CN106441928B

CN106441928B - A kind of vehicle fault detection method, apparatus and system

Info

Publication number: CN106441928B
Application number: CN201610766308.6A
Authority: CN
Inventors: 徐丽丽; 董俊龙
Original assignee: Neusoft Corp
Current assignee: Neusoft Corp
Priority date: 2016-08-30
Filing date: 2016-08-30
Publication date: 2019-12-03
Anticipated expiration: 2036-08-30
Also published as: CN106441928A

Abstract

The invention discloses a kind of vehicle fault detection method, apparatus and systems, are related to field of computer technology, and main purpose is through failure problems existing for the supplemental characteristic real-time diagnosis vehicle in analysis travel condition of vehicle.The main technical solution of the present invention are as follows: receive the supplemental characteristic that data recording equipment uploads, the data recording equipment is installed on vehicle, for obtaining and saving the supplemental characteristic of the vehicle operation in real time；It calls vehicle fault detection knowledge base to analyze the supplemental characteristic, obtains the fault detection address of the vehicle；The fault detection address is exported to the vehicle.Present invention is mainly used for detection vehicle troubles.

Description

A kind of vehicle fault detection method, apparatus and system

Technical field

The present invention relates to field of computer technology more particularly to a kind of vehicle fault detection method, apparatus and system.

Background technique

With the development and progress of Hyundai Motor technology, the manufacturing technology and technique of automobile are also increasingly advanced, automobile It is also stronger and stronger, comprehensive for driving performance.But automobile in actual use, due to natural wastage or other outside Vehicle failure caused by power factor is still inevitable.Therefore, auto repair maintenance has weight for the normal use of automobile The meaning wanted.

Currently, it includes: Artificial Diagnosis method that the basic skills of automobile failure diagnosis, which has, mainly rely on the practice of diagnostic personnel Experience and knowledge, by simple tool, with soon, ear is listened, sense organs means, the frontier inspection such as fingerprint are looked into, analyzed when testing, in turn Technical condition of vehicle is judged.This method is easy to be intuitive, and establishes modern fault diagnosis expert system knowledge base Basis.But the practical experience and knowledge of Artificial Diagnosis method heavy dependence diagnostic personnel, cause the accuracy in detection of failure because Depending on people, it can not promote on a large scale.In addition to Artificial Diagnosis method, there are also a kind of instrument and equipment diagnosis, this method is using logical With or dedicated instrument and equipment detect the necessary technical parameter of automobile compared with parameter when normal technology situation, to be It analyzes technical condition of vehicle and judges that failure provides quantitative basis.But this method needs car owner to the auto repair of profession The detection and investigation that point carries out failure are all in most cases to feel vehicle during using vehicle by car owner There are conscious just going to carry out fault detection after exception, and this vehicle trouble that can be perceived is mostly all wrong Optimal maintenance timing has been crossed, car owner is caused to need to pay higher breakdown maintenance cost.

Summary of the invention

In view of this, the present invention provides a kind of vehicle fault detection method, apparatus and system, main purpose be by point Analyse failure problems existing for the supplemental characteristic real-time diagnosis vehicle in travel condition of vehicle.

In order to achieve the above objectives, the invention provides the following technical scheme:

According to one aspect of the present invention, a kind of vehicle fault detection method is proposed, this method comprises:

The supplemental characteristic that data recording equipment uploads is received, the data recording equipment is installed on vehicle, for real-time Obtain and save the supplemental characteristic of the vehicle operation；

It calls vehicle fault detection knowledge base to analyze the supplemental characteristic, obtains the fault detection report of the vehicle It accuses；

The fault detection address is exported to the vehicle.

According to another aspect of the invention, a kind of vehicle fault detection device is proposed, which includes:

Receiving unit, the supplemental characteristic that recording device uploads for receiving data, the data recording equipment are mounted on vehicle On, for obtaining and saving the supplemental characteristic of the vehicle operation in real time；

Analytical unit, the supplemental characteristic for calling vehicle fault detection knowledge base to obtain the receiving unit divide Analysis, obtains the fault detection address of the vehicle；

Output unit, for exporting fault detection address that the analytical unit obtains to the vehicle.

According to another aspect of the invention, it is also proposed that a kind of vehicle fault detection system, the system include being mounted on Data recording equipment and above-mentioned vehicle fault detection device on vehicle；

Wherein, the data recording equipment is used to record the supplemental characteristic of the vehicle, the parameter that will be recorded in real time Data are sent to the vehicle fault detection device；

The vehicle fault detection device is used to obtain the supplemental characteristic of the data recording equipment record, passes through vehicle event Barrier detection knowledge base analyzes the supplemental characteristic, obtains the fault detection address of the vehicle, and export the fault detection report It accuses to the vehicle.

A kind of vehicle fault detection method, apparatus and system of the present invention can be installed on vehicle by receiving The supplemental characteristic that data recording equipment uploads, it is ensured that obtaining and saving in real time to information of vehicles, then by calling vehicle trouble Detection knowledge base analyzes these real time datas, quickly obtains the real-time running state of vehicle, detects existing for vehicle Failure, and will test the car owner that result feeds back to the vehicle in the form of examining report, prompt car owner to carry out failure further Detection or maintenance.Can be understood by vehicle at any time and worked as the real-time acquisition of vehicle parameter data and analysis, car owner due to realizing Preceding situation, relative to existing car fault diagnosis mode, vehicle fault detection result of the invention is capable of the feedback of active To car owner, to prompt car owner to repair vehicle, so that car owner be made to accomplish to find ahead of time to vehicle trouble, solves, keep away ahead of time Exempt to travel due to vehicle tape jam and may cause more serious failure appearance, has improved the service life of vehicle, also help vehicle The main maintenance expense for reducing vehicle.And for using the detection of the vehicle fault detection method of use of the present invention Side is able to ascend the added value to vehicle service by the active detecting to vehicle, increases the service quality to car owner.

The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention, And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can It is clearer and more comprehensible, the followings are specific embodiments of the present invention.

Detailed description of the invention

By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:

Fig. 1 shows a kind of vehicle fault detection method flow diagram of proposition of the embodiment of the present invention；

Fig. 2 shows the framework maps of vehicle fault detection knowledge base in the embodiment of the present invention；

Fig. 3 shows the schematic diagram that data pattern library in the embodiment of the present invention divides data pattern；

Fig. 4 shows the analysis process schematic diagram of Data Analysis Model in the embodiment of the present invention；

Fig. 5 shows a kind of composition block diagram of vehicle fault detection device of proposition of the embodiment of the present invention；

Fig. 6 shows the composition block diagram of another vehicle fault detection device of proposition of the embodiment of the present invention；

Fig. 7 shows a kind of composition block diagram with vehicle fault detection system of proposition of the embodiment of the present invention.

Specific embodiment

The exemplary embodiment that the present invention will be described in more detail below with reference to accompanying drawings.Although showing the present invention in attached drawing Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here It is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention It is fully disclosed to those skilled in the art.

The embodiment of the invention provides a kind of vehicle fault detection method, this method be can be realized to the real-time of vehicle trouble The early processing of early discovery of vehicle trouble is accomplished in detection.This method can be used in the detection system platform to vehicle trouble, this is flat Platform can obtain a large amount of vehicle parameter data, and be analyzed to obtain failure detection result, be directed to and answer in system platform With the fault detection method, specific steps are as shown in Figure 1, comprising:

101, the supplemental characteristic that data recording equipment uploads is received.

Firstly, to realize the real-time detection to vehicle trouble, it is necessary to realize the real-time acquisition to the supplemental characteristic of vehicle And it saves.In the embodiment of the present invention by vehicle installation data recording device run to obtain and save the vehicle in real time Supplemental characteristic.The supplemental characteristic that data recording equipment is saved includes each sensing in information of vehicles and vehicle operation Device parameter, wherein information of vehicles is the unique identification information for identifying the vehicle, such as engine model, Vehicle Identify Number etc., due to this A little information are relatively fixed constant, are acquired when being installed on vehicle by data recording equipment for information of vehicles therefore Data information certainly when vehicle carries out large repairs, set if having replaced the keys such as engine without the acquisition again in later period Standby, corresponding information of vehicles is to need to reacquire to be changed.And for each sensor in vehicle operation Parameter is generated since these parameters need just to have corresponding data in vehicle operation, the reality in the embodiment of the present invention When obtain and save supplemental characteristic and refer to Real time data acquisition and preservation in vehicle operation, and saving number in real time According to while, moreover it is possible to supplemental characteristic is uploaded by the data transmission module in data recording equipment, carries out further failure It tests and analyzes.Wherein, transmission mode used by the data transmission module in data recording equipment is not limited to by mobile logical News network carries out data transmission, or the data transfer mode carried out by satellite network.

It should be noted that due to the analysis that the analysis of some supplemental characteristics mainly changes process status, for example, cold But the data of liquid temperature just need to analyze when vehicle just starts the variation in a period of time to determine whether normal.Also, vehicle In the process of moving, for the uncertain factor of Network status, therefore, the upload for supplemental characteristic is good in Network status When good, institute can also be first recorded by data recording equipment by the way of real-time Transmission, and when Network status is bad The supplemental characteristic of acquisition regularly uploads recorded vehicle parameter data, this mode, which also can be analyzed preferably, to be needed to carry out The supplemental characteristic of state change analysis.Selection and the switch mode that mode is uploaded for both the above, can have according to the actual situation Body setting, without limitation to this embodiment of the present invention.

In addition, the data transmission module in data recording equipment can be also used for other than uploading the supplemental characteristic of vehicle The examining report of fault detection analysis is received, and the examining report is shown by the media presentation device in vehicle.When So, data transmission module can also be served only for uploading the supplemental characteristic of vehicle, and corresponding examining report can then pass through other Delivering path be transmitted directly to car owner, for example, can will test report is sent to the hand of car owner in a manner of mail or information On machine.

It, can be according to the information of vehicles of upload after fault detection platform receives the supplemental characteristic of data recording equipment upload Classification storage is carried out to supplemental characteristic, to facilitate subsequent calling to analyze.In addition, by the supplemental characteristic with same vehicle information Classified and stored also helps creation vehicle parameter data sample, and then is instructed again to the analysis model in fault detection platform Practice, to obtain more accurately analyzing result.

102, it calls vehicle fault detection knowledge base to analyze vehicle parameter data, obtains the fault detection of the vehicle Report.

Vehicle fault detection knowledge base is to analyze the core content of vehicle parameter data, the vehicle fault detection knowledge reservoir area Not in terms of existing fault test set is primarily present following two:

First is that the vehicle fault detection knowledge base can be carried out by the supplemental characteristic of received different vehicle to analysis mould The intelligent updating of type, and existing fault test set is typically all targetedly detection, used analysis model is opposite Fixed, otherwise the software version of the update fault test set of only equipment manufacturer's active not will be updated upgrading detection generally Equipment, also, existing equipment can not save the data of vehicle, and which results in failure detection results can not be according to vehicle The detection and analysis for having comparison are carried out under different conditions.And the vehicle fault detection knowledge base in the embodiment of the present invention can then be remembered A large amount of vehicle parameter data are recorded, the operating status that parameter database is used to analyze the vehicle can be constructed for each vehicle, led to The analysis compared is crossed to obtain more accurately analyzing result.In addition, by the supplemental characteristic with same configuration vehicle Comparative analysis can also oppositely check analysis model analysis as a result, to improve the precision of analysis of analysis model.

Second is that the scope of application is wider, existing fault test set is generally non-universal equipment, for different brands, difference The vehicle of vehicle system has corresponding fault test set, even for different failures, can also be examined using different equipment It surveys.And the vehicle fault detection knowledge base in the embodiment of the present invention passes through the ginseng of a large amount of different brands of reception, different model vehicle Number data can carry out comprehensive analysis to the data content of identical parameters, create corresponding analysis model.Meanwhile vehicle trouble Detection knowledge base also has powerful scalability, easily can add new parameter in the vehicle fault detection knowledge base, It can be somebody's turn to do by the data and corresponding analysis method that receive newly-increased parameter with increasing to be directed to for vehicle fault detection knowledge base The fault-detecting ability of new parameter.

It is also preserved for the concrete analysis to vehicle parameter data, in vehicle fault detection knowledge base currently used more Kind analysis method, such as range analysis, association analysis, causality analysis.When analyzing the received supplemental characteristic of institute, vehicle Different supplemental characteristics can be carried out the analysis of the multi-modes such as independent, combination by fault detection knowledge base, then pass through different mode institute Corresponding analysis model is made a concrete analysis of, and finally summarizes the analysis result of different analysis models, generates a failure Examining report.Wherein, which can be the only out of order analysis of record detection as a result, being also possible to mark event Hinder result all analysis results displaying report, further can also will analysis result in fail result and it is potentially possible go out Displaying is marked in existing failure.The form embodiment of the present invention specifically is showed without limitation for examining report.

103, fault detection address is exported to corresponding vehicle.

After obtaining fault detection address, this report is saved and according to the corresponding correspondent party of the vehicle analyzed by system platform Formula feeds back the fault detection address.As described in 101, when there are the specific contact methods of car owner for the vehicle analyzed When, such as E-mail address or cell-phone number, fault detection address will be transmitted directly to car owner, inform this detection as a result, and working as When specific contact method is not present in the vehicle analyzed, then the fault detection address can be sent to the data record of the vehicle On device.

Further, since record the analysis of quantity of parameters data in fault detection address as a result, and some are analyzed among these Result, which is not that car owner is really necessary, to be wanted, some parameters do not have any reference value, Che Zhusuo for car owner in other words Concern is more vehicle with the presence or absence of failure, and the data value of some intermediate parameters is not relevant for.Therefore, in output event When hindering examining report, the analysis checked needed for can also being customized as car owner is as a result, check scheme according to customization by system platform Corresponding analysis result is sent to car owner.

It can be seen that a kind of vehicle fault detection used by the embodiment of the present invention by the explanation to above-mentioned realization step Method, the supplemental characteristic that can be uploaded by receiving the data recording equipment installed on vehicle, it is ensured that obtaining in real time for information of vehicles It takes and saves, then by calling vehicle fault detection knowledge base to analyze these real-time data, quickly obtain vehicle Real-time running state, the failure existing for first time detection vehicle, and will test result and fed back in the form of examining report The car owner of the vehicle prompts car owner that the failure is further detected or repaired.Due to realizing to vehicle parameter data Real-time acquisition and analysis, car owner can get the current health status of vehicle at any time, examine relative to existing vehicle trouble Disconnected mode, the fault detection of vehicle does not need to be driven vehicle by car owner to the progress of specified detection place, but is examined in real time Survey, and its testing result be capable of active feed back to car owner, to prompt car owner to repair vehicle, to make car owner to vehicle Failure is accomplished to find ahead of time, be solved ahead of time, avoids and occurs since vehicle tape jam traveling may cause more serious failure, The service life of vehicle is improved, car owner is also helped to reduce the maintenance expense of vehicle.And for using implementation of the present invention The vehicle fault detection method of the example use carries out passing through the active detecting to vehicle, energy for the detection side of detection service Enough added values promoted to vehicle service, increase the service quality to car owner.

Further, for the above-mentioned vehicle fault detection method of more detailed explanation, especially to wherein being called Vehicle fault detection knowledge base framework and analysis process, will focus on the composition for introducing vehicle fault detection knowledge base below And concrete application.

As shown in Fig. 2, being the framework map of vehicle fault detection knowledge base, wherein the vehicle fault detection knowledge base is main It include: data pattern library, Data Definition Library, model library and model parameter library.

Firstly, data pattern library is mainly used for saving information of vehicles and corresponding data pattern.Wherein, information of vehicles is vehicle Unique identification information, and data pattern be then by the type of different parameters data that uploads of received same vehicle carry out Combination, constitutes multiple data patterns.The combination of specific data pattern divides as shown in Figure 3, wherein " root node " is expressed as same The supplemental characteristic source of vehicle, the supplemental characteristic in Fig. 3 includes: ignition advance angle, and air throttle absolute position, air throttle is with respect to position It sets, coolant temperature, this 4 parameters and information of vehicles mark is identified, respectively C1, C2, C3, C4, C5, then carried out phase After mutual combination collocation, obtained combination is exactly data pattern, i.e. (C1, C2), (C1, C2, C4), (C1, C3, C4, C5) etc..From figure Data pattern shown by 3 can be seen that include in each data pattern information of vehicles data, that is to say, that number There is unique corresponding vehicle according to each of pattern base mode.Therefore, it is seen that the data pattern library is an incremental data Library, the data pattern saved can increase with the increase of vehicle, and data pattern library can be each upload parameter data Vehicle creates corresponding supplemental characteristic mode.

Secondly, Data Definition Library is mainly used for the source identification of flag parameters data and point of the analysis supplemental characteristic Analysis method mark.For example, vehicle, after the parameter for uploading a coolant temperature, platform receives the parameter, and mark the ginseng Number be uploaded by which vehicle, meanwhile, can also be transferred from Data Definition Library coolant temperature mark mark in the parameter On, it is coolant temperature represented by the value of the parameter to indicate.Data Definition Library is other than flag parameters, another function Analysis method corresponding to each parameter is exactly marked, because each parameter is in different states, different analysis sides It is combined to or with different parameters when being analyzed, will use different analysis methods, therefore, Data Definition Library can will fit Analysis method for analyzing the parameter is marked in the parameter, to facilitate the subsequent selection when analyzing the parameter corresponding Analysis method.Specific analysis method can be illustrated in the analysis process below, not enumerate herein.

Third, model library are mainly used for saving point that different parameters data and corresponding analysis method are established jointly Analyse model.Model library can go out suitable analysis model according to different data patterns match, can be directed to by analysis model Parameters data in data pattern carry out comprehensive analysis, obtain the analysis result of supplemental characteristic under the data pattern.

Finally, model parameter library is for saving different vehicle, different parameters data, failure corresponding to different analysis method Parameter.Parameter in model parameter library is used for whether the obtained analysis result of discriminatory analysis model to be failure.

For the composition of above-mentioned vehicle fault detection knowledge base, vehicle fault detection knowledge base is described below and is carrying out vehicle When the analysis of supplemental characteristic, 4 points of above-mentioned libraries are how to carry out cooperation analysis:

Firstly, parameters are marked by Data Definition Library, at supplemental characteristic after receiving the supplemental characteristic of vehicle Reason is the data that system can identify；

Secondly, corresponding to received vehicle parameter Data Matching according to the label of parameters by data pattern library Data pattern.It should be noted that received parameter type is more, combined mode out is more, corresponding to divide The fault type of analysis is also more, is exactly that parameter is more briefly, and the complexity of analysis is bigger, corresponding obtained point It is also abundanter to analyse result.

Third, then by Data Definition Library according to different data patterns, corresponding analysis method is matched for parameters.

4th, by model library according to data pattern the suitable analysis model of matched analysis method choice, or combine Analysis method creates new analysis model.Wherein, the quantity of the matching analysis model is not limited to one analysis model of matching, according to Analyze the difference of result, or the parameter in same group of data mode matches multiple analysis models, to obtain multiple points Analyse result.And these analysis results can be unidirectional, for being mutually authenticated, be also possible to different directions.

Finally, being exactly to determine the corresponding fault parameter of analysis result from model parameter library, obtained for discriminatory analysis model To analysis result whether be failure.

It is analyzed by the cooperation in data pattern library, Data Definition Library, model library and model parameter library, to acquired vehicle Supplemental characteristic carries out the analysis of various combination collocation, obtains final fault detection address.It should be noted that vehicle parameter number According to type will have a direct impact on the complexity of analysis, and complicated analysis then needs longer treatment process.And it is of the invention The had real-time data analysis ability of embodiment is not only embodied in the real-time acquisition of supplemental characteristic, is also embodied in analysis result It since the embodiment of the present invention is the application based on system platform, and is to outclass for operational capability system platform in actual effect The checkout and diagnosis equipment of single machine.Whether using the calculation of multi-process either distributed computing, complexity can be made Analytic operation quickly obtain as a result, be the operating status that car owner can understand vehicle in real time in turn, and with the presence or absence of therefore Barrier problem.

During vehicle fault detection knowledge base analyzes vehicle parameter data, model library is to parameter number again According to the core analyzed, by model library matched analysis model can regard as and constituted combined by different analysis methods Testing process.And in the model library of the embodiment of the present invention, each analysis model, all can be first to different analysis sides in creation Method is classified, and two-stage can be generally divided into according to data mechanism and data feature, the first order is to vehicle control system mechanism The analysis method that the intrinsic relationship determined is analyzed, such as data range analysis, data relation analysis.The second level is to vehicle The analysis method that the state of data interval and data variation is analyzed under different operating conditions, such as data mutation analysis, data Comparative analysis etc..According to different classifications, when formulating testing process, usually first using the analysis method of same rank to ginseng Number data are analyzed, and reuse another grade of analytical supplemental characteristic after the completion.For example, first carrying out point of the first order Analysis, carries out the analysis of the second level, certainly, different stage is determined according to different division modes again after the analysis is complete. According to the way that different ranks is analyzed, the analysis that can be mainly oriented according to the analysis result that user specifies, The workload of data analysis is reduced, for example, the specified analysis result checked of user is by data value field analysis and data relation analysis When can be obtained by, then analysis model when being analyzed, can only carry out the data analysis of the first order completely.

In the following, for the analysis stream that the analysis model is illustrated by the analysis model that different analysis methods is constituted Journey, as shown in figure 4, used in the analysis model embodiment to analysis method be include the first order analysis method, There is the analysis method of the second level, specifically: data value field analysis, data relation analysis and data causality analysis are first order analysis Method, date comprision and data mutation analysis belong to second level analysis method.Wherein, setting first carries out the to supplemental characteristic Level-one analysis carries out second level analysis if analyzing result normally.Further, in first order analysis, the sequence of analysis is Advanced row data range analysis, then data relation analysis is carried out, it is finally to carry out data causality analysis, and analyze in the second level In, date comprision and data mutation analysis then depend on vehicle-state.Wherein, above-mentioned analysis sequence is only a kind of realization One of mode can need to carry out customized setting according to concrete analysis in practical applications.

It can be obtained by analysis process shown in Fig. 4 according to above-mentioned setting, be directed to using the analysis process as analysis model Vehicle parameter data A, the process that B, C are analyzed are as follows:

First range analysis is carried out to supplemental characteristic A, B, C respectively, that is, whether is fallen within according to the value of the supplemental characteristic Failure is judged whether there is in the data value field of fault parameter setting.By taking a supplemental characteristic as an example, when acquired parameter number When according to for coolant temperature, the range of temperature of coolant liquid is generally -40~199 DEG C, if numerical value is -40 DEG C, illustrates to cool down Liquid temperature sensor damage or line broken circuit, and if numerical value is more than 185 DEG C, illustrate cooling-water temperature transmitter damage or route Short circuit.Wherein, the reference value of range analysis is provided by model parameter library, which can be a codomain section, can also be with It is a specific numerical value.According to analysis as a result, failure then no longer carries out subsequent judgement if it exists, direct output failure, If result is normal, data relation analysis is carried out；

Data relation analysis is the analysis carried out to the supplemental characteristic with incidence relation, according to the phase between supplemental characteristic Guan Du judges whether there is failure, such as A is air throttle relative position, and B is air throttle absolute position, and the relationship of the two is positive It closes, if the correlation of A, B data is smaller, there may be failures for vehicle.With regard to defeated when the result of data relation analysis is failure It out should be as a result, otherwise then carrying out data causality analysis；

Data causality analysis is the analysis to carrying out with causal supplemental characteristic, according in the supplemental characteristic Input judges whether there is failure with output matching relationship, for example, A is accelerator pedal position, C is throttle opening, then, A When becoming larger, the aperture of C, which can correspond to, to become larger, and if data variation does not match that, there may be failure.

After the completion of data causality analysis, directly output is as a result, and result is normally, to illustrate to pass through if result is failure The analysis of the first order is crossed, the analysis result of supplemental characteristic A, B, C are normal, at this time, it may be necessary to carry out the analysis of the second level.And due to The analysis of the second level is therefore, before the analysis for carrying out the second level, should first to judge the operation of vehicle based on travel condition of vehicle State, in embodiments of the present invention, the state of setting vehicle in the process of running can be divided into: idling mode, Acceleration of starting shape This 4 kinds of state, on-position and operating status.Wherein it is determined that the method for this 4 kinds of states has very much, and the present embodiment provides wherein A kind of relatively simple judgment mode, specific as follows:

It, can be by judging the specific power of vehicle, i.e. automobile engine maximum power and the total matter of automobile for idling mode The ratio between amount determines that the state of vehicle is idling mode when specific power is less than 0；

For Acceleration of starting state, can be determined by judging the acceleration of vehicle when acceleration is greater than starting threshold value The state of vehicle is Acceleration of starting state, in general, in view of factors such as road friction, road grade and windages, actuation threshold Value is set as 0.5m/s2；

For on-position, corresponds to Acceleration of starting state, can also be judged by the acceleration of vehicle, work as acceleration When degree is less than braking threshold, determine that the state of vehicle is on-position, braking threshold is traditionally arranged to be -0.5m/s2；

The state of vehicle is determined as running by operating status when vehicle is not belonging to above-mentioned any state State.

It, can be to parameter if the current state of vehicle is idling or operating status by the analysis to vehicle-state Data A, B, C carry out date comprision, and when current state is starting or on-position, then it can be to supplemental characteristic Carry out data variation analysis.

Wherein, date comprision is to judge that vehicle whether there is failure according to the data value of comparison fault parameter setting, Either compared with the data of the vehicle in normal state.And the data compared can be identical parameters different vehicle Comparison, what is compared in this way can refer to range and will become larger, and corresponding data sample can also increase.This is for relatively shared parameter Data, the value that can refer to can be bigger, such as coolant temperature, speed, acceleration data etc..And for there are mass data samples This comparative analysis, can be by similarity in analysis, and the methods of clustering judges supplemental characteristic and correlation data phase It is more abnormal than whether there is, and then judge vehicle with the presence or absence of failure.

Data variation analysis is to judge that vehicle whether there is failure according to the data variation range of matching fault parameter setting, That is, the variation of state will lead to the variation of data when vehicle is from a kind of state to another status transition, if number According to constant or misfit with state change, just there may be failures for explanation.For example, ignition advance angle is in engine idling operation When, which is usually 15 ° or so, and when engine accelerates or middle and high speed operates, the value of the parameter will increase, if the ginseng Several states with vehicle mismatch, then illustrate that there may be failures for the vehicle.

After the analysis for completing the second level, which will carry out final analysis result to analysis result and export, When all analysis results are normal, illustrate supplemental characteristic A, B, C is without exception, and vehicle-state is good.And when in analysis result There are when the judgement of failure, then the supplemental characteristic for analyzing the failure and possible failure problems are exported together.

The analysis process of above-mentioned analysis model can be a general Analysis Model Framework, when there are new analysis methods When, just the analysis method is added in the frame according to the rank of analysis method, and when the analysis method that supplemental characteristic needs subtracts When few, unnecessary analysis method can also be deleted.Also, it, can be according to reality for the analysis method in the analysis model Different analysis process is arranged in situation, to obtain required analysis result faster.

More than, it is involved for the main flow for planting vehicle fault detection method of inventive embodiments offer, and wherein Vehicle fault detection knowledge base be all described in detail.As the specific device for realizing the above method, the embodiment of the present invention A kind of vehicle fault detection device is additionally provided, the Installation practice is corresponding with preceding method embodiment, is easy to read, this dress It sets embodiment no longer to repeat the detail content in preceding method embodiment one by one, it should be understood that in the present embodiment Device can correspond to the full content realized in preceding method embodiment.The vehicle fault detection device can be set for examining It surveys in the system platform of vehicle trouble, is realized by grid and joined with the real-time data interaction of vehicle, the operation for obtaining vehicle Number data simultaneously test and analyze the vehicle with the presence or absence of failure problems.The specific structure of the vehicle fault detection device as shown in figure 5, Include:

Receiving unit 51, the supplemental characteristic that recording device uploads for receiving data, the data recording equipment are mounted on On vehicle, for obtaining and saving the supplemental characteristic of the vehicle operation in real time；

Analytical unit 52, supplemental characteristic for calling vehicle fault detection knowledge base to obtain the receiving unit 51 into Row analysis, obtains the fault detection address of the vehicle；

Output unit 53, for exporting fault detection address that the analytical unit 52 obtains to the vehicle.

Further, the vehicle fault detection knowledge base called in the analytical unit 52 includes:

Data pattern library, the data pattern library is for saving information of vehicles and corresponding data pattern, wherein the number It is the combination of different parameters data type according to mode；

Data Definition Library, source identification and the analysis parameter number of the Data Definition Library for flag parameters data According to analytical equipment mark；

Model library, the analysis mould that the model library is used to save different parameters data and corresponding analytical equipment is established Type；

Model parameter library, the model parameter library is for saving different vehicle, different parameters data, different analytical equipments institute Corresponding fault parameter.

Further, as shown in fig. 6, the analytical unit 52 includes:

First matching module 521 matches corresponding number in the data pattern library for supplemental characteristic based on the received According to mode；

Module 522 is obtained, the data pattern for obtaining using first matching module 521 is in the Data Definition Library It is middle to obtain analysis method corresponding to each supplemental characteristic；

Second matching module 523, the analysis method for being obtained according to the acquisition module 522 is in the model library With corresponding analysis model；

Determining module 524, for determining corresponding fault parameter in the model parameter library according to the supplemental characteristic；

Analysis module 525, analysis model and the determining module for being obtained in conjunction with second matching module 523 524 fault parameters determined analyze the supplemental characteristic, obtain the fault detection address of the vehicle.

Further, the analysis module 525 is used for, and the intrinsic relationship determined to vehicle control system mechanism is divided Analysis；And/or vehicle analyzes the state of data interval and data variation under different operating conditions.

Further, the intrinsic relationship that the analysis module 525 determines vehicle control system mechanism is analyzed, packet It includes:

Data value field analysis is carried out to supplemental characteristic, is set according to whether the value of the supplemental characteristic falls within the fault parameter Judge vehicle with the presence or absence of failure in fixed data value field；

And/or data relation analysis is carried out to the supplemental characteristic with incidence relation, according to the correlation of the supplemental characteristic Degree judges vehicle with the presence or absence of failure；

And/or data causality analysis is carried out to causal supplemental characteristic, it is inputted according in the supplemental characteristic Judge vehicle with the presence or absence of failure with output matching relationship.

Further, the analysis module 525 to vehicle under different operating conditions to the state of data interval and data variation It is analyzed, comprising:

Data variation analysis is carried out to the supplemental characteristic of reflection vehicle-state, according to the number for matching the fault parameter setting Judge the vehicle with the presence or absence of failure according to variation range；

And/or date comprision is carried out to the supplemental characteristic of reflection vehicle-state, it is set according to the fault parameter is compared Fixed data value judges the vehicle with the presence or absence of failure；

Wherein, the vehicle-state includes: idling mode, operating status, Acceleration of starting state and on-position.

Further, the analysis module 525 is also used to determine the vehicle-state, comprising:

When the specific power of the vehicle is less than 0, determine that the state of the vehicle is idling mode；

When the acceleration of the vehicle is greater than starting threshold value, determine that the state of the vehicle is Acceleration of starting state；

When the acceleration of the vehicle is less than braking threshold, determine that the state of the vehicle is on-position；

When the vehicle-state is not belonging to the idling mode, Acceleration of starting state and on-position, the vehicle is determined State be operating status.

Further, the receiving unit 51 is also used to, and the supplemental characteristic of long-range real-time Transmission is received by network； Alternatively, receiving the supplemental characteristic of long-range periodic transmission by network.

Further, in conjunction with above-mentioned vehicle fault detection device, the embodiment of the invention also provides a kind of vehicle troubles Detection system, as shown in fig. 7, the system is filled by the data recording equipment 71 being installed on vehicle and above-mentioned vehicle fault detection 72 are set to be formed.

The data recording equipment 71 is used to record the supplemental characteristic of the vehicle, the supplemental characteristic that will be recorded in real time It is sent to the vehicle fault detection device 72, wherein

The vehicle fault detection device 72 is used to obtain the supplemental characteristic of the record of mass data recording device 71, passes through vehicle Fault detection knowledge base analyzes the supplemental characteristic, obtains the fault detection address of vehicle, and export fault detection address extremely Corresponding vehicle, the i.e. vehicle of upload parameter data.

In conclusion a kind of vehicle fault detection method, apparatus and system provided by the embodiment of the present invention, it can be by connecing The supplemental characteristic that the upper data recording equipment installed that returns the vehicle to the garage and knock off uploads, it is ensured that obtaining and saving in real time to information of vehicles, then lead to It crosses calling vehicle fault detection knowledge base to analyze these real-time data, quickly obtains the real-time running state of vehicle, The failure existing for first time detection vehicle, and will test the car owner that result feeds back to the vehicle in the form of examining report, Prompt car owner is further detected or is repaired to the failure.Due to realizing the real-time acquisition to vehicle parameter data and dividing Analysis, car owner can get the current health status of vehicle at any time, relative to existing car fault diagnosis mode, the event of vehicle Barrier detection does not need to be carried out by car owner's driving vehicle to specified detection place, but is detected in real time, and its detection is tied What fruit was capable of active feeds back to car owner, to prompt car owner to repair vehicle, so that car owner be made to accomplish to do sth. in advance to vehicle trouble It was found that solving ahead of time, avoids and occur since vehicle tape jam traveling may cause more serious failure, improve making for vehicle With the service life, car owner is also helped to reduce the maintenance expense of vehicle.In addition, the vehicle fault detection in the embodiment of the present invention is known The training sample data of a large amount of analysis model can be obtained, pass through these by the supplemental characteristic of a large amount of vehicles of storage by knowing library Sample data can further increase the accuracy of analysis of analysis model, but also vehicle fault detection knowledge base has intelligence The function of replacement analysis model, meanwhile, the sample based on big data quantity but also vehicle fault detection knowledge base have it is good Newly-increased supplemental characteristic can rapidly be established corresponding analysis model and be used for fault detection analysis by scalability.

In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment Point, reference can be made to the related descriptions of other embodiments.

It is understood that the correlated characteristic in above-mentioned cloud server and device can be referred to mutually.In addition, above-mentioned reality Applying " first " in example, " second " etc. is and not represent the superiority and inferiority of each embodiment for distinguishing each embodiment.

It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description, The specific work process of device and unit, can be no longer superfluous herein with reference to the corresponding process in aforementioned cloud server embodiment It states.

Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein. Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair Bright preferred forms.

In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention Example can be practiced without these specific details.In some instances, well known cloud service is not been shown in detail Device, structure and technology, so as not to obscure the understanding of this specification.

Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects, In Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes In example, figure or descriptions thereof.However, the cloud server of the disclosure should not be construed to reflect an intention that i.e. institute Claimed invention requires features more more than feature expressly recited in each claim.More precisely, As reflected in the following claims, inventive aspect is all spies less than single embodiment disclosed above Sign.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the specific embodiment, wherein each right It is required that itself is all as a separate embodiment of the present invention.

Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed All process or units of what cloud server or equipment are combined.Unless expressly stated otherwise, this specification (including companion With the claims, abstract and drawings) disclosed in each feature can be special by providing the substitution of identical, equivalent, or similar purpose Sign is to replace.

In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed Meaning one of can in any combination mode come using.

Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice Microprocessor or digital signal processor (DSP) realize the denomination of invention according to an embodiment of the present invention (as determined in website The device of Hyperlink rank) in some or all components some or all functions.The present invention is also implemented as being used for Some or all device or device programs of cloud server as described herein are executed (for example, computer program And computer program product).It is such to realize that program of the invention can store on a computer-readable medium, or can have There is the form of one or more signal.Such signal can be downloaded from an internet website to obtain, or in carrier signal Upper offer, or be provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims, Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame Claim.

The embodiment of the invention also discloses:

A1, a kind of vehicle fault detection method, which comprises

The fault detection address is exported to the vehicle.

A2, method according to a1, the vehicle fault detection knowledge base include:

Data Definition Library, source identification and the analysis parameter number of the Data Definition Library for flag parameters data According to analysis method mark；

Model library, the model library is for saving the analysis mould that different parameters data and corresponding analysis method are established Type；

Model parameter library, the model parameter library is for saving different vehicle, different parameters data, different analysis methods institute Corresponding fault parameter.

A3, the method according to A2 call vehicle fault detection knowledge base to analyze the supplemental characteristic, obtain The fault detection address of the vehicle includes:

Supplemental characteristic matches corresponding data pattern in the data pattern library based on the received；

Analysis method corresponding to each supplemental characteristic is obtained in the Data Definition Library using the data pattern；

Corresponding analysis model is matched in the model library according to the analysis method；

Corresponding fault parameter is determined in the model parameter library according to the supplemental characteristic；

The supplemental characteristic is analyzed in conjunction with the analysis model and the fault parameter, obtains the fault detection of the vehicle Report.

A4, according to A3 the method, analysis model described in the combination and the fault parameter analyze the supplemental characteristic, Include:

The intrinsic relationship determined to vehicle control system mechanism is analyzed；And/or

Vehicle analyzes the state of data interval and data variation under different operating conditions.

A5, method according to a4, the intrinsic relationship determined to vehicle control system mechanism are analyzed, are wrapped It includes:

A6, method according to a4, it is described to vehicle under different operating conditions to the state of data interval and data variation It is analyzed, comprising:

A7, the method according to A6, the method further includes:

A8, method according to a1, the supplemental characteristic for receiving data recording equipment upload include:

The supplemental characteristic of long-range real-time Transmission is received by network；

Alternatively, receiving the supplemental characteristic of long-range periodic transmission by network.

B9, a kind of vehicle fault detection device, described device include:

B10, the device according to B9, the vehicle fault detection knowledge base called in the analytical unit include:

B11, device according to b10, the analytical unit include:

First matching module matches corresponding data mould for supplemental characteristic based on the received in the data pattern library Formula；

Module is obtained, the data pattern for being obtained using first matching module is obtained in the Data Definition Library Analysis method corresponding to each supplemental characteristic；

Second matching module, the analysis method for being obtained according to the acquisition module match correspondence in the model library Analysis model；

Determining module, for determining corresponding fault parameter in the model parameter library according to the supplemental characteristic；

Analysis module, the event that analysis model and the determining module for obtaining in conjunction with second matching module determine Hinder supplemental characteristic described in Parameter analysis, obtains the fault detection address of the vehicle.

B12, according to B11 described device, the analysis module is used for, to vehicle control system mechanism determine intrinsic relationship It is analyzed；And/or vehicle analyzes the state of data interval and data variation under different operating conditions.

B13, device according to b12, the intrinsic relationship that the analysis module determines vehicle control system mechanism into Row analysis, comprising:

B14, device according to b12, the analysis module is to vehicle to data interval and data under different operating conditions The state of variation is analyzed, comprising:

B15, device according to b14, the analysis module are also used to determine the vehicle-state, comprising:

B16, the device according to B9, the receiving unit are also used to, and the institute of long-range real-time Transmission is received by network State supplemental characteristic；Alternatively, receiving the supplemental characteristic of long-range periodic transmission by network.

C17, a kind of vehicle fault detection system, the system comprises the data recording equipment being installed on vehicle and such as Vehicle fault detection device described in any one of B9-B16；

Claims

1. a kind of vehicle fault detection method, which is characterized in that the described method includes:

The supplemental characteristic that data recording equipment uploads is received, the data recording equipment is installed on vehicle, for obtaining in real time And save the supplemental characteristic of the vehicle operation；

It calls vehicle fault detection knowledge base to analyze the supplemental characteristic, obtains the fault detection address of the vehicle, The vehicle fault detection knowledge base includes: the data pattern library of increment type, and the data pattern library is each upload parameter number According to vehicle create corresponding data pattern, the data pattern includes the group of vehicle identification information and different parameters data type It closes；Data Definition Library, the Data Definition Library are used for the source identification of flag parameters data and analyze the supplemental characteristic Analysis method mark；Model library, the model library is used to saving different parameters data and corresponding analysis method is established Analysis model；Model parameter library, the model parameter library is for saving different vehicle, different parameters data, different analysis methods Corresponding fault parameter；

Wherein, the calling vehicle fault detection knowledge base analyzes the supplemental characteristic, obtains the failure of the vehicle Examining report specifically includes: supplemental characteristic matches corresponding data pattern in the data pattern library based on the received；It utilizes The data pattern obtains analysis method corresponding to each supplemental characteristic in the Data Definition Library；According to the analysis method Corresponding analysis model is matched in the model library；According to the supplemental characteristic, determination is corresponding in the model parameter library Fault parameter；The supplemental characteristic is analyzed in conjunction with the analysis model and the fault parameter, obtains the failure inspection of the vehicle Observe and predict announcement；

The fault detection address is exported to the vehicle.

2. method according to claim 1, which is characterized in that analysis model described in the combination and the fault parameter are analyzed The supplemental characteristic, comprising:

3. according to the method described in claim 2, it is characterized in that, the intrinsic relationship determined to vehicle control system mechanism It is analyzed, comprising:

Data value field analysis is carried out to supplemental characteristic, whether the fault parameter setting is fallen within according to the value of the supplemental characteristic Judge vehicle with the presence or absence of failure in data value field；

And/or data relation analysis is carried out to the supplemental characteristic with incidence relation, sentenced according to the degree of correlation of the supplemental characteristic Disconnected vehicle whether there is failure；

And/or to causal supplemental characteristic carry out data causality analysis, according in the supplemental characteristic input with it is defeated Haveing matching relationship judges vehicle with the presence or absence of failure.

4. according to the method described in claim 2, it is characterized in that, it is described to vehicle under different operating conditions to data interval sum number It is analyzed according to the state of variation, comprising:

Data variation analysis is carried out to the supplemental characteristic of reflection vehicle-state, is become according to the data for matching the fault parameter setting Changing range judges the vehicle with the presence or absence of failure；

And/or date comprision is carried out to the supplemental characteristic of reflection vehicle-state, according to the comparison fault parameter setting Data value judges the vehicle with the presence or absence of failure；

5. according to the method described in claim 4, it is characterized in that, the method further includes:

When the vehicle-state is not belonging to the idling mode, Acceleration of starting state and on-position, the vehicle is determined State is operating status.

6. the method according to claim 1, wherein the supplemental characteristic packet for receiving data recording equipment and uploading It includes:

7. a kind of vehicle fault detection device, which is characterized in that described device includes:

Receiving unit, the supplemental characteristic that recording device uploads for receiving data, the data recording equipment are installed on vehicle, For obtaining and saving the supplemental characteristic of the vehicle operation in real time；

Analytical unit, the supplemental characteristic for calling vehicle fault detection knowledge base to obtain the receiving unit are analyzed, The fault detection address of the vehicle is obtained, the vehicle fault detection knowledge base includes: the data pattern library of increment type, described Data pattern library is that the vehicle of each upload parameter data creates corresponding data pattern, and the data pattern includes vehicles identifications The combination of information and different parameters data type；Data Definition Library, the Data Definition Library are used for the source of flag parameters data Identify and analyze the analysis method mark of the supplemental characteristic；Model library, the model library is for saving different parameters data And the analysis model that corresponding analysis method is established；Model parameter library, the model parameter library for save different vehicle, Fault parameter corresponding to different parameters data, different analysis methods；

The analytical unit includes: the first matching module, obtains module, the second matching module, determining module and analysis module；

The acquisition module, the data pattern for being obtained using first matching module are obtained in the Data Definition Library Analysis method corresponding to each supplemental characteristic；

The determining module, for determining corresponding fault parameter in the model parameter library according to the supplemental characteristic；

The analysis module, the event that analysis model and the determining module for obtaining in conjunction with second matching module determine Hinder supplemental characteristic described in Parameter analysis, obtains the fault detection address of the vehicle；Output unit, it is single for exporting the analysis The fault detection address that member obtains is to the vehicle.

8. device according to claim 7, which is characterized in that the analysis module is used for, and is determined to vehicle control system mechanism Fixed intrinsic relationship is analyzed；And/or vehicle divides the state of data interval and data variation under different operating conditions Analysis.

9. device according to claim 8, which is characterized in that the analysis module determines vehicle control system mechanism Intrinsic relationship is analyzed, comprising:

10. device according to claim 8, which is characterized in that analysis module logarithm under different operating conditions to vehicle It is analyzed according to the state of section and data variation, comprising:

11. device according to claim 10, which is characterized in that the analysis module is also used to determine the vehicle shape State, comprising:

12. device according to claim 7, which is characterized in that the receiving unit is also used to, and is received by network long-range The supplemental characteristic of real-time Transmission；Alternatively, receiving the supplemental characteristic of long-range periodic transmission by network.

13. a kind of vehicle fault detection system, which is characterized in that the system comprises the data recording equipments being installed on vehicle With the vehicle fault detection device as described in any one of claim 7-12；

Wherein, the data recording equipment is used to record the supplemental characteristic of the vehicle, the supplemental characteristic that will be recorded in real time It is sent to the vehicle fault detection device；

The vehicle fault detection device is used to obtain the supplemental characteristic of the data recording equipment record, is examined by vehicle trouble It surveys knowledge base and analyzes the supplemental characteristic, obtain the fault detection address of the vehicle, and export the fault detection address extremely The vehicle.