CN112558592A - Vehicle fault prediction method and system and vehicle - Google Patents
Vehicle fault prediction method and system and vehicle Download PDFInfo
- Publication number
- CN112558592A CN112558592A CN202011565411.7A CN202011565411A CN112558592A CN 112558592 A CN112558592 A CN 112558592A CN 202011565411 A CN202011565411 A CN 202011565411A CN 112558592 A CN112558592 A CN 112558592A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- model
- moment
- statistical analysis
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0267—Fault communication, e.g. human machine interface [HMI]
- G05B23/027—Alarm generation, e.g. communication protocol; Forms of alarm
Abstract
The invention provides a vehicle fault prediction method, a prediction method and a vehicle, and relates to the technical field of vehicles, wherein the vehicle fault prediction method comprises the following steps: and collecting data of the vehicle in real time and sending the data to a big data platform. And receiving and displaying the data of the vehicle after the data is cleaned and statistically analyzed by the big data platform. The vehicle fault prediction method and the vehicle fault prediction system can predict whether the vehicle is in the moment or about to break down, and the part and the probability of the broken down are not required to be manually eliminated one by one, so that the time and the labor cost are saved. And the vehicle can be directly reminded to alarm when a fault is obtained, and the vehicle can be reminded before a real accident happens, so that the safety of the vehicle is improved.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a vehicle fault prediction method, a prediction system and a vehicle.
Background
Through big data analysis of network users, the engine shake condition is remarkably increased when the users commonly complain about the change of the three-cylinder engine along with the use time. At present, the reason of vehicle fault jitter is continuously checked and judged according to the perception of a user, so that time and labor cost are wasted, and the checking is difficult. In addition, even if the judgments are checked one by one, whether the vehicle shakes or not is judged subjectively by testers, and when the test is insufficient, or the test working condition is not comprehensive or the sensitivity of the driver is insufficient, the slight shake of the whole vehicle is possibly brought to mass production to cause customer complaints.
Disclosure of Invention
An object of the first aspect of the present invention is to provide a vehicle fault prediction method, which solves the problem of resource waste caused by the need of a laboratory technician to troubleshoot vehicle faults one by one in the prior art.
It is a further object of the first aspect of the present invention to address the problem of the prior art that vehicle failure cannot be predicted.
The second aspect of the invention aims to provide a vehicle, which solves the problem of resource waste caused by the fact that experimenters need to check vehicle faults one by one in the prior art;
it is an object of a third aspect of the invention to provide a vehicle failure prediction system.
In particular, the present invention provides a vehicle failure prediction method comprising:
collecting data of a vehicle in real time and sending the data to a big data platform, wherein the data comprises vehicle vibration data, vehicle speed, engine rotating speed, engine temperature, current, electric quantity and/or tire pressure;
receiving and displaying the data of the vehicle after the data are cleaned and statistically analyzed by the big data platform;
and displaying and alarming whether the vehicle is at the moment or about to fail and the part and probability of the vehicle at the moment or about to fail, wherein the part and probability of the vehicle at the moment or about to fail are obtained by inputting the data after statistical analysis into a model by the big data platform.
Optionally, the model includes a discriminant model, and the discriminant model receives the data after the statistical analysis, predicts whether the vehicle will fail at this moment according to data at a certain moment, and obtains a location and a probability that the vehicle will fail at this moment.
Optionally, the model further includes a prediction model, where the prediction model receives the data after the statistical analysis, predicts whether the vehicle will fail at the next time according to the data at a certain time, and obtains a location and a probability that the vehicle will fail at the next time.
Optionally, the vehicle vibration data includes vibration frequencies and vibration amplitudes of the vehicle components;
the step of performing statistical analysis on the cleaned data comprises:
and classifying the vibration condition of the vehicle according to the vibration amplitude and the vibration frequency, and counting the ratio of the vibration amplitude of each component of the vehicle in each grade and the ratio of the vibration frequency in each grade.
Optionally, the statistically analyzed data is displayed through a BI system;
the BI system also displays vibration data information of each part of the vehicle, information whether the vehicle is in failure or not, information whether the vehicle is about to be in failure or not and information of a part in failure or about to be in failure in real time.
Optionally, the step of the big data platform cleaning the data includes: cleaning the data of the vehicle through spark/flink to remove abnormal data in the data of the vehicle; the discrimination model is an XGboost model; the prediction model is an RNN model, and an LSTM module is introduced into the RNN model.
In particular, the invention also provides a vehicle comprising:
the system comprises a collecting unit, a big data platform and a data processing unit, wherein the collecting unit is used for collecting data of a vehicle in real time and sending the data to the big data platform, and the data comprises vehicle vibration data, vehicle speed, engine rotating speed, engine temperature, current, electric quantity and/or tire pressure;
the display unit is used for cleaning the data by the big data platform, receiving the data after statistical analysis and displaying the data; and
and the alarm unit is used for outputting, displaying and alarming the part and the probability of the vehicle at the moment or about to fail, wherein the part and the probability of the vehicle at the moment or about to fail are obtained by inputting the data after statistical analysis into the model by the big data platform.
Particularly, the invention also provides a vehicle fault prediction system, which comprises the vehicle and a big data platform, wherein the big data platform comprises:
a cleaning module for receiving and cleaning data of the vehicle;
the statistical analysis module is used for performing statistical analysis on the cleaned data;
and the model module is used for receiving the data after the statistical analysis, obtaining whether the vehicle is at the moment or about to fail according to the data after the statistical analysis, and obtaining the part and the probability of the vehicle at the moment or about to fail.
Optionally, the model module includes a discriminant model, and the discriminant model is configured to receive the data after the statistical analysis, predict whether the vehicle will fail at this moment according to data at a certain time, and obtain a location and a probability of the vehicle failing.
Optionally, the model module further includes a prediction model, where the prediction model is configured to receive the data after the statistical analysis, predict whether the vehicle will fail at the next time according to the data at a certain time, and obtain a location and a probability that the vehicle will fail at the next time.
According to the vehicle fault prediction method and system, the data are input into the model after being subjected to statistical analysis according to the detected data of the vehicle, whether the vehicle is at the moment or is about to have a fault and the position and the probability of the fault can be directly obtained through the algorithm of the model, manual elimination is not needed, and time and labor cost are saved. And the vehicle can be directly reminded to alarm when the vehicle is in the moment or is about to break down, and the vehicle can be reminded before a real accident happens, so that the safety of the vehicle is improved.
The vehicle fault prediction system comprises a big data platform, wherein the big data platform is mainly used for cleaning, counting, analyzing and judging data acquired by a vehicle to obtain the fault position and the fault probability of the vehicle, so that the accuracy of data analysis is ensured, the accuracy of fault judgment and prediction of the vehicle is improved, and the user experience is improved.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
FIG. 1 is a schematic flow diagram of a vehicle fault prediction method according to one embodiment of the invention;
FIG. 2 is a flow diagram of a discriminant model in accordance with an embodiment of the present invention;
FIG. 3 is a flow diagram of a prediction model in making predictions according to one embodiment of the invention;
FIG. 4 is a schematic block diagram of a vehicle according to one embodiment of the present invention;
FIG. 5 is a schematic block diagram of a vehicle fault prediction system according to one embodiment of the present invention;
fig. 6 is a schematic block diagram of a vehicle failure prediction system according to another embodiment of the present invention.
Detailed Description
FIG. 1 is a schematic flow diagram of a vehicle fault prediction method according to one embodiment of the invention. The present embodiment provides a vehicle failure prediction method, which may include:
s10, collecting data of the vehicle in real time and sending the data to a big data platform, wherein the data comprise vehicle vibration data, vehicle speed, engine rotating speed, engine temperature, current, electric quantity and/or tire pressure;
s20, receiving and displaying the data of the vehicle after the data are cleaned and statistically analyzed by the big data platform, wherein the data are firstly transmitted to the big data platform for cleaning, and then statistically analyzed on the big data platform;
and S30, displaying and alarming whether the vehicle is at the moment or about to fail and the position and probability of the vehicle at the moment or about to fail, wherein the position and probability of the vehicle at the moment or about to fail are obtained by inputting the data after statistical analysis into the model by the big data platform.
Normally, since the collection and transmission of the vehicle data are a periodic process, "this moment" in this embodiment represents the result of the data calculation in this collection period. The term "about to" in this embodiment means that the failure of the next detection period is calculated and predicted by the data of this acquisition period.
Specifically, the vibration sensor is firstly installed at the position of an engine, a vehicle body, a chassis and important parts. The vibration sensors are arranged around the vehicle, so that the road condition, such as the degree of jolt, can be judged according to the vibration amplitude and the frequency of the vibration sensors at different positions. The vibration amplitude of the vibration sensor arranged on the vehicle body can detect the influence of different vibrations on a user, and can show the influence degree on people. A vibration sensor mounted on the engine may detect a shake condition of the engine. The vibration sensor arranged on the tail gas pipe can detect whether the vibration is caused by carbon deposition at the tail gas pipe, and meanwhile, the important vibration position can show the influence on a human body in real time. In addition, sensors on the vehicle may detect vehicle vibration data, vehicle speed, engine temperature, current, electrical power, and/or tire pressure, among other data that may predict vehicle failure.
According to the vehicle fault prediction method, the data are input into the model after being subjected to statistical analysis according to the detected data of the vehicle, whether the vehicle is at the moment or is about to have a fault and the position and the probability of the fault can be directly obtained through the algorithm of the model, manual elimination is not needed, and time and labor cost are saved. And the vehicle can be directly reminded to alarm when the vehicle is in the moment or is about to break down, and the vehicle can be reminded before a real accident happens, so that the safety of the vehicle is improved.
As a specific embodiment of the present invention, the model described in this embodiment includes a discriminant model, and the discriminant model receives data after statistical analysis, predicts whether the vehicle will fail at this moment according to data at a certain time, and obtains a location and a probability that the vehicle will fail at this moment.
The judgment model of the embodiment is mainly used for judging the fault of the vehicle at the moment according to the data of the vehicle, so that the probability and the position of the fault of the vehicle before the fault occurs are known, and the safety of the vehicle is improved. As another embodiment of the present invention, the model of the present embodiment further includes a prediction model. The prediction model receives the data after statistical analysis, predicts whether the vehicle will break down at the next moment according to the data at a certain moment, and obtains the part and the probability of the vehicle breaking down at the next moment.
In the embodiment, the analyzed data is input into the prediction model, whether the vehicle at the next moment (namely, the position and the probability of the occurrence of the fault) is predicted according to the data of the currently detected vehicle, so that a user is reminded in advance, fault maintenance can be performed in advance according to the prediction result, and the safety of the vehicle is ensured.
As a specific embodiment of the present invention, the vehicle vibration data includes vibration frequencies and vibration amplitudes of the components of the vehicle;
the step of performing statistical analysis on the cleaned data comprises:
and classifying the vibration condition of the vehicle according to the vibration amplitude and the vibration frequency, and counting the ratio of the vibration amplitude of each component of the vehicle under each grade and the ratio of the vibration frequency under each grade.
The initial vibration amplitude and the vibration frequency are classified as follows:
| frequency of vibration | Grade | Amplitude of vibration | Grade |
| 0～10Hz | 1 | 0～20mm | 1 |
| 10～20Hz | 2 | 20～50mm | 2 |
| 20～30Hz | 3 | 50～100mm | 3 |
| 30～50Hz | 4 | 100～500mm | 4 |
| 50～ | 5 | 500～ | 5 |
The above-described gradation of the vibration frequency and the vibration amplitude is divided according to an actual empirical value. Subsequently, after the received data are gradually increased, specific division can be performed according to big data analysis. Because the frequency of each part is different, the vibration frequency and the vibration amplitude of each different part are adjusted in an unsupervised mode at the later stage.
As a specific embodiment of the present invention, the statistically analyzed data is presented by the BI system. The BI system also displays vibration data information of each component of the vehicle, information whether the vehicle is about to have a fault and information about the fault or the position where the vehicle is about to have a fault in real time.
Specifically, the BI system is an English abbreviation of Business Intelligence (Business Intelligence) software. The system is a set of complete solution scheme and is used for effectively integrating the existing data in an enterprise, rapidly and accurately providing a report form, providing a decision basis and helping the enterprise make an intelligent business operation decision.
The present embodiment utilizes the BI system to display the data so as to better prompt the user and further improve the safety of the vehicle.
As a specific embodiment of the present invention, the step of cleaning the data by the big data platform includes: and cleaning the data of the vehicle through spark/flink to remove abnormal data in the data of the vehicle. The abnormal data (such as overlarge data, undersize data and obviously abnormal data) are removed so as to better analyze the data, obtain the analyzed data more accurately, ensure that the result obtained by subsequently inputting the data into the model is more ready and avoid false alarm.
FIG. 2 is a flow diagram of a discriminant model in accordance with an embodiment of the present invention; as a specific embodiment of the present invention, the discriminant model is an XGBoost model. The discrimination model discriminates whether or not a failure occurs based on the history data. And establishing a deep learning discriminant model through the analyzed data. The vibration fault and the vibration part can be immediately known according to the discrimination model; and judging whether the automobile has faults and fault parts according to the data transmitted in real time through the XGboost model.
The data sources include vehicle speed, engine temperature, current, electrical quantity, tire pressure, and vehicle body, chassis, tires, seats, etc. Maximum, minimum and mean values of vibration amplitude data in the vibration sensor. Amplitude ratio per unit time, frequency ratio, etc. The data is split into training and test sets and validation set data.
And (3) passing the training set data through a XGboost machine learning model training model, a test set data test model and a verification set data verification model to obtain an optimal model. After data are transmitted to the model through Flink statistics, the probability of failure and the failure position are output, if no failure occurs, the failure is positive, and output demo is as follows: {0.07, - }, {0.03, - }, {0.9, engine }, {0.8, engine }, as shown in fig. 2 in particular.
FIG. 3 is a flow diagram of a prediction model in making predictions according to one embodiment of the invention; the prediction model is an RNN model, and an LSTM module is introduced into the RNN model. The prediction model is based on the time series data; slight faults can be known in advance by the predictive model. When the previous sign of the fault occurs, it can be known that some parts may have faults; this is mainly achieved by the RNN model. And predicting the data condition of the next time period by aiming at the data input at the previous moment, introducing an LSTM module into the RNN, and enabling the training speed to be higher than the training accuracy of the RNN by introducing the LSTM module. The RNN model mainly inputs data including: engine temperature, tire pressure, engine speed, vibration sensor data, and the like. The specific predicted feature flow is shown in fig. 3.
FIG. 4 is a schematic block diagram of a vehicle according to one embodiment of the present invention; the present invention also provides a vehicle 100 as a specific embodiment of the present invention, and the vehicle 100 may include a collecting unit 10, a display unit 20, and an alarm unit 30. The acquisition unit 10 is configured to acquire data of a vehicle in real time and send the data to a big data platform, where the data includes vibration data of the vehicle, a vehicle speed, an engine temperature, a current, an electric quantity, and/or a tire pressure. The display unit 20 is used for cleaning the data by the big data platform, receiving the data after statistical analysis, and displaying the data, wherein the data is firstly transmitted to the big data platform for cleaning, and then the cleaned data is statistically analyzed on the big data platform. And the alarm unit 30 is used for displaying and alarming the output of the part and the probability of the vehicle at the moment or about to fail, wherein the part and the probability of the vehicle at the moment or about to fail are obtained by inputting the data after the statistical analysis into the model by the big data platform. The presentation unit 20 of the present embodiment may be a multimedia electronic display of a vehicle. And displaying the BI system on a multimedia electronic display screen. The alarm unit 30 may be an audible and visual electric alarm, which can give an alarm and prompt with voice.
The vehicle of the embodiment carries out statistical analysis on the data according to the detected data of the vehicle and then inputs the data into the judgment model, and whether the vehicle is at the moment or about to break down and the position and the probability of the breaking down can be directly obtained through the algorithm of the judgment model without manually removing the parts one by one, so that the time and the labor cost are saved. And the vehicle can be directly reminded to alarm when a fault is obtained, and the vehicle can be reminded before a real accident happens, so that the safety of the vehicle is improved.
FIG. 6 is a schematic block diagram of a vehicle fault prediction system according to one embodiment of the present invention;
as a specific embodiment of the present invention, the present invention also provides a vehicle failure prediction system 300, the vehicle failure prediction system 300 may include the above vehicle 100 and the big data platform 200, wherein the big data platform 200 may include a cleaning module 210, a statistical analysis module 220, and a model module 230. The washing module 210 is used for receiving and washing data of the vehicle. The statistical analysis module 220 is used for performing statistical analysis on the cleaned data. The model module 230 is used for receiving the data after statistical analysis and obtaining whether the vehicle is at the moment or about to fail and obtaining the position and probability of the vehicle at the moment or about to fail according to the data after statistical analysis.
The model module 230 in this embodiment may include a discriminant model 231, where the discriminant model is configured to receive the data after statistical analysis, predict whether the vehicle will fail at this moment according to the data at a certain time, and obtain a location and a probability of the vehicle failing.
The model module 230 of this embodiment may further include a prediction model 232, which is configured to receive the data after statistical analysis, predict whether the vehicle will fail at the next time according to the data at a certain time, and obtain the location and the probability that the vehicle will fail at the next time.
The vehicle failure prediction system of the embodiment can predict whether the vehicle will fail at the moment and can predict whether the vehicle will fail at the next moment. When the vehicle is possibly at the moment or about to fail, the predicted part and probability of the vehicle to fail are output and displayed and an alarm is given. And the system can give an alarm in advance to remind a user, and can carry out fault maintenance in advance according to a predicted result, so that the safety of the vehicle is ensured. After the large data platform obtains the fault location, probability and other conditions, the fault type can be reported to the 4S store while being output to the alarm unit 30 of the vehicle, and the user is informed of the possible fault and fault type of the vehicle. When the automobile is repaired, the system can immediately know where the fault is serious and recommend the repair position.
The vehicle fault prediction system 300 of the embodiment comprises a big data platform 200, wherein the big data platform 200 mainly cleans, statistically analyzes and judges data collected by a vehicle to obtain a fault position and probability of the vehicle, so that the accuracy of data analysis is ensured, the accuracy of fault judgment and prediction of the vehicle is improved, and the user experience is improved.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (10)
1. A vehicle failure prediction method characterized by comprising:
collecting data of a vehicle in real time and sending the data to a big data platform, wherein the data comprises vehicle vibration data, vehicle speed, engine rotating speed, engine temperature, current, electric quantity and/or tire pressure;
receiving and displaying the data of the vehicle after the data are cleaned and statistically analyzed by the big data platform;
and displaying and alarming whether the vehicle is at the moment or about to fail and the part and probability of the vehicle at the moment or about to fail, wherein the part and probability of the vehicle at the moment or about to fail are obtained by inputting the data after statistical analysis into a model by the big data platform.
2. The vehicle failure prediction method according to claim 1,
the model comprises a discrimination model, the discrimination model receives the data after statistical analysis, predicts whether the vehicle breaks down at the moment according to the data at a certain moment, and obtains the part and the probability of the vehicle breaking down at the moment.
3. The vehicle failure prediction method according to claim 2,
the model also comprises a prediction model, the prediction model receives the data after the statistical analysis, predicts whether the vehicle will break down at the next moment according to the data at a certain moment, and obtains the part and the probability of the vehicle breaking down at the next moment.
4. The vehicle failure prediction method according to claim 2 or 3,
the vehicle vibration data includes vibration frequencies and vibration amplitudes of the vehicle components;
the step of performing statistical analysis on the cleaned data comprises:
and classifying the vibration condition of the vehicle according to the vibration amplitude and the vibration frequency, and counting the ratio of the vibration amplitude of each component of the vehicle in each grade and the ratio of the vibration frequency in each grade.
5. The vehicle failure prediction method according to claim 2 or 3,
displaying the data after statistical analysis through a BI system;
the BI system also displays vibration data information of each part of the vehicle, information whether the vehicle is in failure or not, information whether the vehicle is about to be in failure or not and information of a part in failure or about to be in failure in real time.
6. The vehicle failure prediction method according to claim 3,
the step of cleaning the data by the big data platform comprises the following steps: cleaning the data of the vehicle through spark/flink to remove abnormal data in the data of the vehicle; the discrimination model is an XGboost model; the prediction model is an RNN model, and an LSTM module is introduced into the RNN model.
7. A vehicle, characterized by comprising:
the system comprises a collecting unit, a big data platform and a data processing unit, wherein the collecting unit is used for collecting data of a vehicle in real time and sending the data to the big data platform, and the data comprises vehicle vibration data, vehicle speed, engine rotating speed, engine temperature, current, electric quantity and/or tire pressure;
the display unit is used for cleaning the data by the big data platform, receiving the data after statistical analysis and displaying the data; and
and the alarm unit is used for outputting, displaying and alarming the part and the probability of the vehicle at the moment or about to fail, wherein the part and the probability of the vehicle at the moment or about to fail are obtained by inputting the data after statistical analysis into the model by the big data platform.
8. A vehicle failure prediction system comprising the vehicle of claim 7 and a big data platform, wherein the big data platform comprises:
a cleaning module for receiving and cleaning data of the vehicle;
the statistical analysis module is used for performing statistical analysis on the cleaned data;
and the model module is used for receiving the data after the statistical analysis, obtaining whether the vehicle is at the moment or about to fail according to the data after the statistical analysis, and obtaining the part and the probability of the vehicle at the moment or about to fail.
9. The vehicle failure prediction system according to claim 8,
the model module comprises a discrimination model, and the discrimination model is used for receiving the data after statistical analysis, predicting whether the vehicle breaks down at the moment according to the data at a certain moment, and obtaining the position and the probability of the vehicle breaking down.
10. The vehicle failure prediction system according to claim 8 or 9,
the model module further comprises a prediction model, wherein the prediction model is used for receiving the data after statistical analysis, predicting whether the vehicle will break down at the next moment according to the data at a certain moment, and meanwhile obtaining the part and the probability of the vehicle breaking down at the next moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011565411.7A CN112558592B (en) | 2020-12-25 | 2020-12-25 | Vehicle fault prediction method and system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011565411.7A CN112558592B (en) | 2020-12-25 | 2020-12-25 | Vehicle fault prediction method and system and vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112558592A true CN112558592A (en) | 2021-03-26 |
| CN112558592B CN112558592B (en) | 2022-04-08 |
Family
ID=75033041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011565411.7A Active CN112558592B (en) | 2020-12-25 | 2020-12-25 | Vehicle fault prediction method and system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112558592B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113865879A (en) * | 2021-08-12 | 2021-12-31 | 浙江车速达软件科技有限公司 | Guide system for automobile detection |
| CN113918372A (en) * | 2021-10-27 | 2022-01-11 | 北京科杰科技有限公司 | Early warning system of data development platform based on flink realization |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5772238A (en) * | 1995-12-12 | 1998-06-30 | Automotive Technologies International Inc. | Efficient airbag module |
| DE102012206836A1 (en) * | 2012-04-25 | 2013-10-31 | Siemens Aktiengesellschaft | Method for forecasting an error or for detecting errors in a transport machine and transport machine |
| CN103455026A (en) * | 2013-08-23 | 2013-12-18 | 王绍兰 | Method and device for diagnosis and early warning of vehicle faults |
| CN103592122A (en) * | 2013-10-25 | 2014-02-19 | 北京交通大学 | Fault diagnosis device and method for urban rail transit train running gear |
| CN106406287A (en) * | 2016-11-08 | 2017-02-15 | 思建科技有限公司 | Method and system for vehicle safety state monitoring and early warning |
| GB201820308D0 (en) * | 2018-12-13 | 2019-01-30 | Continental Automotive Systems Srl | Device and method of integrity monitoring and failure predicting for a vehicle system |
| CN110059325A (en) * | 2018-01-19 | 2019-07-26 | 罗伯特·博世有限公司 | Vehicle trouble early warning system and corresponding vehicle trouble method for early warning |
| CN110647539A (en) * | 2019-09-26 | 2020-01-03 | 汉纳森（厦门）数据股份有限公司 | Prediction method and system for vehicle faults |
| CN110879102A (en) * | 2019-12-03 | 2020-03-13 | 扬州后潮科技有限公司 | Train vibration monitoring system for track |
| CN111433095A (en) * | 2018-10-26 | 2020-07-17 | 深圳市大疆创新科技有限公司 | Automated vehicle action and related systems and methods |
-
2020
- 2020-12-25 CN CN202011565411.7A patent/CN112558592B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5772238A (en) * | 1995-12-12 | 1998-06-30 | Automotive Technologies International Inc. | Efficient airbag module |
| DE102012206836A1 (en) * | 2012-04-25 | 2013-10-31 | Siemens Aktiengesellschaft | Method for forecasting an error or for detecting errors in a transport machine and transport machine |
| CN103455026A (en) * | 2013-08-23 | 2013-12-18 | 王绍兰 | Method and device for diagnosis and early warning of vehicle faults |
| CN103592122A (en) * | 2013-10-25 | 2014-02-19 | 北京交通大学 | Fault diagnosis device and method for urban rail transit train running gear |
| CN106406287A (en) * | 2016-11-08 | 2017-02-15 | 思建科技有限公司 | Method and system for vehicle safety state monitoring and early warning |
| CN110059325A (en) * | 2018-01-19 | 2019-07-26 | 罗伯特·博世有限公司 | Vehicle trouble early warning system and corresponding vehicle trouble method for early warning |
| CN111433095A (en) * | 2018-10-26 | 2020-07-17 | 深圳市大疆创新科技有限公司 | Automated vehicle action and related systems and methods |
| GB201820308D0 (en) * | 2018-12-13 | 2019-01-30 | Continental Automotive Systems Srl | Device and method of integrity monitoring and failure predicting for a vehicle system |
| CN110647539A (en) * | 2019-09-26 | 2020-01-03 | 汉纳森（厦门）数据股份有限公司 | Prediction method and system for vehicle faults |
| CN110879102A (en) * | 2019-12-03 | 2020-03-13 | 扬州后潮科技有限公司 | Train vibration monitoring system for track |
Non-Patent Citations (2)
| Title |
|---|
| QIN ZHANG: "《Dynamic Uncertain Causality Graph for Knowledge Representation and Reasoning: Continuous Variable, Uncertain Evidence, and Failure Forecast》", 《IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS》 * |
| 梁建英: "《高速列车智能诊断与故障预测技术研究》", 《北京交通大学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113865879A (en) * | 2021-08-12 | 2021-12-31 | 浙江车速达软件科技有限公司 | Guide system for automobile detection |
| CN113918372A (en) * | 2021-10-27 | 2022-01-11 | 北京科杰科技有限公司 | Early warning system of data development platform based on flink realization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112558592B (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112558592B (en) | Vehicle fault prediction method and system and vehicle | |
| CN108829088B (en) | Automobile diagnosis method and device and storage medium | |
| CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
| CN112326070B (en) | Temperature sensor fault diagnosis method and device, electronic equipment and storage medium | |
| CN111506048B (en) | Vehicle fault early warning method and related equipment | |
| EP3913453A1 (en) | Fault detection system and method for a vehicle | |
| CN107426013A (en) | Facility information monitoring method, apparatus and system | |
| CN112491920A (en) | Abnormity detection method and device for vehicle-mounted CAN bus | |
| CN113807547A (en) | Vehicle fault early warning method and system, readable storage medium and computer equipment | |
| CN105335599A (en) | Vehicle failure diagnosis rate detection method and system | |
| KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
| CN112606779B (en) | Automobile fault early warning method and electronic equipment | |
| CN113982850A (en) | Fan comprehensive health analysis method and system fusing high-frequency and low-frequency signals | |
| CN109615879B (en) | Vehicle speed abnormity early warning model and method based on Internet of vehicles and model construction method | |
| CN111125195A (en) | Data anomaly detection method and device | |
| CN114633709A (en) | Vehicle fault processing system and method | |
| CN115630284A (en) | Air compressor fault analysis and service life prediction system considering service period | |
| CN115186007A (en) | Airborne data identification real-time display method and system for monitoring and reminding | |
| CN115203014A (en) | Ecological service abnormity restoration system and restoration method based on deep learning | |
| CN113487189A (en) | Petrochemical equipment fault probability risk assessment system and assessment method | |
| CN113570840A (en) | Gas station dangerous accident early warning method, device and equipment based on computer vision | |
| CN113888775A (en) | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle | |
| CN113093709B (en) | Active on-vehicle running state monitoring and fault forecasting method | |
| CN113093712B (en) | Active vehicle transmission system on-vehicle running state monitoring and fault forecasting system | |
| CN113168739A (en) | Method for checking at least one vehicle and electronic computing device |
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 |