A digital management system and method for vehicle parts

By analyzing the wear rate, urban wear factor and artificial wear factor of vehicle components, the dynamic detection point of the vehicle is calculated, and the problem of difficulty in dynamic analysis of vehicle components in the prior art is solved, and the accuracy and safety of maintenance are improved.

CN118627763BActive Publication Date: 2024-11-19长沙润伟机电科技有限责任公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411110603.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-19
Estimated Expiration
2044-08-14

AI Technical Summary

Technical Problem

The existing digital management system for vehicle components is difficult to dynamically analyze the critical points of vehicle components based on drivers' driving habits and road conditions within the city, resulting in inaccurate maintenance time and possible safety hazards.

Method used

By obtaining the wear rate of each usable component, the urban wear factor and artificial wear factor are obtained based on the wear rate analysis, and the dynamic detection point of the vehicle is calculated based on the wear rate of the component, which is used as the time point for the next maintenance of the vehicle.

Benefits of technology

It realizes dynamic analysis of vehicle parts maintenance time based on driver's habits and urban road conditions, avoids safety hazards caused by fixed-time maintenance, and improves maintenance efficiency and safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118627763B_ABST
    Figure CN118627763B_ABST
Patent Text Reader

Abstract

The present invention discloses a digital management system and method for vehicle parts, which relates to the technical field of vehicle engineering management, and solves the technical problem that it is difficult to dynamically analyze the critical points of vehicle parts according to the driving habits of drivers and road conditions in a city to obtain the next maintenance time point of the vehicle in the digital management of vehicle parts. The present invention obtains the wear rate of each usable part, and obtains the urban wear factor of each usable part based on the wear rate; obtains the human wear factor of each usable part based on the man-made damaged parts; obtains the vehicle dynamic detection point by analyzing the component wear rate, the urban wear factor and the human wear factor, and uses the vehicle dynamic detection point as the next maintenance time point of the vehicle. The present invention can avoid the situation where fixed time detection leads to certain safety hazards in vehicles due to bad driving habits of drivers and long-term driving on high-wear roads.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the field of vehicle engineering management, relates to digital management technology, and specifically is a vehicle component digital management system and method. Background Art

[0002] With the rapid development of the automotive industry, the maintenance of automotive parts has become increasingly important. Traditional vehicle parts maintenance methods often have problems such as low efficiency, inaccurate information, and difficulty in tracing, which can no longer meet the needs of the modern automotive industry. And with the development of digital technology, applying digital technology to vehicle parts maintenance management can greatly improve the efficiency and quality of maintenance. Through real-time tracking and recording of the maintenance process through digital technology, the maintenance efficiency and quality can be improved, human errors can be reduced, and valuable information can be extracted from a large amount of data through data analysis tools to provide decision makers with a scientific basis for decision making.

[0003] At present, most digital management systems for vehicle parts only involve integrating vehicle parts information and storing the integrated information in the system. This integrated information can only serve as a database and is difficult to actively provide data assistance to managers; and most digital management systems for vehicle parts, in the digital management of vehicle parts, find it difficult to dynamically analyze the critical points of vehicle parts use based on the driver's driving habits and road conditions within the city to obtain the next maintenance time of the vehicle. When using a fixed inspection schedule, it is easy to lead to certain safety hazards due to drivers' bad driving habits and long-term driving on high-wear roads.

[0004] Therefore, the present invention discloses a vehicle parts digital management system and method to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a digital management system and method for vehicle parts, which are used to solve the technical problem that it is difficult to dynamically analyze the critical points of vehicle parts according to the driving habits of the driver and the road conditions in the city to obtain the next maintenance time of the vehicle in the digital management of vehicle parts. The present invention obtains the wear rate of each usable part, and obtains the urban wear factor of each usable part based on the wear rate; obtains the human wear factor of each usable part based on the man-made damaged parts; and obtains the vehicle dynamic detection point by analyzing the part wear rate, urban wear factor and human wear factor to solve the above problems.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides a vehicle component digital management system, comprising: a digital analysis module, and an information acquisition module, a digital management module and a database connected thereto;

[0007] The information acquisition module is used to divide vehicle parts into maintenance-specified parts and non-specified parts, and to obtain maintenance information by performing maintenance on the specified parts through the maintenance device; wherein the maintenance information includes the number of maintenance parts and the status of maintenance parts; the status of maintenance parts includes usable parts and damaged parts;

[0008] The digital analysis module is used to obtain the wear rate of each usable component, and to obtain the urban wear factor of each usable component by performing data analysis based on the wear rate; to extract the artificially damaged components of the current vehicle from the database, and to obtain the artificial wear factor of each usable component based on the artificially damaged components; to obtain the comprehensive wear factor based on the urban wear factor and the artificial wear factor; to obtain the critical point of use of each usable component based on the comprehensive wear factor and the component wear rate; to obtain the vehicle dynamic detection point by performing analysis based on the critical point of use of each usable component; wherein the artificially damaged component refers to the component that is easily damaged due to the driver's driving habits; the critical point of use is placed before the component damage point;

[0009] The digital management module extracts the vehicle dynamic detection points and transmits the vehicle dynamic detection points as the vehicle's next maintenance time point to the client to remind the user to pay attention to the maintenance.

[0010] It should be noted that the status of the repaired parts includes usable parts and damaged parts. Usable parts refer to parts that have not exceeded the critical point of use in this inspection; damaged parts include parts that have exceeded the critical point of use and have been damaged in this inspection; usable parts continue to be used, and damaged parts are replaced with new parts. Since the replaced new parts are in a brand new state, the subsequent analysis of the parts in the present invention only analyzes the usable parts. This can reduce the calculation of the system and improve the efficiency of the analysis.

[0011] It should be noted that the critical point of use does not refer to the point where the component is damaged, but is placed before the point where the component is damaged. When the component reaches the critical point of use, the component can still be used, but is in a state where replacement is required. Setting the critical point of use of the component can intuitively analyze the next maintenance time of the vehicle, thereby improving the efficiency of system analysis.

[0012] It should be noted that if the current vehicle comes to this maintenance station for maintenance for the first time, standard data will be selected from the database according to the current vehicle's age to analyze the next maintenance time of the current vehicle, or the next maintenance time of the vehicle will be set according to the specified maintenance interval.

[0013] It should be noted that artificially damaged parts are manually set. For example, human driving habits can easily lead to engine damage or horn damage. By setting artificially damaged parts, the relationship between the parts and the driver's usage impact can be quickly divided, avoiding a large amount of useless calculations in the subsequent analysis of artificial wear factors.

[0014] Preferably, the digital analysis module communicates and / or is electrically connected to the information acquisition module, the digital management module and the database respectively; the database communicates and / or is electrically connected to the information acquisition module and the digital analysis module respectively.

[0015] Preferably, the urban wear factor of each usable component obtained by performing data analysis based on the wear rate includes:

[0016] Extract the wear rate of each usable component, establish a sequence table based on the importance of the components, and number each usable component;

[0017] According to the number, extract the historical wear rate of the same type of parts as the numbered parts, and the historical service life corresponding to the historical wear rate from the database, perform data cleaning on the historical service life to obtain a historical service life library corresponding to the historical wear rate; obtain the average value of the data in the historical service life library, and mark the average value as the average service life PJMn; wherein n is the sequence number of the sequence table;

[0018] The standard service life BMn corresponding to the wear rate of the usable component is obtained based on the formula BMn=(1-MLn)×BZn; where MLn is the corresponding wear rate of the component, and BZn is the corresponding standard life cycle of the component;

[0019] Extract the average service life PJMn and the standard service life BMn, and determine whether the average service life PJMn is greater than the standard service life BMn; if yes, mark the urban wear factor CMYn as 0; if not, obtain the urban wear factor CMYn of each usable component through the formula CMYn=α×(exp((BMn-PJMn) / BMn)-1); where α is the weight adjustment coefficient.

[0020] In the present invention, by analyzing the historical data of the same type and the same wear rate as each usable component, the data interference caused by other factors is removed, and the average service life of this component in the current city under this wear rate is obtained. Then, by analyzing the average service life and the standard service life, the wear of the component caused by the infrastructure factors in the current city is obtained. The smaller the value of the average service life, the greater the wear of the component caused by the infrastructure factors in the current city, and the larger the corresponding city wear factor. In this way, the wear of the component caused by the infrastructure factors in the city can be intuitively expressed in a digital way, which improves the efficiency of the system in analyzing the wear of vehicle components.

[0021] Preferably, the data cleaning of the historical service life to obtain a historical service life library corresponding to the historical wear rate includes:

[0022] Establish a data group according to the historical service life from long to short, obtain the variance of the data group, and judge whether the variance is less than a set value; if yes, retain the data in the data group; if no, extract the mode in the data group, remove the number with the largest absolute value of the difference between the mode and the data group, and recalculate the variance of the data group until the variance of the data group is less than the set value, stop judging the variance, and retain the data in the data group that has not been removed; wherein the set value is obtained through experience;

[0023] The data retained in the data group are integrated into a historical service life library.

[0024] It should be noted that the vehicles that undergo vehicle component maintenance at the same maintenance station have similar approximate ranges of activity, and most of them are active around the current city. Therefore, the service life of these vehicle components is studied, and after removing the interference of human driving factors, what is obtained is the interference caused by urban road facilities to vehicle components. The present invention performs variance judgment on the data in order to remove the human interference factors in the data group. The data close to the mode in the data group represent that the driving habits of the current vehicle driver are in line with the habits of most people; removing the number with the largest absolute value of the difference from the mode in the data group is to remove some changes in the service life of vehicle components caused by different driving habits. After removing the interference factors caused by different driving habits, the data obtained is a service life database caused by the activities of some vehicles with the same driving habits around the current city, which provides data support for the subsequent calculation of the urban wear factor.

[0025] Preferably, obtaining the artificial wear factor of each usable component based on the artificially damaged component includes:

[0026] Extract the probability of man-made damage parts for each inspection of the current vehicle and establish a probability library of man-made damage parts; remove the abnormal probability in the probability library of man-made damage parts, obtain the average value of the data in the probability library of man-made damage parts after removing the abnormal probability, and mark the average value of the data in the probability library of man-made damage parts as the average probability of man-made damage for the current vehicle;

[0027] Extract the sequence table, extract the usable parts in sequence based on the numbers, and judge whether the current usable parts are non-human-damaged parts; if yes, mark the human-damaged factor as 0; if no, train the artificial intelligence model based on historical data to obtain the human-damaged model; obtain the ratio of the number of damages of the current usable parts to the number of maintenances of the current vehicle, and mark the ratio as the human-damaged parts ratio; input the current vehicle's average human-damaged probability and the human-damaged parts ratio of the current usable parts into the human-damaged model to obtain the human-damaged factor RMYn.

[0028] It should be noted that the present invention extracts the probability of man-made damaged parts in each maintenance of the current vehicle. The probability of man-made damaged parts obtained in this step refers to the ratio of the number of man-made damaged parts in each maintenance to the total number of damaged parts at that time in the historical data of the current vehicle maintenance. This ratio can indicate the impact of the current driver's driving habits on the vehicle. The higher the ratio, the greater the impact of the driver's driving habits on the vehicle.

[0029] Preferably, the training of the artificial intelligence model based on historical data includes:

[0030] The standard average probability of human damage and the ratio of the historical damage times of the same type of human-damaged parts in other similar vehicles to the corresponding vehicle maintenance times are obtained through the database, and the average ratio is obtained, and the average ratio is marked as the standard human-damaged parts ratio of the current human-damaged parts; the standard average probability of human damage and the standard human-damaged parts ratio are marked as standard input data, and the human wear factors corresponding to the standard average probability of human damage and the standard human-damaged parts ratio are marked as standard output data; an artificial intelligence model is trained based on the standard input data and the standard output data to obtain an artificial wear model; wherein the artificial intelligence model includes a BP neural network or a deep belief network.

[0031] It should be noted that the artificial wear factors corresponding to the standard artificial average probability and the standard artificial component ratio are obtained by manual analysis.

[0032] Preferably, the comprehensive wear factor obtained based on the urban wear factor and the human wear factor includes:

[0033] The urban wear factor CMYn and the human wear factor RMYn of each usable component are extracted; the comprehensive wear factor ZMYn of the corresponding component is obtained by calculating the urban wear factor CMYn and the human wear factor RMYn according to the formula. The specific calculation method is ZMYn=δ×ln(β×CMYn+γ×RMYn+1)+1; wherein β and γ are proportional adjustment coefficients, and β+γ=1; δ is the amplitude adjustment coefficient.

[0034] Preferably, obtaining the critical point of each usable component based on the comprehensive wear factor and the component wear rate includes:

[0035] Extract the component wear rate of each usable component, extract the same type of components of the same type as each usable component from the database, remove the components of the same type that have different component wear rates from the corresponding usable components, and establish a corresponding same type database for the remaining components;

[0036] Obtain the usage time of each component in the same type database of each usable component from the current component wear rate to the usage critical point, and establish several usage time groups; obtain the variance of each usage time group, and determine whether the variance is less than a set threshold; if so, calculate the average value of the group; if not, extract the mode of the usage time group, remove the number with the largest absolute value of the difference between the mode and the group, and recalculate the variance of the group until the variance of the group is less than the set threshold and calculate the average value of the group;

[0037] The average value corresponding to the usage time group is marked as the standard usage time BSCn of each usable component corresponding to the group;

[0038] The comprehensive wear factor ZMYn and the corresponding standard service life BSCn of each usable component are extracted, and the critical point of use of each usable component is obtained based on the formula SLDn=BSCn / ZMYn+DS; where DS is the time point of the current maintenance.

[0039] It should be noted that in obtaining the critical point of each usable component based on the formula SLDn=BSCn / ZMYn+DS, this formula first divides the standard usage time by the comprehensive wear factor of the component to obtain the time it takes for the component to reach the critical point of use, and then adds the time it takes for the component to reach the critical point of use and the current maintenance time point to obtain the critical point of use of the component.

[0040] Preferably, the vehicle dynamic detection point is obtained by analyzing the critical points of each usable component, including:

[0041] Extract the critical points of each usable component, sort the critical points based on time priority to establish a sorting table; wherein the earlier the time, the higher the priority;

[0042] Extract each usage critical point in the sorting table in turn, and judge whether the ratio of the number of serial numbers of the extracted usage critical points to the total number of serial numbers in the sorting table is less than a preset ratio; if yes, continue to extract the next usage critical point in the sorting table, and make a judgment until the ratio of the number of serial numbers of the extracted usage critical points to the total number of serial numbers in the sorting table exceeds the preset ratio, and stop the operation, and use the time of the current usage critical point as the vehicle dynamic detection point; if no, use the time of the current usage critical point as the vehicle dynamic detection point; wherein the preset ratio is set manually.

[0043] It should be noted that the preset ratio can be understood as a threshold value. When the number of each usable component reaching the critical point exceeds the threshold value, it means that the current vehicle needs to be repaired. The present invention first sorts the critical points of the usable components from front to back based on time, and then sets the threshold value to the preset ratio equivalently. When the ratio of the number of extracted critical points of use to the total number of serial numbers in the sorting table reaches the preset ratio, it means that at the time of the current critical point of use, the number of each usable component reaching the critical point exceeds the threshold value, and the current vehicle needs to be repaired. Establishing a sorting table and setting the threshold value to a preset ratio equivalently can more quickly obtain the vehicle dynamic detection point when the threshold is reached.

[0044] A second aspect of the present invention provides a vehicle component digital management method, comprising the following steps:

[0045] S1: Divide vehicle parts into maintenance-specified parts and non-specified parts, and perform maintenance on the specified parts through the maintenance device to obtain maintenance information;

[0046] S2: Obtain the wear rate of each usable component, and perform data analysis based on the wear rate to obtain the urban wear factor of each usable component; extract the artificially damaged components of the current vehicle in historical maintenance from the database, and obtain the artificial wear factor of each usable component based on the artificially damaged components; obtain the comprehensive wear factor based on the urban wear factor and the artificial wear factor; obtain the critical point of use of each usable component based on the comprehensive wear factor and the component wear rate; and obtain the vehicle dynamic detection point based on the critical point of use of each usable component;

[0047] S3: Extract the vehicle dynamic detection point, and transmit the vehicle dynamic detection point as the vehicle's next maintenance time point to the client to remind the user to pay attention to the maintenance.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. The present invention obtains the wear rate of each usable component, performs data analysis based on the wear rate to obtain the urban wear factor of each usable component; obtains the artificial wear factor of each usable component based on the artificially damaged component; and obtains the vehicle dynamic detection point by analyzing the component wear rate, urban wear factor and artificial wear factor, thereby solving the problem that it is difficult to dynamically analyze the critical point of vehicle component use according to the driver's driving habits and the road conditions within the city to obtain the next vehicle inspection time point in the digital management of vehicle components. By dynamically obtaining the next vehicle inspection time point, a set of inspection schedules based on the driver's driving habits and the road conditions around the city can be set, avoiding the situation where fixed time inspections lead to certain safety hazards for vehicles with bad driving habits and long-term driving on high-wear roads.

[0050] 2. The present invention analyzes the historical data of the same type and the same wear rate of each usable component, removes the data interference caused by other factors, and obtains the average service life of this component in the current city under this wear rate. Then, by analyzing the average service life and the standard service life, the wear of the component caused by the infrastructure factors in the current city is obtained. The smaller the value of the average service life, the greater the wear of the component caused by the infrastructure factors in the current city, and the larger the corresponding city wear factor. In this way, the wear of the component caused by the infrastructure factors in the city can be intuitively expressed in a digital way, which improves the efficiency of the system in analyzing the wear of vehicle components. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 It is a schematic diagram of the system module of the present invention;

[0053] Figure 2 It is a schematic diagram of the operation steps of the present invention;

[0054] Figure 3 It is a schematic diagram of the operating steps for obtaining the urban wear factor of each usable component in the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] See also Figure 1-Figure 3 , the first aspect of the present invention provides a vehicle parts digital management system, including: a digital analysis module, and an information acquisition module, a digital management module and a database connected thereto;

[0057] Information acquisition module: used to divide vehicle parts into maintenance-specified parts and non-specified parts, and obtain maintenance information by performing maintenance on the specified parts through maintenance devices; wherein the maintenance information includes the number of maintenance parts and the status of maintenance parts; the status of maintenance parts includes usable parts and damaged parts;

[0058] Digital analysis module: used to obtain the wear rate of each usable component, and obtain the urban wear factor of each usable component based on the wear rate through data analysis; extract the artificially damaged components of the current vehicle's historical maintenance from the database, and obtain the artificial wear factor of each usable component based on the artificially damaged components; obtain the comprehensive wear factor based on the urban wear factor and the artificial wear factor; obtain the critical point of use of each usable component based on the comprehensive wear factor and the component wear rate; obtain the vehicle dynamic detection point based on the critical point of use of each usable component; among which, the artificially damaged component refers to the component that is easily damaged due to the driver's driving habits; the critical point of use is placed before the component damage point;

[0059] Digital management module: extract vehicle dynamic detection points, and transmit the vehicle dynamic detection points as the vehicle's next maintenance time point to the client to remind users to pay attention to maintenance.

[0060] In this embodiment, the user's vehicle type is a C-class sedan, and the age is 2 years;

[0061] The specific operation steps of this embodiment are: after inspecting the specified parts of the vehicle to obtain usable parts and damaged parts, the damaged parts are replaced with new parts, and the usable parts are further analyzed to obtain the next inspection time of the vehicle. The analysis steps are:

[0062] 1. Obtain the wear rate of each usable component through the inspection results of this time, extract the historical wear rate of the same component type and the same wear rate, and the historical service life corresponding to the historical wear rate from the database, perform data cleaning on the historical service life corresponding to each usable component, calculate the average service life, and then perform standard calculation on the wear rate of the usable component to obtain the standard service life. Calculate the formula of the average service life and the standard service life to obtain the urban wear factor of each usable component;

[0063] For example: the wear rate of each usable component is obtained through the results of this maintenance. If the type is a usable component with a wear rate of 50%, the information of usable components with a wear rate of 50% is extracted from the database in the maintenance station. If there is a time for the component to be damaged from a wear rate of 50% in this information, the time for the component to be damaged is marked as the corresponding historical service life. Then, the historical service life corresponding to each usable component is cleaned and the average value is calculated to obtain the average service life. Then the standard life cycle BZn of the usable component is obtained. When the wear rate of the component is 50%, the standard usable service life BM of the usable component can be obtained. The value of n is BZn / 2; when the average life PJMn is greater than the standard service life BMn, it means that the current vehicle's driving in the range of activities is in a state of zero wear, low wear or protection for the current components. At this time, the urban wear factor CMYn is marked as 0. When the average life PJMn is not greater than the standard service life BMn, the average life PJMn and the standard service life BMn are substituted into the formula CMYn=α×(exp((BMn-PJMn) / BMn)-1) to obtain the urban wear factor of each usable component; among them, the usable components include brake pads, gearboxes, tires, headlights or rearview mirrors.

[0064] 2. Extract the man-made damaged parts of the current vehicle from the historical maintenance from the database, obtain the corresponding man-made damaged parts probability, and establish a man-made damaged parts probability library. After removing the abnormal probability, calculate the average value of the man-made damaged parts probability library to obtain the man-made average probability of the current vehicle; then obtain the man-made wear factor through judgment analysis and training of artificial intelligence models;

[0065] For example: extract the probability of artificially damaged parts in the historical maintenance of the current vehicle from the database, and calculate the average value of the probability library of artificially damaged parts after removing the abnormal probability, and the obtained artificial average probability is 60%, which proves that the current driver has bad driving habits, which will affect the service life of the vehicle; then judge whether the current usable parts are non-artificially damaged parts; if yes, it means that the usable parts are not parts that are easily damaged by artificial driving habits, so the artificial wear factor is marked as 0; if no, it means that the usable parts are parts that are easily damaged by artificial driving habits. At this time, first obtain the artificial average probability of all people through the maintenance station database, and calculate the average value to obtain the standard artificial average probability, then obtain the proportion of the historical damage times of the usable parts in other C-class cars to the corresponding vehicle maintenance times and calculate the average value, mark the average value as the standard artificial part ratio of the usable parts, and train the artificial intelligence model based on the standard artificial average probability and the standard artificial part ratio to obtain the artificial wear model; obtain the proportion of the damage times of the usable parts to the current vehicle maintenance times is 50%, mark 50% as the artificial part ratio of the usable parts, and input the current vehicle's artificial average probability of 60% and the artificial part ratio of the usable parts of 50% into the artificial wear model to obtain the artificial wear factor.

[0066] 3. Extract the urban wear factor and human wear factor of each usable component; calculate the comprehensive wear factor of the corresponding component by formulating the urban wear factor and human wear factor;

[0067] 4. Based on the comprehensive wear factor and component wear rate, the critical point of each usable component is obtained; based on the critical point of each usable component, the dynamic detection point of the vehicle is obtained by analysis;

[0068] 5. Extract the vehicle dynamic detection points and transmit them to the client as the next vehicle maintenance time point to remind the user to pay attention to maintenance.

[0069] In the present invention, the urban wear factor of each usable component is obtained by data analysis based on the wear rate, including:

[0070] Extract the wear rate of each usable component, establish a sequence table based on the importance of the components, and number each usable component;

[0071] According to the number, extract the historical wear rate of the same type of parts as the numbered parts, and the historical service life corresponding to the historical wear rate from the database, perform data cleaning on the historical service life to obtain a historical service life library corresponding to the historical wear rate; obtain the average value of the data in the historical service life library, and mark the average value as the average service life PJMn; wherein n is the sequence number of the sequence table;

[0072] The standard service life BMn corresponding to the wear rate of the usable component is obtained based on the formula BMn=(1-MLn)×BZn; where MLn is the corresponding wear rate of the component, and BZn is the corresponding standard life cycle of the component;

[0073] Extract the average service life PJMn and the standard service life BMn, and determine whether the average service life PJMn is greater than the standard service life BMn; if yes, mark the urban wear factor CMYn as 0; if not, obtain the urban wear factor CMYn of each usable component through the formula CMYn=α×(exp((BMn-PJMn) / BMn)-1); where α is the weight adjustment coefficient.

[0074] It should be noted that the importance of components is set manually.

[0075] It should be noted that in the present invention, the historical wear rate of the same type of parts with the same wear rate as the numbered parts and the historical service life corresponding to the historical wear rate are extracted from the database according to the number. This step means that if the part is a usable part and the wear rate is 50%, then the historical service life corresponding to the usable part and the wear rate of 50% is extracted from the historical data in the maintenance station.

[0076] It should be noted that in the historical service life corresponding to the historical wear rate, the data impacts caused by human factors and urban infrastructure factors are different. At this time, the human factors are removed through data cleaning to obtain the impact caused by urban infrastructure factors.

[0077] It should be noted that the average service life PJMn represents the service life of this component under this wear rate in the current city.

[0078] It should be noted that marking the urban wear factor CMYn as 0 does not mean that urban infrastructure has no impact on vehicle components, but rather that the impact on the components is negligible.

[0079] In the present invention, the artificial wear factor of each usable component is obtained based on the artificially damaged component, including:

[0080] Extract the probability of man-made damage parts for each inspection of the current vehicle and establish a probability library of man-made damage parts; remove the abnormal probability in the probability library of man-made damage parts, obtain the average value of the data in the probability library of man-made damage parts after removing the abnormal probability, and mark the average value of the data in the probability library of man-made damage parts as the average probability of man-made damage for the current vehicle;

[0081] Extract the sequence table, extract the usable parts based on the number in sequence, and judge whether the current usable parts are non-human-damaged parts; if yes, mark the human-damaged factor as 0; if no, train the artificial intelligence model based on historical data to obtain the human-damaged model; obtain the ratio of the number of damages of the current usable parts to the number of maintenances of the current vehicle, and mark the ratio as the ratio of human-damaged parts; input the average human-damaged probability of the current vehicle and the ratio of human-damaged parts of the current usable parts into the human-damaged model to obtain the human-damaged factor RMYn.

[0082] It should be noted that the present invention removes abnormal probabilities in the probability library of man-made damaged parts, which refers to the probability when the probability exceeds the maximum threshold of normal damage. This situation may be damage to vehicle parts caused by abnormal driving and cannot be analyzed as normal data.

[0083] It should be noted that marking the human wear factor as 0 does not mean that the driver's driving habits have no impact on the vehicle components, but rather that the impact on the components is negligible.

[0084] The present invention trains an artificial intelligence model based on historical data, including:

[0085] The standard average probability of human damage and the ratio of the historical damage times of the same type of human-damaged parts in other similar vehicles to the corresponding vehicle maintenance times are obtained through the database, and the average ratio is obtained, and the average ratio is marked as the standard human-damaged parts ratio of the current human-damaged parts; the standard average probability of human damage and the standard human-damaged parts ratio are marked as standard input data, and the human wear factors corresponding to the standard average probability of human damage and the standard human-damaged parts ratio are marked as standard output data; an artificial intelligence model is trained based on the standard input data and the standard output data to obtain an artificial wear model; wherein the artificial intelligence model includes a BP neural network or a deep belief network.

[0086] It should be noted that, in the present invention, the standard human average probability is obtained through the database, and the standard human average probability refers to the average value of the human average probabilities of all vehicles in the maintenance station database.

[0087] In the present invention, a comprehensive wear factor is obtained based on the urban wear factor and the human wear factor, including:

[0088] The urban wear factor CMYn and the human wear factor RMYn of each usable component are extracted; the comprehensive wear factor ZMYn of the corresponding component is obtained by calculating the urban wear factor CMYn and the human wear factor RMYn according to the formula. The specific calculation method is ZMYn=δ×ln(β×CMYn+γ×RMYn+1)+1; wherein β and γ are proportional adjustment coefficients, and β+γ=1; δ is the amplitude adjustment coefficient.

[0089] It should be noted that the value of the comprehensive wear factor increases with the increase in the total value of the ratio of urban wear factor and human wear factor.

[0090] It should be noted that the comprehensive wear factor obtained in the present invention based on the urban wear factor and the human wear factor is used to comprehensively analyze the wear of vehicle components caused by the current driver's driving within the previous activity range, and is used for subsequent analysis of the critical points of use of usable components.

[0091] A second aspect of the present invention provides a vehicle component digital management method, comprising the following steps:

[0092] S1: Divide vehicle parts into maintenance-specified parts and non-specified parts, and perform maintenance on the specified parts through the maintenance device to obtain maintenance information;

[0093] S2: Obtain the wear rate of each usable component, and perform data analysis based on the wear rate to obtain the urban wear factor of each usable component; extract the artificially damaged components of the current vehicle in historical maintenance from the database, and obtain the artificial wear factor of each usable component based on the artificially damaged components; obtain the comprehensive wear factor based on the urban wear factor and the artificial wear factor; obtain the critical point of use of each usable component based on the comprehensive wear factor and the component wear rate; and obtain the vehicle dynamic detection point based on the critical point of use of each usable component;

[0094] S3: Extract the vehicle dynamic detection point, and transmit the vehicle dynamic detection point as the vehicle's next maintenance time point to the client to remind the user to pay attention to the maintenance.

[0095] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0096] Working principle of the present invention:

[0097] The present invention divides vehicle parts into parts specified for maintenance and parts not specified for maintenance, and uses a maintenance device to repair the specified parts to obtain the status of the repaired parts, including usable parts and damaged parts; obtains the wear rate of each usable part, and performs data analysis based on the wear rate to obtain the urban wear factor of each usable part; extracts artificially damaged parts from historical repairs of the current vehicle from a database, and obtains the artificial wear factor of each usable part based on the artificially damaged parts; obtains a comprehensive wear factor based on the urban wear factor and the artificial wear factor; obtains the critical point of use of each usable part based on the comprehensive wear factor and the part wear rate; analyzes based on the critical point of use of each usable part to obtain the vehicle dynamic detection point; and transmits the vehicle dynamic detection point to the client as the next maintenance time point of the vehicle to remind the user to pay attention to maintenance.

[0098] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A digital management system for vehicle parts, It is characterized in that include: A digital analysis module, and an information acquisition module, a digital management module and a database connected thereto; The information acquisition module is used to divide vehicle parts into maintenance-specified parts and non-specified parts, and to obtain maintenance information by performing maintenance on the specified parts through the maintenance device; wherein the maintenance information includes the number of maintenance parts and the status of maintenance parts; the status of maintenance parts includes usable parts and damaged parts; The digital analysis module is used to obtain the wear rate of each usable component, and to obtain the urban wear factor of each usable component by performing data analysis based on the wear rate; to extract the artificially damaged components of the current vehicle from the database, and to obtain the artificial wear factor of each usable component based on the artificially damaged components; to obtain the comprehensive wear factor based on the urban wear factor and the artificial wear factor; to obtain the critical point of use of each usable component based on the comprehensive wear factor and the component wear rate; to obtain the vehicle dynamic detection point by performing analysis based on the critical point of use of each usable component; wherein the artificially damaged component refers to the component that is easily damaged due to the driver's driving habits; the critical point of use is placed before the component damage point; The digital management module extracts the vehicle dynamic detection points and transmits the vehicle dynamic detection points as the next vehicle maintenance time point to the client to remind the user to pay attention to the maintenance; The urban wear factor of each usable component obtained by data analysis based on the wear rate includes: Extract the wear rate of each usable component, establish a sequence table based on the importance of the components, and number each usable component; According to the number, extract the historical wear rate of the same type of parts as the numbered parts, and the historical service life corresponding to the historical wear rate from the database, perform data cleaning on the historical service life to obtain a historical service life library corresponding to the historical wear rate; obtain the average value of the data in the historical service life library, and mark the average value as the average service life PJMn; wherein n is the sequence number of the sequence table; The standard service life BMn corresponding to the wear rate of the usable component is obtained based on the formula BMn=(1-MLn)×BZn; where MLn is the corresponding wear rate of the component, and BZn is the corresponding standard life cycle of the component; Extract the average service life PJMn and the standard service life BMn, and determine whether the average service life PJMn is greater than the standard service life BMn; if yes, mark the urban wear factor CMYn as 0; if no, obtain the urban wear factor CMYn of each usable component through the formula CMYn=α×(exp((BMn-PJMn) / BMn)-1); where α is the weight adjustment coefficient; The method of obtaining the artificial wear factor of each usable component based on the artificially damaged component includes: Extract the probability of man-made damage parts for each inspection of the current vehicle and establish a probability library of man-made damage parts; remove the abnormal probability in the probability library of man-made damage parts, obtain the average value of the data in the probability library of man-made damage parts after removing the abnormal probability, and mark the average value of the data in the probability library of man-made damage parts as the average probability of man-made damage for the current vehicle; Extract the sequence table, extract the usable parts based on the serial number, and judge whether the currently usable parts are non-human-damaged parts; if yes, mark the human-damaged factor as 0; if no, train the artificial intelligence model based on historical data to obtain the human-damaged model; obtain the ratio of the number of times the currently usable parts are damaged to the number of times the current vehicle is overhauled, and mark the ratio as the ratio of human-damaged parts; input the average human-damaged probability of the current vehicle and the ratio of human-damaged parts of the currently usable parts into the human-damaged model to obtain the human-damaged factor RMYn; The comprehensive wear factor obtained based on the urban wear factor and the human wear factor includes: Extract the urban wear factor CMYn and the man-made wear factor RMYn of each usable component; calculate the comprehensive wear factor ZMYn of the corresponding component by formulating the urban wear factor CMYn and the man-made wear factor RMYn. The specific calculation method is ZMYn=δ×ln(β×CMYn+γ×RMYn+1)+1; where β and γ are proportional adjustment coefficients, and β+γ=1; δ is the amplitude adjustment coefficient; The method of obtaining the critical point of each usable component based on the comprehensive wear factor and the component wear rate includes: Extract the component wear rate of each usable component, extract the same type of components of the same type as each usable component from the database, remove the components of the same type that have different component wear rates from the corresponding usable components, and establish a corresponding same type database for the remaining components; Obtain the usage time of each component in the same type database of each usable component from the current component wear rate to the critical point of use, and establish several usage time groups; obtain the variance of each usage time group, and determine whether the variance is less than a set threshold; if yes, calculate the average value of the usage time group; if no, extract the mode of the usage time group, remove the number with the largest absolute value of the difference between the mode and the usage time group, and recalculate the variance of the usage time group until the variance of the usage time group is less than the set threshold, and then calculate the average value of the usage time group; The average value corresponding to the usage time group is marked as the standard usage time BSCn of each usable component corresponding to the usage time group; The comprehensive wear factor ZMYn and the corresponding standard service life BSCn of each usable component are extracted, and the critical point of use of each usable component is obtained based on the formula SLDn=BSCn / ZMYn+DS; where DS is the time point of the current maintenance.

2. A vehicle parts digital management system according to claim 1, It is characterized in that The digital analysis module communicates and / or is electrically connected to the information acquisition module, the digital management module and the database respectively; the database communicates and / or is electrically connected to the information acquisition module and the digital analysis module respectively.

3. A vehicle parts digital management system according to claim 1, It is characterized in that The historical service life database corresponding to the historical wear rate is obtained by data cleaning of the historical service life, including: Establish a data group according to the historical service life from long to short, obtain the variance of the data group, and judge whether the variance is less than a set value; if yes, retain the data in the data group; if no, extract the mode in the data group, remove the number with the largest absolute value of the difference between the mode and the data group, and recalculate the variance of the data group until the variance of the data group is less than the set value, stop judging the variance, and retain the data in the data group that has not been removed; The data retained in the data group are integrated into a historical service life library.

4. A vehicle parts digital management system according to claim 1, It is characterized in that The training of the artificial intelligence model based on historical data includes: The standard average probability of human damage and the ratio of the historical damage times of the same type of human-damaged parts in other similar vehicles to the corresponding vehicle maintenance times are obtained through the database, and the average ratio is obtained, and the average ratio is marked as the standard human-damaged parts ratio of the current human-damaged parts; the standard average probability of human damage and the standard human-damaged parts ratio are marked as standard input data, and the human wear factors corresponding to the standard average probability of human damage and the standard human-damaged parts ratio are marked as standard output data; an artificial intelligence model is trained based on the standard input data and the standard output data to obtain an artificial wear model; wherein the artificial intelligence model includes a BP neural network or a deep belief network.

5. A vehicle parts digital management system according to claim 1, It is characterized in that The vehicle dynamic detection points are obtained by analyzing the critical points of each usable component, including: Extract the critical points of each usable component, sort the critical points based on time priority to establish a sorting table; wherein the earlier the time, the higher the priority; Extract each usage critical point in the sorting table in turn, and judge whether the ratio of the number of serial numbers of the extracted usage critical points to the total number of serial numbers in the sorting table is less than a preset ratio; if yes, continue to extract the next usage critical point in the sorting table, and make a judgment until the ratio of the number of serial numbers of the extracted usage critical points to the total number of serial numbers in the sorting table exceeds the preset ratio, and stop the operation, and use the time of the current usage critical point as the vehicle dynamic detection point; if no, use the time of the current usage critical point as the vehicle dynamic detection point.

6. A vehicle parts digital management method, based on the vehicle parts digital management system according to any one of claims 1 to 5, Features: S1: Divide vehicle parts into maintenance-specified parts and non-specified parts, and perform maintenance on the specified parts through the maintenance device to obtain maintenance information; S2: Obtain the wear rate of each usable component, and perform data analysis based on the wear rate to obtain the urban wear factor of each usable component; extract the artificially damaged components of the current vehicle in historical maintenance from the database, and obtain the artificial wear factor of each usable component based on the artificially damaged components; obtain the comprehensive wear factor based on the urban wear factor and the artificial wear factor; obtain the critical point of use of each usable component based on the comprehensive wear factor and the component wear rate; and obtain the vehicle dynamic detection point based on the critical point of use of each usable component; S3: Extract the vehicle dynamic detection point, and transmit the vehicle dynamic detection point as the vehicle's next maintenance time point to the client to remind the user to pay attention to the maintenance.