CN111105522B - Vehicle health prediction system and method - Google Patents
Vehicle health prediction system and method Download PDFInfo
- Publication number
- CN111105522B CN111105522B CN201911258817.8A CN201911258817A CN111105522B CN 111105522 B CN111105522 B CN 111105522B CN 201911258817 A CN201911258817 A CN 201911258817A CN 111105522 B CN111105522 B CN 111105522B
- Authority
- CN
- China
- Prior art keywords
- fault
- vehicle
- sub
- data
- component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention discloses a vehicle health prediction system and a vehicle health prediction method. The system adopts a B/S architecture; the server collects the working parameters of each sub-component in the running process of the vehicle and the working parameter information when the fault of the specific sub-component occurs through the intelligent terminal installed on the vehicle; and carrying out persistent storage on the received working parameter information when the specific sub-component fault occurs, screening and counting the probability distribution of the working parameters related to the specific type fault of the sub-component when the type fault occurs. And the server determines the risk probability of the sub-component failing according to the collected working parameters of the sub-component in the vehicle operation and the probability distribution corresponding to the working parameters when the specific type of the sub-component fails and informs a user in time. The system provided by the invention can predict the failure probability of related subcomponents in the vehicle operation, and informs a user before the actual failure so as to avoid the safety problem of the vehicle caused by sudden failure of the subcomponents.
Description
Technical Field
The invention relates to the field of vehicle health assessment, in particular to a vehicle health prediction system and a vehicle health prediction method. The system and the method can evaluate and feed back the health condition of the related sub-components when the vehicle runs to the user in time.
Background
The operating parameters of each sub-component of the vehicle have preset ranges. Often, the operating parameters of the related sub-components are not within the corresponding predetermined ranges due to out-of-specification operation or other uncontrollable factors during operation of the vehicle. The greater the operating parameter of the vehicle sub-component is greater than the upper limit of the preset range, the higher the risk of failure.
Failure of a sub-component in the operation of a vehicle can have serious consequences, and the operator may not be immediately aware of the small failure when it is hidden, leading to a larger failure. Therefore, the safety problem of the current vehicle operation is generally concerned, but no effective scheme is available at present for timely sensing faults generated in the sub-component during the vehicle operation and reminding a user of timely preventing the faults.
Disclosure of Invention
Aiming at the defects of the traditional scheme, the invention provides a vehicle health prediction system, wherein a data server of the system timely acquires the working state of a related sub-component in the running of a vehicle through an intelligent terminal fixedly arranged on the vehicle to evaluate the risk probability of the sub-component generating specific faults, and timely sends out warning information to a user when the risk probability reaches a preset threshold value to remind the user of timely prevention.
The technical scheme provided by the invention is specifically realized as follows:
a vehicle health prediction system, the system comprising: the system comprises a plurality of intelligent terminals and a data server, wherein the intelligent terminals and the data server are communicated by adopting a B/S (browser/server) architecture.
Each intelligent terminal is installed in a corresponding vehicle and used for collecting working data of related sub-components when the vehicle runs and related working data, namely sub-component fault data, reported by a user when the vehicle is in fault and when a specific sub-component is in fault, and uploading the working data to a data server in real time. The sub-component failure data comprises: identification ID of the sub-component, specific fault type, and identification information of the vehicle model. The intelligent terminal attaches identification information corresponding to the vehicle model every time when uploading the working data, and each item of data attaches an agreed identification ID and a label flag to identify the specific type of the working data of a specific sub-component. Wherein the identification ID is used to identify a specific sub-component, such as a pump motor, a traction motor, an accelerator pedal, etc.; the tag flag identifies the specific type of data, such as temperature, item current, etc.
The data server persists the received sub-component failure data; the method can be specifically realized as follows: the received vehicle sub-component failure data is persistently classified for storage according to a particular failure type generated by a particular sub-component of a particular vehicle model. And the data server is also used for counting the probability distribution of the relevant fault parameters of the specific sub-component with the specific vehicle model in the specific type of fault according to the persistently stored sub-component fault data and storing the probability distribution. The data server screens out working data related to the type fault to be predicted from the received working parameters of the subcomponents in the running vehicle as matching data; and calculating based on the matching data, and the fault parameters corresponding to the matching data, the model of the running vehicle, the specific sub-component and the probability distribution corresponding to the type fault to be predicted so as to predict the risk probability of the sub-component having the type fault and timely inform a user.
Further, the data server counts the probability distribution of relevant fault parameters of specific sub-components of specific vehicle models with specific types of faults according to the sub-component fault data stored persistently, and stores the probability distribution; the concrete implementation is as follows: screening out working data corresponding to relevant fault parameters when specific sub-components of specific vehicle models have specific types of faults from the vehicle sub-component fault data stored in the persistent classification; grouping the screened working data according to a certain data interval, and counting the number of the working data falling into each group; carrying out normal distribution curve fitting by taking the abscissa x as a data interval and the ordinate y as the number of working data in the data interval to obtain a normal distribution function N (u, sigma)2) Where u is the mean, σ2Is the variance; the mean value u, the mean square error σ, and the identification information of the vehicle model of the vehicle, the sub-component ID, and the failure type identification information are stored in association in the failure database.
Correspondingly, the data server predicts the risk probability of the sub-component having the type fault based on the matching data, the fault parameter corresponding to the matching data, the model of the running vehicle, the specific sub-component, and the probability distribution corresponding to the type fault to be predicted, and is specifically realized as follows: inquiring a fault database according to the identification information of the vehicle model, the subcomponent ID and the fault type identification information of the vehicle to obtain a corresponding mean value u0Mean square error σ0(ii) a Let the matching data be x0For which x is given by the formula x ═ x0-u0/σ0Performing a normalization process to (u)0+x'，+∞)、(-∞，u0-x') is that the sub-component fails of the type at the time of the matching parameterThe confidence interval of the risk probability of the subcomponent (b) is calculated according to the standard normal distribution model N (0,1) as the risk probability of the subcomponent having the type of fault.
Correspondingly, the invention also provides a vehicle health prediction method, which comprises the following steps:
s1, collecting working data of related sub-components of a vehicle in real time through an intelligent terminal installed in the vehicle, and collecting related working data, namely sub-component fault data, reported by a user when the vehicle is in fault and when a specific sub-component is in fault, of the vehicle in real time;
s2, performing persistent storage on the received sub-component fault data; according to the sub-component fault data stored persistently, the probability distribution of relevant fault parameters when a specific sub-component of a specific vehicle model has a specific type fault is counted and stored;
and S3, screening out working data related to the type fault to be predicted from the received working parameters of the subcomponents in the running vehicle as matching data, predicting the risk probability of the subcomponent having the type fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific subcomponents and the probability distribution corresponding to the type fault to be predicted, and timely informing a user.
The implementation details of each step in the method are the same as those of the corresponding part of the vehicle health prediction system.
Drawings
Fig. 1 is a flowchart of a vehicle health prediction method provided by the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages solved by the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a vehicle health prediction system.
The system comprises a plurality of intelligent terminals and a data server, wherein the intelligent terminals and the data server are communicated by adopting a B/S framework. Preferably, the intelligent terminal performs data interaction with the data server by creating a Socket based on a TCP/IP protocol.
Each intelligent terminal is installed in a corresponding vehicle and used for collecting working data of related sub-components when the vehicle runs and related working data, namely sub-component fault data, reported by a user when a specific sub-component is in fault when the vehicle is in fault, and uploading the working data to a data server in real time. The power supply end of the intelligent terminal is connected to one side of a vehicle key switch, so that the intelligent terminal is powered on after the key switch is closed, and the intelligent terminal is subjected to data interaction with a data server by creating a socket after the intelligent terminal is powered on.
The sub-component failure data comprises: identification ID of the sub-component, specific fault type, and identification information of the vehicle model. The intelligent terminal is added with identification information corresponding to the vehicle model every time when uploading the working data, and each item of data is added with an agreed identification ID and a label flag to identify the specific type of the working data of the specific sub-component. Wherein the identification ID is used to identify a specific sub-component, such as a pump motor, a traction motor, an accelerator pedal, etc.; the tag flag identifies the specific type of data, such as temperature, item current, etc.
The fault parameters related to the specific type of fault of each related sub-component of the specific vehicle model type comprise: the load of a certain bearing of a certain type of vehicle when broken; the temperature and phase current of a traction motor of a certain type of electric vehicle when burnout occurs, the temperature and phase current of a pump motor when burnout occurs, and the analog input quantity of an accelerator pedal when the accelerator pedal fails.
The data server persistently classifies the received vehicle sub-component fault data for storage according to a particular fault type generated by a particular sub-component of a particular vehicle model. And the data server counts the probability distribution of the relevant fault parameters of the specific sub-component of the specific vehicle model with the specific type of fault according to the sub-component fault data stored persistently, and stores the probability distribution. The data server is also used for screening out the working data related to the type fault to be predicted from the received working parameters of the sub-component in the running vehicle as matching data, predicting the risk probability of the sub-component having the type fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific sub-component and the probability corresponding to the type fault to be predicted, and timely informing a user.
The data server counts the probability distribution of relevant fault parameters of specific sub-components of specific vehicle models with specific types of faults according to the sub-component fault data stored persistently, and stores the probability distribution; the method specifically comprises the following steps: screening out working data corresponding to relevant fault parameters when specific sub-components of specific vehicle models have specific types of faults from the vehicle sub-component fault data stored in the persistent classification; grouping the screened working data according to a certain data interval, and counting the number of the working data falling into each group; carrying out normal distribution curve fitting by taking the abscissa x as a data interval and the ordinate y as the number of working data in the data interval to obtain a normal distribution function N (u, sigma)2) Where u is the mean, σ2Is the variance; the mean value u, the mean square error σ, and the identification information of the vehicle model of the vehicle, the sub-component ID, and the failure type identification information are stored in association in the failure database.
In order to realize that the counted probability distribution can better meet the actual situation, the data server also periodically re-counts the probability distribution of the relevant fault parameters when the specific sub-component of the specific vehicle model has a specific type of fault according to the continuously increased sub-component fault data stored persistently so as to iteratively update the probability distribution parameters in the fault database. Or when the increment of the received fault data of the specific sub-component of the specific vehicle model with the specific type of fault reaches a preset threshold value, triggering the data server to re-count the probability distribution of the relevant fault parameters of the specific sub-component of the specific vehicle model with the specific type of fault, and performing iterative update on the probability distribution parameters in the fault database.
The normal distribution curve fitting is adopted because the related working parameters are mutually independent when the same sub-component of a large number of the same vehicle model has a specific fault type, the higher the risk of fault occurrence is when the related working parameters are larger than the upper limit of the preset range, and the statistical law of a large number of data can be known to follow the left half part of the normal distribution function according to the probability theory central limit theorem. For example, the traction motor of a certain type of electric vehicle is related to the temperature and phase current when being burnt; the higher the temperature deviates from the normal working value, the larger the phase current deviates from the normal working value, the greater the risk of burning, and the probability of burning out at a certain threshold is almost one hundred percent; the temperature/term current distribution when the traction motors of a large number of certain types of electric vehicles burn out conforms to the left half of the normal distribution curve.
Correspondingly, the data server predicts the risk probability of the sub-component having the type fault based on the matching data and the corresponding fault parameter thereof, the matching data, the fault parameter corresponding to the matching data, the model of the running vehicle, the specific sub-component, and the probability distribution corresponding to the type fault to be predicted, and the specific implementation is as follows: inquiring a fault database according to the identification information of the vehicle model, the subcomponent ID and the fault type identification information of the vehicle to obtain a corresponding mean value u0Mean square error σ0(ii) a Let the matching data be x0For which x is given by the formula x ═ x0-u0/σ0Performing a normalization process to (u)0+x'，+∞)、(-∞，u0-x') is the confidence interval of the risk probability of the sub-component having the type of fault at the time of the matching parameter, and the confidence rate calculated according to the standard normal distribution model N (0,1) is taken as the risk probability of the sub-component having the type of fault. This is because although the statistical law of the relevant operating parameters obeys the left half of the normal distribution function when a specific fault type occurs in a large number of identical sub-components of the same vehicle model, the statistical law of the relevant operating parameters is due to the standard normal distribution functionThe numbers are left-right symmetric, so long as the symmetric confidence intervals are chosen to derive the risk probability that it is still true.
And when the data server predicts that the risk probability of a certain sub-component of a specific vehicle having a fault of a specific type is greater than a preset threshold value, the data server issues alarm information to the intelligent terminal corresponding to the specific vehicle. For example, when the risk probability of the electric vehicle traction motor burnout is set to be greater than 80%, the data server sends alarm information to the intelligent terminal on the data server to remind a user.
Correspondingly, the invention further provides a vehicle health prediction method. As shown in fig. 1, the method comprises the steps of:
s1, collecting working data of related sub-components of a vehicle in real time through an intelligent terminal installed in the vehicle, and collecting related working data, namely sub-component fault data, reported by a user when the vehicle is in fault and when a specific sub-component is in fault, of the vehicle in real time;
s2, performing persistent storage on the received sub-component fault data; according to the sub-component fault data stored persistently, the probability distribution of fault parameters related to specific type faults of specific sub-components of specific vehicle models is counted and stored;
and S3, screening out working data related to the type fault to be predicted from the received working parameters of the subcomponents in the running vehicle as matching data, predicting the risk probability of the subcomponent having the type fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific subcomponents and the probability distribution corresponding to the type fault to be predicted, and timely informing a user.
The implementation details of each step in the method are the same as those of the corresponding part of the vehicle health prediction system.
According to the technical scheme provided by the invention, the working state of the related sub-component in the running of the vehicle can be timely obtained to evaluate the risk probability of the sub-component generating the specific fault, when the risk probability reaches the preset threshold value, the warning message is timely sent to the user to remind the user, and the generation of larger faults caused by hiding of small faults in the vehicle and incapability of timely knowing of operators can be effectively avoided.
Claims (12)
1. A vehicle health prediction system, the system comprising: a plurality of intelligent terminals and a data server; each intelligent terminal is installed in a corresponding vehicle, and is used for collecting working data of each sub-component in the running of the vehicle and related working data, namely sub-component fault data, reported by a user when the vehicle is in fault and when a specific sub-component is in fault, and uploading the data to a data server in real time; the data server is used for carrying out persistent storage on the received sub-component fault data; according to the sub-component fault data stored persistently, the probability distribution of relevant fault parameters of specific sub-components of specific vehicle models with specific types of faults is counted and stored; screening out working data related to the type fault to be predicted from the received working parameters of the subcomponents in the running vehicle as matching data, predicting the risk probability of the subcomponent having the type fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific subcomponent and the probability distribution corresponding to the type fault to be predicted, and timely informing related users; the sub-component failure data comprises: identification ID of the sub-component, identification information of the specific failure type and the vehicle model; the intelligent terminal adds identification information corresponding to the vehicle model every time when uploading the working data, and each item of data is added with an agreed identification ID and a label flag to identify the specific type of the working data of a specific sub-component; the server performs persistent storage on the received sub-component fault data, and the implementation is specifically as follows: identifying the type of the vehicle which uploads the sub-component fault data, and carrying out persistent classified storage on the received vehicle sub-component fault data according to the type of the specific fault generated by the specific sub-component of the specific vehicle type; according to the sub-component fault data stored persistently, the probability distribution of relevant fault parameters of specific sub-components of specific vehicle models with specific types of faults is counted and stored; the method specifically comprises the following steps: screening out working data corresponding to relevant fault parameters when specific sub-components of specific vehicle models have specific types of faults from the persistently stored vehicle sub-component fault data; grouping the screened working data according to a certain data interval, and counting the number of the working data falling into each group; performing normal distribution curve fitting by taking an abscissa x as a data interval and taking an ordinate y as the number of working data in the data interval to obtain a normal distribution function N (u, sigma 2), wherein u is a mean value and sigma 2 is a variance; storing the mean value u, the mean square error σ, and identification information of the vehicle model of the vehicle, the sub-component ID, and the failure type identification information in association in a failure database; predicting the risk probability of the sub-component having the type fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific sub-component and the probability distribution corresponding to the type fault to be predicted; the concrete implementation is as follows: inquiring a fault database according to the identification information of the vehicle model of the vehicle, the sub-component ID and the fault type identification information to obtain a corresponding mean value u0 and a mean square error sigma 0; assuming that the matching data is x0, the matching data is normalized according to the formula x ' ═ x0-u0/σ 0, and the probability of risk of the sub-component of the type of fault is determined according to a standard normal distribution model N (0,1) with (u0+ x ', + ∞), (∞, u0-x ') as the confidence interval of the probability of risk of the sub-component of the type of fault occurring at the time of the matching parameter.
2. The vehicle health prediction system of claim 1, wherein the data server periodically re-counts the probability distribution of relevant failure parameters at the occurrence of a particular type of failure for a particular sub-component of a particular vehicle model to iteratively update the probability distribution parameters in the failure database; or when the increment of the received fault data of the specific sub-component of the specific vehicle model with the specific type of fault reaches a preset threshold value, triggering the data server to re-count the probability distribution of the relevant fault parameters of the specific sub-component of the specific vehicle model with the specific type of fault, and carrying out iterative update on the relevant probability distribution parameters in the fault database.
3. The vehicle health prediction system of claim 2, wherein the data server issues an alarm message to the intelligent terminal corresponding to a specific vehicle when the risk probability that a sub-component of the specific vehicle has a fault of a specific type is predicted to be greater than a preset threshold.
4. The vehicle health prognosis system of claim 3, wherein the fault parameters associated with a specific type of fault occurring in a specific sub-component of a specific vehicle model include at least one or more of: the temperature and phase current of a traction motor of a certain type of electric vehicle when burnout occurs, the temperature and phase current of a pump motor when burnout occurs, and the analog input quantity of an accelerator pedal when the accelerator pedal fails; the load of a specific bearing of a certain vehicle when the bearing is broken.
5. The vehicle health prediction system of claim 4, wherein the intelligent terminal is powered on when a key switch of the vehicle is closed, and the intelligent terminal performs data interaction with a data server by creating a socket after the intelligent terminal is powered on.
6. A vehicle health prediction method based on the vehicle health prediction system according to any one of claims 1 to 5, characterized by comprising the steps of: s1, collecting working data of related sub-components of a vehicle in operation and related working data, namely sub-component fault data, reported by a user when the vehicle is in fault and when a specific sub-component is in fault, in real time through an intelligent terminal installed in the vehicle; s2, performing persistent storage on the collected sub-component fault data; according to the sub-component fault data stored persistently, the probability distribution of relevant fault parameters of specific sub-components of specific vehicle models with specific types of faults is counted, and the probability distribution is stored in a fault database; s3, screening out working data related to the type of fault to be predicted from the received working parameters of the subcomponents in the running vehicle as matching data, predicting the risk probability of the subcomponent having the type of fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific subcomponents and the probability distribution corresponding to the type of fault to be predicted, and timely informing related users; s4, screening out working data related to the type fault to be predicted from the working parameters of the operating vehicle subcomponents to serve as matching data; and predicting the risk probability of the sub-component having the type fault based on the matching data, the fault parameters corresponding to the matching data, the model of the running vehicle, the specific sub-component and the probability distribution corresponding to the type fault to be predicted, and timely informing related users.
7. The vehicle health prediction method of claim 6, wherein the sub-component fault data comprises: identification ID of the sub-component, identification information of the specific failure type and the vehicle model; the intelligent terminal attaches identification information corresponding to the vehicle model every time when uploading the working data, and each item of data attaches an agreed identification ID and a label flag to identify the specific type of the working data of a specific sub-component.
8. The vehicle health prediction method of claim 7, wherein the probability distribution of fault parameters associated with a specific type of fault occurring for a specific sub-component of a specific vehicle model is counted from the persistently stored sub-component fault data and stored in a fault database; the method specifically comprises the following steps: screening out working data corresponding to relevant fault parameters when specific sub-components of specific vehicle models have specific types of faults from the persistently stored vehicle sub-component fault data; grouping the screened working data according to a certain data interval, and counting the number of the working data falling into each group; performing normal distribution curve fitting by taking an abscissa x as a data interval and taking an ordinate y as the number of working data in the data interval to obtain a normal distribution function N (u, sigma 2), wherein u is a mean value and sigma 2 is a variance; the mean value u, the mean square error σ, and the identification information of the vehicle model of the vehicle, the sub-component ID, and the failure type identification information are stored in association in the failure database.
9. The vehicle health prediction method according to claim 8, wherein the risk probability of the sub-component having the type of fault is predicted based on the matching data, and the fault parameters corresponding to the matching data, the model of the running vehicle, the specific sub-component, and the probability distribution corresponding to the type of fault to be predicted, and the related user is informed in time; the concrete implementation is as follows: inquiring a fault database according to the identification information of the vehicle model of the vehicle, the sub-component ID and the fault type identification information to obtain a corresponding mean value u0 and a mean square error sigma 0; assuming that the matching data is x0, normalizing the matching data according to the formula x ' ═ x0-u 0/sigma 0, and determining the risk probability of the sub-component having the type fault according to a standard normal distribution model N (0,1) by taking (u0+ x ', + ∞), (∞, u0-x ') as a confidence interval of the risk probability of the sub-component having the type fault at the time of the matching parameter; and when the risk probability of the sub-component having the type fault is predicted to be larger than a preset threshold value, issuing alarm information to the intelligent terminal corresponding to the running vehicle.
10. The vehicle health prediction method of claim 9, further comprising: periodically re-counting the probability distribution of relevant fault parameters when a specific sub-component of a specific vehicle model has a specific type of fault, and carrying out iterative updating on the probability distribution parameters in the fault database; or when the received increment of the fault data of the specific sub-component of the specific vehicle model with the specific type of fault reaches a preset threshold value, carrying out statistics again on the probability distribution of the relevant fault parameters of the specific sub-component of the specific vehicle model with the specific type of fault, and carrying out iterative updating on the relevant probability distribution parameters in the fault database.
11. The vehicle health prediction method of claim 10, wherein the fault parameters associated with a particular type of fault occurring in a particular sub-component of a particular vehicle model include at least one or more of: the temperature and phase current of a traction motor of a certain type of electric vehicle when burnout occurs, the temperature and phase current of a pump motor when burnout occurs, and the analog input quantity of an accelerator pedal when the accelerator pedal fails; the load of a specific bearing of a certain vehicle when the bearing is broken.
12. The vehicle health prediction method of claim 11, wherein the intelligent terminal is powered on after a key switch of a vehicle on which the intelligent terminal is installed is closed, and performs data interaction with the data server by creating a socket after the power on is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911258817.8A CN111105522B (en) | 2019-12-10 | 2019-12-10 | Vehicle health prediction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911258817.8A CN111105522B (en) | 2019-12-10 | 2019-12-10 | Vehicle health prediction system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111105522A CN111105522A (en) | 2020-05-05 |
| CN111105522B true CN111105522B (en) | 2022-02-22 |
Family
ID=70422773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911258817.8A Active CN111105522B (en) | 2019-12-10 | 2019-12-10 | Vehicle health prediction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111105522B (en) |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6738748B2 (en) * | 2001-04-03 | 2004-05-18 | Accenture Llp | Performing predictive maintenance on equipment |
| KR100564362B1 (en) * | 2003-12-16 | 2006-03-27 | 한국철도기술연구원 | Prevention system and the method for maintenance of railway car using RAMS analysis |
| US7751955B2 (en) * | 2006-06-30 | 2010-07-06 | Spx Corporation | Diagnostics data collection and analysis method and apparatus to diagnose vehicle component failures |
| KR20120049672A (en) * | 2010-11-09 | 2012-05-17 | 현대자동차주식회사 | Scheduled vehicle management system and method of the same |
| CN106682795A (en) * | 2015-11-05 | 2017-05-17 | 大陆汽车投资（上海）有限公司 | Data analysis based automobile part information processing method |
| CN105511450A (en) * | 2015-12-30 | 2016-04-20 | 福建工程学院 | Method for remotely monitoring and predicting fault of forklift loader |
| CN108303264B (en) * | 2017-01-13 | 2020-03-20 | 华为技术有限公司 | Cloud-based vehicle fault diagnosis method, device and system |
| CN107085773A (en) * | 2017-05-16 | 2017-08-22 | 交通运输部公路科学研究所 | A kind of system and method for being used to evaluate vehicle in use technology status |
| CN107544457A (en) * | 2017-08-31 | 2018-01-05 | 广东石油化工学院 | Refinery plant running cycle expert decision system and method based on fail-safe analysis |
| CN108693868B (en) * | 2018-05-25 | 2021-06-11 | 深圳市轱辘车联数据技术有限公司 | Method for training fault prediction model, and method and device for predicting vehicle fault |
| CN108919776B (en) * | 2018-06-19 | 2021-04-09 | 深圳市元征科技股份有限公司 | Fault assessment method and terminal |
| CN109460567B (en) * | 2018-09-21 | 2021-02-09 | 华中科技大学 | Maintenance method and system of multi-component device |
| CN110135733A (en) * | 2019-05-17 | 2019-08-16 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | A kind of appraisal procedure and device of power equipment operational reliability |
-
2019
- 2019-12-10 CN CN201911258817.8A patent/CN111105522B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111105522A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110596486B (en) | Intelligent early warning operation and maintenance method and system for charging pile | |
| CN113724437B (en) | Unattended alarm method and system for unattended selling cabinet | |
| CN115356636A (en) | Data-driven new energy automobile battery fault alarm and fault early warning model | |
| CN113313918B (en) | Terminal anti-dismantling alarm identification method and device, computer equipment and storage medium | |
| CN102568147A (en) | Alarm method for software failure of semiconductor device | |
| CN114202238A (en) | Power supply equipment health degree evaluation method, operation and maintenance method, device and server | |
| CN113807547A (en) | Vehicle fault early warning method and system, readable storage medium and computer equipment | |
| CN111105522B (en) | Vehicle health prediction system and method | |
| WO2022016862A1 (en) | Method and system for monitoring health status of battery pack | |
| CN108288019B (en) | Method and device for identifying preventive maintenance object of urban rail transit | |
| CN117294000A (en) | Intelligent power failure early warning system for power grid | |
| CN116664015A (en) | Intelligent charging pile management system and method thereof | |
| CN114415646B (en) | Remote vehicle diagnosis method, system and terminal equipment based on DoIP protocol | |
| CN115508713A (en) | Battery system safety early warning method and device, storage medium and equipment | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| US20220187814A1 (en) | Collection and use of data distributed throughout industrial systems | |
| KR20220096729A (en) | Electric vehicle charger monitoring system | |
| CN113172764A (en) | Mixing station monitoring method and system | |
| CN110852459A (en) | Automatic repair reporting system | |
| CN111371179A (en) | Closed-loop monitoring method for electricity utilization processing flow | |
| CN110673036B (en) | Vehicle fault early warning method and system based on OBD computing technology | |
| CN116634473B (en) | Method and device for predicting failure of power failure and service withdrawal of wireless station | |
| CN116136684B (en) | Vehicle fault diagnosis method, device, electronic equipment and storage medium | |
| CN111832978A (en) | Intelligent rubber mixing system and method | |
| CN111932097A (en) | Data quality monitoring method and device based on electric vehicle service platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 450016 No.99, Jingbei 6th Road, Zhengzhou area (Jingkai), Henan pilot Free Trade Zone, Zhengzhou City, Henan Province Applicant after: Henan Jiachen Intelligent Control Co.,Ltd. Address before: 450016 No.99, Jingbei 6th Road, Zhengzhou area (Jingkai), Henan pilot Free Trade Zone, Zhengzhou City, Henan Province Applicant before: ZHENGZHOU JIACHEN ELECTRIC Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |