Data processing method and device for vehicle and computer readable storage medium

By generating and fitting the data sample set and probability distribution model of electric vehicle components, the problem of difficult to adapt to the task profile data of electric vehicles in the existing technology is solved, high-quality task profile data acquisition is achieved, and the vehicle development and Efficiency and accuracy of reliability management.

CN119066773APending Publication Date: 2024-12-03NIO TECH ANHUI CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411197515.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing component task profile data standards are difficult to adapt to electric vehicles, and they cannot effectively predict and prevent problems in electric vehicle components in their life cycle, affecting their reliability and life.

Method used

By generating a data sample set based on the usage data of multiple vehicle components, extracting feature samples, and determining the task profile of the component using the probability distribution model, providing high-quality task profile data. The method includes filtering of the data sample set, generation of feature samples, and fitting of probability distribution models, to describe the usage characteristics and state characteristics of components.

Benefits of technology

Obtain large-scale and high-quality component usage data in a short period of time, improve the vehicle development process and reliability management level, suppress the impact of data noise, and the generated task profile data is highly interpretable and refined.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066773A_ABST
    Figure CN119066773A_ABST
Patent Text Reader

Abstract

The invention relates to a data processing technology and a vehicle design technology, in particular to a data processing method and device for a vehicle and a computer readable storage medium and a computer program product for implementing the method. According to one aspect of the application, a data processing method for a vehicle is provided, comprising the following steps executed by a data processing device: generating a data sample set based on data associated with use of a plurality of parts of the vehicle; generating a plurality of feature samples of the part based on the data sample set; generating a probability distribution model about the plurality of feature samples based on the plurality of feature samples; and determining a mission profile of the part based on the probability distribution model.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to data processing technology and vehicle design technology, and in particular to a data processing method and device for a vehicle, and a computer-readable storage medium and a computer program product for implementing the method. Background Art

[0002] The reliability management of vehicle parts is a systematic project, which is an indispensable part to ensure that each vehicle component can operate normally and safely throughout its service life. Through effective reliability management, customer satisfaction can be improved, maintenance costs can be reduced, and potential safety risks can be avoided.

[0003] The mission profile of a component is an important basis for evaluating its performance and reliability, and is also an important reference for component design and selection. By fully considering the mission profile of a component, it is possible to better predict and prevent problems that may be encountered during its life cycle, thereby improving its reliability and lifespan.

[0004] At present, the mission profile data of parts and components mainly come from the standards of fuel vehicles. Due to the application scenarios on which such standards are based, these standards cannot be well adapted to electric vehicles. Summary of the invention

[0005] An object of the present application is to provide a data processing method and device for a vehicle, as well as a computer-readable storage medium and a computer program product for implementing the method, which are helpful in providing high-quality component mission profile data for determining the mission profile.

[0006] According to one aspect of the present application, a data processing method for a vehicle is provided, comprising the following steps performed by a data processing device:

[0007] generating a data sample set based on data associated with usage of components of a plurality of vehicles;

[0008] Generate a plurality of feature samples of the component based on the data sample set;

[0009] generating a probability distribution model about the plurality of feature samples based on the plurality of feature samples; and

[0010] A mission profile of the component is determined based on the probability distribution model.

[0011] Optionally, in the above data processing method, the data samples in the data sample set are used to describe the operation or status of the component.

[0012] Optionally, in the above data processing method, the step of generating the data sample set includes:

[0013] Based on the filtering condition, required data samples are screened out from the data associated with the usage of the components of the plurality of vehicles to generate the data sample set.

[0014] Further optionally, in the above data processing method, the filtering conditions include one or more of the following: a specified time range, a specified vehicle model, a specified driving area, a specified production batch and a specified mileage range.

[0015] Optionally, in the above data processing method, the components include at least one of the following: an electric motor, an on-board charger, a headlight, a windshield wiper, a rearview mirror heater, a seat adjustment mechanism, and a window lifting mechanism.

[0016] Optionally, in the above data processing method, the multiple feature samples are used to describe at least one of the following component usage characteristics: the number of times the component enters a set state within a specified time interval, the cumulative time that the component is in the set state within a specified time interval, the maximum or minimum duration of the component being in the set state at a single time within a specified time interval, and the peak or mean value of the state value of the component within the specified time interval.

[0017] Optionally, in the above data processing method, the step of generating the probability distribution model includes:

[0018] The parameters of the probability distribution model are estimated using the multiple feature samples.

[0019] Optionally, in the above data processing method, the step of generating the probability distribution model includes:

[0020] Using the multiple feature samples to estimate parameters of multiple candidate probability distribution models;

[0021] Determining fitting results of the plurality of candidate probability distribution models; and

[0022] The candidate probability distribution model having the best fitting result is determined as the probability distribution model.

[0023] Optionally, in the above data processing method, the task profile includes one or more of the following statistical distribution characteristics of the probability distribution model: mean, median, mode, variance, standard deviation, skewness, kurtosis, range, percentile, covariance, correlation coefficient, expected value, cumulative distribution function, probability density function and probability mass function.

[0024] According to another aspect of the present application, there is provided a data processing device, comprising:

[0025] at least one processor;

[0026] at least one memory; and

[0027] The computer program / instructions stored on the memory, when executed on the processor, result in the following operations:

[0028] generating a data sample set based on data associated with usage of components of a plurality of vehicles;

[0029] Generate a plurality of feature samples of the component based on the data sample set;

[0030] generating a probability distribution model about the plurality of feature samples based on the plurality of feature samples; and

[0031] A mission profile of the component is determined based on the probability distribution model.

[0032] Optionally, in the above-mentioned data processing device, the data samples in the data sample set are used to describe the operation or status of the component.

[0033] Optionally, in the above data processing device, the execution of the computer program / instructions on the processor further results in the following operations:

[0034] Based on the filtering condition, required data samples are screened out from the data associated with the usage of the components of the plurality of vehicles to generate the data sample set.

[0035] Further optionally, in the above-mentioned data processing device, the filtering conditions include one or more of the following: a specified time range, a specified vehicle model, a specified driving area, a specified production batch and a specified mileage range.

[0036] Optionally, in the above-mentioned data processing device, the components include at least one of the following: an electric motor, an on-board charger, a headlight, a windshield wiper, a rearview mirror heater, a seat adjustment mechanism and a window lifting mechanism.

[0037] Optionally, in the above-mentioned data processing device, the multiple feature samples are used to describe at least one of the following component usage characteristics: the number of times the component enters a set state within a specified time interval, the cumulative time that the component is in the set state within a specified time interval, the maximum or minimum duration of the component being in the set state at a single time within a specified time interval, and the peak or mean value of the state value of the component within the specified time interval.

[0038] Optionally, in the above data processing device, the execution of the computer program / instructions on the processor causes the probability distribution model to be generated in the following manner:

[0039] The parameters of the probability distribution model are estimated using the multiple feature samples.

[0040] Optionally, in the above data processing device, the execution of the computer program / instructions on the processor causes the probability distribution model to be generated in the following manner:

[0041] Using the multiple feature samples to estimate parameters of multiple candidate probability distribution models;

[0042] Determining fitting results of the plurality of candidate probability distribution models; and

[0043] The candidate probability distribution model having the best fitting result is determined as the probability distribution model.

[0044] Optionally, in the above-mentioned data processing device, the task profile includes one or more of the following statistical distribution characteristics of the probability distribution model: mean, median, mode, variance, standard deviation, skewness, kurtosis, range, percentile, covariance, correlation coefficient, expected value, cumulative distribution function, probability density function and probability mass function.

[0045] According to another aspect of the present application, a non-transitory computer-readable storage medium is provided, on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps of the method described above are implemented.

[0046] According to another aspect of the present application, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the method described above when the computer program / instruction is executed by a processor.

[0047] In some embodiments of the present application, the task profile generation method based on vehicle background big data can obtain large-scale, high-quality parts usage data in a short time, which is conducive to accelerating the vehicle development process and improving the level of reliability management. In addition, by flexibly setting various filtering conditions according to application requirements during the generation of the data sample set, the generated data sample set is closer to various application requirements, thereby obtaining more refined task profile data. Furthermore, compared with the method of directly using feature samples to generate task profiles, in some embodiments of the present application, the method of fitting the parameter distribution of feature samples and generating task profiles using probability distribution models can suppress or control the impact of data noise and make the task profile data more interpretable. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and / or other aspects and advantages of the present application will become clearer and easier to understand through the following description of various aspects in conjunction with the accompanying drawings, in which the same or similar units are represented by the same reference numerals. The accompanying drawings include:

[0049] Figure 1 The present invention is a flowchart of a data processing method for a vehicle according to an embodiment of the present application.

[0050] Figure 2 A schematic diagram of the calculation logic for generating corresponding feature samples from the driving signal of the vehicle door mechanism is shown.

[0051] Figure 3 A schematic diagram showing the calculation logic for generating corresponding characteristic samples from the control signal of the rearview mirror heater.

[0052] Figure 4 A flow chart of a method for determining a probability distribution model from a plurality of candidate probability models is shown.

[0053] Figure 5 A schematic block diagram of a data processing device. DETAILED DESCRIPTION

[0054] The present application is described more fully below with reference to the accompanying drawings in which illustrative embodiments of the present application are illustrated. However, the present application may be implemented in different forms and should not be interpreted as being limited to the embodiments given herein. The above embodiments are given to make the disclosure herein comprehensive and complete, so as to more fully convey the scope of protection of the present application to those skilled in the art.

[0055] In this specification, terms such as "comprise" and "include" indicate that in addition to the units and steps directly and explicitly stated in the specification and claims, the technical solution of the present application does not exclude the situation where there are other units and steps that are not directly or explicitly stated.

[0056] Unless otherwise specified, terms such as "first" and "second" do not indicate the order of the units in terms of time, space, size, etc., but are merely used to distinguish the units.

[0057] It should be noted that the vehicle components can be divided into multiple levels. For example, the rearview mirror heater itself can be regarded as a component, and the heating element and the heating circuit can be further regarded as components that constitute the heater. In this specification, "components" generally refer to physical units at various levels in the vehicle that can achieve specific functions. Typical components include, but are not limited to, electric motors, on-board chargers, lights, wipers, rearview mirror heaters, seat adjustment mechanisms, and window lifting mechanisms.

[0058] Figure 1 The present invention is a flowchart of a data processing method for a vehicle according to an embodiment of the present application. Figure 1Each step of the method shown is performed by a data processing device. It should be noted that the data processing device described here generally refers to various computer systems including hardware entities and software components, in which various computing tasks and information processing tasks are performed through the collaborative work of hardware entities and software components.

[0059] like Figure 1 The method of this embodiment includes steps 110-150 which are performed in sequence. Each step is described in detail below.

[0060] Step 110: Receiving data associated with the component

[0061] In step 110 , the data processing device receives data associated with usage of components on a plurality of vehicles (hereinafter also referred to as component usage data or usage data).

[0062] It should be noted that the association described here refers to the data being related to the use of vehicle parts, or the data being generated due to the use of parts. In one example, this correlation is reflected in the use data being generated at the vehicle and used to describe the operation or status of the parts.

[0063] The operation of the components described here includes but is not limited to starting operation (such as turning on the lights, etc.), stopping operation (such as turning off the wipers, etc.), adjusting and / or controlling operation (such as controlling the motor, shifting operation of the gearbox, etc.), monitoring / or testing (such as regular monitoring and testing of the brake system, airbags, etc.), maintenance and / or servicing operation (such as changing tires, etc.). The state of the components described here should be broadly understood as the performance and physical condition of the components. In some examples, the state of the components can be described, for example, by the output torque of the motor, the output current of the motor, the tire pressure, the seat tilt angle, and the reciprocating frequency of the wipers.

[0064] As the level of vehicle intelligence continues to increase (especially in new energy vehicles such as pure electric vehicles, plug-in hybrid electric vehicles, hybrid electric vehicles, extended-range electric vehicles and fuel cell electric vehicles), the ability to monitor the use of parts has also been strengthened, making it possible to obtain massive amounts of part usage data. This massive amount of data can be sent by the vehicle to a data processing device (such as a server that constitutes a cloud computing infrastructure) in real time or when the communication bandwidth is idle, and the latter is used to determine the mission profile data of the parts. Compared with traditional methods, this mission profile generation method based on vehicle background big data can obtain large-scale, high-quality part usage data in a short time, thereby accelerating the vehicle development process and improving the level of reliability management.

[0065] Step 120: Generation of data sample set

[0066] In some examples, a component may have a single type of component usage data, for example, for a lamp, the type of usage data is a control signal for turning the lamp on or off; or for a motor, the type of usage data is a combination of the motor's winding current and output torque. In other examples, a component may have multiple types of component usage data, for example, for a motor, the usage data may be the motor's winding current, real-time speed, and rotation direction.

[0067] In step 120, the data processing device generates one or more data sample sets from the received component usage data, each data sample set corresponding to one type of usage data of a component. For example, the data samples included in the data sample set are from n vehicles (n is in the order of 10 2 ~10 5 ) and is associated with the i-th component on the vehicle.

[0068] In the case where the data used is of a single type, the data sample set will be denoted as Ω, and the data sample in it will be denoted as S ij , where i represents the serial number of the component and j represents the serial number of the vehicle. On the other hand, in multiple types of situations, the data sample set will be recorded as Ω k , and the data sample is recorded as S k ij , where i represents the serial number of the component, j represents the serial number of the vehicle, and k represents the serial number of the type of component usage data.

[0069] In some embodiments, n vehicles may have one or more of the same attributes, such as but not limited to vehicle type, driving region (e.g., determined based on the vehicle registration location or based on the vehicle driving trajectory determined by a satellite positioning system), production batch, and mileage range. These attributes can be flexibly set by the user according to application requirements to obtain the required data. For example, by setting an appropriate mileage range, rarely used vehicles and vehicles that have exceeded their service life can be excluded to obtain more valuable mission profile data for vehicle reliability management.

[0070] In step 120, the data processing device may, for example, filter out the required data samples from the received component usage data according to the set filtering conditions to construct a data sample set. The above filtering conditions may be based on the attributes of the n vehicles and / or the generation time or timestamp of the data samples, which may include, for example, but not limited to, one or more of the following: a specified time range, a specified vehicle model, a specified driving region, a specified production batch, and a specified driving mileage range. By using various filtering conditions to filter the component usage data during the generation of the data sample set, various application requirements can be met, and the provided mission profile data is also more refined.

[0071] It should also be noted that each data sample may include one sample value (eg, a mark indicating whether a component has been replaced) or multiple sample values ​​(eg, a control signal sequence of a rearview mirror heater that may vary over time).

[0072] Step 130: Generation of feature sample set

[0073] As described above, each component may have one or more types of component usage data. In step 130, when the usage data is of a single type, the data processing device generates a feature sample set Ψ based on the data sample set Ω, and when the usage data is of multiple types, the data processing device generates a feature sample set Ψ based on the data sample set Ω. k Generate a feature sample set Ψ of the kth type of usage data k , thus obtaining a set of feature sample sets {Ψ k}.

[0074] Feature sample sets Ψ and Ψ k Contains multiple feature samples. For example, the following will be based on the usage data S of the i-th component of the j-th vehicle ij The generated feature sample is recorded as f ij , and the kth usage data S based on the i-th component of the j-th vehicle k ij The generated feature sample is recorded as f k ij .

[0075] The feature samples mentioned here refer to various measurements that can be used to describe the usage characteristics of parts. The usage characteristics of parts mentioned here include, but are not limited to:

[0076] The number of times a component enters a set state within a specified time range: for example, the number of times a door is opened between January 1, 2020 and December 31, 2023.

[0077] The cumulative time that a component is in a set state within a specified time range: for example, the cumulative heating time of a rearview mirror heater within the time range from January 1, 2020 to December 31, 2023.

[0078] The maximum or minimum duration that a component can be in a set state at one time within a specified time range: for example, the maximum or minimum duration that a rearview mirror heater can be heated at one time within the time range from January 1, 2020 to December 31, 2023.

[0079] The peak or average value of a component’s status value within a specified time range: for example, the highest output torque or average output torque of a motor within the time range from January 1, 2020 to December 31, 2023.

[0080] In addition, the value type of the feature sample may include, but is not limited to, numerical value, date, time, text, logical value, and user-defined.

[0081] The following is with the help of Figure 2 and 3 A specific example of generating corresponding feature samples from one type of component usage data (eg, a drive signal of a door mechanism or a control signal of a rearview mirror heater) is described.

[0082] Figure 2 FIG. 1 is a schematic diagram showing the calculation logic for generating corresponding characteristic samples from the driving signal of the door mechanism, wherein the vertical axis and the horizontal axis represent the level value DRV of the driving signal and the time t, respectively. Figure 2 When the driving signal DRV changes from a low level to a high level (corresponding to the driving signal change shown in the dotted box in the figure), it is regarded as an event of entering a set state (door opening), thereby obtaining the number of occurrences of the event within a specified time range. The number of occurrences can be used as a characteristic sample of the driving signal of the door mechanism.

[0083] Figure 3 The figure shows a schematic diagram of the calculation logic for generating corresponding characteristic samples from the control signal of the rearview mirror heater, wherein the vertical axis and the horizontal axis represent the level value CTRL and the time of the control signal respectively. Figure 3 In the figure, each time the level value of the control signal CTRL is high, it means that the heater is in the heating state. By timing each heating (the time interval shown by the double arrows in the figure), the cumulative heating time within the specified time range can be obtained. The cumulative heating time can be used as a characteristic sample of the control signal of the heater.

[0084] Step 140: Generation of probability distribution model

[0085] In step 140, when the data is of a single type, the data processing device determines the corresponding probability distribution model P based on the feature samples in the feature sample set Ψ; when the data is of multiple types, the data processing device determines the corresponding probability distribution model P based on a set of feature samples and {Ψ k}Determine a corresponding set of probability distribution models {Ρ k}, where the probability distribution model P k The k-th type of feature sample set Ψ k The feature samples are determined in .

[0086] The probability distribution model described here and the candidate probability distribution models described below refer to statistical models used to describe the distribution characteristics of feature samples, which include, but are not limited to, normal distribution, binomial distribution, Poisson distribution, exponential distribution, uniform distribution, Bernoulli distribution, geometric distribution, Pareto distribution, Weibull distribution, gamma distribution, beta distribution, multivariate distribution and mixed distribution, etc.

[0087] In some cases, the type of probability distribution model for the feature sample may be already determined (e.g., based on the experience of the technician). In some embodiments, the type of probability distribution model P or P may be determined by parameter estimation. k Parameters of . Commonly used parameter estimation methods include, but are not limited to, maximum likelihood estimation, Bayesian estimation, moment estimation, least squares method, gradient descent, expectation maximization, Markov chain Monte Carlo, direct search, Newton-Raphson method, and goodness-of-fit test.

[0088] In other cases, the type of probability distribution model for the feature samples may be unknown or undetermined. Figure 4 A flow chart of a method for determining a probability distribution model in this case is shown.

[0089] Figure 4 The method shown starts at step 410. In step 410, a feature sample of usage data of a type of component (eg, a feature sample set Ψ from usage data of the kth type) is generated. k ) Determine the type of candidate probability distribution model Θ1, Θ1…Θ m , where m represents the number of types of candidate probability distribution models. In some embodiments, the type can be determined by a user-specified method; in other embodiments, the type of the candidate probability distribution model can also be determined randomly or automatically by a data processing device based on prior knowledge.

[0090] Then, the process proceeds to step 420, where the data processing device estimates candidate probability distribution models Θ1, Θ2, ...Θ m The parameters λ1, λ1…λ of each model in mIn some embodiments, for the lth candidate probability model Θ l , determine the parameter λ of the probability distribution model through parameter estimation l The commonly used parameter estimation methods have been listed above and will not be repeated here.

[0091] After step 420, Figure 4 The process shown enters step 430. In step 430, the data processing device determines the candidate probability distribution models Θ1, Θ2, ...Θ m This can be done, for example, through goodness of fit tests and residual analysis.

[0092] Then, the process proceeds to step 440, where the data processing device determines the candidate probability distribution model with the best fitting result as the probability distribution model P or P k .

[0093] Step 150: Determination of mission profile

[0094] A component mission profile is a document that describes in detail the performance, functionality, and manufacturing requirements that a component must meet in a specific application or system. This profile is often used in engineering design, procurement, and supply chain management to ensure that the component meets design and production requirements. The mission profile of an automotive component usually describes the design and production requirements of the component from multiple aspects, such as technical specifications (such as material type, size, weight, and tolerance), performance indicators (such as heat resistance, wear resistance, and strength), manufacturing processes, quality standards, safety standards, expected life, and cost control targets. When determining these contents, it is necessary to understand the actual use of the component.

[0095] In step 150, the data processing device processes the probability distribution model P or {P k} to determine the mission profile of the component. In some embodiments, one or more statistical distribution characteristics of a probability distribution model can be used as mission profile data reflecting the actual use of the corresponding component to generate the mission profile. These statistical distribution characteristics include, but are not limited to, mean, median, mode, variance, standard deviation, skewness, kurtosis, range, percentile, covariance, correlation coefficient, expected value, cumulative distribution function, probability density function and probability mass function.

[0096] It should be noted that when a component contains multiple types (for example, k types) of usage data, its mission profile may include mission profile data of multiple dimensions, and the mission profile data of each dimension may be based on multiple probability distribution models {Ρ k} to determine one of them.

[0097] Compared with the method of directly using feature samples to generate task profiles, in the above embodiment, the task profile of the component is described by fitting the parameter distribution of the feature samples and using the statistical distribution characteristics of the probability distribution model. The latter can suppress or control the influence of data noise, thereby improving the robustness of the calculation results; in addition, since the parameters and statistical distribution characteristics of the probability distribution model have clear definitions and can be associated with the real physical world, the task profile data has strong interpretability.

[0098] Figure 5 The present invention is a schematic block diagram of a data processing device, which can be used to implement the above data processing method.

[0099] Figure 5 The illustrated device 50 comprises one or more memories 510 (eg, non-volatile memory such as flash memory, ROM, hard drive, magnetic disk, optical disk), one or more processors 520 , and computer programs / instructions 530 stored on the memories 510 .

[0100] The computer program / instructions 530 may be executed by a single processor 520, or by multiple processors 520 (which may be located in the same physical location or in different physical locations) in coordination to perform the above-mentioned Figure 1-4 Steps of the method described.

[0101] Optionally, Figure 5 The device 50 shown can be implemented in the form of a cloud computing platform or cloud platform, in which computing, network and storage services are provided in the form of a resource pool, wherein most of the computing resources are hosted on the Internet and allocated to users on demand. Alternatively, the device 50 can also be implemented in the form of a stand-alone system, in which computing resources are basically limited to a single local system.

[0102] Those skilled in the art will appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described herein may be implemented as electronic hardware, computer software, or a combination of both.

[0103] In order to show the interchangeability between hardware and software, various schematic components, blocks, modules, circuits and steps are generally described above according to their functionality. Such functionality is implemented in hardware form or software form depending on the specific application and the design restrictions imposed on the overall system. Those skilled in the art can implement the described functionality in a variable manner for specific specific applications, but such implementation decisions should not be understood as causing deviations from the scope of the present application.

[0104] Although only some of the specific embodiments of the present application are described, it should be understood by those skilled in the art that the present application can be implemented in many other forms without departing from its subject matter and scope. Therefore, the examples and embodiments shown are considered to be illustrative rather than restrictive, and the present application may include various modifications and substitutions without departing from the spirit and scope of the present application as defined in the appended claims.

[0105] The embodiments and examples set forth herein are provided to best illustrate embodiments according to the present technology and its specific applications, and thereby enable those skilled in the art to implement and use the present application. However, those skilled in the art will appreciate that the above description and examples are provided only for ease of illustration and example. The description set forth is not intended to cover all aspects of the present application or to limit the present application to the precise form disclosed.

Claims

1. A data processing method for a vehicle, characterized in that: The method comprises the following steps performed by a data processing device: generating a data sample set based on data associated with usage of components of a plurality of vehicles; Generate a plurality of feature samples of the component based on the data sample set; generating a probability distribution model about the plurality of feature samples based on the plurality of feature samples; and A mission profile of the component is determined based on the probability distribution model.

2. The data processing method according to claim 1, wherein: The data samples in the data sample set are used to describe the operation or status of the component.

3. The data processing method according to claim 1, wherein: The steps of generating the data sample set include: Based on the filtering condition, required data samples are screened out from the data associated with the usage of the components of the plurality of vehicles to generate the data sample set.

4. The data processing method according to claim 3, wherein: The filtering conditions include one or more of the following: a specified time range, a specified vehicle model, a specified driving area, a specified production batch, and a specified driving mileage range.

5. The data processing method according to claim 2, wherein: The multiple feature samples are used to describe at least one of the following component usage characteristics: the number of times the component enters a set state within a specified time interval, the cumulative time that the component is in the set state within a specified time interval, the maximum or minimum duration of the component being in the set state at a single time within a specified time interval, and the peak or mean value of the state value of the component within the specified time interval.

6. The data processing method according to claim 1, wherein: The steps of generating the probability distribution model include: The plurality of feature samples are used to estimate a first parameter of the probability distribution model.

7. The data processing method according to claim 1, wherein: The steps of generating the probability distribution model include: Using the plurality of feature samples to estimate second parameters of a plurality of candidate probability distribution models; Determining fitting results of the plurality of candidate probability distribution models; and The candidate probability distribution model having the best fitting result is determined as the probability distribution model.

8. A data processing device, comprising: at least one processor; at least one memory; as well as The computer program / instructions stored on the memory, when executed on the processor, result in the following operations: generating a data sample set based on data associated with usage of components of a plurality of vehicles; Generate a plurality of feature samples of the component based on the data sample set; generating a probability distribution model about the plurality of feature samples based on the plurality of feature samples; and A mission profile of the component is determined based on the probability distribution model.

9. A non-transitory computer-readable storage medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Vehicle continuous driving working condition generation method and system based on GIS road network and data-driven Markov chain

    CN122332848A