CN106055777A - Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles - Google Patents
Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles Download PDFInfo
- Publication number
- CN106055777A CN106055777A CN201610363670.9A CN201610363670A CN106055777A CN 106055777 A CN106055777 A CN 106055777A CN 201610363670 A CN201610363670 A CN 201610363670A CN 106055777 A CN106055777 A CN 106055777A
- Authority
- CN
- China
- Prior art keywords
- collision
- data
- model
- training
- operating mode
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Economics (AREA)
- Marketing (AREA)
- Geometry (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Provided are a remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles. In order to detect parts after vehicles collide to each other, the system comprises a working condition detection subsystem for detecting all working condition information on collided vehicles and learning working condition training data such that a working condition model is generated. The working condition model is set up by the e semi-supervised learning self-training method. The remote damage-assessment system and method have following beneficial effects: through the above technical scheme, part detection of collided vehicles is achieved; a machine learning method is used in the technical field of remote damage-assessment; and as for the machine learning method, determination accuracy is improved during a damage-assessment process.
Description
Technical field
The invention belongs to car damage identification field, relate to one and set up not based on artificial intelligence's semi-supervised learning self-training method
The long-range loss assessment system of part and method is divided with vehicle.
Background technology
During low-speed motion (including low speed links traveling, vehicle parking etc.), take place frequently collision accident for vehicle and lead
The Claims Resolution dispute problem caused, long-range setting loss technology by multi-signal in collection vehicle driving process (as speed, acceleration,
Angular velocity, sound etc.) and analyzed with signal processing and machine learning techniques, to judge whether collision occurs and collision rift
The damage situation of vehicle.
After vehicle crashes, headend equipment is capable of detecting when the generation of collision and intercepts the signal of collision process,
Being sent to high in the clouds by wireless network, remote server extracts the eigenvalue of design in advance from the signal received, and uses machine
Learning algorithm is analyzed, and first judges the accuracy of crash data, then judges collision object and operating mode situation, to determine Collision Number
Create the damage of which kind of grade according to what part of set pair, then go out with reference to amount for which loss settled concurrent according to part injury rating calculation
Deliver to insurance company.The detection for vehicle, operating mode, target, part and region can be related to during this.
Summary of the invention
After solving vehicle collision, for the problem of piece test, the present invention proposes based on artificial intelligence semi-supervised
Study self-training method is set up different automobile types and is divided the long-range loss assessment system of part and method, to realize the inspection of part during setting loss
Survey.
In order to solve above-mentioned technical problem, the technical scheme that the present invention provides is characterized by: including:
Truck type choice subsystem, selects the model data corresponding to vehicle as total data set；
Data classification subsystem, reads CAE emulation data and real vehicle data, and classifies data accordingly；
Collision detection subsystem, it is judged that the most whether vehicle collides；Described collision detection subsystem pair
Collision training data carries out learning thus generates collision model, and described collision model is set up and used semi-supervised learning self-training side
Method；
Operating mode detection subsystem, it is judged that all work informations that collision occurs；Operating mode is instructed by described operating mode detection subsystem
White silk data carry out learning thus generate condition model, and described condition model is set up and used semi-supervised learning self-training method；
Piece test subsystem, it is judged that impairment scale produced by part during vehicle collision；Described piece test subsystem
Learning part training data thus generate part model, described Establishing Model uses semi-supervised learning self-training side
Method.
Beneficial effect: technique scheme, it is possible to achieve for the piece test of vehicle collision, at this of long-range setting loss
Technical field employs the method for machine learning, for machine learning method, during setting loss, it determines accuracy rate on
To promote；The present invention is by selecting vehicle to import the data corresponding to this vehicle, and data classification is then for model training
With the purpose of test and the step that adds；The detection of part is the purpose that the program realizes, and is to obtain through sequence of operations
The result arrived.
Accompanying drawing explanation
Fig. 1 is the structural schematic block diagram of system of the present invention.
Detailed description of the invention
In order to the present invention being made apparent explanation, below the technical term that the present invention relates to is made definitions:
Operating mode: all collision informations such as collision angle, direction, target, region；
Vehicle: automobile model；
Target: collision target；
Region: position of collision；
Part: auto parts；
Operating mode detects: detect all collision informations such as this car collision angle, direction, target, region；
Vehicle detects: the automobile model that detection collides with this car；
Target detection: detect this car collision target；
Region detection: detect this car position of collision；
Piece test: detect this car auto parts.
Embodiment 1:
One is set up different automobile types based on artificial intelligence's semi-supervised learning self-training method and is divided part long-range loss assessment system, bag
Include:
Truck type choice subsystem, selects the model data corresponding to vehicle as total data set；
Data classification subsystem, reads CAE emulation data and real vehicle data, and classifies data accordingly；
Collision detection subsystem, it is judged that the most whether vehicle collides；Described collision detection subsystem pair
Collision training data carries out learning thus generates collision model, and described collision model is set up and used semi-supervised learning self-training side
Method；
Operating mode detection subsystem, it is judged that all work informations that collision occurs；Operating mode is instructed by described operating mode detection subsystem
White silk data carry out learning thus generate condition model, and described condition model is set up and used semi-supervised learning self-training method；
Piece test subsystem, it is judged that impairment scale produced by part during vehicle collision；Described piece test subsystem
Learning part training data thus generate part model, described Establishing Model uses semi-supervised learning self-training side
Method.
Described collision detection subsystem includes, collision training module, crash tests module, collision authentication module, described in touch
Hitting training module and generate collision model for learning collision training data, crash tests module is for surveying collision
Examination data bring the result detecting collision model in collision model into, and collision authentication module uses true sport car data verification collision mould
The reliability of type and accuracy rate；
Described operating mode detection subsystem includes, operating mode training module, working condition measurement module, operating mode authentication module, described work
Condition training module generates condition model for learning operating mode training data, and described working condition measurement module is for by work
Condition test data bring the result detecting condition model in model into, and operating mode authentication module uses true sport car data verification operating mode mould
The reliability of type and accuracy rate；
Described piece test subsystem includes, part training module, part testing module, part authentication module, described zero
Part training module generates part model for carrying out learning by part training data, and part testing module is for surveying part
Examination data bring the result detecting part model in model into, and part authentication module uses true sport car data verification part model
Reliability and accuracy rate.
As a kind of embodiment, the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample
For to mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out damage etc.
The sample that level or operating mode numbering or collision are numbered；
Perform following algorithm
Repeat:
1. generate classification policy F with Labeled sample；
2., with F classification Unlabeled sample, calculate error；
3. choose subset u that the error of U is little, the subset that error is little here, can see during being embodied as, permissible
Choose according to the concrete accuracy requirement in implementation process is actual, add label L=L+u；
Repeat the above steps, until U is empty set, U is exactly Unlabeld, and L is exactly Labeld.
In algorithm above, Labeled sample, by constantly in Unlabeled sample, selects the sample that performance is good
Adding, and constantly update the algorithm F of subset, finally obtain the F of a most effective fruit, the judgement rate of this F is the highest and stable.
As another kind of embodiment, the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample
For to mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out damage etc.
The sample that level or operating mode numbering or collision are numbered；Note d (x1, x2) is the Euclidean distance of two samples, performs following algorithm:
Repeat:
1. generate classification policy F with Labeled；
2. selecting x=argmind (x, x0). wherein x ∈ U, minx0 ∈ Labeled. namely selects from marker samples
Near unmarked sample；
3. with F to fixed classification F (x) of x.
4. (x, F (x)) is added in Labeled
Repeat the above steps, until U is empty set.
Embodiment 2:
One is set up different automobile types based on artificial intelligence's semi-supervised learning self-training method and is divided part long-range damage identification method, bag
Include following steps:
Step one. select the model data corresponding to vehicle as total data set；
Step 2. read CAE emulation data and real vehicle data, and accordingly data are classified；
Step 3. judge the most whether vehicle collides；Described collision detection subsystem is to collision training
Data carry out learning thus generate collision model, and described collision model is set up and used semi-supervised learning self-training method；
Step 4. judge all work informations that collision occurs；Operating mode training data is entered by described operating mode detection subsystem
Row learns thus generates condition model, and described condition model is set up and used semi-supervised learning self-training method；
Step 5. judge impairment scale produced by part during vehicle collision；Part is instructed by described piece test subsystem
White silk data carry out learning thus generate part model, and described Establishing Model uses semi-supervised learning self-training method.
Comprise the concrete steps that:
Step 3 includes:
S3.1. use collision detection subsystem that CAE collision simulation data are processed, then classify to produce collision to it
Training data and crash tests data；
S3.2. in collision training module, collision training data learnt and produces collision model, carrying out simulated crash
The effect of training data；
S3.3. crash tests data are used to carry out the result of test collisions model in crash tests module；
S3.4. use true sport car data as collision checking data and to bring collision authentication module into, verify collision mould
The accuracy of type；
Step 4 includes:
S4.1. CAE operating mode emulation data are processed by applying working condition detection subsystem, then it is carried out classification generation operating mode instruction
Practice data and working condition measurement data；
S4.2. in operating mode training module, operating mode training data learnt and produce condition model, carrying out simulated condition
The effect of training data；
S4.3. in working condition measurement module, applying working condition test data carry out the result of measurement condition model；
S4.4. use true sport car data as operating mode checking data and to bring operating mode authentication module into, verify operating mode mould
The accuracy of type；
Step 5 includes:
S1. use piece test subsystem that CAE part emulation data are processed, then classify to produce part instruction to it
Practice data and part testing data；
S2. in part training module, part training data learnt and produce part model, simulating part instruction
Practice the effect of data；
S3. part testing data are used to carry out the result of test part model in part testing module；
S4. use true sport car data as part checking data and to bring part authentication module into, verify part model
Accuracy.
In a lot of practical problems, the markd data of the most a small amount of band, because the cost being marked data has
Time the highest, such as in biology, structural analysis or the Function Identification to certain protein, biologist may be taken very
Work for many years, and substantial amounts of unlabelled data are readily available.
Semi-supervised learning has two sample sets, and one has labelling, and one does not has labelling. it is denoted as respectively
Lable={ (xi, yi) }, Unlabled={ (xi) }. and in quantity, L < < U.
1.: be used alone marker samples, we can generate Supervised classification algorithm
2.: be used alone unmarked sample, we can generate Unsupervised clustering algorithm
3.: both use, it is intended that in 1, add unmarked sample, strengthen the effect of Supervised classification；Equally
, it is intended that in 2, there was added marker samples, strengthen the effect of Unsupervised clustering.
It is said that in general, semi-supervised learning lays particular emphasis on and adds unmarked sample in the sorting algorithm have supervision and realize half prison
Superintend and direct classification. in 1, namely add unmarked sample, strengthen classifying quality.
As a kind of embodiment, the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample
For to mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out damage etc.
The sample that level or operating mode numbering or collision are numbered；
Perform following algorithm
Repeat:
1. generate classification policy F with Labeled sample；
2., with F classification Unlabeled sample, calculate error；
3. choose subset u that the error of U is little, the subset that error is little here, can see during being embodied as, permissible
Choose according to the concrete accuracy requirement in implementation process is actual, add label L=L+u；
Repeat the above steps, until U is empty set, U is exactly Unlabeld, and L is exactly Labeld.
In algorithm above, Labeled sample, by constantly in Unlabeled sample, selects the sample that performance is good
Adding, and constantly update the algorithm F of subset, finally obtain the F of a most effective fruit, the judgement rate of this F is the highest and stable.
As another kind of embodiment, the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample
For to mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out damage etc.
The sample that level or operating mode numbering or collision are numbered；Note d (x1, x2) is the Euclidean distance of two samples, performs following algorithm:
Repeat:
1. generate classification policy F with Labeled；
2. selecting x=argmind (x, x0). wherein x ∈ U, minx0 ∈ Labeled. namely selects from marker samples
Near unmarked sample；
3. with F to fixed classification F (x) of x.
4. (x, F (x)) is added in Labeled
Repeat the above steps, until U is empty set.
Embodiment 3:There is the technical scheme identical with embodiment 1 or 2, more specifically:
Conceptual data collection in such scheme: be entirely CAE emulation data and sport car data；Be divided into three parts as follows
1. training dataset: be used to training pattern or determine model parameter (CAE emulation data and sport car data).
2. checking data set: be used to do Model Selection (modelselection), i.e. does the final optimization pass and really of model
Fixed (CAE emulation data and sport car data).
3. test data set: the Generalization Ability of the model then trained for purely test.(CAE emulates data
With sport car data).
In the present embodiment also to the filtering related to during setting loss, weighting choose, feature extraction, normalization, eigentransformation
Have been described.
1. wave filter technology: the filtering method realized includes FIR filtering, FIR Chebyshev approximation, Chebyshev's filter
Ripple, butterworth filter etc., the Filtering.m file in mastery routine realizes.Each wave filter is common wave filter,
Matlab has corresponding function to realize, and specific algorithm refers to signal processing professional book.Provide the interior of FIR filter herein
Hold and the introduction of flow process.
Limited impulse response digital filter (FIR, FiniteImpulseResponse) is the system of a kind of full zero point,
The design of FIR filter is ensureing that amplitude characteristic meets the colleague that technology requires, it is easy to accomplish strict linear phase characteristic,
So being the outstanding advantages of FIR filter according to there being stable and linear phase characteristic.Chebyshev approximation is that the ripples such as one are forced
Nearly method, it is possible to make error frequency band be uniformly distributed, to same technical specification, this filter order sending out needs shoulder to shoulder is low, right
In the wave filter of same exponent number, this approximatioss maximum error is minimum, and the key step of its design is as follows:
Step 1: the setting of filter parameter
The parameter of wave filter includes: cut-off frequecy of passband, stopband cut-off frequency, passband maximum attenuation and stopband minimum decline
Subtract；
Step 2: be arranged on passband and the amplitude-frequency response of stopband coideal
Step 3: be scheduled on the weighting on cut-off frequecy of passband and stopband cut-off frequency point
Step 4: utilize Equation for Calculating Chebyshev approximation filter coefficient
Step 5: preserve coefficient
Step 6: extraction coefficient carries out data filtering
Wherein: the guarantee signal that is disposed to of filter parameter does not haves distortion now during processing
As, the cut-off frequency of filtered signal and sample frequency need to meet Nyquist's theorem, the most after the filtering signal
Highest frequency not can exceed that the 1/2 of original signal sample frequency, otherwise arises that Lou frequency phenomenon.According to the signal in current project
The sample frequency of collection plate is mainly 50Hz and 1KHz, according to formula F as a example by 50HzCut-off< 50/2, therefore select filter cutoff
Frequency is below 25.
2. Feature Extraction Technology: feature extraction is carried out on collision alarm.Judge that the feature that collision uses includes window
Acceleration in difference between acceleration maxima and minima, window in the maximum of acceleration absolute value, window in mouthful
In average energy (in window the quadratic sum of acceleration a little divided by counting), window, the absolute value of each point slope is average
Value.
Judge the feature that part category is used include the average energy between speed, acceleration peak to peak,
Amplitude between maximum and minima/width between the two, acceleration maximum, acceleration minima, maximum place
The width of half-wave, minima place half-wave width, maximum and minima between difference, between peak to peak
Span, the meansigma methods of absolute value of each point slope, signal carry out each of the signal after Fourier transform in 0～38 frequency ranges
The amplitude of frequency component.
3. normalization technology: that causes classification task to eliminate the dimension between feature or order of magnitude difference is unfavorable
Impact, needs to be normalized characteristic so that have comparability between each eigenvalue, it is to avoid the spy that numerical value is bigger
Levy and flood the feature that numerical value is less.Original characteristic is after normalized, and each feature is in identical codomain scope.
Owing to the performance of Z-Score is more preferable, use Z-Score as method for normalizing.
4. feature transform technique: in the case of feature is more, for the dependency eliminated between feature and reduce redundancy
Feature, needs to convert feature, carrys out reflected sample information with the fewest new feature.In the less situation of experiment sample
Under (practical situation of this project) reduce too much intrinsic dimensionality, moreover it is possible to avoid sending out of over-fitting or poor fitting to a certain extent
Raw.According to actual needs, the eigentransformation the most realized is PCA.Being found through experiments, PCA divides for improving this project
Class performance there is no help, has declined, and this is that the feature owing to being used at present is less, does not has redundancy feature, therefore
PCA wouldn't be used, but be as being stepped up of subsequent characteristics, however not excluded that use the probability of PCA later.
In accompanying drawing 1, record: the Truck type choice subsystem that Truck type choice is in the present invention；Data categorization module is
Data classification subsystem in the present invention；The collision detection subsystem that collision judgment module is in the present invention；Operating mode detection mould
Block is the operating mode detection subsystem of the present invention；Vehicle detection module is the vehicle detection subsystem of the present invention；Piece test
Module i.e. piece test subsystem；Module of target detection is the target detection subsystem of the present invention, and region detection module is
The region detection subsystem of the present invention.
The above, only the invention preferably detailed description of the invention, but the protection domain of the invention is not
Being confined to this, any those familiar with the art is in the technical scope that the invention discloses, according to the present invention
The technical scheme created and inventive concept thereof in addition equivalent or change, all should contain the invention protection domain it
In.
Claims (8)
1. setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method divides part a long-range loss assessment system, and it is special
Levy and be, including:
Truck type choice subsystem, selects the model data corresponding to vehicle as total data set；
Data classification subsystem, reads CAE emulation data and real vehicle data, and classifies data accordingly；
Collision detection subsystem, it is judged that the most whether vehicle collides；Described collision detection subsystem is to collision
Training data carries out learning thus generates collision model, and described collision model is set up and used semi-supervised learning self-training method；
Operating mode detection subsystem, it is judged that all work informations that collision occurs；Operating mode is trained number by described operating mode detection subsystem
Generating condition model according to carrying out learning, described condition model is set up and is used semi-supervised learning self-training method；
Piece test subsystem, it is judged that impairment scale produced by part during vehicle collision；Described piece test subsystem is to zero
Part training data carries out learning thus generates part model, and described Establishing Model uses semi-supervised learning self-training method.
2. setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method as claimed in claim 1 divides part long-range
Loss assessment system, it is characterised in that
Described collision detection subsystem includes, collision training module, crash tests module, collision authentication module, described collision is instructed
Practicing module and generate collision model for learning collision training data, crash tests module is for by crash tests number
According to bringing the result detecting collision model in collision model into, collision authentication module uses true sport car data verification collision model
Reliability and accuracy rate；
Described operating mode detection subsystem includes, operating mode training module, working condition measurement module, operating mode authentication module, and described operating mode is instructed
Practicing module and generate condition model for learning operating mode training data, described working condition measurement module is for surveying operating mode
Examination data bring the result detecting condition model in model into, and operating mode authentication module uses true sport car data verification condition model
Reliability and accuracy rate；
Described piece test subsystem includes, part training module, part testing module, part authentication module, and described part is instructed
Practicing module and generate part model for carrying out learning by part training data, part testing module is for by part testing number
According to bringing the result detecting part model in model into, part authentication module uses the reliable of true sport car data verification part model
Property and accuracy rate.
3. setting up different automobile types such as claim 1 or 2 based on artificial intelligence's semi-supervised learning self-training method divides part remotely fixed
Damage system, it is characterised in that the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample be with
Mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out impairment scale or
Operating mode numbering or the sample of collision numbering；
Perform following algorithm
S1.1. classification policy F is generated with Labeled sample；
S1.2. with F classification Unlabeled sample, error is calculated；
S1.3. choose subset u that the error in U is little, add label L=L+u；
Repeat the above steps, until U is empty set, U is exactly Unlabeld, and L is exactly Labeld.
4. setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method as claimed in claim 3 divides part long-range
Damage identification method, it is characterised in that the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample be with
Mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out impairment scale or
Operating mode numbering or the sample of collision numbering；Note d (x1, x2) is the Euclidean distance of two samples, performs following algorithm:
S1.1. classification policy F is generated with Labeled；
S1.2. x=argmind (x, x0) is selected. wherein x ∈ U, minx0 ∈ Labeled. namely selects from marker samples
Near unmarked sample；
S1.3. with F to fixed classification F (x) of x.
S1.4. (x, F (x)) is added in Labeled
Repeat the above steps, until U is empty set.
5. setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method divides part a long-range damage identification method, and it is special
Levy and be, comprise the following steps:
Step one. select the model data corresponding to vehicle as total data set；
Step 2. read CAE emulation data and real vehicle data, and accordingly data are classified；
Step 3. judge the most whether vehicle collides；Collision training data is learnt thus generates and touch
Hitting model, described collision model is set up and is used semi-supervised learning self-training method；
Step 4. judge all work informations that collision occurs；Operating mode training data is learnt thus generates condition model,
Described condition model is set up and is used semi-supervised learning self-training method；
Step 5. judge impairment scale produced by part during vehicle collision；Part training data is learnt thus generates
Part model, described Establishing Model uses semi-supervised learning self-training method.
6. require setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method and divide part remotely fixed as described in 5 such as profit
Damage method, it is characterised in that comprise the concrete steps that:
Step 3 includes:
S3.1. use collision detection subsystem that CAE collision simulation data are processed, then classify to produce collision training to it
Data and crash tests data；
S3.2. in collision training module, collision training data learnt and produces collision model, carrying out simulated crash training
The effect of data；
S3.3. crash tests data are used to carry out the result of test collisions model in crash tests module；
S3.4. use true sport car data as collision checking data and to bring collision authentication module into, verify collision model
Accuracy；
Step 4 includes:
S4.1. CAE operating mode emulation data are processed by applying working condition detection subsystem, then it is carried out classification generation operating mode training number
According to working condition measurement data；
S4.2. in operating mode training module, operating mode training data learnt and produce condition model, carrying out simulated condition training
The effect of data；
S4.3. in working condition measurement module, applying working condition test data carry out the result of measurement condition model；
S4.4. use true sport car data as operating mode checking data and to bring operating mode authentication module into, verify condition model
Accuracy；
Step 5 includes:
S1. use piece test subsystem that CAE part emulation data are processed, then classify to produce part training number to it
According to part testing data；
S2. in part training module, part training data learnt and produce part model, simulating part training number
According to effect；
S3. part testing data are used to carry out the result of test part model in part testing module；
S4. use true sport car data as part checking data and to bring part authentication module into, verify the standard of part model
Really property.
7. setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method and divide part as described in claim 5 or 6
Remotely damage identification method, it is characterised in that the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample be with
Mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out impairment scale or
Operating mode numbering or the sample of collision numbering；
Perform following algorithm
S1.1. classification policy F is generated with Labeled sample；
S1.2. with F classification Unlabeled sample, error is calculated；
S1.3. choose subset u that the error in U is little, add label L=L+u；
Repeat the above steps, until U is empty set, U is exactly Unlabeld, and L is exactly Labeld.
8. setting up different automobile types based on artificial intelligence's semi-supervised learning self-training method and divide part as described in claim 5 or 6
Remotely damage identification method, it is characterised in that the step of described semi-supervised learning self-training method is:
S1. two sample set: Labeld={ (xi, yi) are set }；Unlabeld={xj}, wherein Labeled sample be with
Mark impairment scale or operating mode numbering or the sample of collision numbering；And Unlabeled sample be unmarked go out impairment scale or
Operating mode numbering or the sample of collision numbering；Note d (x1, x2) is the Euclidean distance of two samples, performs following algorithm:
S1.1. classification policy F is generated with Labeled；
S1.2. x=argmind (x, x0) is selected. wherein x ∈ U, minx0 ∈ Labeled. namely selects from marker samples
Near unmarked sample；
S1.3. with F to fixed classification F (x) of x.
S1.4. (x, F (x)) is added in Labeled
Repeat the above steps, until U is empty set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610363670.9A CN106055777A (en) | 2016-05-27 | 2016-05-27 | Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610363670.9A CN106055777A (en) | 2016-05-27 | 2016-05-27 | Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106055777A true CN106055777A (en) | 2016-10-26 |
Family
ID=57175097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610363670.9A Pending CN106055777A (en) | 2016-05-27 | 2016-05-27 | Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106055777A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418200A (en) * | 2021-12-31 | 2022-04-29 | 清华大学 | Vehicle type specific passenger damage prediction model training method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104932359A (en) * | 2015-05-29 | 2015-09-23 | 大连楼兰科技股份有限公司 | Vehicle remote unattended loss assessment system based on CAE technology and loss assessment method thereof |
| CN105488258A (en) * | 2015-11-24 | 2016-04-13 | 大连楼兰科技股份有限公司 | CAE technology based automated vehicle collision damage assessment method |
| CN105512359A (en) * | 2015-11-24 | 2016-04-20 | 大连楼兰科技股份有限公司 | Method and system for processing CAE simulation results |
| CN105512358A (en) * | 2015-11-24 | 2016-04-20 | 大连楼兰科技股份有限公司 | Loss assessment method of vehicle collision accidents based on CAE simulation technology |
-
2016
- 2016-05-27 CN CN201610363670.9A patent/CN106055777A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104932359A (en) * | 2015-05-29 | 2015-09-23 | 大连楼兰科技股份有限公司 | Vehicle remote unattended loss assessment system based on CAE technology and loss assessment method thereof |
| CN105488258A (en) * | 2015-11-24 | 2016-04-13 | 大连楼兰科技股份有限公司 | CAE technology based automated vehicle collision damage assessment method |
| CN105512359A (en) * | 2015-11-24 | 2016-04-20 | 大连楼兰科技股份有限公司 | Method and system for processing CAE simulation results |
| CN105512358A (en) * | 2015-11-24 | 2016-04-20 | 大连楼兰科技股份有限公司 | Loss assessment method of vehicle collision accidents based on CAE simulation technology |
Non-Patent Citations (3)
| Title |
|---|
| CLASS XMAN: "半监督学习（一）", 《HTTPS://WWW.CNBLOGS.COM/JAMES1207/P/3400126.HTML》 * |
| YHDZW: "半监督学习（一）", 《HTTPS://BLOG.CSDN.NET/YHDZW/ARTICLE/DETAILS/22733371》 * |
| 数据娃掘: "语义分析若干知识", 《HTTPS://BLOG.CSDN.NET/JDBC/ARTICLE/DETAILS/50579751》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418200A (en) * | 2021-12-31 | 2022-04-29 | 清华大学 | Vehicle type specific passenger damage prediction model training method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110567720B (en) | Method for diagnosing depth confrontation of fault of fan bearing under unbalanced small sample scene | |
| CN105320966A (en) | Vehicle driving state recognition method and apparatus | |
| CN106056147A (en) | System and method for establishing target division remote damage assessment of different vehicle types based artificial intelligence radial basis function neural network method | |
| CN102147866A (en) | Target identification method based on training Adaboost and support vector machine | |
| CN104766042A (en) | Method and apparatus for and recognizing traffic sign board | |
| CN107830996B (en) | Fault diagnosis method for aircraft control surface system | |
| CN104850865A (en) | Real-time compression tracking method of multi-characteristic transfer learning | |
| CN105046259B (en) | Coronal mass ejection detection method based on multi-feature fusion | |
| CN106055776A (en) | Regional and remote damage-assessment system and method established based on artificial-intelligence supervised learning linear regression method for different types of vehicles | |
| CN106056150A (en) | System and method for establishing part division remote damage assessment of different vehicle types based on artificial intelligence random forest method | |
| CN106067035A (en) | The long-range loss assessment system of different automobile types partial objectives for and method is set up based on artificial intelligence's supervised learning traditional decision-tree | |
| Sabour et al. | Deepflow: Abnormal traffic flow detection using siamese networks | |
| CN106055779A (en) | Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning logistic-regression method for different types of vehicles | |
| CN105404858A (en) | Vehicle type recognition method based on deep Fisher network | |
| CN104964736A (en) | Optical fiber invasion vibration source identification method based on time-frequency characteristic EM classification | |
| CN106067036A (en) | Set up different automobile types based on artificial intelligence's unsupervised learning K means method and divide the long-range loss assessment system of part and method | |
| CN106055891A (en) | Remote damage-assessment system and method established based on artificial intelligence Softmax regression method for different types of vehicles | |
| CN106055777A (en) | Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning self-training method for parts in different types of vehicles | |
| CN106056453A (en) | System and method for establishing working condition division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning clustering hypothesis method | |
| CN106056140A (en) | System and method for establishing working condition division remote damage assessment of different vehicle types based on artificial intelligence supervised learning linear regression method | |
| CN106067038A (en) | Point long-range loss assessment system of vehicle and a method is set up based on artificial intelligence's supervised learning Nae Bayesianmethod | |
| CN106056152A (en) | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method | |
| Han et al. | Generative adversarial network-based fault diagnosis model for railway point machine in sustainable railway transportation | |
| CN106096624A (en) | The long-range loss assessment system of different automobile types divided working status and method is set up based on artificial intelligence | |
| CN117237911A (en) | Image-based dynamic obstacle rapid detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161026 |
|
| RJ01 | Rejection of invention patent application after publication |