CN112116023B - Tire leakage real-time detection method based on machine learning and storage medium - Google Patents
Tire leakage real-time detection method based on machine learning and storage medium Download PDFInfo
- Publication number
- CN112116023B CN112116023B CN202011041933.7A CN202011041933A CN112116023B CN 112116023 B CN112116023 B CN 112116023B CN 202011041933 A CN202011041933 A CN 202011041933A CN 112116023 B CN112116023 B CN 112116023B
- Authority
- CN
- China
- Prior art keywords
- tire
- vehicle
- classification algorithm
- slope
- gas quantity
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a real-time tire leakage detection method based on machine learning and a storage medium, which comprises the steps of selecting data of more vehicle types of the same type in a longer time range, sliding according to a time window of N days based on a preset slope value, marking the leakage of the vehicle tire of the current vehicle data if the slope value of the gas quantity of the vehicle tire of the previous N days is larger than a slope value K when the vehicle tire slides to a certain day, and otherwise, the vehicle tire is not leaked, and obtaining a sample set with a label, then verifying and training the sample set by using different types of classification algorithms to obtain an optimal classification algorithm, and performing engineering deployment on the optimal classification algorithm based on the optimal classification algorithm to enable a model of the optimal classification algorithm to be uploaded to a production environment for predicting tire pressure data newly uploaded to a cloud in real time to obtain a prediction result. The technical problems that the tire air leakage result is not accurate enough or other production costs are required to be increased in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of automobile safety, in particular to a tire air leakage real-time detection method based on machine learning and a storage medium.
Background
The automobile is a modern vehicle and becomes an essential vehicle for daily life of people. With the development of the automobile industry, people pay more and more attention to safety, and automobile tires are one of important parts of automobiles. According to incomplete statistics, the accident rate caused by tires on highways is up to 42%, the current national regulations require that a TPMS (tire pressure monitoring system) installed by an automobile manufacturer can alarm only when a certain time requirement and a certain threshold condition are met, the TPMS monitors the condition of the tire pressure, the tire pressure is influenced by objective factors such as climate, road conditions, load, environmental temperature, altitude and the like, and the TPMS cannot detect the slow air leakage tires such as pricked nails.
The first method is a method and a system for detecting the air leakage of the automobile tires, which are disclosed in application number CN201510872288.6, and uses a big data outlier algorithm to periodically acquire and store original tire pressure data of four tires through pressure sensors, and when the acquired tire pressure value of a plurality of tires is larger than the original tire pressure change value of other tires and exceeds a set threshold value, the tire is determined to be air leakage. However, this method has several problems as follows: 1. separate storage equipment needs to be additionally arranged on the vehicle machine, so that the cost of each vehicle is increased, and the storage space of the equipment is always limited; 2. the method has no data deletion or updating strategy, and after the storage space of the equipment is saturated, the historical data which is unchanged before is used for carrying out the outlier every time the tire air leakage prediction is carried out, so that the prediction result is inaccurate. 3. The method has no data caching strategy, and when the vehicle runs to a place with a poor network signal, the journey with the poor network signal cannot be effectively predicted.
The second is a tire code and tire state identification method based on machine learning disclosed in application No. CN201910319072.5, which is to manually mark a tire picture, apply a multilayer neural network to supervise and urge learning on a training set and a verification set to obtain a model, and when a new picture is fed to the model, identify whether the tire leaks air in real time, but the method has the following problems: 1. a large amount of pictures need to be marked manually in the early stage, the more pictures are marked, the better the recognition effect is, but the more manual work is consumed in the early stage; 2. the method can achieve better effect theoretically, but has a practical problem that an independent camera needs to be added to shoot real-time pictures of the tire on a vehicle machine aiming at the tire, the camera can have a good shooting angle only when being installed, and the practical situation that the camera is installed most safely and is not easy to fall off needs to be considered.
Therefore, it is necessary to develop a real-time tire leakage detection method and a storage medium based on machine learning.
Disclosure of Invention
In view of the above, the present invention provides a real-time tire leakage detection method based on machine learning and a storage medium thereof, which are used to solve the technical problems of the prior art that the tire leakage result is not accurate enough or other production costs need to be increased.
In a first aspect, the present invention provides a real-time tire leakage detection method based on machine learning, including the following steps:
step 1, collecting vehicle data of A vehicles of the same type in a time period T1, and preprocessing the vehicle data, wherein the vehicle data at least comprises a vehicle ID, a tire temperature, a tire position, an environment temperature, a plateau coefficient, a timestamp and a tire pressure;
step 7, dividing the labeled sample set in the step 6 according to a preset proportion to obtain a verification set and a training set, and then respectively training and verifying the training set and the verification set by using different classification algorithms to obtain verification indexes of the respective algorithms, wherein the classification algorithms at least comprise an SVM classification algorithm, a logistic regression classification algorithm, a naive Bayes classification algorithm, a random forest classification algorithm and an SGBoost classification algorithm, and the verification indexes at least comprise accuracy, recall rate, F1 value, AUC and ROC;
step 8, comprehensively analyzing and comparing the verification indexes of the classification algorithms in the step 7 to obtain an optimal classification algorithm as an SVM classification algorithm, and carrying out parameter tuning on the SVM classification algorithm to determine optimal SVM parameters;
and 9, performing engineering deployment on the model of the SVM classification algorithm which is optimized in the step 8 so that the model of the SVM classification algorithm is online to a production environment and is used for predicting tire pressure data which is newly uploaded to the cloud in real time to obtain a prediction result, and if the prediction results of a plurality of times show that a certain tire of the vehicle leaks, sending tire air leakage early warning prompt information to a vehicle owner.
Further, the value range of M in step 4 is set between 4.0 and 6.0.
Further, the time period T2 in the step 6 is greater than the time period T1 in the step 1, and the number of vehicles a2 in the step 6 is greater than the number of vehicles a1 in the step 1.
In a second aspect, the present invention also provides a storage medium storing one or more programs which, when executed by one or more processors, enable the steps of the machine-learning-based method for real-time tire leak detection.
The invention brings the following beneficial effects:
according to the tire air leakage real-time detection method and the storage medium based on machine learning, the existing tire pressure related data at the cloud end are utilized to conduct data mining and variable construction, training is conducted through a plurality of classification algorithms, and a better tire air leakage prediction model is obtained. When the cloud end in the system monitors that new tire pressure data comes, the air leakage condition can be predicted through the better tire air leakage prediction model, and early warning prompt is timely carried out on an automobile owner. And carrying out data mining and variable construction, and training through a plurality of classification algorithms to obtain a better tire air leakage prediction model. When the cloud end in the system monitors that new tire pressure data comes, the air leakage condition can be predicted through the better tire air leakage prediction model, and early warning prompt is timely carried out on an automobile owner. The probability of the occurrence of the driving accident is reduced to a certain extent. In addition, the invention does not need to increase hardware, thereby reducing the development cost.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for real-time tire leak detection based on machine learning according to the present invention;
FIG. 2 is a flow chart of a variable construction of a real-time tire leakage detection method based on machine learning according to the present invention;
FIG. 3 is a flow chart of data tagging and algorithm model selection for a machine learning based method for real-time tire leak detection in accordance with the present invention;
fig. 4 is a prediction flowchart of a tire leakage real-time detection method based on machine learning according to the present invention.
Detailed Description
As shown in fig. 1 or fig. 2, a real-time tire leakage detection method based on machine learning includes the following steps:
step 1, collecting vehicle data of A vehicles of the same type in a time period T1, and preprocessing the vehicle data, wherein the vehicle data at least comprises a vehicle ID, a tire temperature, a tire position, an environment temperature, a plateau coefficient, a time stamp and a tire pressure.
In the present embodiment, in order to calculate and record raw data, the time period T1 is exemplified by 30 days or 1 month, the number of a vehicles is exemplified by 1000, that is, vehicle air pressure data of 1000 vehicles of the same type in one month is collected first, the vehicle air pressure data includes vehicle ID, tire temperature, tire position, ambient temperature, altitude coefficient, time stamp, air pressure, and the like, wherein the vehicle ID and the tire position are identifiers of different tire positions of different vehicles. And then, in the effective value range of the vehicle tire pressure data signal, removing invalid data of the temperature and the tire pressure in the original data to reduce the influence of the vehicle tire pressure data with less driving on the whole data, and screening out vehicles which drive for more than 15 days in one month to mine and construct variable tire pressure data of the vehicles.
And 2, performing primary variable construction, namely firstly compensating the original tire pressure and temperature, converting the tire pressure into the pressure under the standard atmospheric pressure, converting the temperature into absolute temperature, calculating the gas quantity at the four tire positions according to an ideal gas equation (PV = NRT) to reduce the influence of noise data, calculating the gas quantity average value of each tire every day to obtain the gas quantity data of each tire position of each vehicle every day, and screening the vehicles meeting the conditions according to certain data requirements, wherein the screening conditions are related to the actual weather and the vehicle running conditions on the same day. And drawing a gas quantity line graph by the average value of the gas quantity of each tire every day, observing the change condition of the line graph to judge whether the tire is flat, if the gas quantity line graph is in a slow descending trend and the slope is a negative value, judging that the tire is flat, and if the trend of the gas quantity line graph is relatively stable, judging that the tire is not flat.
And 3, performing linear least square fitting according to the gas quantity dispersion points of each tire of the screened vehicles (taking 200 vehicles as an example) every day to obtain a gas quantity slope value K1 of each vehicle tire for one month and an intercept b. Meanwhile, the influence of the actual days of the date on the tire pressure is considered, and the slope value is optimized secondarily according to the actual days of the date of the vehicle. For example, if the vehicle is used in both 5 th month 1 and 5 th month 31 of the year, but actually the vehicle is actually used for only 20 days in 5 th month, when the slope is optimized, the number of days the vehicle is used is 31 days, and the new slope value K2= (K1 × 31+ b-K1 × 1+ b)/31), the slope value after the vehicle is optimized can be obtained.
And step 5, according to the gas slope values of the vehicle tires at different positions, a scatter diagram of the gas slope values at different tire positions can be drawn, the slope of the vehicle tire far away from most of the vehicle tires is screened, a gas quantity line graph of the vehicle tire is drawn, and the vehicle with the slope value larger than the slope value K is extracted. And meanwhile, randomly acquiring the air leakage conditions of a plurality of vehicle tires according to the screened vehicles. The random acquisition mode is usually to select several vehicles for call return visit, so that the air leakage condition of the vehicle tires can be known more conveniently and rapidly.
And 6, collecting and processing vehicle data of A2 vehicles of the same type in a T2 time period, wherein the T2 time period is larger than the T1 time period, and the number of the A2 vehicles of the same type is larger than that of the A1 vehicles of the same type. And meanwhile, sliding according to the time window of N days according to the slope value K, when the vehicle slides to a certain day in the time window, if the gas quantity slope value of the vehicle tire of the previous N days is larger than the slope value K, marking the vehicle tire of the current vehicle data to be air-leakage, and if the gas quantity slope value of the vehicle tire of the previous N days is smaller than or equal to the slope value K, marking the vehicle tire of the current vehicle data to be air-leakage, and thus obtaining a sample set with a label.
And 7, in order to enable the data result to be more universal and representative, vehicle data of more vehicles of the same type in a longer time range are selected for analysis, training and verification, and the data result is shown in fig. 3. Meanwhile, according to the slope value K, a sliding window is carried out according to a time window of 15 days (for convenience of statistical calculation, the N days in the step 6 take 15 days as an example), when the vehicle is slid to a certain day, if the slope of the gas quantity of the vehicle tire of the previous 15 days is larger than the slope value K mined before, the vehicle tire of the current vehicle data is marked to be flat, otherwise, the vehicle tire of the current vehicle data is marked to be flat, and a large number of sample sets with labels are obtained. Then setting random seeds a, taking the proportion of pseudo-ginseng as an example, dividing the sample set in proportion to obtain the same verification set and training set, then respectively using a plurality of classification algorithms such as SVM classification algorithm, logistic regression classification algorithm, naive Bayes classification algorithm, random trial classification algorithm, XGboost and the like to train and verify the sample set, and obtaining verification indexes of the respective classification algorithms, namely accuracy, recall rate, F1 value, AUC and ROC.
And 8, comprehensively comparing and analyzing the verification indexes of the classification algorithms in the step 7 to obtain a better SVM classification algorithm, and then carrying out parameter optimization on the SVM to determine the optimal SVM parameter.
Step 9, performing online prediction on the optimized SVM classification algorithm model, as shown in FIG. 4, wherein the specific prediction process comprises the following steps:
firstly, the model of the optimal classification algorithm is subjected to engineering deployment and is on-line to a production environment, so that the system can monitor the tire pressure data newly uploaded to the cloud end in real time.
And after monitoring new tire pressure data of the vehicle, the system carries out preprocessing on the relevant data, wherein the preprocessing measures on the relevant data comprise extracting characteristic data such as tire pressure, temperature, calculated gas quantity and the like, the characteristic data are transmitted into a model of an optimal SVM classification algorithm after being processed, a prediction result is obtained, if the prediction result of a certain tire of the vehicle is predicted to be gas leakage for N times continuously, early warning information is pushed to a vehicle main driver and a HU, then the process is ended, and if the prediction result of a certain tire of the vehicle shows that the gas is not leaked, the whole process is directly ended.
In this embodiment, a storage medium is further provided, which stores one or more programs that, when executed by one or more processors, enable the steps of the machine-learning-based real-time tire leak detection method to be implemented.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Claims (4)
1. A real-time tire air leakage detection method based on machine learning is characterized by comprising the following steps:
step 1, collecting vehicle data of A1 vehicles of the same type in a time period of T1, and preprocessing the vehicle data, wherein the vehicle data at least comprises a vehicle ID, a tire temperature, a tire position, an environment temperature, a plateau coefficient, a time stamp and a tire pressure;
step 2, calculating the gas quantity and the gas quantity average value of each tire according to an ideal gas equation, and screening out vehicles meeting preset conditions;
step 3, performing linear least square fitting according to the screened gas quantity dispersion points of each tire of the vehicle every day to obtain a gas quantity slope of the vehicle tire, and performing secondary optimization on the gas quantity slope based on the influence of actual days on the tire pressure;
step 4, calculating a gas quantity slope average value of the vehicle tires according to the vehicle tires at different positions, screening out vehicles with the slope values larger than M times of the gas quantity slope average value, and recording the slope values as K;
step 5, randomly acquiring the air leakage conditions of a plurality of vehicle tires according to the vehicles screened in the step 4;
step 6, collecting vehicle data of A2 vehicles of the same type in a T2 time period, sliding according to the slope value K and a time window of N days, when the vehicle data slides to a certain day, if the slope value of the gas quantity of the vehicle tires of the previous N days is larger than the slope value K, marking that the vehicle tires of the current vehicle data are air-leaked, otherwise, the vehicle tires of the current vehicle data are air-leaked, and obtaining a sample set with labels;
step 7, dividing the labeled sample set in the step 6 according to a preset proportion to obtain a verification set and a training set, and then respectively training and verifying the training set and the verification set by using different classification algorithms to obtain verification indexes of the respective algorithms, wherein the classification algorithms at least comprise an SVM classification algorithm, a logistic regression classification algorithm, a naive Bayes classification algorithm, a random forest classification algorithm and an SGBoost classification algorithm, and the verification indexes at least comprise accuracy, recall rate, F1 value, AUC and ROC;
step 8, comprehensively analyzing and comparing the verification indexes of the classification algorithms in the step 7 to obtain an optimal classification algorithm as an SVM classification algorithm, and carrying out parameter tuning on the SVM classification algorithm to determine optimal SVM parameters;
and 9, performing engineering deployment on the model of the SVM classification algorithm which is optimized in the step 8 so that the model of the SVM classification algorithm is online to a production environment and is used for predicting tire pressure data which is newly uploaded to the cloud in real time to obtain a prediction result, and if the prediction results of a plurality of times show that a certain tire of the vehicle leaks, sending tire air leakage early warning prompt information to a vehicle owner.
2. The machine-learning-based real-time tire leak detection method according to claim 1, wherein the M value range in step 4 is set between 4.0 and 6.0.
3. The machine-learning-based real-time tire leakage detection method according to claim 1, wherein the time period T2 in step 6 is greater than the time period T1 in step 1, and the number of vehicles a2 in step 6 is greater than the number of vehicles a1 in step 1.
4. A storage medium storing one or more programs which, when executed by one or more processors, perform the steps of the method for real-time machine learning-based tire leakage detection according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041933.7A CN112116023B (en) | 2020-09-28 | 2020-09-28 | Tire leakage real-time detection method based on machine learning and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041933.7A CN112116023B (en) | 2020-09-28 | 2020-09-28 | Tire leakage real-time detection method based on machine learning and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116023A CN112116023A (en) | 2020-12-22 |
| CN112116023B true CN112116023B (en) | 2022-08-09 |
Family
ID=73798268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011041933.7A Active CN112116023B (en) | 2020-09-28 | 2020-09-28 | Tire leakage real-time detection method based on machine learning and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116023B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113085450A (en) * | 2021-04-16 | 2021-07-09 | 上海仙塔智能科技有限公司 | Tire slow air leakage detection method and device, vehicle and computer storage medium |
| CN115042566A (en) * | 2022-06-27 | 2022-09-13 | 重庆长安汽车股份有限公司 | Method for optimizing tire pressure historical track, tire pressure prediction method, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103115736A (en) * | 2013-02-05 | 2013-05-22 | 广州市华南橡胶轮胎有限公司 | Tire air tightness performance detecting device and detecting method |
| CN103317981A (en) * | 2013-07-01 | 2013-09-25 | 合肥美赛电子有限公司 | Rapid air leakage detection method for tyre pressure monitoring system |
| FR2989315A1 (en) * | 2012-04-12 | 2013-10-18 | Continental Automotive France | METHOD FOR DETECTING LEAKAGE OF A VEHICLE TIRE |
| CN107089102A (en) * | 2017-04-21 | 2017-08-25 | 重庆长安汽车股份有限公司 | A kind of detection method of the slow gas leakage of tire |
| CN109677214A (en) * | 2017-10-19 | 2019-04-26 | 英飞凌科技股份有限公司 | Determine the method and TPMS component of the duration of the contact trace event of rolling tire |
| CN110825917A (en) * | 2019-11-04 | 2020-02-21 | 广州亚美信息科技有限公司 | Vehicle tire pressure abnormity identification method and device and data analysis equipment |
| CN111062093A (en) * | 2019-12-26 | 2020-04-24 | 上海理工大学 | Automobile tire service life prediction method based on image processing and machine learning technology |
| CN111511588A (en) * | 2017-12-20 | 2020-08-07 | 尼拉动力公司 | Determining tire pressure status in a vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9079461B2 (en) * | 2013-03-14 | 2015-07-14 | The Goodyear Tire & Rubber Company | Predictive peer-based tire health monitoring |
-
2020
- 2020-09-28 CN CN202011041933.7A patent/CN112116023B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2989315A1 (en) * | 2012-04-12 | 2013-10-18 | Continental Automotive France | METHOD FOR DETECTING LEAKAGE OF A VEHICLE TIRE |
| CN103115736A (en) * | 2013-02-05 | 2013-05-22 | 广州市华南橡胶轮胎有限公司 | Tire air tightness performance detecting device and detecting method |
| CN103317981A (en) * | 2013-07-01 | 2013-09-25 | 合肥美赛电子有限公司 | Rapid air leakage detection method for tyre pressure monitoring system |
| CN107089102A (en) * | 2017-04-21 | 2017-08-25 | 重庆长安汽车股份有限公司 | A kind of detection method of the slow gas leakage of tire |
| CN109677214A (en) * | 2017-10-19 | 2019-04-26 | 英飞凌科技股份有限公司 | Determine the method and TPMS component of the duration of the contact trace event of rolling tire |
| CN111511588A (en) * | 2017-12-20 | 2020-08-07 | 尼拉动力公司 | Determining tire pressure status in a vehicle |
| CN110825917A (en) * | 2019-11-04 | 2020-02-21 | 广州亚美信息科技有限公司 | Vehicle tire pressure abnormity identification method and device and data analysis equipment |
| CN111062093A (en) * | 2019-12-26 | 2020-04-24 | 上海理工大学 | Automobile tire service life prediction method based on image processing and machine learning technology |
Non-Patent Citations (4)
| Title |
|---|
| Vehicle tire pressure monitoring systems;Jacek CABAN等;《Diagnostyka》;20141231;第15卷(第3期);第11-14页 * |
| 基于机器视觉的轮胎内胎漏气在线检测系统;余涛;《中国优秀硕士学位论文全文数据库 信息科技辑》;20200115;第I138-1219页 * |
| 轮胎气压异常的危害与判断;马祥存;《湖南农业》;20121201(第10期);第22页 * |
| 载货汽车危险状态辨识及监测预警研究;姚雪萍等;《中国博士学位论文全文数据库 工程科技II辑》;20141015;第C034-47页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116023A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200346656A1 (en) | Driver Assist Design Analysis System | |
| US9600541B2 (en) | Method of processing and analysing vehicle driving big data and system thereof | |
| CN112116023B (en) | Tire leakage real-time detection method based on machine learning and storage medium | |
| WO2019185657A1 (en) | Predictive vehicle diagnostics method | |
| CN106650157B (en) | Method, device and system for estimating fault occurrence probability of vehicle parts | |
| CN109767597B (en) | Vehicle accident early warning method and system | |
| US20170092021A1 (en) | Method and system for monitoring equipment | |
| US20220266839A1 (en) | Driver Assist Design Analysis System | |
| EP3319050A1 (en) | Vehicle operation data collection apparatus, vehicle operation data collection system, and vehicle operation data collection method | |
| US11807253B2 (en) | Method and system for detecting driving anomalies | |
| CN110704987B (en) | Bearing abnormal state assessment method based on similar working condition of failure data mining | |
| CN111948541A (en) | Vehicle battery overvoltage prediction method and device, server and storage medium | |
| CN110519382A (en) | A kind of automobile intelligent monitoring system | |
| CN110633729A (en) | Driving risk hierarchical clustering method for intelligent networking vehicle group test | |
| CN112883645A (en) | Single battery voltage inconsistency fault prediction method and device and server | |
| CN112036581A (en) | Performance detection method and device of vehicle air conditioning system, storage medium and terminal | |
| Svensson et al. | Indirect tire monitoring system-machine learning approach | |
| CN106910334B (en) | Method and device for predicting road section conditions based on big data | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN115171242A (en) | Remote fault detection system for industrial vehicle | |
| CN117113259B (en) | Coal mine state data processing method and system for predicting potential safety hazards | |
| CN117315943B (en) | Monitoring analysis and early warning method and system for overrun transportation violations | |
| CN116691715B (en) | Vehicle starting difficulty identification method and system based on Internet of Vehicles big data | |
| EP4095957A1 (en) | Method for detecting a possible anomaly in the operation of a fuel cell as a power source of a mobile or stationary system | |
| CN115235692A (en) | Method, device and system for diagnosing sudden gas leakage |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |