CN113033860A - Automobile fault prediction method and device, electronic equipment and storage medium - Google Patents
Automobile fault prediction method and device, electronic equipment and storage mediumDownload PDFInfo
- Publication number
- CN113033860A CN113033860ACN201911353213.1ACN201911353213ACN113033860ACN 113033860 ACN113033860 ACN 113033860ACN 201911353213 ACN201911353213 ACN 201911353213ACN 113033860 ACN113033860 ACN 113033860A
- Authority
- CN
- China
- Prior art keywords
- fault
- driving
- driving information
- vehicle
- risk identification
- 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
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
- G—PHYSICS
- 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
- G07C5/0841—Registering performance data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The present invention relates to the field of vehicle fault prediction technologies, and in particular, to a vehicle fault prediction method and apparatus, an electronic device, and a storage medium.
Background
According to statistics, the number of automobiles in the world is kept to break through 10 hundred million automobiles, and people can not leave the automobiles more and more. Some abnormalities or faults occur inevitably during the use process of the vehicle. The number of automobile fault codes is as many as ten thousands, and often the occurrence reasons of a fault are multiple, at present, a reliable automobile fault prediction system does not exist, and generally, after the fault occurs, a driver drives the automobile to a 4S store or a repair shop, reads the fault codes by using OBD equipment, and inspects the fault reasons one by one.
With the development of automobiles to electromotion, networking and intellectualization, the mechanical structure and the electronic system of the automobile become more and more complex, and the number and the probability of component failure will increase. Some faults can bring great safety hazards to driving and can also cause loss of time and money, particularly for new energy automobiles, and due to the fact that battery technology is still not mature at the present stage, the consequences caused by related faults are more serious.
Therefore, it is highly desirable to provide a technical solution of a method for predicting a failure of an automobile, which can predict the occurrence time of the failure and notify an owner of the failure to perform inspection, repair or maintenance before the failure occurs, so as to avoid the failure and improve the safety of the automobile.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for predicting a vehicle failure, comprising:
receiving driving information of a vehicle to be tested;
determining a driving target characteristic set according to the driving information;
determining fault occurrence time corresponding to the driving information by utilizing a fault risk identification model strategy according to the driving target feature set, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
and sending the fault occurrence time corresponding to the driving information to the vehicle to be tested so that the vehicle to be tested generates a corresponding prompt according to the fault occurrence time.
Further, the fault risk identification model component is arranged to be built in the following manner:
acquiring a plurality of historical vehicle driving information, wherein the historical vehicle driving information comprises: the driving target feature set and the fault occurrence time corresponding to the historical vehicle driving information;
establishing the fault risk identification model component, wherein the fault risk identification model component comprises a plurality of model parameters;
and taking the driving target feature set in the historical vehicle driving information as input data of the fault risk identification model component, taking the fault occurrence time corresponding to the historical vehicle driving information as output data of the fault risk identification model component, and adjusting the model parameters of the fault risk identification model component until the fault risk identification model component meets the preset requirement.
Further, the driving information includes: fault coding and driving parameters;
the determining of the driving target feature set according to the driving information includes:
cleaning the driving parameters according to the fault codes to obtain a driving initial characteristic subset;
filtering invalid features in the initial feature subset of the driving to obtain an effective driving feature subset;
and carrying out normalization processing on the effective driving feature subset to obtain the driving target feature set.
Further, the driving parameters comprise at least one of the following: the maximum external temperature, the minimum external temperature, the maximum external humidity, the minimum external humidity, the mileage, the age of the vehicle, the accumulated running time, the accumulated idle time, the maximum number of days during which the engine is not started, the air conditioner use time, the average engine speed, the red line speed, the maximum water temperature, the minimum water temperature, the maximum oil pressure, the minimum oil pressure, the maximum accumulator voltage, the minimum accumulator voltage, the average motor speed, the minimum motor voltage, the minimum motor current, the maximum power battery voltage, the minimum power battery current, the maximum power battery temperature, the minimum power battery temperature, the average speed, the number of starts, the number of rapid accelerations, the number of rapid decelerations, the average lateral acceleration of the vehicle body, the maximum power battery voltage, the minimum power, An accelerator pedal travel average, an accelerator pedal acceleration average, a brake pedal travel average, a brake pedal acceleration average, a steering wheel angular velocity average, and a vehicle model.
Another aspect of the present invention provides an apparatus for predicting a vehicle failure, comprising:
the driving information receiving module is used for receiving driving information of the vehicle to be detected;
the driving target characteristic set determining module is used for determining a driving target characteristic set according to the driving information;
and the fault occurrence time determining module is used for determining fault occurrence time corresponding to the driving information by utilizing a fault risk identification model strategy according to the driving target feature set, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
and the fault occurrence time sending module is used for sending the fault occurrence time corresponding to the driving information to the vehicle to be detected so that the vehicle to be detected generates a corresponding prompt according to the fault occurrence time.
Further, the driving target feature set determination module comprises:
the cleaning unit is used for cleaning the driving parameters according to the fault codes to obtain a driving initial characteristic subset;
the filtering unit is used for filtering invalid characteristics in the driving initial characteristic subset to obtain an effective driving characteristic subset;
and the normalization unit is used for performing normalization processing on the effective driving feature subset to obtain the driving target feature set.
Another aspect of the present invention provides a server, which includes a processor and a memory, where at least one instruction, at least one program, a code set, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the vehicle fault prediction method as described above.
Another aspect of the present invention provides a computer-readable storage medium having at least one instruction, at least one program, a set of codes, or a set of instructions stored therein, loaded and executed by a processor to implement the vehicle fault prediction method as described above.
The invention provides a vehicle fault prediction method on the other hand, which comprises the following steps:
acquiring a prediction request;
sending driving information to a server based on the prediction request so that the server determines the fault occurrence time corresponding to the driving information by using a fault risk identification model strategy, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
receiving fault occurrence time corresponding to the driving information;
and generating a corresponding prompt according to the fault occurrence time.
Another aspect of the present invention provides an apparatus for predicting a vehicle failure, comprising:
the prediction request acquisition module is used for acquiring a prediction request;
a driving information sending module, configured to send driving information to a server based on the prediction request, so that the server determines a fault occurrence time corresponding to the driving information by using a fault risk identification model policy, where the fault risk identification model policy includes: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
the fault occurrence time receiving module is used for receiving fault occurrence time corresponding to the driving information;
and the prompt generation module is used for generating a corresponding prompt according to the fault occurrence time.
Another aspect of the present invention provides a terminal, including a processor and a memory, where at least one instruction, at least one program, a code set, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the vehicle fault prediction method as described above.
Another aspect of the present invention provides a computer-readable storage medium having at least one instruction, at least one program, a set of codes, or a set of instructions stored therein, loaded and executed by a processor to implement the vehicle fault prediction method as described above.
Due to the technical scheme, the invention has the following beneficial effects:
(1) the applicability is strong: the different vehicle types can carry out the fault prediction function according to the requirements;
(2) the accuracy is high: and classifying the vehicles with similar use conditions by using a clustering algorithm, so that the automobiles in one class have similar fault occurrence conditions, and mining the commonalities among user groups and the values behind the user groups by using big data and machine learning.
(3) The speed is high: the invention can clean and filter information irrelevant to the fault information according to the fault information and the vehicle type, and improve the running speed of the model assembly.
(4) The safety is strong: the method comprises the steps of extracting features from data of driving behaviors and driving environments, selecting features related to faults by applying a feature selection algorithm, constructing a feature subset, selecting different cluster numbers, selecting the cluster number with the best clustering effect after clustering evaluation, predicting vehicle fault occurrence time in each cluster of a certain vehicle type based on clustering results, reducing vehicle fault occurrence frequency and improving user friendliness.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description of the embodiment or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a flow chart of a method for predicting vehicle failure according to an embodiment of the present invention;
FIG. 2 is another flow chart of a method for predicting vehicle failure according to an embodiment of the present invention;
fig. 3 is a block diagram of an automobile failure prediction apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram of an automobile failure prediction apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a storage medium according to an embodiment of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or device.
The automobile fault prediction method of the present invention is described below with a server as an execution subject, where the server may be a server operating independently, or a server cluster composed of a plurality of servers, or a cloud computing service center. The server may include a network communication unit, a processor, a memory, and the like. The server can establish communication connection with the user terminal through a wireless or wired network, and the user terminal can be a vehicle. Referring to the accompanying drawings of the specification, fig. 1 shows a flow of a vehicle failure prediction method according to an embodiment of the present invention. As shown in fig. 1, the method includes:
s102, receiving driving information of a vehicle to be tested;
specifically, the server may receive driving information sent by the vehicle to be tested, where the driving information may at least include one of the following: fault coding and driving parameters.
It should be noted that the fault code may be a fault category customized by a user, such as: low battery voltage, and the like. The driving parameters may be at least one or more of: the maximum external temperature, the minimum external temperature, the maximum external humidity, the minimum external humidity, the mileage, the age of the vehicle, the accumulated running time, the accumulated idle time, the maximum number of days during which the engine is not started, the air conditioner use time, the average engine speed, the red line speed, the maximum water temperature, the minimum water temperature, the maximum oil pressure, the minimum oil pressure, the maximum accumulator voltage, the minimum accumulator voltage, the average motor speed, the minimum motor voltage, the minimum motor current, the maximum power battery voltage, the minimum power battery current, the maximum power battery temperature, the minimum power battery temperature, the average speed, the number of starts, the number of rapid accelerations, the number of rapid decelerations, the average lateral acceleration of the vehicle body, the maximum power battery voltage, the minimum power, An accelerator pedal travel average, an accelerator pedal acceleration average, a brake pedal travel average, a brake pedal acceleration average, a steering wheel angular velocity average, and a vehicle model.
S104, determining a driving target feature set according to the driving information;
in some possible embodiments, the determining a driving target feature set according to the driving information includes:
cleaning the driving parameters according to the fault codes to obtain a driving initial characteristic subset;
filtering invalid features in the initial feature subset of the driving to obtain an effective driving feature subset;
and carrying out normalization processing on the effective driving feature subset to obtain the driving target feature set.
Illustratively, for a fault "low battery voltage" fault, k-means clustering may be performed as follows:
and cleaning the data, namely removing the data which are not logical and the driving data of the non-paved road surface, and complementing the data with partial missing values to obtain the initial characteristic subset of the driving.
And (3) filtering data: and combining the features with high association degree, and removing the features which have little influence on the clustering result to obtain an effective driving feature subset.
Processing data: and carrying out normalization processing on the effective driving feature subset to obtain the driving target feature set.
S106, determining the fault occurrence time corresponding to the driving information by utilizing a fault risk identification model strategy according to the driving target feature set, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
specifically, the server may determine the fault occurrence time corresponding to the driving information by using a fault risk identification model strategy according to the driving target feature set.
In some possible embodiments, the fault risk identification model component is arranged to be built in the following way:
acquiring a plurality of historical vehicle driving information, wherein the historical vehicle driving information comprises: the driving target feature set and the fault occurrence time corresponding to the historical vehicle driving information;
establishing the fault risk identification model component, wherein the fault risk identification model component comprises a plurality of model parameters;
and taking the driving target feature set in the historical vehicle driving information as input data of the fault risk identification model component, taking the fault occurrence time corresponding to the historical vehicle driving information as output data of the fault risk identification model component, and adjusting the model parameters of the fault risk identification model component until the fault risk identification model component meets the preset requirement.
Specifically, the server may obtain driving information of a plurality of historical vehicles in advance, where the driving information may include: driving parameters, vehicle types and fault codes, wherein a driving target feature set in historical vehicle driving information is used as input data of the fault risk identification model component, fault occurrence time corresponding to the historical vehicle driving information is used as output data of the fault risk identification model component, the fault risk identification model component is built, and model parameters are adjusted through multiple groups of historical driving information until the fault risk identification model component meets preset requirements. The preset requirements can be set according to actual needs.
And S108, sending the fault occurrence time corresponding to the driving information to the vehicle to be tested so that the vehicle to be tested generates a corresponding prompt according to the fault occurrence time.
Specifically, the software and hardware foundation can be a vehicle networking system and a big data platform built by each vehicle enterprise, and can also be a national monitoring and management center of the new energy vehicle. The Internet of vehicles system encrypts and packages data recorded by the T-box into small files, uploads the small files to a big data platform (namely a server) at regular intervals through 3G and 4G mobile networks, and the big data platform analyzes the files after receiving the files, then stores the analyzed files into HBase and deletes original files.
The big data platform is deployed on a cloud or a local physical server, a MapReduce assembly is installed as a computing engine on the basis of Hadoop at the bottom layer, HBase is used as a data warehouse, platform data are defaulted to be 3 backups, and data security is guaranteed. The big data platform should also purchase the service of the operator, provide the function of sending short messages, and inform the user about the failure and maintenance related information.
The big data platform obtains the vehicle type of the vehicle from the vehicle networking information, each vehicle type is clustered independently, partial driving data possibly has no value due to sensor abnormity, network and the like, a module in a spark MLlib preprocessing library is used for completing the data, and in addition, some data which are not in accordance with logic are filtered.
Most vehicles mainly run on paved road surfaces, and in comparison, the proportion of the running data of non-paved road surfaces in the total data is small, but the clustering result is greatly influenced, so that a good clustering result cannot be obtained. And positioning the driving path of the vehicle through the longitude and latitude information in the internet of vehicles, and removing the data of the non-paved road surface.
And applying a feature selection algorithm to remove features with variance lower than a certain threshold, wherein the features have small influence on the clustering result, and the features with high association degree are combined to realize feature dimension reduction so as to reduce the complexity and time cost of clustering analysis, and the obtained data is called as a feature complete set.
For each fault, the features associated with the fault are selected, and a subset of features is constructed from the full set of features.
The feature subset comprises driving behavior features of multiple dimensions, all the features are subjected to normalization processing, and proper clustering numbers are selected, wherein the clustering numbers can be multiple.
And clustering the vehicles by using different clustering numbers through a k-means clustering algorithm, and calculating the contour coefficient of each clustering result so as to evaluate the clustering results. And selecting the clustering number with the contour coefficient closest to 1, and combining related professional knowledge to obtain the clustering results of all vehicles of the vehicle type.
Calculating the average fault time of each fault of each cluster under different vehicle types through a spark or mapreduce engine, predicting the faults of all vehicles of the vehicle type according to the cluster to which the vehicle belongs, informing a vehicle owner of the prediction result through a short message or a vehicle machine system, and selecting a proper time for maintenance by the vehicle owner according to the actual state of the vehicle.
Illustratively, for a fault "low battery voltage" fault, k-means clustering is performed as follows:
1. and cleaning data, namely removing the data which are not logical and the driving data of the non-paved road surface, and complementing the data with partial value loss.
2. And combining the features with high association degree, and filtering out the features which have little influence on the clustering result.
3. The fault is analyzed to be related to the data of the lowest value of the external temperature, the age (days) of the vehicle, the longest days when the engine is not started and the lowest value of the voltage of the storage battery. A mysql table is established independently from data of all vehicles of a certain vehicle type and is called as a storage battery analysis table. In the table, data of the vehicle A are-20, 800, 5 and 11.4 respectively, data of the vehicle B are-3, 500, 3 and 10.2 respectively, data of the vehicle C are-1, 300, 4 and 10.5 respectively, data of the vehicle D are 2, 600, 15 and 11.8 respectively, data of the vehicle E are-7, 1300, 7 and 9.8 respectively, and data of the vehicle F are-5, 1400, 6 and 10.0 respectively. Feature subsets are constructed from the above data.
4. And uniformly carrying out non-dimensionalization on temperature, time and voltage data.
5. Selecting the number of clusters as 4, the clusters as 4: the first type has A car, the characteristic is that the external temperature is too low; the second type is a vehicle B and a vehicle C, and is characterized in that the batteries are normally used and have quality problems; the third type has a D vehicle and is characterized in that the vehicle is not started after being placed for a long time; the fourth category is vehicle E and vehicle F, and is characterized by aging of batteries and capacity reduction. Then, selecting other clustering numbers, such as 5, and after clustering, determining a final clustering result by using the contour coefficient and the professional knowledge, wherein the clustering result is optimal when the clustering number is 4 in the example.
6. The average time of the first type vehicle fault is 12 hours, and when the battery power is insufficient, the starting difficulty can occur in the morning next day after the vehicle is placed in cold weather. The average failure time of the second type of vehicles is 3-6 months after the vehicles are off line. The average failure time of the third type of vehicles is 15-30 days after the vehicles are stopped. The average fault time of the fourth type of fault is 24-36 months of vehicle use.
7. And sending a short message to the vehicle owner or pushing a notice in the vehicle machine system to inform the time period when the fault is possible.
8. The owner selects the opportunity to inspect and maintain the vehicle.
The automobile fault prediction method provided by the invention has the following technical effects:
the applicability is strong: the different vehicle types can carry out the fault prediction function according to the requirements;
the accuracy is high: and classifying the vehicles with similar use conditions by using a clustering algorithm, so that the automobiles in one class have similar fault occurrence conditions, and mining the commonalities among user groups and the values behind the user groups by using big data and machine learning.
The speed is high: the invention can clean and filter information irrelevant to the fault information according to the fault information and the vehicle type, and improve the running speed of the model assembly.
The safety is strong: the method comprises the steps of extracting features from data of driving behaviors and driving environments, selecting features related to faults by applying a feature selection algorithm, constructing a feature subset, selecting different cluster numbers, selecting the cluster number with the best clustering effect after clustering evaluation, predicting vehicle fault occurrence time in each cluster of a certain vehicle type based on clustering results, reducing vehicle fault occurrence frequency and improving user friendliness.
An embodiment of the present invention further provides an automobilefault prediction apparatus 200, as shown in fig. 2, where theapparatus 200 includes:
the driving information receiving module is used for receiving driving information of the vehicle to be detected;
the driving target characteristic set determining module is used for determining a driving target characteristic set according to the driving information;
and the fault occurrence time determining module is used for determining fault occurrence time corresponding to the driving information by utilizing a fault risk identification model strategy according to the driving target feature set, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
and the fault occurrence time sending module is used for sending the fault occurrence time corresponding to the driving information to the vehicle to be detected so that the vehicle to be detected generates a corresponding prompt according to the fault occurrence time.
On the basis of the foregoing embodiment, in an embodiment of the present specification, the driving target feature set determining module includes:
the cleaning unit is used for cleaning the driving parameters according to the fault codes to obtain a driving initial characteristic subset;
the filtering unit is used for filtering invalid characteristics in the driving initial characteristic subset to obtain an effective driving characteristic subset;
and the normalization unit is used for performing normalization processing on the effective driving feature subset to obtain the driving target feature set.
On the basis of the above embodiment, in an embodiment of the present specification, the apparatus further includes:
the second clustering result generation module is used for merging the results which are successfully filtered according to a preset merging rule if the target to be clustered is a null value so as to obtain a second clustering result;
and the second clustering result sorting module is used for sorting the second clustering results according to a preset arrangement rule.
The flow of the automobile fault prediction method shown in fig. 1 is mainly described from the perspective of a server, and the embodiment of the present invention also provides a flow of the automobile fault prediction method described from the perspective of a user terminal (i.e., a vehicle), which corresponds to the flow in fig. 1. Since the above has described some operations of the server in the solution of the present invention in detail, supplementary description is mainly given here, and description is not repeated or only briefly described if it relates to overlapping contents.
Referring to the specification and fig. 3, a flow of a method for predicting a failure of an automobile according to another embodiment of the present invention is shown. As shown in fig. 3, the method includes:
s502, obtaining a prediction request;
specifically, in the embodiment of the present invention, the prediction request may be obtained by the user terminal from any program on the own device, or obtained from a network, and the like. For example, the user terminal may obtain the prediction request through third-party software, may call the third-party software and the clock software through one or more installed application programs, and may also send the prediction request through a button provided on the driver side of the vehicle.
S504, traffic information is sent to a server based on the prediction request, so that the server determines fault occurrence time corresponding to the traffic information by using a fault risk identification model strategy, wherein the fault risk identification model strategy comprises: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
specifically, the driving information may be acquired by the vehicle ECU in real time, and the driving information is sent to the server after the prediction request is acquired.
S506, receiving fault occurrence time corresponding to the driving information;
and S508, generating a corresponding prompt according to the fault occurrence time.
Specifically, the prompt can be provided for the driver through one or more of a display screen, a light alarm unit or sound.
An embodiment of the present invention further provides anapplication recommendation apparatus 400, as shown in fig. 4, where theapparatus 400 includes:
the prediction request acquisition module is used for acquiring a prediction request;
a driving information sending module, configured to send driving information to a server based on the prediction request, so that the server determines a fault occurrence time corresponding to the driving information by using a fault risk identification model policy, where the fault risk identification model policy includes: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
the fault occurrence time receiving module is used for receiving fault occurrence time corresponding to the driving information;
and the prompt generation module is used for generating a corresponding prompt according to the fault occurrence time.
It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, where the electronic device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the vehicle fault prediction method described above.
In a specific embodiment, as shown in fig. 5, a schematic structural diagram of an electronic device provided in an embodiment of the present invention is shown. Theelectronic device 800 may include components such asmemory 810 for one or more computer-readable storage media,processor 820 for one or more processing cores,input unit 830,display unit 840, Radio Frequency (RF)circuitry 850, wireless fidelity (WiFi)module 860, andpower supply 870. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 5 does not constitute a limitation ofelectronic device 800, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components. Wherein:
thememory 810 may be used to store software programs and modules, and theprocessor 820 executes various functional applications and data processing by operating or executing the software programs and modules stored in thememory 810 and calling data stored in thememory 810. Thememory 810 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, thememory 810 may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device. Accordingly,memory 810 may also include a memory controller to provideprocessor 820 with access tomemory 810.
Theprocessor 820 is a control center of theelectronic device 800, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of theelectronic device 800 and processes data by operating or executing software programs and/or modules stored in thememory 810 and calling data stored in thememory 810, thereby performing overall monitoring of theelectronic device 800. TheProcessor 820 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Theinput unit 830 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. Specifically, theinput unit 830 may include animage input device 831 andother input devices 832. Theimage input device 831 may be a camera or a photoelectric scanning device. Theinput unit 830 may includeother input devices 832 in addition to theimage input device 831. In particular,other input devices 832 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
Thedisplay unit 840 may be used to display information input by or provided to a user and various graphical user interfaces of an electronic device, which may be made up of graphics, text, icons, video, and any combination thereof. TheDisplay unit 840 may include aDisplay panel 841, and theDisplay panel 841 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like, as an option.
TheRF circuit 850 may be used for receiving and transmitting signals during a message transmission or communication process, and in particular, for receiving downlink messages from a base station and then processing the received downlink messages by the one ormore processors 820; in addition, data relating to uplink is transmitted to the base station. In general, theRF circuitry 850 includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, theRF circuit 850 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), and the like.
WiFi belongs to short-range wireless transmission technology, and theelectronic device 800 can help the user send and receive e-mails, browse web pages, access streaming media, etc. through theWiFi module 860, and it provides the user with wireless broadband internet access. Although fig. 5 showsWiFi module 860, it is understood that it does not belong to the essential components ofelectronic device 800, and may be omitted entirely as needed within the scope not changing the essence of the invention.
Theelectronic device 800 also includes a power supply 870 (e.g., a battery) for powering the various components, which may be logically coupled to theprocessor 820 via a power management system to manage charging, discharging, and power consumption via the power management system. Thepower source 870 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
It should be noted that, although not shown, theelectronic device 800 may further include a bluetooth module, and the like, which is not described herein again.
An embodiment of the present invention further provides a storage medium, as shown in fig. 6, where at least one instruction, at least one program, a code set, or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set may be executed by a processor of an electronic device to implement any one of the above-mentioned vehicle fault prediction methods.
Optionally, in an embodiment of the present invention, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, the electronic device and the storage medium embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and the relevant points can be referred to the partial description of the method embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A vehicle fault prediction method is characterized by comprising the following steps:
receiving driving information of a vehicle to be tested;
determining a driving target characteristic set according to the driving information;
determining fault occurrence time corresponding to the driving information by utilizing a fault risk identification model strategy according to the driving target feature set, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
and sending the fault occurrence time corresponding to the driving information to the vehicle to be tested so that the vehicle to be tested generates a corresponding prompt according to the fault occurrence time.
2. The method of claim 1, wherein the fault risk identification model component is arranged to be built in the following way:
acquiring a plurality of historical vehicle driving information, wherein the historical vehicle driving information comprises: the driving target feature set and the fault occurrence time corresponding to the historical vehicle driving information;
establishing the fault risk identification model component, wherein the fault risk identification model component comprises a plurality of model parameters;
and taking the driving target feature set in the historical vehicle driving information as input data of the fault risk identification model component, taking the fault occurrence time corresponding to the historical vehicle driving information as output data of the fault risk identification model component, and adjusting the model parameters of the fault risk identification model component until the fault risk identification model component meets the preset requirement.
3. The method of claim 1, wherein the driving information comprises: fault coding and driving parameters;
the determining of the driving target feature set according to the driving information includes:
cleaning the driving parameters according to the fault codes to obtain a driving initial characteristic subset;
filtering invalid features in the initial feature subset of the driving to obtain an effective driving feature subset;
and carrying out normalization processing on the effective driving feature subset to obtain the driving target feature set.
4. The method of claim 3, wherein the driving parameters comprise at least one of: the maximum external temperature, the minimum external temperature, the maximum external humidity, the minimum external humidity, the mileage, the age of the vehicle, the accumulated running time, the accumulated idle time, the maximum number of days during which the engine is not started, the air conditioner use time, the average engine speed, the red line speed, the maximum water temperature, the minimum water temperature, the maximum oil pressure, the minimum oil pressure, the maximum accumulator voltage, the minimum accumulator voltage, the average motor speed, the minimum motor voltage, the minimum motor current, the maximum power battery voltage, the minimum power battery current, the maximum power battery temperature, the minimum power battery temperature, the average speed, the number of starts, the number of rapid accelerations, the number of rapid decelerations, the average lateral acceleration of the vehicle body, the maximum power battery voltage, the minimum power, An accelerator pedal travel average, an accelerator pedal acceleration average, a brake pedal travel average, a brake pedal acceleration average, a steering wheel angular velocity average, and a vehicle model.
5. A vehicle fault prediction method is characterized by comprising the following steps:
acquiring a prediction request;
sending driving information to a server based on the prediction request so that the server determines the fault occurrence time corresponding to the driving information by using a fault risk identification model strategy, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
receiving fault occurrence time corresponding to the driving information;
and generating a corresponding prompt according to the fault occurrence time.
6. An automobile failure prediction device, characterized by comprising:
the driving information receiving module is used for receiving driving information of the vehicle to be detected;
the driving target characteristic set determining module is used for determining a driving target characteristic set according to the driving information;
and the fault occurrence time determining module is used for determining fault occurrence time corresponding to the driving information by utilizing a fault risk identification model strategy according to the driving target feature set, wherein the fault risk identification model strategy comprises the following steps: the fault risk identification module is obtained by training according to the corresponding relation between the driving target feature set of the plurality of historical vehicle driving information and the fault sending time corresponding to the historical vehicle driving information;
and the fault occurrence time sending module is used for sending the fault occurrence time corresponding to the driving information to the vehicle to be detected so that the vehicle to be detected generates a corresponding prompt according to the fault occurrence time.
7. The apparatus of claim 6, wherein the driving target feature set determination module comprises:
the cleaning unit is used for cleaning the driving parameters according to the fault codes to obtain a driving initial characteristic subset;
the filtering unit is used for filtering invalid characteristics in the driving initial characteristic subset to obtain an effective driving characteristic subset;
and the normalization unit is used for performing normalization processing on the effective driving feature subset to obtain the driving target feature set.
8. An automobile failure prediction device, characterized by comprising:
the prediction request acquisition module is used for acquiring a prediction request;
the driving information sending module is used for sending driving information to a server based on the prediction request so that the server can determine fault occurrence time corresponding to the driving information according to the driving information;
the fault occurrence time receiving module is used for receiving fault occurrence time corresponding to the driving information;
and the prompt generation module is used for generating a corresponding prompt according to the fault occurrence time.
9. An electronic device, comprising a processor and a memory, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the memory, and wherein the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the vehicle fault prediction method according to any one of claims 1-4 or claim 5.
10. A computer readable storage medium, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the storage medium, which is loaded and executed by a processor to implement the method of vehicle fault prediction according to any one of claims 1-4 or claim 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353213.1ACN113033860A (en) | 2019-12-25 | 2019-12-25 | Automobile fault prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353213.1ACN113033860A (en) | 2019-12-25 | 2019-12-25 | Automobile fault prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033860Atrue CN113033860A (en) | 2021-06-25 |
Family
ID=76452362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911353213.1APendingCN113033860A (en) | 2019-12-25 | 2019-12-25 | Automobile fault prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033860A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114661787A (en)* | 2022-03-17 | 2022-06-24 | 桂林电子科技大学 | Itemset mining method and device |
| CN114676758A (en)* | 2022-03-08 | 2022-06-28 | 北京中交兴路信息科技有限公司 | Method, device, electronic equipment and medium for detecting vehicle fault |
| CN114757366A (en)* | 2022-01-26 | 2022-07-15 | 广州汽车集团股份有限公司 | A fault prediction method and system for a vehicle |
| CN115209374A (en)* | 2022-09-14 | 2022-10-18 | 深圳位置网科技有限公司 | Motor vehicle alarm system based on third party call center |
| CN115511648A (en)* | 2022-10-17 | 2022-12-23 | 中国银行股份有限公司 | Method and device for detecting use risk of electric vehicle |
| CN115616435A (en)* | 2022-09-22 | 2023-01-17 | 中汽创智科技有限公司 | Method, device, equipment and storage medium for predicting service life of fuel cell |
| CN116484221A (en)* | 2023-04-21 | 2023-07-25 | 中国第一汽车股份有限公司 | Vehicle state detection method and device, storage medium, processor and electronic device |
| CN116561581A (en)* | 2023-05-22 | 2023-08-08 | 重庆长安汽车股份有限公司 | Model verification method, device, equipment and storage medium |
| CN117540199A (en)* | 2024-01-05 | 2024-02-09 | 中国汽车技术研究中心有限公司 | Fault prediction method, device and storage medium for fuel cell vehicle |
| CN119682778A (en)* | 2024-12-17 | 2025-03-25 | 长城汽车股份有限公司 | Vehicle control method, vehicle, and computer-readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682795A (en)* | 2015-11-05 | 2017-05-17 | 大陆汽车投资（上海）有限公司 | Data analysis based automobile part information processing method |
| CN108469802A (en)* | 2018-01-31 | 2018-08-31 | 武汉华威专用汽车检测有限责任公司 | A kind of information of vehicles remote monitoring and diagnostics system |
| CN108693868A (en)* | 2018-05-25 | 2018-10-23 | 深圳市轱辘车联数据技术有限公司 | The method of failure predication model training, the method and device of vehicle trouble prediction |
- 2019
- 2019-12-25CNCN201911353213.1Apatent/CN113033860A/enactivePending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682795A (en)* | 2015-11-05 | 2017-05-17 | 大陆汽车投资（上海）有限公司 | Data analysis based automobile part information processing method |
| CN108469802A (en)* | 2018-01-31 | 2018-08-31 | 武汉华威专用汽车检测有限责任公司 | A kind of information of vehicles remote monitoring and diagnostics system |
| CN108693868A (en)* | 2018-05-25 | 2018-10-23 | 深圳市轱辘车联数据技术有限公司 | The method of failure predication model training, the method and device of vehicle trouble prediction |
Non-Patent Citations (1)
| Title |
|---|
| 杨良斌 编著: "《信息分析方法与实践》", 31 January 2017, 东北师范法学出版社, pages: 298* |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114757366A (en)* | 2022-01-26 | 2022-07-15 | 广州汽车集团股份有限公司 | A fault prediction method and system for a vehicle |
| CN114757366B (en)* | 2022-01-26 | 2023-02-03 | 广州汽车集团股份有限公司 | A fault prediction method and system for vehicles |
| CN114676758A (en)* | 2022-03-08 | 2022-06-28 | 北京中交兴路信息科技有限公司 | Method, device, electronic equipment and medium for detecting vehicle fault |
| CN114661787A (en)* | 2022-03-17 | 2022-06-24 | 桂林电子科技大学 | Itemset mining method and device |
| CN115209374A (en)* | 2022-09-14 | 2022-10-18 | 深圳位置网科技有限公司 | Motor vehicle alarm system based on third party call center |
| CN115616435A (en)* | 2022-09-22 | 2023-01-17 | 中汽创智科技有限公司 | Method, device, equipment and storage medium for predicting service life of fuel cell |
| CN115511648A (en)* | 2022-10-17 | 2022-12-23 | 中国银行股份有限公司 | Method and device for detecting use risk of electric vehicle |
| CN116484221A (en)* | 2023-04-21 | 2023-07-25 | 中国第一汽车股份有限公司 | Vehicle state detection method and device, storage medium, processor and electronic device |
| CN116561581A (en)* | 2023-05-22 | 2023-08-08 | 重庆长安汽车股份有限公司 | Model verification method, device, equipment and storage medium |
| CN117540199A (en)* | 2024-01-05 | 2024-02-09 | 中国汽车技术研究中心有限公司 | Fault prediction method, device and storage medium for fuel cell vehicle |
| CN117540199B (en)* | 2024-01-05 | 2024-05-07 | 中国汽车技术研究中心有限公司 | Fault prediction method, device and storage medium for fuel cell vehicles |
| CN119682778A (en)* | 2024-12-17 | 2025-03-25 | 长城汽车股份有限公司 | Vehicle control method, vehicle, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033860A (en) | Automobile fault prediction method and device, electronic equipment and storage medium | |
| US20210005027A1 (en) | System and method for battery maintenance management | |
| CN102902752B (en) | Method and system for monitoring log | |
| CN112519631B (en) | Battery control device, charging and discharging system, parking system, secondary battery recycling system, battery control method and storage medium | |
| US20170116793A1 (en) | Method for generating vehicle health parameters, method for displaying vehicle health parameters and devices thereof | |
| CN108427393B (en) | Method and apparatus for detecting battery depletion | |
| KR102576987B1 (en) | Apparatus and method for determining state of battery based on data of vehicle | |
| US11454967B2 (en) | Systems and methods for collecting vehicle data to train a machine learning model to identify a driving behavior or a vehicle issue | |
| CN111142038A (en) | Storage battery health state assessment method and device | |
| CN106170826A (en) | The monitoring method and system of cab-getter's number | |
| AU2021335183A1 (en) | Predictive maintenance of vehicle components | |
| CN110362455A (en) | A kind of data processing method and data processing equipment | |
| CN110210980A (en) | A kind of driving behavior appraisal procedure, device and storage medium | |
| CN113611104B (en) | Risk identification method and device for freight vehicle, storage medium and terminal | |
| CN104750753A (en) | A driving behavior report generation method and device | |
| CN110012069A (en) | A kind of vehicle data processing unit, method and vehicle monitoring platform | |
| CN118732662A (en) | A vehicle remote fault diagnosis and recovery system and method | |
| CN113920618A (en) | Vehicle unlocking method and device, shared vehicle and storage medium | |
| CN112950955A (en) | Vehicle illegal parking data management method and device | |
| CN116442778A (en) | Method, device, intelligent gateway, medium and program product for vehicle early warning | |
| CN112712002B (en) | Environmental monitoring method, device, system and storage medium based on CGAN | |
| CN115042731B (en) | Maintenance reminder method, device, automobile and computer-readable storage medium | |
| CN117360413A (en) | Method and device for reminding of power shortage of storage battery, vehicle and storage medium | |
| CN207475609U (en) | The vehicle-mounted interactive communication system of Internet of Things based on cloud platform | |
| CN116303072A (en) | Full-link performance test method and 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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20210625 | |
| RJ01 | Rejection of invention patent application after publication |