CN107403480A - A kind of vehicle trouble method for early warning, system and vehicle - Google Patents
A kind of vehicle trouble method for early warning, system and vehicle Download PDFInfo
- Publication number
- CN107403480A CN107403480A CN201710452989.3A CN201710452989A CN107403480A CN 107403480 A CN107403480 A CN 107403480A CN 201710452989 A CN201710452989 A CN 201710452989A CN 107403480 A CN107403480 A CN 107403480A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- early warning
- data
- detection algorithm
- algorithm program
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000013179 statistical model Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000001514 detection method Methods 0.000 claims description 62
- 238000012545 processing Methods 0.000 claims description 25
- 230000007613 environmental effect Effects 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 8
- 230000007257 malfunction Effects 0.000 claims 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013450 outlier detection Methods 0.000 abstract 3
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- 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
- G07C5/0816—Indicating performance data, e.g. occurrence of a malfunction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
This application discloses a kind of vehicle trouble method for early warning, including：The vehicle early warning related data collected；Vehicle early warning related data is handled using Outlier Detection Algorithm program, judges whether vehicle trouble warning information；Wherein, Outlier Detection Algorithm program is that statistical model is trained to obtain using the history vehicle early warning related data collected；This method training statistical model obtains Outlier Detection Algorithm program and judged to be predicted, and improves Scalability and data adaptability, adds prediction controllable period and improves the precision of prediction；Disclosed herein as well is a kind of vehicle trouble early warning system and vehicle, has above-mentioned beneficial effect.
Description
Technical Field
The application relates to the technical field of vehicle engineering, in particular to a vehicle fault early warning method, a system and a vehicle.
Background
With the development of the vehicle industry in China and the improvement of the living standard of people, vehicles increasingly enter common families. With the continuous increase of vehicles, road traffic accidents have increased dramatically. In which traffic accidents caused by problems of vehicle parts themselves account for over 30% of traffic accidents. Vehicle failure early warning system is increasing in importance in the car networking service as the main means of vehicle active safety.
The conventional vehicle online fault early warning system mainly carries out prediction based on a single reference threshold value of vehicle data, has short prediction period and poor accuracy, and cannot meet the user requirement of vehicle active safety due to reliability. Therefore, how to improve the accuracy of vehicle fault early warning is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The method and the system for early warning of the vehicle fault and the vehicle are characterized in that a statistical model is trained to obtain an abnormal detection algorithm program for prediction and judgment, so that the flexibility and the data adaptability of the system are improved, the controllable prediction period is increased, and the prediction precision is improved.
In order to solve the technical problem, the application provides a vehicle fault early warning method, which comprises the following steps:
receiving collected vehicle early warning related data;
processing the vehicle early warning related data by using an anomaly detection algorithm program, and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
Optionally, the receiving the collected vehicle early warning related data includes:
receiving vehicle operation data and vehicle CAN bus data sent by a vehicle terminal;
and receiving the vehicle environment data sent by the environment data interface.
Optionally, the receiving vehicle operation data and vehicle CAN bus data that the vehicle terminal sent includes:
the vehicle terminal machine collects vehicle operation data by using a satellite positioning system; wherein the vehicle operation data comprises vehicle position data, vehicle speed data, and vehicle direction data;
the vehicle terminal machine collects vehicle CAN bus data by using a CAN bus data receiver;
and the vehicle fault early warning server receives the vehicle operation data and the vehicle CAN bus data by utilizing TCP long connection.
Optionally, the receiving the vehicle environment data sent by the environment data interface includes:
the environment data interface acquires vehicle environment data from the environment public service interface by using an HTTP request;
and the vehicle fault early warning server receives the vehicle environment data by using a web socket network connection.
Optionally, the training of the statistical model by using the collected historical vehicle early warning related data to obtain the anomaly detection algorithm program includes:
mapping historical vehicle early warning related data to form a training data set { X(1),...,X(m)}；
Establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2)；
Determining each eigenvalue x from the training datasetiCorresponding muiAnd
using said muiThe above-mentionedObtaining the abnormal detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
Optionally, the scheme further includes:
and receiving feedback information of the user on the processing result and updating the abnormal detection algorithm program.
The present application further provides a vehicle comprising:
the data acquisition unit is used for acquiring vehicle early warning related data and sending the vehicle early warning related data to the vehicle fault early warning processor;
the vehicle fault early warning processor is used for processing the received vehicle early warning related data by using an anomaly detection algorithm program and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
Optionally, the vehicle fault warning processor includes:
an anomaly detection algorithm program trainer for mapping historical vehicle early warning related data into a training data set { X }(1),...,X(m)}; establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2) (ii) a Determining each eigenvalue x from the training datasetiCorresponding muiAndusing said muiThe above-mentionedObtaining the abnormal detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
Optionally, the vehicle fault warning processor includes:
and the anomaly detection algorithm program updater is used for receiving feedback information of a user on a processing result and updating the anomaly detection algorithm program.
The present application further provides a vehicle fault early warning system, the system includes:
the vehicle is used for collecting vehicle early warning related data and sending the vehicle early warning related data to the vehicle fault early warning server;
the vehicle fault early warning server is used for processing the received vehicle early warning related data by using an anomaly detection algorithm program and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
The application provides a vehicle fault early warning method, including: receiving collected vehicle early warning related data; processing the vehicle early warning related data by using an anomaly detection algorithm program, and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
Therefore, the method trains the statistical model to obtain an abnormal detection algorithm program for prediction and judgment, improves the flexibility and data adaptability of the system, increases the controllable prediction period and improves the prediction precision; the application also provides a vehicle fault early warning system and a vehicle, which have the beneficial effects and are not repeated herein.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a vehicle fault warning method provided in an embodiment of the present application;
fig. 2 is a schematic diagram illustrating a result of processing vehicle early warning related data by an anomaly detection algorithm program according to an embodiment of the present application;
fig. 3 is a block diagram of a vehicle fault warning system according to an embodiment of the present disclosure;
fig. 4 is a block diagram of a vehicle according to an embodiment of the present application.
Detailed Description
The core of the application is to provide a vehicle fault early warning method, a system and a vehicle, a statistical model is trained to obtain an abnormal detection algorithm program for prediction and judgment, the flexibility and the data adaptability of the system are improved, the controllable prediction period is increased, and the prediction precision is improved.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the embodiment, an anomaly detection algorithm program is used for analyzing vehicle early warning related data, namely an instant analysis method for vehicle fault prediction of the internet of vehicles by using an anomaly detection unsupervised algorithm is used, and for solving the problems of the existing early warning system, the anomaly detection algorithm program is used for uniformly processing vehicle early warning related data (such as vehicle running data, vehicle CAN bus data and environmental data) so as to prolong the prediction period and improve the prediction accuracy; referring to fig. 1 in detail, fig. 1 is a flowchart of a vehicle fault early warning method according to an embodiment of the present disclosure; the method can comprise the following steps:
and S100, receiving the collected vehicle early warning related data.
Specifically, the present embodiment does not limit the specific content of the vehicle early warning related data, and may be single vehicle data acquired in the prior art or multiple vehicle data. Preferably, when the user selects various types of vehicle data as the vehicle early warning related data, the dimensionality of the vehicle early warning related data can be widened, and the prediction precision and the controllable period are further increased. Namely, the selection of the vehicle early warning related data can be selected by the user according to the actual required prediction precision and hardware computing capacity. For example, vehicle operating data, vehicle CAN bus data, vehicle environmental data, and the like may be included.
Further, the embodiment does not limit the device for collecting the vehicle early warning related data, and the device can be selected according to the actual vehicle early warning related data collection requirement. For example, vehicle CAN bus data CAN be acquired by a CAN bus data receiver. Because the device for collecting the vehicle early warning related data is not limited, the corresponding embodiment does not limit the receiving mode for receiving the collected vehicle early warning related data. Which can be chosen adaptively according to the specific situation. The step is only required to acquire the required vehicle early warning related data. For example, when the vehicle early warning related data includes vehicle CAN bus data, the corresponding data CAN be acquired through the device on the vehicle, and the device on the vehicle CAN acquire the accurate vehicle CAN bus data more easily. When the vehicle early warning related data contains vehicle environment data, the corresponding data of the vehicle can be acquired through an environment public service interface (such as a China air network public interface). Namely, the determination of the acquisition mode can take the accuracy of the data and the convenience of the acquisition process as reference bases. In order to ensure the reliability and accuracy of the collected data, optionally, receiving the collected vehicle early warning related data may include:
and receiving vehicle operation data and vehicle CAN bus data sent by the vehicle terminal.
Specifically, a vehicle terminal is added in the vehicle to collect vehicle operation data and vehicle CAN bus data. The current vehicle early warning related data of the vehicle can be obtained in time. The embodiment does not limit the vehicle operation data and the vehicle CAN bus data acquisition mode, and does not limit the specific vehicle operation data and the vehicle CAN bus data acquisition content. The vehicle operation data may be acquired, for example, by a dashboard of the vehicle or may be acquired by a satellite positioning system. Further to ensure convenience of data acquisition, optionally, receiving the vehicle operation data and the vehicle CAN bus data sent by the vehicle terminal machine may include: the vehicle terminal machine collects vehicle operation data by using a satellite positioning system; wherein the vehicle operation data comprises vehicle position data, vehicle speed data, and vehicle direction data; the vehicle terminal machine collects vehicle CAN bus data by using a CAN bus data receiver. The vehicle terminal uses the satellite positioning system to collect the data of the position, speed, direction, etc. of the vehicle. The vehicle terminal collects the engine-related CAN data of the vehicle and the vehicle-related CAN data using the CAN line data receiver.
And receiving the vehicle environment data sent by the environment data interface.
Specifically, the present embodiment does not limit the vehicle environment data collection manner, nor the specific vehicle environment data collection content. Vehicle environmental data may be obtained, for example, from an environmental public service interface (e.g., china air network public interface) using HTTP requests by an environmental data interface. Namely, the environment data interface service acquires the vehicle environment data, which is the environment parameter related to the vehicle, from the environment public service (for example, the china air network public interface) by using the HTTP request according to the need. The environment data interface may be disposed on the vehicle, or may be disposed in the vehicle failure warning server, which is not limited in this embodiment.
The execution subject in this embodiment may be a vehicle failure warning server, or may be a processor in a vehicle. When the execution subject in this embodiment is a vehicle fault early warning server, the vehicle fault early warning server receives vehicle operation data, vehicle CAN bus data, and vehicle environment data. The present embodiment does not limit the manner of data transmission. Further, in order to ensure the reliability of data transmission, data transmission can be performed through a TCP protocol and a web socket network. Optionally, the vehicle fault early warning server receives vehicle operation data and vehicle CAN bus data by using a TCP long connection, and receives vehicle environment data by using a web socket network connection. Namely, the vehicle terminal transmits data to a vehicle fault early warning background system (namely, a vehicle fault early warning server) by using a TCP long connection. The environment data interface utilizes a web socket to push vehicle environment data to the vehicle fault early warning background system. The internet environment information interface is used for extracting data in real time, and the prediction precision of the system is improved.
S110, processing vehicle early warning related data by using an anomaly detection algorithm program, and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
Specifically, the execution subject in this embodiment may be a vehicle failure warning server, or may be a processor in a vehicle. They may comprise two processing modules or be understood as processing means, for example comprising a vehicle warning-related data receiving module and a vehicle warning-related data processing module. The vehicle early warning related data processing module processes vehicle running data, vehicle CAN bus data and vehicle environment data in real time by using a trained anomaly detection algorithm program, and judges whether vehicle faults are possible to occur or not. The vehicle fault early warning background system comprises a vehicle terminal for collecting and uploading vehicle running data and vehicle CAN bus data, an environment data interface service for acquiring corresponding environment data, and a vehicle fault early warning background system for comprehensively processing data to judge vehicle faults. The present embodiment does not limit the specific statistical model. For example, a gaussian statistical model. The prediction judgment is carried out by using Gaussian distribution, the flexibility and the data adaptability of the system are improved, and the controllable period of prediction is increased.
The training of the statistical model by using the collected historical vehicle early warning related data to obtain the anomaly detection algorithm program may include:
mapping historical vehicle early warning related data to form a training data set { X(1),...,X(m)}；
Establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2)；
Determining each eigenvalue x from a training datasetiCorresponding muiAnd
using mui、Obtaining an anomaly detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
The following takes the vehicle operation data, the vehicle CAN bus data and the vehicle environment data as examples to explain the specific contents of the above process:
the first step is as follows: mapping historical vehicle early warning related data to form a training data set { X(1),...,X(m)}; wherein X(i)The multi-dimensional feature vector is composed of three parts: vehicle operation data, vehicle CAN data and real-time vehicle environment data (each of which is a characteristic value X)(i))。
The second step is that: establishing Gaussian statistics for prediction of vehicle faultsAnd (4) modeling. Gauss modelThere are two parameters, i.e. the expected (mean) μ and the standard deviation σ, σ2Is the variance.
The third step: determining each eigenvalue x through a training datasetiCorresponding muiAndwherein, m is the size of the training data set.
The fourth step: and (3) performing online prediction calculation processing on the vehicle fault through a trained Gaussian statistical model, namely an anomaly detection algorithm program, and judging whether vehicle fault early warning information exists or not. Referring to fig. 2, a possible failure situation corresponds to data that deviates from the legitimate data set.
Based on the technical scheme, the vehicle fault early warning method provided by the embodiment of the application trains the Gaussian statistical model to obtain an abnormal detection algorithm program for prediction and judgment, and widens the data dimension through the data of the vehicle and the environmental data of the vehicle, so that the flexibility and the data adaptability of the system are improved, the controllable prediction period is increased, and the prediction precision is improved; and a reasonable statistical model is used for machine learning, so that the prediction precision is improved, and the dependency of the prediction result on single data is decoupled.
Based on the above embodiment, the method may further include:
and receiving feedback information of the user on the processing result and updating the anomaly detection algorithm program.
Specifically, vehicle early warning related data is processed according to the anomaly detection algorithm program, whether the processing result of the vehicle fault early warning information is fed back is judged (namely whether the processed vehicle fault early warning information is correct is judged), and the anomaly detection algorithm program is updated by using feedback information of a user. Therefore, the detection accuracy of the abnormal detection algorithm program can be improved.
Based on the technical scheme, the vehicle fault early warning method provided by the embodiment of the application trains the Gaussian statistical model to obtain an abnormal detection algorithm program for prediction and judgment, and widens the data dimension through the data of the vehicle and the environmental data of the vehicle, so that the flexibility and the data adaptability of the system are improved, the controllable prediction period is increased, and the prediction precision is improved; and a reasonable statistical model is used for machine learning, so that the prediction precision is improved, and the dependency of the prediction result on single data is decoupled. And the accuracy of the anomaly detection algorithm program is improved through a feedback mechanism.
In the following, the vehicle fault early warning system and the vehicle provided by the embodiment of the present application are introduced, and the vehicle fault early warning system and the vehicle described below and the vehicle fault early warning method described above may be referred to correspondingly.
Referring to fig. 3, fig. 3 is a block diagram of a vehicle fault warning system according to an embodiment of the present disclosure; the system may include:
the vehicle 100 is used for collecting vehicle early warning related data and sending the vehicle early warning related data to a vehicle fault early warning server;
the vehicle fault early warning server 200 is used for processing the received vehicle early warning related data by using an anomaly detection algorithm program and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a Gaussian statistical model by using collected historical vehicle early warning related data.
Based on the above embodiment, the vehicle 100 may include:
the vehicle terminal is used for collecting vehicle operation data by using a satellite positioning system; wherein the vehicle operation data comprises vehicle position data, vehicle speed data, and vehicle direction data; collecting vehicle CAN bus data by using a CAN bus data receiver;
an environmental data interface for obtaining vehicle environmental data from the environmental public service interface using an HTTP request.
Based on the above embodiment, the vehicle failure early warning server 200 may include:
the TCP interface is used for receiving vehicle operation data and vehicle CAN bus data by utilizing a TCP long connection;
and the web socket interface is used for receiving the vehicle environment data by using a web socket network connection.
Based on any of the above embodiments, the vehicle failure early warning server 200 may include: an anomaly detection algorithm program trainer; wherein, the abnormal detection algorithm program trainer is used for mapping the historical vehicle early warning related data to form a training data set { X(1),...,X(m)}; establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2) (ii) a Determining each eigenvalue x from a training datasetiCorresponding muiAndusing mui、Obtaining an anomaly detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
Based on the above embodiment, the vehicle failure early warning server 200 may further include:
and the anomaly detection algorithm program updater is used for receiving feedback information of the processing result from the user and updating the anomaly detection algorithm program.
Referring to fig. 4, fig. 4 is a block diagram of a vehicle according to an embodiment of the present disclosure; the vehicle may include:
the data acquisition unit 300 is used for acquiring vehicle early warning related data and sending the vehicle early warning related data to the vehicle fault early warning processor;
a vehicle failure early warning processor 400, configured to process the received vehicle early warning related data by using an anomaly detection algorithm program, and determine whether vehicle failure early warning information exists; the anomaly detection algorithm program is obtained by training a Gaussian statistical model by using collected historical vehicle early warning related data.
Based on the above embodiments, the data collector 300 may include:
the vehicle terminal is used for collecting vehicle operation data by using a satellite positioning system; wherein the vehicle operation data comprises vehicle position data, vehicle speed data, and vehicle direction data; collecting vehicle CAN bus data by using a CAN bus data receiver;
an environmental data interface for obtaining vehicle environmental data from the environmental public service interface using an HTTP request.
Based on the above embodiments, the vehicle fault warning processor 400 may include:
an anomaly detection algorithm program trainer for mapping historical vehicle early warning related data into a training data set { X }(1),...,X(m)}; establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2) (ii) a Determining each eigenvalue x from a training datasetiCorresponding muiAndusing mui、Obtaining an anomaly detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
Based on the above embodiment, the vehicle fault warning processor 400 may further include:
and the anomaly detection algorithm program updater is used for receiving feedback information of the processing result from the user and updating the anomaly detection algorithm program.
Based on any of the embodiments above, the vehicle may further include:
and the alarm equipment is used for giving an alarm when the vehicle fault early warning information exists. The system can remind the user to master the vehicle fault condition in time, and can make corresponding countermeasures in time to ensure the safe running of the vehicle. The specific type of the alarm device is not limited herein, and the alarm device may be a voice prompt device, an indicator light display device, or other alarm devices.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The vehicle fault early warning method, the vehicle fault early warning system and the vehicle provided by the application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
Claims (10)
1. A vehicle fault early warning method, characterized in that the method comprises:
receiving collected vehicle early warning related data;
processing the vehicle early warning related data by using an anomaly detection algorithm program, and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
2. The method of claim 1, wherein receiving the collected vehicle warning-related data comprises:
receiving vehicle operation data and vehicle CAN bus data sent by a vehicle terminal;
and receiving the vehicle environment data sent by the environment data interface.
3. The method of claim 2, wherein receiving vehicle operation data and vehicle CAN bus data from the vehicle terminal comprises:
the vehicle terminal machine collects vehicle operation data by using a satellite positioning system; wherein the vehicle operation data comprises vehicle position data, vehicle speed data, and vehicle direction data;
the vehicle terminal machine collects vehicle CAN bus data by using a CAN bus data receiver;
and the vehicle fault early warning server receives the vehicle operation data and the vehicle CAN bus data by utilizing TCP long connection.
4. The method of claim 2, wherein receiving the vehicle environmental data sent by the environmental data interface comprises:
the environment data interface acquires vehicle environment data from the environment public service interface by using an HTTP request;
and the vehicle fault early warning server receives the vehicle environment data by using a web socket network connection.
5. The method according to any one of claims 1-4, wherein training a statistical model using the collected historical vehicle warning related data to obtain the anomaly detection algorithm program comprises:
mapping historical vehicle early warning related data to form a training data set { X(1),...,X(m)}；
Establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2)；
Determining each eigenvalue x from the training datasetiCorresponding muiAnd
using said muiThe above-mentionedObtaining the abnormal detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
6. The method of claim 5, further comprising:
and receiving feedback information of the user on the processing result and updating the abnormal detection algorithm program.
7. A vehicle, characterized by comprising:
the data acquisition unit is used for acquiring vehicle early warning related data and sending the vehicle early warning related data to the vehicle fault early warning processor;
the vehicle fault early warning processor is used for processing the received vehicle early warning related data by using an anomaly detection algorithm program and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
8. The vehicle of claim 7, wherein the vehicle malfunction early warning processor comprises:
an anomaly detection algorithm program trainer for mapping historical vehicle early warning related data into a training data set { X }(1),...,X(m)}; establishing a Gaussian statistical model p (x; mu, sigma) for executing vehicle fault early warning2) (ii) a Determining each eigenvalue x from the training datasetiCorresponding muiAndusing said muiThe above-mentionedObtaining the abnormal detection algorithm program by the Gaussian statistical model;
wherein, X(i)In the form of a multi-dimensional feature vector,mu is the expectation, sigma is the standard deviation, sigma2Is the variance, x is a variable,m is the size of the training data set.
9. The vehicle of claim 8, wherein the vehicle malfunction early warning processor comprises:
and the anomaly detection algorithm program updater is used for receiving feedback information of a user on a processing result and updating the anomaly detection algorithm program.
10. A vehicle fault early warning system, the system comprising:
the vehicle is used for collecting vehicle early warning related data and sending the vehicle early warning related data to the vehicle fault early warning server;
the vehicle fault early warning server is used for processing the received vehicle early warning related data by using an anomaly detection algorithm program and judging whether vehicle fault early warning information exists or not; the anomaly detection algorithm program is obtained by training a statistical model by utilizing collected historical vehicle early warning related data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710452989.3A CN107403480A (en) | 2017-06-15 | 2017-06-15 | A kind of vehicle trouble method for early warning, system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710452989.3A CN107403480A (en) | 2017-06-15 | 2017-06-15 | A kind of vehicle trouble method for early warning, system and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107403480A true CN107403480A (en) | 2017-11-28 |
Family
ID=60405078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710452989.3A Pending CN107403480A (en) | 2017-06-15 | 2017-06-15 | A kind of vehicle trouble method for early warning, system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107403480A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523651A (en) * | 2018-11-14 | 2019-03-26 | 湖北文理学院 | Vehicle abnormality detection method and vehicle abnormality detection system |
| CN109615726A (en) * | 2018-12-12 | 2019-04-12 | 湖北汽车工业学院 | Information output method, device, dumper system, computer and storage medium |
| CN110389572A (en) * | 2018-04-23 | 2019-10-29 | 上海博泰悦臻电子设备制造有限公司 | Vehicle part failure gives warning in advance method, system and server |
| CN110599620A (en) * | 2019-07-26 | 2019-12-20 | 广州亚美信息科技有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN111988342A (en) * | 2020-09-18 | 2020-11-24 | 大连理工大学 | Online automobile CAN network anomaly detection system |
| CN112486136A (en) * | 2019-09-11 | 2021-03-12 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN112606779A (en) * | 2020-12-24 | 2021-04-06 | 东风汽车有限公司 | Automobile fault early warning method and electronic equipment |
| CN113888775A (en) * | 2020-06-19 | 2022-01-04 | 比亚迪股份有限公司 | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle |
| CN114296426A (en) * | 2021-12-08 | 2022-04-08 | 奇瑞新能源汽车股份有限公司 | Remote diagnosis method and device for vehicle, server and storage medium |
| US11320813B2 (en) | 2018-10-25 | 2022-05-03 | General Electric Company | Industrial asset temporal anomaly detection with fault variable ranking |
| CN117389256A (en) * | 2023-12-11 | 2024-01-12 | 青岛盈智科技有限公司 | Early warning method for truck vehicle state in transportation process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1788267A (en) * | 2003-04-07 | 2006-06-14 | 通用汽车公司 | Vehicle diagnostic knowledge delivery |
| CN101118694A (en) * | 2007-05-18 | 2008-02-06 | 李克明 | Vehicle intellectualized management system |
| CN102129447A (en) * | 2010-01-13 | 2011-07-20 | 通用汽车环球科技运作有限责任公司 | Fault prediction framework using temporal data mining |
| CN103455026A (en) * | 2013-08-23 | 2013-12-18 | 王绍兰 | Method and device for diagnosis and early warning of vehicle faults |
| CN104986157A (en) * | 2015-03-05 | 2015-10-21 | 贵阳杰能科技有限公司 | Fault monitoring and prewarning system of vehicle brake system |
-
2017
- 2017-06-15 CN CN201710452989.3A patent/CN107403480A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1788267A (en) * | 2003-04-07 | 2006-06-14 | 通用汽车公司 | Vehicle diagnostic knowledge delivery |
| CN101118694A (en) * | 2007-05-18 | 2008-02-06 | 李克明 | Vehicle intellectualized management system |
| CN102129447A (en) * | 2010-01-13 | 2011-07-20 | 通用汽车环球科技运作有限责任公司 | Fault prediction framework using temporal data mining |
| CN103455026A (en) * | 2013-08-23 | 2013-12-18 | 王绍兰 | Method and device for diagnosis and early warning of vehicle faults |
| CN104986157A (en) * | 2015-03-05 | 2015-10-21 | 贵阳杰能科技有限公司 | Fault monitoring and prewarning system of vehicle brake system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110389572A (en) * | 2018-04-23 | 2019-10-29 | 上海博泰悦臻电子设备制造有限公司 | Vehicle part failure gives warning in advance method, system and server |
| US11320813B2 (en) | 2018-10-25 | 2022-05-03 | General Electric Company | Industrial asset temporal anomaly detection with fault variable ranking |
| CN109523651A (en) * | 2018-11-14 | 2019-03-26 | 湖北文理学院 | Vehicle abnormality detection method and vehicle abnormality detection system |
| CN109615726B (en) * | 2018-12-12 | 2022-01-14 | 湖北汽车工业学院 | Information output method, information output device, dump truck system, computer, and storage medium |
| CN109615726A (en) * | 2018-12-12 | 2019-04-12 | 湖北汽车工业学院 | Information output method, device, dumper system, computer and storage medium |
| CN110599620A (en) * | 2019-07-26 | 2019-12-20 | 广州亚美信息科技有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN110599620B (en) * | 2019-07-26 | 2021-12-24 | 广州亚美信息科技有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN112486136A (en) * | 2019-09-11 | 2021-03-12 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN113888775A (en) * | 2020-06-19 | 2022-01-04 | 比亚迪股份有限公司 | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle |
| CN111988342A (en) * | 2020-09-18 | 2020-11-24 | 大连理工大学 | Online automobile CAN network anomaly detection system |
| CN112606779A (en) * | 2020-12-24 | 2021-04-06 | 东风汽车有限公司 | Automobile fault early warning method and electronic equipment |
| CN114296426A (en) * | 2021-12-08 | 2022-04-08 | 奇瑞新能源汽车股份有限公司 | Remote diagnosis method and device for vehicle, server and storage medium |
| CN117389256A (en) * | 2023-12-11 | 2024-01-12 | 青岛盈智科技有限公司 | Early warning method for truck vehicle state in transportation process |
| CN117389256B (en) * | 2023-12-11 | 2024-03-08 | 青岛盈智科技有限公司 | Early warning method for truck vehicle state in transportation process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107403480A (en) | A kind of vehicle trouble method for early warning, system and vehicle | |
| EP2863282B1 (en) | System and method for detecting anomaly associated with driving a vehicle | |
| US9324192B2 (en) | Real-time monitoring of vehicle | |
| CN111506048B (en) | Vehicle fault early warning method and related equipment | |
| CN112073393A (en) | Flow detection method based on cloud computing and user behavior analysis and big data center | |
| CN108306997B (en) | Domain name resolution monitoring method and device | |
| CN115599077B (en) | Vehicle fault delimiting method and device, electronic equipment and storage medium | |
| CN111489459A (en) | Vehicle data analysis method | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| CN114462897B (en) | Comprehensive performance evaluation method and device for highway electromechanical system and storage medium | |
| CN115514620A (en) | Anomaly detection method and cloud network platform | |
| CN111157245A (en) | Supervision method and system for rail transit running gear bearing | |
| JP7348243B2 (en) | Test methods, devices and equipment for traffic flow monitoring measurement systems | |
| CN116743637B (en) | Abnormal flow detection method and device, electronic equipment and storage medium | |
| CN113888775A (en) | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle | |
| CN115392730A (en) | Rental vehicle warning method and device, electronic equipment and storage medium | |
| CN114677039A (en) | Vehicle running control evaluation method and device, readable storage medium and electronic equipment | |
| CN112398706B (en) | Data evaluation standard determining method and device, storage medium and electronic equipment | |
| CN112685610A (en) | False registration account identification method and related device | |
| CN115373369B (en) | Vehicle fault diagnosis system and method | |
| CN117493820B (en) | Data element processing method and device | |
| CN118494510B (en) | Active safe driving auxiliary integrated machine cloud management platform | |
| CN110989556B (en) | Fault diagnosis method and system for vehicle-mounted equipment | |
| CN114239645A (en) | Driving mode identification method and device, terminal equipment and storage medium | |
| CN116957402A (en) | Target defect-based processing method and device and computer readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171128 |