Part damage extrapolation method and system based on user use characteristics

Abstract

The invention relates to the technical field of engineering part damage extrapolation, in particular to a part damage extrapolation method and system based on user use characteristics. The method comprises the following steps: acquiring i driving working conditions of a target part and load data of j signal channels; extrapolation is carried out according to the load data, and a damage intensity matrix is obtained through damage calculation; constructing a user feature model; and predicting part damage matrixes of different logistics types according to the user feature model and the damage intensity matrix. According to the method, the part damage matrix of the target logistics type is obtained according to the user feature model and the damage intensity matrix, and target damage analysis can be performed on the target part according to the engine part damage matrix. Compared with traditional single-sample mileage extrapolation, the method has the advantages that user simulation extrapolation is performed based on driving condition data of different logistics types at the same time, and an obtained engine damage result can reflect an actual use scene more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of engineering component damage extrapolation, and in particular to a component damage extrapolation method and system based on user usage characteristics. Background Art

[0002] In the reliability design project of the entire life cycle of vehicle components, traditional engine damage assessment and life prediction methods mainly rely on statistical analysis of test bench data or limited historical failure data.

[0003] The amount of test bench data and historical fault data is limited, and their statistical analysis results are not sufficient to characterize the fault performance of the engine under various operating conditions in actual operation.

[0004] To address the issue of insufficient failure statistics, damage extrapolation can be performed based on test bench data. Engine damage extrapolation uses limited experimental data or known damage conditions to predict the damage development trend of the engine over a longer period of time, under higher loads, or under other operating conditions using mathematical models or statistical methods.

[0005] For example, patent publication number CN118445989A discloses a method for converting a transmission durability bench load spectrum, which describes a method for performing rain flow extrapolation on a vehicle transmission load spectrum obtained through an indoor bench test.

[0006] However, engine failures manifest differently in different logistics segments or among different driver groups. For example, drivers in express delivery and resource transportation face significantly different road conditions, load fluctuations, and driving habits. Existing technologies struggle to accurately extrapolate target damage thresholds under actual user conditions, hindering the scientific nature of product reliability design and iterative optimization.

[0007] Therefore, the statistical analysis results obtained by the existing engine damage extrapolation method can only reflect the engine failure performance on the test bench, but cannot reflect the differences in engine failure performance in vehicles of different logistics types.

[0008] In order to perform extrapolated damage analysis on parts in different logistics scenarios, the present application provides a method and system for extrapolating part damage based on user usage characteristics. Summary of the Invention

[0009] To overcome the problems existing in the related art, the first aspect of the present application provides a component damage extrapolation method based on user usage characteristics, comprising: Collect load data of i driving conditions and j signal channels of the target component; i and j are both integers greater than or equal to 1; Extrapolating the load data, and obtaining a damage intensity matrix through damage calculation; Constructing a user feature model; the user feature model is a distributed matrix of mileage ratios under at least one logistics type; the rows of the distributed matrix represent the logistics type, the columns of the distributed matrix represent the driving conditions, and the elements of the distributed matrix represent the mileage ratios; The damage matrix of parts of different logistics types is predicted based on the user feature model and the damage intensity matrix.

[0010] In one embodiment, collecting load data of i driving conditions and j signal channels of a target component specifically includes: Obtaining the type of data to be collected of the target component; Acquire road test data according to the data type to be collected; the road test data includes raw data of i driving conditions and j signal channels; Determining the confidence level of the road test data according to a minimum test mileage calculation function; Determine whether the confidence level of the road test data is greater than a preset confidence threshold; if so, use the road test data as the load data; if not, retest the road test data.

[0011] In one embodiment, the minimum test mileage calculation function is:

[0012] in, for The numerical value corresponding to the percentile point; for Confidence under the conditions,

[0013] is the inverse function of the normal distribution function; is the significance level; is the average length of the road test data slice, sample The sum of is equal to the minimum test mileage; for Standard deviation of damage values;

[0014] In one embodiment, extrapolating the load data to obtain a damage intensity matrix through damage calculation specifically includes: Performing rain flow counting on the load data to obtain a From-to matrix of the rain flow counting; Rain flow is extrapolated based on the kernel density estimation formula to obtain the rain flow matrix of annual mileage; The rain flow matrix is ​​proportionally extrapolated to obtain the damage intensity matrix based on the SN curve of the corresponding material.

[0015] In one embodiment, constructing the user feature model specifically includes: Obtaining road driving samples of different logistics types; Preprocessing the road driving sample; The user factor model is quantitatively evaluated through road network identification and load estimation to construct the user feature model.

[0016] Check whether the user feature model has reached convergence. If the relative error value of the model parameter is less than the convergence expectation threshold, the user feature model construction is completed; if not, obtain the new road driving sample and execute the step: obtain the road driving samples of the different logistics types.

[0017] In one embodiment, predicting the component damage matrix of different logistics types based on the user feature model and the damage intensity matrix specifically includes: Performing Monte Carlo simulation on the user feature model to obtain random samples of virtual users of each logistics type; Determine a virtual user model based on the virtual user random sample; The component damage matrix is ​​determined according to the damage intensity matrix and the virtual user model.

[0018] In one embodiment, in determining the component damage matrix based on the damage intensity matrix and the virtual user model, the calculation formula specifically includes:

[0019] in, is the mean The traversal segment number; is the minimum mean value of each driving condition of the user characteristic model; Calculate the step size for the mean traversal; is the standard deviation The traversal segment number; is the minimum standard deviation of each driving condition of the user characteristic model; Calculate the step size for the standard deviation traversal; For the the virtual user model of the logistics type; For the Channels of the stated logistics type The component damage matrix.

[0020] In one embodiment, after predicting the component damage matrices of different logistics types based on the user feature model and the damage intensity matrix, the method further includes: The target damage result of the component is determined based on the preset damage percentage and design life mileage.

[0021] In one embodiment, determining the target damage result of a component based on a preset damage percentage and a design life mileage specifically includes: Obtain preset damage percentage and design life mileage; Calculate the target damage results of components in each channel under the design life mileage.

[0022] The second aspect of the present application provides a component damage extrapolation system based on user usage characteristics, which is characterized by being used to execute the steps in the component damage extrapolation method described in the first aspect of the present application.

[0023] The technical solution provided by this application may have the following beneficial effects: This application collects feedback signals from each signal channel of the target engine under different driving conditions. The feedback signal is used as load data for rainflow extrapolation, and the damage intensity matrix is ​​obtained through damage calculation. The user characteristic model is surveyed and statistically analyzed to obtain the mileage percentage of each driving condition of the target logistics type. The component damage matrix of the target logistics type is obtained based on the product of the mileage percentage and the damage intensity matrix. Compared with the traditional single-sample mileage extrapolation, this application simultaneously performs user simulation extrapolation on the driving condition data of different logistics types. The analysis of the component damage matrix and the test mileage can more accurately reflect the damage of the components in different logistics conditions.

[0024] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0026] Figure 1 Schematic diagram of the process of component damage extrapolation method shown in the embodiment of the present application; Figure 2 This is an example diagram of load data shown in an embodiment of the present application; Figure 3 This is an example diagram of the rainflow counting From-to matrix shown in an embodiment of the present application; Figure 4 for Figure 3The following is an example of the rain flow matrix before and after the From-to matrix extrapolation: Figure 5 for Figure 3 and Figure 4 Comparison diagram of the cumulative distribution curve of ; Figure 6 This is an example diagram of the target damage results of the components shown in the embodiment of the present application. DETAILED DESCRIPTION

[0027] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0028] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are 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 encompasses any and all possible combinations of one or more of the associated listed items.

[0029] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0030] Example 1 In response to the above problems, the present application provides an engine target damage extrapolation method based on user usage characteristics, such as Figure 1 As shown, the following steps are included: S1. Collect load data of i driving conditions and j signal channels of the target component; i and j are both integers greater than or equal to 1; S2. Extrapolating the load data to obtain a damage intensity matrix through damage calculation; S3. Build user feature model; S4. Predicting the component damage matrix of each logistics type based on the user feature model and the damage intensity matrix.

[0031] The target parts in the embodiment of the present application are engine parts. It is understood that the target parts can also be other parts such as the frame. The elements of the damage intensity matrix are damage intensities, which represent the degree of damage per unit mileage.

[0032] Specifically, in the data collection step in S1, load data for i driving conditions and j channels are collected. The driving conditions include, but are not limited to, vehicle load, road type, and terrain type. The signal channels include, but are not limited to, suspension three-component force, acceleration, strain, speed and torque, and GPS positioning signal channel types.

[0033] Specifically, in S3, the user feature model is a distributed matrix of the mileage ratio under at least one logistics type; the rows of the distributed matrix represent the logistics type, the columns of the distributed matrix represent the driving conditions, and the elements of the distributed matrix represent the mileage ratio.

[0034] For example, the user feature model is shown in the user feature model data table in Table 1. The rows in the user feature model represent logistics types, such as express delivery, cold chain, green channel, daily bulk, and sedan transport; the columns represent driving conditions, such as highway, suburban, and urban areas according to road type.

[0035] Table 1: User feature model data table

[0036] Different logistics types represent different user groups. This embodiment collects feedback signals from various signal channels of a target engine under different driving conditions. This feedback signal is used as load data for rainflow extrapolation to generate a damage intensity matrix. A table lookup is performed on the user characteristic model to obtain the mileage percentage for each driving condition of the target logistics type. The product of the mileage percentage and the damage intensity matrix yields the engine damage result for the target logistics type.

[0037] Compared with the traditional single-sample mileage extrapolation, the embodiment of the present application simultaneously performs user simulation extrapolation on driving condition data of different logistics types, and the analysis of the component damage matrix and test mileage can more accurately reflect the damage status of components in working conditions of different logistics types.

[0038] Example 2 Based on the first embodiment, the present application also provides a component damage extrapolation method based on user usage characteristics, such as Figure 1 As shown, the following steps are included: S1. Collect load data of i driving conditions and j signal channels of the target component; i and j are both integers greater than or equal to 1; S2. Extrapolating the load data to obtain a damage intensity matrix through damage calculation; S3. Build user feature model; S4. Predicting the component damage matrix of each logistics type based on the user feature model and the damage intensity matrix.

[0039] In step S1, in order to simulate the effective test data of various levels of user road test mileage under different influencing factors, the embodiment of the present application is divided into road type, payload, topography and landform according to the influencing factors of driving, and the load acquisition signal channel type and measurement point location are determined according to the product historical fault information, product DFMEA and CAE analysis of the product's weak links.

[0040] Furthermore, S1 includes the following steps: S11, obtaining the data type to be collected of the target component; S12. Acquire road test data according to the type of data to be collected; the road test data includes raw data of i driving conditions and j signal channels; S13, determining the confidence level of the road test data according to a minimum test mileage calculation function; S14. Determine whether the confidence level of the road test data is greater than a preset confidence threshold. If so, use the road test data as the load data; if not, perform additional testing on the road test data.

[0041] Furthermore, the minimum test mileage calculation function is:

[0042] in, for The numerical value corresponding to the percentile point; for Confidence under the conditions, is the inverse function of the normal distribution function; is the significance level; is the average length of the road test data slice, sample The sum of is equal to the minimum test mileage; for Standard deviation of damage values; is the number of road test data slices, and the product of the number of road test data slices and the average length of the road test data slices is the minimum test mileage.

[0043] It is understandable that Represents the value corresponding to the 90th percentile; is the percentile. For example, when the percentile is 90%, it is recorded as . , indicating a confidence level of 50%.

[0044] In step S2, rainflow extrapolation is used to infer the actual load conditions within the preset service life. It can be understood that rainflow extrapolation is a load data processing technology based on statistical principles. It analyzes load data within a limited time period to infer the actual load conditions throughout the entire service life.

[0045] In step S2, it specifically includes: S21, performing rain flow counting on the load data to obtain a From-to matrix of the rain flow counting; S22. Extrapolate the rain flow based on the kernel density estimation formula to obtain the rain flow matrix of the annual mileage; S23. Proportional extrapolation is performed on the rain flow matrix to obtain the damage intensity matrix based on the SN curve of the corresponding material.

[0046] Specifically, the kernel density estimation formula is:

[0047] in, is the kernel function, is the bandwidth, is the rainflow count frequency.

[0048] Preferably, the bandwidth is determined according to an optimal bandwidth calculation formula. The optimal bandwidth calculation formula is:

[0049] in, For variables or The standard deviation of For variables or interquartile range.

[0050] Preferably, the kernel function may be a Gaussian kernel function or an Epanechnikov kernel function; the extrapolation factor may be set to: (annual mileage or half-year mileage of the vehicle) / actual test mileage.

[0051] Preferably, the damage calculation may use the Basquin life equation:

[0052] in, is the fatigue life, i.e. the number of cycles before failure; is the value of alternating stress; 、 is the material constant.

[0053] In the embodiment of the present application, corresponding to each channel load data in the load data, the damage intensity matrix is:

[0054]

[0055]

[0056] in, Corresponding stress level Rainflow counting results under the conditions; For actual test mileage.

[0057] For example, the damage intensity matrix constructed based on the engine is shown in Table 2.

[0058] Table 2: Damage Intensity Matrix

[0059] Furthermore, in order to process user vehicle driving data separately based on target market segments, the embodiment of the present application constructs a user feature model and the damage intensity matrix for analysis.

[0060] Specifically, step S3 includes: S31, obtaining road driving samples of different logistics types; S32, preprocessing the road driving sample; S33. Quantitatively evaluate the user factor model through road network identification and load estimation to construct the user feature model.

[0061] S34, checking whether the user characteristic model has reached convergence. If the relative error value of the model parameter is less than the convergence expectation threshold, the user characteristic model construction is completed; if not, obtaining a new road driving sample and executing step S31.

[0062] Specifically, the user characteristic model is shown in Table 1, including the mean and standard deviation of the mileage ratio under different driving conditions.

[0063] To ensure product reliability is comprehensive and encompassing, the target damage results for the defined components must cover all possible user scenarios. This embodiment uses Monte Carlo simulation to generate random samples of the user feature model and constructs a virtual user model based on these random samples, enabling simulation of component damage matrices across different user groups.

[0064] Furthermore, step S4 includes: S41, performing a Monte Carlo simulation on the user feature model to obtain a random sample of virtual users of each logistics type; S42, determining a virtual user model based on the virtual user random sample; the virtual user model includes A virtual user, is an integer greater than or equal to 1; S43. Determine the component damage matrix according to the damage intensity matrix and the virtual user model.

[0065] In step S42, assuming that user usage follows normal distribution characteristics, Monte Carlo simulation technology is used to perform virtual user expansion to obtain a random sample of virtual users; The constraints are as follows:

[0066] in, For the driving condition The mileage percentage below; For the allowable error.

[0067] In step S43, the component damage matrix is ​​calculated using the damage intensity matrix and the virtual user model.

[0068] In the calculation of the component damage matrix, the component damage matrix can be obtained by the product of the damage intensity matrix and the virtual user model, that is:

[0069] in, For the driving condition and signal channels The damage intensity matrix; is the virtual user model; is the component damage matrix.

[0070] In this embodiment of the application, the sampled road driving samples only reflect the driving habits of the sampled individual users. In order to ensure that the component damage matrix can truly reflect the results brought about by the driving habits of the user group, this embodiment of the application uses a virtual user model to solve the damage results.

[0071] Specifically, in step S43, the calculation formula is as follows:

[0072] in, is the mean The traversal segment number; is the minimum mean value of each driving condition of the user characteristic model; Calculate the step size for the mean traversal; is the standard deviation The traversal segment number; is the minimum standard deviation of each driving condition of the user characteristic model; Calculate the step size for the standard deviation traversal; For the the virtual user model of the logistics type; For the Channels of the stated logistics type The component damage matrix.

[0073] Preferably, Take 0.05; Take 0.1; ; Take 0.1; Take 0.1; .

[0074] After step S4, the method further includes: S5, determining target damage results of components according to a preset damage percentage and a design life mileage.

[0075] In step S5, it specifically includes: S51. Obtaining a preset damage percentage and design life mileage; S52. Calculate the target damage results of components in each channel under the design life mileage.

[0076] For example, taking the engine product test data in Table 3 as an example, the preset damage percentages are defined as 90%, 95%, and 99%, and the product design life is defined as 800,000 kilometers.

[0077] Then calculate the target damage results of each channel component of the group user under the product design life , and the damage data shown in Table 3 were obtained.

[0078] Table 3: Example table of target damage results for components.

[0079]

[0080] It should be noted that the damage extrapolation method of the embodiment of the present application is not only applicable to the product target damage extrapolation of the high-cycle fatigue model, but also to other damage models, such as: low-cycle fatigue damage model, temperature damage model and wear damage model.

[0081] The target components of the embodiments of the present application are not only suitable for engine target damage extrapolation, but can also be used as a reference for other vehicle products, traditional power system components, electric drive system components, etc.

[0082] This embodiment of the application establishes a target damage assessment model for engine engines in specific market segments by building a three-tiered analysis framework: "User Profiling - Operating Condition Segmentation - Damage Mapping." This method, combined with big data analytics and Monte Carlo simulation, breaks away from the traditional "vehicle-centric" damage assessment paradigm and instead adopts a dynamic extrapolation mechanism based on the co-evolution of "human-vehicle-environment." This method accurately defines target damage across the entire lifecycle of a user group, laying the foundation for user-dependent product reliability design.

[0083] Example 3 A component damage extrapolation system based on user usage characteristics is used to execute the steps in the component damage extrapolation method described in Example 1 or Example 2.

[0084] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0085] The solution of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own focus. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. Those skilled in the art should also be aware that the actions and modules mentioned in the description are not necessarily required for this application.

[0086] In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0087] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0088] Alternatively, the present application can also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0089] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.

[0090] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems and methods according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] The embodiments of the present application have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to the technology in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

Claims

1. A component damage extrapolation method based on user usage characteristics, characterized in that: include: Collect load data of target components for i driving conditions and j signal channels; i and j are both integers greater than or equal to 1; Extrapolating the load data, and obtaining a damage intensity matrix through damage calculation; Constructing a user feature model; The user feature model is a distributed matrix of the mileage ratio under at least one logistics type; the rows of the distributed matrix represent the logistics type, the columns of the distributed matrix represent the driving conditions, and the elements of the distributed matrix represent the mileage ratio; The damage matrix of parts of different logistics types is predicted based on the user feature model and the damage intensity matrix.

2. A component damage extrapolation method based on user usage characteristics according to claim 1, characterized in that: The collecting of load data of i driving conditions and j signal channels of the target component specifically includes: Obtaining the type of data to be collected of the target component; Acquire road test data according to the data type to be collected; the road test data includes raw data of i driving conditions and j signal channels; Determining the confidence level of the road test data according to a minimum test mileage calculation function; Determine whether the confidence level of the road test data is greater than a preset confidence threshold; if so, use the road test data as the load data; if not, retest the road test data.

3. The component damage extrapolation method based on user usage characteristics according to claim 2 is characterized in that: The minimum test mileage calculation function is: in, for The numerical value corresponding to the percentile point; for Confidence under the conditions, for The inverse of the normal distribution function; is the significance level; is the average length of the road test data slice, sample The sum of is equal to the minimum test mileage; for Standard deviation of damage values; is the number of road test data slices, and the product of the number of road test data slices and the average length of the road test data slices is the minimum test mileage.

4. The component damage extrapolation method based on user usage characteristics according to claim 1 is characterized in that: Based on the load data, the damage intensity matrix is ​​obtained by extrapolation through damage calculation, specifically including: Performing rain flow counting on the load data to obtain a From-to matrix of the rain flow counting; Rain flow is extrapolated based on the kernel density estimation formula to obtain the rain flow matrix of annual mileage; The rain flow matrix is ​​proportionally extrapolated to obtain the damage intensity matrix based on the SN curve of the corresponding material.

5. The component damage extrapolation method based on user usage characteristics according to claim 1 is characterized in that: The constructing of the user feature model specifically includes: Obtaining road driving samples of different logistics types; Preprocessing the road driving sample; The user factor model is quantitatively evaluated through road network identification and load estimation to construct the user feature model. Check whether the user feature model has reached convergence. If the relative error value of the model parameter is less than the convergence expectation threshold, the user feature model construction is completed; if not, obtain the new road driving sample and execute the step: obtain the road driving samples of the different logistics types.

6. The component damage extrapolation method based on user usage characteristics according to claim 1 is characterized in that: Predicting the component damage matrix of different logistics types based on the user feature model and the damage intensity matrix specifically includes: Performing Monte Carlo simulation on the user feature model to obtain random samples of virtual users of each logistics type; Determine a virtual user model based on the virtual user random sample; The component damage matrix is ​​determined according to the damage intensity matrix and the virtual user model.

7. The component damage extrapolation method based on user usage characteristics according to claim 6 is characterized in that: In determining the component damage matrix according to the damage intensity matrix and the virtual user model, the calculation formula specifically includes: in, is the mean The traversal segment number; is the minimum mean value of each driving condition of the user characteristic model; Calculate the step size for the mean traversal; is the standard deviation The traversal segment number; is the minimum standard deviation of each driving condition of the user characteristic model; Calculate the step size for the standard deviation traversal; For the the virtual user model of the logistics type; For the Channels of the stated logistics type The component damage matrix.

8. The component damage extrapolation method based on user usage characteristics according to claim 1 is characterized in that: After predicting the component damage matrices of different logistics types according to the user feature model and the damage intensity matrix, the method further includes: The target damage result of the component is determined based on the preset damage percentage and design life mileage.

9. The component damage extrapolation method based on user usage characteristics according to claim 8 is characterized in that: Determining the target damage result of a component based on the preset damage percentage and the design life mileage specifically includes: Obtain preset damage percentage and design life mileage; Calculate the target damage results of components in each channel under the design life mileage.

10. A component damage extrapolation system based on user usage characteristics, characterized in that: Used to execute the steps in the component damage extrapolation method described in any one of claims 1 to 9.

Images