution correlation model (i.e., the Copula function), as shown in formula (18): (18) in, For copula functions, These are the relevant parameters.

[0092] It is understandable that, since there are many types of Copula functions, and since the actual lifespan samples of electronic components in corner modules that are close to failure are relatively few, while the lifespan of most electronic components is concentrated in the normal operating condition or moderate degradation stage, this application uses the Gaussian Copula function to express the lifespan of corner modules. The Gaussian Copula function is shown in formula (19): (19) in, It is the inverse distribution function of the standard normal distribution. Correlation coefficient matrix The three-dimensional multivariate normal distribution function and correlation coefficient matrix As shown in formula (20): (20) in, The correlation coefficient between the motor and the sensor. The correlation coefficient between the motor and the controller. This represents the correlation coefficient between the sensor and the controller.

[0093] S1033: Based on the set of joint lifetime observations, the parameter estimation of the initial component joint lifetime distribution model is performed using the maximum pseudo-likelihood estimation method to obtain the model parameters; the model parameters include the correlation coefficient matrix used to characterize the lifetime of various electronic components.

[0094] Here, the Copula parameters are solved using the joint lifetime observation set and the maximum pseudo-likelihood estimation method. The optimization objective function is shown in Equation (21): (twenty one) in, Let be the density function of Copula. Used to quantitatively characterize the correlation between the lifetimes of electronic components.

[0095] S1034: Based on the correlation coefficient matrix and the initial component joint lifetime distribution model, construct the component joint lifetime distribution model.

[0096] It's easy to understand that after parameter estimation, the correlation coefficient matrix can be obtained. and the correlation coefficient matrix Substituting these values ​​into the initial component joint lifetime distribution model yields the component joint lifetime distribution model.

[0097] S104: Perform lifetime sampling on the joint lifetime distribution model of the components to obtain a joint lifetime sample set, and generate a corner module lifetime sample set based on the joint lifetime sample set and the internal connection logic of the corner module, and predict the lifetime of the vehicle corner module based on the corner module lifetime sample set.

[0098] Regarding step S104, after completing the joint lifetime distribution modeling based on the Copula function in the aforementioned embodiments, how to further map the joint lifetime information of multiple electronic components to the corner module system level to achieve prediction of system lifetime and reliability is a key link in system lifetime analysis.

[0099] Therefore, in this application, based on the constructed component joint lifetime distribution model and combined with the actual structure of the corner module system, relevant lifetime samples are calculated according to the relationship between the system and the corner modules. The lifetime distribution of the corner modules is calculated using statistical methods, thereby achieving lifetime prediction from the electronic component layer to the system layer.

[0100] Regarding step S104, when performing lifetime sampling on the component joint lifetime distribution model to obtain a joint lifetime sample set, correlated joint lifetime samples can be obtained through random sampling. For example, the joint lifetime samples can be represented as... ,in, For motor life, For sensor lifespan, For controller lifespan, i The number of samples.

[0101] In this way, a joint lifetime sample set can be generated.

[0102] The internal connection logic of the corner module refers to the series connection between the drive system, braking system, steering system and suspension system, and the series connection between the sensor elements, motor elements and controller elements within each system.

[0103] Specifically, regarding step S104, when generating the corner module lifetime sample set based on the joint lifetime sample set and the internal connection logic of the corner module, please refer to [link to relevant documentation]. Figure 3 The flowchart provided here is for an exemplary embodiment of this application, showing how to generate a sample set of corner module lifetimes. Figure 3 As shown, the steps S1041~S1043 may be included: S1041: For each joint lifetime sample, determine the minimum lifetime of each electronic component of each system in the joint lifetime sample, and take the minimum lifetime as the system lifetime of the system.

[0104] Here, because the electronic components within each system of the corner module work together in series to complete their respective functions, when any one of these electronic components fails, the entire system fails. Therefore, the system's first... i Sub-simulation lifetime Defined as the minimum lifespan of its internal electronic components, as shown in formula (22): (twenty two) In formula (22), for any system, the system is considered to be in failure when any electronic component inside it fails.

[0105] S1042: The minimum value among the system lifetimes of each system is determined as the corner module lifetime corresponding to the joint lifetime sample.

[0106] As mentioned earlier, the corner module consists of four systems: drive, braking, steering, and suspension, all of which are connected in series. If any one of these systems fails, the overall function of the corner module will be affected.

[0107] Therefore, in the i In this simulation, the lifespan of the corner module... This can be expressed as formula (23): (twenty three) in, For the first i The lifespan of the drive system in this simulation. For the first i The lifespan of the braking system in this simulation For the first i The lifespan of the steering system in this simulation. For the first i The lifespan of the suspension system in this simulation.

[0108] S1043: Generate the corner module lifetime sample set based on the corner module lifetime corresponding to each joint lifetime sample.

[0109] In this way, the corresponding corner module lifetime can be determined for each joint lifetime sample. Based on the corner module lifetimes corresponding to each joint lifetime sample, a corner module lifetime sample set can be generated.

[0110] It is understandable that since the corner module lifetime sample set includes multiple corner module lifetime samples, the distribution of corner module lifetimes can be determined. For example, the B10 lifetime of a corner module refers to the time point in the corner module lifetime distribution where the reliability is 0.9, which is the lifetime value at which 10% of the samples fail.

[0111] Optionally, after determining the corner module lifetime sample set, a preset lifetime time interval can also be obtained; the preset lifetime time interval includes multiple lifetime times, and for each lifetime time, the probability that the lifetime value in the corner module lifetime sample set is greater than the lifetime time is determined, and the reliability value of the corner module is determined based on the probability, and a reliability distribution curve is generated based on the reliability values ​​corresponding to each lifetime time; the reliability distribution curve is used to characterize the trend of the corner module's reliability changing with lifetime time.

[0112] In this embodiment of the application, at a given time Below, the reliability of the corner module Defined as the probability that the corner module's lifetime is greater than the given time, as shown in formula (24): (twenty four) in, This refers to the lifespan of the corner module.

[0113] By statistical analysis over time The proportion of samples that have not yet failed is used to obtain the reliability curves of the corner module at different time scales, as shown in formula (25): (25) in, For indicator functions, This represents the number of samples in the corner module lifetime sample set.

[0114] Corresponding to the aforementioned embodiments of the life prediction method for vehicle corner modules, this application also provides embodiments of a life prediction device for vehicle corner modules.

[0115] Please refer to Figure 4 This is a schematic diagram illustrating the structure of a vehicle corner module life prediction device according to an exemplary embodiment of this application. Figure 4 As shown, the life prediction device 400 for the vehicle corner module includes: Lifetime sample dataset construction module 410 is used to construct a lifetime sample dataset for each type of electronic component. The component lifetime distribution model construction module 420 is used to determine a target lifetime distribution model that matches the type of electronic component, and to perform parameter fitting on the target lifetime distribution model based on the lifetime sample dataset to construct the target lifetime distribution model; The joint lifetime distribution model construction module 430 is used to associate the target lifetime distribution models of various electronic components based on a preset lifetime distribution correlation model to construct a joint lifetime distribution model of components; the joint lifetime distribution model of components is used to characterize the correlation between the lifetimes of various electronic components. The corner module life prediction module 440 is used to perform life sampling on the joint life distribution model to obtain a joint life sample set, and generate a corner module life sample set based on the joint life sample set and the internal connection logic of the corner module, and predict the life of the vehicle corner module based on the corner module life sample set.

[0116] In some implementations, the lifetime sample dataset construction module 410 is specifically used for: For each type of electronic component, based on the degradation influencing factors corresponding to the electronic component, a stochastic process mathematical model corresponding to the degradation influencing factors is determined, and based on the stochastic process mathematical model, an electronic component lifetime degradation model is constructed. The lifespan degradation model of the electronic component is simulated to obtain a lifespan sample dataset of the electronic component.

[0117] In some embodiments, the degradation factors of the motor include temperature factors and motor output torque factors; the life sample dataset construction module 410 is specifically used for: For the motor component, based on the temperature factor, the stochastic process mathematical model matching the temperature factor is determined to be the Wiener process, and based on the Wiener process, a first motor degradation model characterizing temperature rise degradation is constructed. Based on the motor output torque factor, the stochastic process mathematical model matching the motor output torque factor is determined to be a gamma process, and based on the gamma process, a second motor degradation model characterizing the attenuation of motor output torque is constructed. Based on the first motor degradation model and the second motor degradation model, a motor component life degradation model is determined.

[0118] In some embodiments, the degradation factors of the sensor element include zero-point drift and noise; the lifetime sample dataset construction module 410 is specifically used for: For the sensor element, based on the zero-point drift factor, the stochastic process mathematical model matching the zero-point drift factor is determined to be the Wiener process, and based on the Wiener process, a first sensor degradation model is constructed. Based on the noise factors, the mathematical model of the stochastic process that matches the noise factors is determined to be an inverse Gaussian process, and a second sensor degradation model is constructed based on the inverse Gaussian process. Based on the first sensor degradation model and the second sensor degradation model, a sensor element lifetime degradation model is determined.

[0119] In some embodiments, the degradation factors of the controller element include increased control delay and control error fluctuation; the lifetime sample dataset construction module 410 is specifically used for: For the controller element, based on the control delay factor, a stochastic process mathematical model matching the control delay factor is determined to be a gamma process, and a first controller degradation model is constructed based on the gamma process; or based on the control delay factor, a stochastic process mathematical model matching the control delay factor is determined to be an inverse Gaussian process, and a first controller degradation model is constructed based on the inverse Gaussian process. Based on the control error factors, the stochastic process mathematical model matching the control error factors is determined to be the Wiener process, and a second controller degradation model is constructed based on the Wiener process. Based on the first controller degradation model and the second controller degradation model, a controller component lifetime degradation model is determined.

[0120] In some implementations, the lifetime sample dataset construction module 410 is specifically used for: Within a preset lifetime time interval, the lifetime degradation model is simulated to obtain the degradation state trajectory of the electronic component; the degradation state trajectory includes the degradation state of the electronic component at each lifetime time point within the preset lifetime time interval. A lifetime sample dataset of the electronic component is generated based on the lifetime time points corresponding to degradation states that are greater than a preset degradation state threshold.

[0121] In some embodiments, the lifetime distribution model matched with the motor component is a Weibull distribution model; the component lifetime distribution model construction module 420 is specifically used for: Based on the lifetime sample dataset corresponding to the motor component, the parameters of the Weibull distribution model are estimated to obtain the first model parameters. Based on the first model parameters and the Weibull distribution model, the target lifetime distribution model of the motor component is generated.

[0122] In some embodiments, the lifetime distribution model matched with the sensor element is a log-normal distribution model; the element lifetime distribution model construction module 420 is specifically used for: Based on the lifetime sample dataset corresponding to the sensor element, the parameters of the log-normal distribution model are estimated to obtain the second model parameters. Based on the second model parameters and the log-normal distribution model, the target lifetime distribution model of the sensor element is generated.

[0123] In some embodiments, the lifetime distribution model matched with the controller element is a log-normal distribution model; the element lifetime distribution model construction module 420 is specifically used for: Based on the lifetime sample dataset corresponding to the controller element, the parameters of the log-normal distribution model are estimated to obtain the third model parameters. Based on the third model parameters and the log-normal distribution model, the target lifetime distribution model of the controller element is generated.

[0124] In some implementations, the joint lifetime distribution model construction module 430 is specifically used for: The samples from the lifetime sample datasets of various electronic components are substituted into the corresponding lifetime distribution models for probability integral transformation to generate a joint lifetime observation set. Based on the lifetime distribution correlation model and each of the target lifetime distribution models, the initial component joint lifetime distribution model is determined; Based on the set of joint lifetime observations, the parameter estimation of the initial component joint lifetime distribution model is performed using the maximum pseudo-likelihood estimation method to obtain the model parameters; the model parameters include the correlation coefficient matrix used to characterize the lifetime of various electronic components. Based on the correlation coefficient matrix and the initial component joint lifetime distribution model, the component joint lifetime distribution model is constructed.

[0125] In some implementations, the internal connection logic of the corner module refers to the series connection between the drive system, braking system, steering system and suspension system, and the series connection between the sensor elements, motor elements and controller elements within each system.

[0126] In some embodiments, the joint lifetime sample set includes multiple joint lifetime samples; the joint lifetime samples include the lifetime of each electronic component in the corner module; the corner module lifetime prediction module 440 is specifically used for: For each joint lifetime sample, the minimum lifetime of each electronic component in each system in the joint lifetime sample is determined, and the minimum value is taken as the system lifetime of the system. The minimum value among the system lifetimes of each system is determined as the corner module lifetime corresponding to the joint lifetime sample; The corner module lifetime sample set is generated based on the corner module lifetime corresponding to each joint lifetime sample.

[0127] Please refer to Figure 5 This is a schematic diagram illustrating the structure of another vehicle corner module life prediction device according to an exemplary embodiment of this application. Figure 5 As shown, the life prediction device 400 for the vehicle corner module also includes a reliability distribution curve generation module 450, which is used for: Obtain a preset lifespan time interval; the preset lifespan time interval includes multiple lifespan times; For each lifetime, determine the probability that the lifetime value in the corner module lifetime sample set is greater than the lifetime, and determine the reliability value of the corner module based on the probability. Based on the reliability values ​​corresponding to each lifetime, a reliability distribution curve is generated; the reliability distribution curve is used to characterize the trend of the reliability of the corner module as the lifetime changes.

[0128] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0129] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0130] Corresponding to the above-described method for predicting the lifespan of vehicle corner modules, this disclosure also provides a computer device, such as... Figure 6 The diagram shown is a structural schematic of a computer device provided in an embodiment of this disclosure. Figure 6 As shown, the computer device 600 includes a processor 610, an internal bus 620, memory 630, a network interface 640, and non-volatile memory 650, and may also include other hardware required for its functions. One or more embodiments of this specification can be implemented in software, for example, the processor 610 reads the corresponding computer program from the non-volatile memory 650 into the memory 630 and then runs it. Of course, besides software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution entity of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0131] The memory 630, also known as internal memory, is used to temporarily store the computational data in the processor 610, as well as the data exchanged with non-volatile memory 650 such as hard disk. The processor 610 exchanges data with non-volatile memory 650 through the memory 630.

[0132] In this embodiment, memory 630 is specifically used to store application code that executes the solution of this application, and its execution is controlled by processor 610. That is, when the computer device is running, processor 610 communicates with network interface 640, memory 630 and non-volatile memory 650 through internal bus 620, so that processor 610 executes the application code stored in memory 630 and non-volatile memory 650, thereby executing the vehicle corner module life prediction method described in the above method embodiment.

[0133] Processor 610 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware microservices. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0134] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the computer device 600. In other embodiments of this application, the computer device 600 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0135] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the vehicle corner module lifetime prediction method described in the above method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0136] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the life prediction method for the vehicle angle module in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0137] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0138] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0139] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0140] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. Basic computer microservices include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0141] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0142] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0143] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and microservices in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program microservices and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0144] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0145] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for predicting the lifespan of a vehicle corner module, characterized in that, The vehicle corner module includes multiple vehicle subsystems, and each vehicle subsystem includes various electronic components; the method includes: For each type of electronic component, obtain a lifetime sample dataset of the electronic component; A target lifetime distribution model matching the type of electronic component is determined, and parameters of the target lifetime distribution model are estimated based on the lifetime sample dataset to obtain a target lifetime distribution model containing estimated parameter information. Based on a pre-defined lifetime distribution correlation model, the target lifetime distribution models of various electronic components are correlated to construct a joint lifetime distribution model for the components; the joint lifetime distribution model for the components is used to characterize the correlation between the lifetimes of various electronic components. The joint lifetime distribution model of the components is sampled to obtain a joint lifetime sample set. Based on the joint lifetime sample set and the internal connection logic of the corner module, a corner module lifetime sample set is generated. The lifetime of the vehicle corner module is predicted based on the corner module lifetime sample set.

2. The method according to claim 1, characterized in that, The process of constructing a lifetime sample dataset for each type of electronic component includes: For each type of electronic component, based on the degradation influencing factors corresponding to the electronic component, a stochastic process mathematical model corresponding to the degradation influencing factors is determined, and based on the stochastic process mathematical model, an electronic component lifetime degradation model is constructed. The lifespan degradation model of the electronic component is simulated to obtain a lifespan sample dataset of the electronic component.

3. The method according to claim 2, characterized in that, The electronic components include motor components, and the degradation factors affecting the motor components include temperature factors and motor output torque factors. For each type of electronic component, based on the corresponding degradation factors, a stochastic process mathematical model is determined, and based on the stochastic process mathematical model, a lifespan degradation model for the electronic components is constructed, including: For the motor component, based on the temperature factor, the stochastic process mathematical model matching the temperature factor is determined to be the Wiener process, and based on the Wiener process, a first motor degradation model characterizing temperature rise degradation is constructed. Based on the motor output torque factor, the stochastic process mathematical model matching the motor output torque factor is determined to be a gamma process, and based on the gamma process, a second motor degradation model characterizing the attenuation of motor output torque is constructed. Based on the first motor degradation model and the second motor degradation model, a motor component life degradation model is determined.

4. The method according to claim 2, characterized in that, The electronic components include sensor components, and the degradation factors affecting the sensor components include zero-point drift and noise. For each type of electronic component, based on the corresponding degradation factors, a stochastic process mathematical model is determined, and based on the stochastic process mathematical model, a lifetime degradation model for the electronic components is constructed, including: For the sensor element, based on the zero-point drift factor, the stochastic process mathematical model matching the zero-point drift factor is determined to be the Wiener process, and based on the Wiener process, a first sensor degradation model is constructed. Based on the noise factors, the mathematical model of the stochastic process that matches the noise factors is determined to be an inverse Gaussian process, and a second sensor degradation model is constructed based on the inverse Gaussian process. Based on the first sensor degradation model and the second sensor degradation model, a sensor element lifetime degradation model is determined.

5. The method according to claim 2, characterized in that, The electronic components include controller components, and the degradation factors affecting the controller components include control delay increase factors and control error fluctuation factors; for each type of electronic component, based on the corresponding degradation factors, a stochastic process mathematical model corresponding to the degradation factors is determined, and based on the stochastic process mathematical model, a lifetime degradation model of the electronic components is constructed, including: For the controller element, based on the control delay factor, a stochastic process mathematical model matching the control delay factor is determined to be a gamma process, and a first controller degradation model is constructed based on the gamma process; or based on the control delay factor, a stochastic process mathematical model matching the control delay factor is determined to be an inverse Gaussian process, and a first controller degradation model is constructed based on the inverse Gaussian process. Based on the control error factors, the stochastic process mathematical model matching the control error factors is determined to be the Wiener process, and a second controller degradation model is constructed based on the Wiener process. Based on the first controller degradation model and the second controller degradation model, a controller component lifetime degradation model is determined.

6. The method according to claim 2, characterized in that, The simulation of the electronic component's lifespan degradation model yields a lifespan sample dataset of the electronic component, including: Within a preset lifetime time interval, the lifetime degradation model is simulated to obtain the degradation state trajectory of the electronic component; the degradation state trajectory includes the degradation state of the electronic component at each lifetime time point within the preset lifetime time interval. A lifetime sample dataset of the electronic component is generated based on the lifetime time points corresponding to degradation states that are greater than a preset degradation state threshold.

7. The method according to claim 1, characterized in that, The electronic component includes a motor component, and the lifetime distribution model matched with the motor component is a Weibull distribution model; the step of estimating the parameters of the lifetime distribution model based on the lifetime sample dataset of the electronic component, and constructing a target lifetime distribution model for the electronic component, includes: Based on the lifetime sample dataset corresponding to the motor component, the parameters of the Weibull distribution model are estimated to obtain the first model parameters. Based on the first model parameters and the Weibull distribution model, the target lifetime distribution model of the motor component is generated.

8. The method according to claim 1, characterized in that, The electronic component includes a sensor element, and the lifetime distribution model matched with the sensor element is a log-normal distribution model; the step of estimating the parameters of the lifetime distribution model based on the lifetime sample dataset of the electronic component to construct a target lifetime distribution model for the electronic component includes: Based on the lifetime sample dataset corresponding to the sensor element, the parameters of the log-normal distribution model are estimated to obtain the second model parameters. Based on the second model parameters and the log-normal distribution model, the target lifetime distribution model of the sensor element is generated.

9. The method according to claim 1, characterized in that, The electronic component includes a controller element, and the lifetime distribution model matched with the controller element is a log-normal distribution model; the step of estimating the parameters of the lifetime distribution model based on the lifetime sample dataset of the electronic component to construct a target lifetime distribution model for the electronic component includes: Based on the lifetime sample dataset corresponding to the controller element, the parameters of the log-normal distribution model are estimated to obtain the third model parameters. Based on the third model parameters and the log-normal distribution model, the target lifetime distribution model of the controller element is generated.

10. The method according to claim 1, characterized in that, The aforementioned lifetime distribution correlation model associates the target lifetime distribution models of various electronic components to construct a joint lifetime distribution model for the components, including: The samples from the lifetime sample datasets of various electronic components are substituted into the corresponding target lifetime distribution models for probability integral transformation to generate a set of joint lifetime observations. Based on the lifetime distribution correlation model and each of the target lifetime distribution models, the initial component joint lifetime distribution model is determined; Based on the set of joint lifetime observations, the parameter estimation of the initial component joint lifetime distribution model is performed using the maximum pseudo-likelihood estimation method to obtain the model parameters; the model parameters include the correlation coefficient matrix used to characterize the lifetime of various electronic components. Based on the correlation coefficient matrix and the initial component joint lifetime distribution model, the component joint lifetime distribution model is constructed.

11. The method according to claim 1, characterized in that, The multiple vehicle subsystems include a drive system, a braking system, a steering system, and a suspension system. The various electronic components include sensor components, motor components, and controller components. The internal connection logic of the corner module means that the drive system, the braking system, the steering system, and the suspension system are connected in series, and the sensor components, motor components, and controller components within each system are connected in series.

12. The method according to claim 11, characterized in that, The joint lifetime sample set includes multiple joint lifetime samples; the joint lifetime samples include the lifetime of each electronic component in the corner module; the generation of the corner module lifetime sample set based on the joint lifetime sample set and the internal connection logic of the corner module includes: For each joint lifetime sample, the minimum lifetime of each electronic component in each system in the joint lifetime sample is determined, and the minimum value is taken as the system lifetime of the system. The minimum value among the system lifetimes of each system is determined as the corner module lifetime corresponding to the joint lifetime sample; The corner module lifetime sample set is generated based on the corner module lifetime corresponding to each joint lifetime sample.

13. The method according to any one of claims 1-12, characterized in that, The method further includes: Obtain a preset lifespan time interval; the preset lifespan time interval includes multiple lifespan times; For each lifetime, determine the probability that the lifetime value in the corner module lifetime sample set is greater than the lifetime, and determine the reliability value of the corner module based on the probability. Based on the reliability values ​​corresponding to each lifetime, a reliability distribution curve is generated; the reliability distribution curve is used to characterize the trend of the reliability of the corner module as the lifetime changes.

14. A lifespan prediction device for a vehicle corner module, characterized in that, The vehicle corner module includes multiple vehicle subsystems, each vehicle subsystem including various electronic components; the device includes: A lifetime sample dataset construction module is used to obtain a lifetime sample dataset for each type of electronic component. The component lifetime distribution model construction module is used to determine the target lifetime distribution model that matches the type of electronic component, and to perform parameter estimation on the target lifetime distribution model based on the lifetime sample dataset to obtain the target lifetime distribution model containing the estimated parameter information. The joint lifetime distribution model construction module is used to associate the target lifetime distribution models of various electronic components based on a preset lifetime distribution correlation model to construct a joint lifetime distribution model of the components; the joint lifetime distribution model of the components is used to characterize the correlation between the lifetimes of various electronic components. The corner module life prediction module is used to perform life sampling on the joint life distribution model to obtain a joint life sample set, and generate a corner module life sample set based on the joint life sample set and the internal connection logic of the corner module, and predict the life of the vehicle corner module based on the corner module life sample set.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the life prediction method for the vehicle corner module according to any one of claims 1-13.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the life prediction method for the vehicle corner module according to any one of claims 1-13.

Images