CN106056152A - System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method - Google Patents
System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method Download PDFInfo
- Publication number
- CN106056152A CN106056152A CN201610365676.XA CN201610365676A CN106056152A CN 106056152 A CN106056152 A CN 106056152A CN 201610365676 A CN201610365676 A CN 201610365676A CN 106056152 A CN106056152 A CN 106056152A
- Authority
- CN
- China
- Prior art keywords
- data
- collision
- module
- model
- bunch
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a system and method for establishing target division remote damage assessment of different vehicle types based on an artificial intelligence semi-supervised learning BIRCH method and belongs to the vehicle damage assessment field. The objective of the invention is to solve problems in target detection of collision vehicles after a collision. According to the technical schemes of the invention, a target detection subsystem is adopted to judge collision objects in the vehicle collision; and the target type detection subsystem learns target training data so as to generate a target model, wherein the target model is built by adopting the intelligent semi-supervised learning BIRCH algorithm. With the system and method provided by the technical schemes of the invention adopted, target detection in the vehicle collision can be realized; and a machine learning method is used in the remote damage assessment technical field, so that the accuracy of judgment in a damage assessment process can be improved.
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 BIRCH method
With the long-range loss assessment system of vehicle partial objectives for and method.
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, problem collision rift being collided to the target detection of vehicle, the present invention proposes
One sets up the long-range loss assessment system of different automobile types partial objectives for and method, with reality based on artificial intelligence's semi-supervised learning BIRCH method
Target detection during existing setting loss and judgement.
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 intelligence semi-supervised learning BIRCH
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 intelligence semi-supervised learning BIRCH method；
Target detection subsystem, judges that target is trained number by the object that vehicle collides, described target detection subsystem
Generating object module according to carrying out learning, described object module is set up and is used intelligence semi-supervised learning BIRCH method.
Beneficial effect: technique scheme, it is possible to achieve for the target detection 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 target 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 sets up the long-range loss assessment system of different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method, 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 intelligence semi-supervised learning BIRCH
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 intelligence semi-supervised learning BIRCH method；
Target detection subsystem, judges that target is trained number by the object that vehicle collides, described target detection subsystem
Generating object module according to carrying out learning, described object module is set up and is used intelligence semi-supervised learning BIRCH 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 target detection subsystem includes, target training module, target detection module, target verification module, described mesh
Mark training module generates object module for carrying out learning by target training data, and target detection module is for surveying target
Examination data bring the result detecting object module in model into, and target verification module uses true sport car data verification object module
Reliability and accuracy rate.
Described intelligence semi-supervised learning BIRCH method, BIRCH is a kind of clustering algorithm, and the feature of its maximum is to utilize
Limited memory source completes the high-quality cluster to large data sets, simultaneously by single pass data set energy minimization I/O
Cost.
First what is explained is cluster, and from the viewpoint of statistics, the most given one of cluster comprises N number of data
The data set of point and distance metric function F (function of average distance between each two data point in such as calculating bunch),
Require to be divided into this data set K bunch (or do not provide quantity K, algorithm automatically find optimal number of clusters amount), finally
Result be to find a kind of optimum division for data set so that the value of distance metric function F is minimum.From the angle of machine learning
From the point of view of Du, cluster is a kind of non-supervisory learning algorithm, by data set is polymerized to n bunch so that in bunch, the spacing of point is
Littleization, the distance between bunch maximizes.
BIRCH algorithm characteristic:
(1) BIRCH attempt to can resource to generate best cluster result, given limited main memory, a weight
The consideration wanted is to minimize the I/O time.
(2) BIRCH have employed a kind of multi-stage cluster-ing technology: the single side scan of data set creates basic gathering
Class, one or the extra scanning of multipass can improve clustering result quality further.
(3) BIRCH is the clustering method of a kind of increment, because the decision-making of the cluster of each data point is all based on by it
The most processed current data point rather than data point based on the overall situation.
(4) if bunch not being spherical, BIRCH can not well work, because the concept that it has been used radius or diameter is come
Control the border of cluster.
Its implementation is: a given data set comprising N number of data point and a distance metric function F, by described
Data set is divided into K bunch, obtains the optimum division for data set so that the value of distance metric function F is minimum.
In BIRCH algorithm, CF is the core of BIRCH incremental clustering algorithm, obtains node and be all made up of CF in CF tree, one
CF is a tlv triple, all information that this tlv triple just represents bunch.The data point of given N number of d dimension x1, x2 ....,
Xn}, CF are defined as follows:
CF=(N, LS, SS)
Wherein, N is the number of subclass interior joint, LS be the linear of N number of node and, SS is the quadratic sum of N number of node.
CF has individual characteristic, i.e. can sue for peace, be described as follows: CF1=(n1, LS1, SS1), CF2=(n2, LS2,
SS2), then CF1+CF2=(n1+n2, LS1+LS2, SS1+SS2).
Such as:
Assume that bunch C1 has three data points: (2,3), (4,5), (5,6), then CF1={3, (2+4+5,3+5+6), (2^2
+ 4^2+5^2,3^2+5^2+6^2) }=3, (11,14), (45,70) }, same, the CF2={4 of bunch C2, (40,42),
(100,101) }, then, cluster feature CF3 of bunch C3 being merged by bunch C1 and bunch C2 and being come is calculated as follows:
CF3={3+4, (11+40,14+42), (45+100,70+101) }=7, (51,56), (145,171) }
Additionally introducing two concepts: bunch barycenter and bunch radius.If one bunch comprises n data point: Xi},
I=1,2,3...n., then barycenter C and radius R computing formula are as follows:
C=(X1+X2+...+Xn)/n, (X1+X2+...+Xn is that vector adds here)
R=(| X1-C | ^2+ | X2-C | ^2+...+ | Xn-C | ^2)/n
Wherein, bunch radius arrives a little the average distance of bunch barycenter in representing bunch.In CF storage be bunch in all data
The statistics of the characteristic of point and, so when we add certain bunch a data point when, then this data point detailed
Feature, such as property value, just lost, and due to this feature, data set can be pressed by BIRCH cluster to a great extent
Contracting.
Embodiment 2:
One sets up the long-range damage identification method of different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH 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 intelligence semi-supervised learning BIRCH 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 intelligence semi-supervised learning BIRCH method；
Step 5. judging the object that vehicle collides, described target detection subsystem is to target training data
Practising thus generate object module, described object module is set up and is used intelligence semi-supervised learning BIRCH 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 target detection subsystem processes CAE damage simulation data process, then to its carry out classification produce damage sentence
Disconnected training data and damage judge test data；
S2. in target training module, damage training of judgement data learnt and produce damage model, simulating mesh
The effect of mark training data；
S3. damage is used to judge that test data carry out the result of test target judgment models in target detection model；
S4. use true sport car data as target verification data and to bring target verification module into, verify object judgement
The accuracy of model.
Described intelligence semi-supervised learning BIRCH method, BIRCH is a kind of clustering algorithm, and the feature of its maximum is to utilize
Limited memory source completes the high-quality cluster to large data sets, simultaneously by single pass data set energy minimization I/O
Cost.
First what is explained is cluster, and from the viewpoint of statistics, the most given one of cluster comprises N number of data
The data set of point and distance metric function F (function of average distance between each two data point in such as calculating bunch),
Require to be divided into this data set K bunch (or do not provide quantity K, algorithm automatically find optimal number of clusters amount), finally
Result be to find a kind of optimum division for data set so that the value of distance metric function F is minimum.From the angle of machine learning
From the point of view of Du, cluster is a kind of non-supervisory learning algorithm, by data set is polymerized to n bunch so that in bunch, the spacing of point is
Littleization, the distance between bunch maximizes.
BIRCH algorithm characteristic:
(1) BIRCH attempt to can resource to generate best cluster result, given limited main memory, a weight
The consideration wanted is to minimize the I/O time.
(2) BIRCH have employed a kind of multi-stage cluster-ing technology: the single side scan of data set creates basic gathering
Class, one or the extra scanning of multipass can improve clustering result quality further.
(3) BIRCH is the clustering method of a kind of increment, because the decision-making of the cluster of each data point is all based on by it
The most processed current data point rather than data point based on the overall situation.
(4) if bunch not being spherical, BIRCH can not well work, because the concept that it has been used radius or diameter is come
Control the border of cluster.
Its implementation is: a given data set comprising N number of data point and a distance metric function F, by described
Data set is divided into K bunch, obtains the optimum division for data set so that the value of distance metric function F is minimum.
In BIRCH algorithm, the node in CF tree is all made up of CF, and a CF is a tlv triple, and this tlv triple is just
The all information represented bunch, the data point of given N number of d dimension x1, x2 ...., xn}, CF are defined as follows:
CF=(N, LS, SS)
Wherein, N is the number of subclass interior joint, LS be the linear of N number of node and, SS is the quadratic sum of N number of node；
Bunch barycenter and bunch radius.If one bunch comprises n data point: { Xi}, i=1,2,3...n., then matter
Heart C and radius R computing formula are as follows:
C=(X1+X2+...+Xn)/n,
R=(| X1-C | ^2+ | X2-C | ^2+...+ | Xn-C | ^2)/n
Wherein, bunch radius arrives a little the average distance of bunch barycenter in representing bunch, in CF storage be bunch in all data
The statistics of the characteristic of point and, the when that a data point being added certain bunch, the detailed features of this data point loss, BIRCH
Data set is compressed by cluster with this.
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 (model selection), i.e. do model final optimization pass and
(CAE emulation data and the sport car data) determined.
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, Finite Impulse Response) be a kind of full zero point be
System, the design of FIR filter is ensureing that amplitude characteristic meets the colleague that technology requires, it is easy to accomplish that strict linear phase is special
Property, so being the outstanding advantages of FIR filter according to there being stable and linear phase characteristic.Chebyshev approximation is the ripples such as one
Approximatioss, 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,
For 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 the long-range loss assessment system of different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method, 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 intelligence semi-supervised learning BIRCH 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 intelligence semi-supervised learning BIRCH method；
Target detection subsystem, judges that target training data is entered by the object that vehicle collides, described target detection subsystem
Row learns thus generates object module, and described object module is set up and used intelligence semi-supervised learning BIRCH method.
2. set up different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method as claimed in claim 1 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 target detection subsystem includes, target training module, target detection module, target verification module, and described target is instructed
Practicing module and generate object module for carrying out learning by target training data, target detection module is for by target detection number
According to bringing the result detecting object module in model into, target verification module uses the reliable of true sport car data verification object module
Property and accuracy rate.
3. set up the long-range setting loss of different automobile types partial objectives for such as claim 1 or 2 based on artificial intelligence's semi-supervised learning BIRCH method
System, it is characterised in that described intelligence semi-supervised learning BIRCH method, a given data set comprising N number of data point and
Individual distance metric function F, is divided into described data set K bunch, obtains the optimum division for data set so that distance metric
The value of function F is minimum.
4. set up different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method as claimed in claim 3 long-range
Damage identification method, it is characterised in that in BIRCH algorithm, the node in CF tree is all made up of CF, and a CF is a tlv triple,
All information that this tlv triple just represents bunch, the data point of given N number of d dimension x1, x2 ...., xn}, CF are defined as follows:
CF=(N, LS, SS)
Wherein, N is the number of subclass interior joint, LS be the linear of N number of node and, SS is the quadratic sum of N number of node；
Bunch barycenter and bunch radius.If one bunch comprises n data point: Xi}, i=1,2,3...n., then barycenter C and
Radius R computing formula is as follows:
C=(X1+X2+...+Xn)/n,
R=(| X1-C | ^2+ | X2-C | ^2+...+ | Xn-C | ^2)/n
Wherein, bunch radius arrives a little the average distance of bunch barycenter in representing bunch, in CF storage be bunch in all data points
The statistics of characteristic and, the when that a data point being added certain bunch, the detailed features of this data point is lost, BIRCH cluster
With this, data set is compressed.
5. setting up the long-range damage identification method of different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method, 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 intelligence semi-supervised learning BIRCH 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 intelligence semi-supervised learning BIRCH method；
Step 5. judge the object that vehicle collides, target training data is learnt thus generates object module, described
Object module is set up and is used intelligence semi-supervised learning BIRCH method.
6. set up different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method as claimed in claim 5 long-range
Damage identification 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 target detection subsystem processes CAE damage simulation data process, then it is carried out classification generation damage judgement instruction
Practice data and damage judges test data；
S2. in target training module, damage training of judgement data learnt and produce damage model, carrying out simulated target instruction
Practice the effect of data；
S3. damage is used to judge that test data carry out the result of test target judgment models in target detection model；
S4. use true sport car data as target verification data and to bring target verification module into, verify object judgement model
Accuracy.
7. as described in claim 5 or 6 to set up different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method remote
Journey damage identification method, it is characterised in that described intelligence semi-supervised learning BIRCH method, the given data comprising N number of data point
Collection and a distance metric function F, be divided into described data set K bunch, obtain the optimum division for data set so that away from
Minimum from the value of metric function F.
8. set up different automobile types partial objectives for based on artificial intelligence's semi-supervised learning BIRCH method as claimed in claim 7 long-range
Damage identification method, it is characterised in that in BIRCH algorithm, the node in CF tree is all made up of CF, and a CF is a tlv triple,
All information that this tlv triple just represents bunch, the data point of given N number of d dimension x1, x2 ...., xn}, CF are defined as follows:
CF=(N, LS, SS)
Wherein, N is the number of subclass interior joint, LS be the linear of N number of node and, SS is the quadratic sum of N number of node；
Bunch barycenter and bunch radius.If one bunch comprises n data point: Xi}, i=1,2,3...n., then barycenter C and
Radius R computing formula is as follows:
C=(X1+X2+...+Xn)/n,
R=(| X1-C | ^2+ | X2-C | ^2+...+ | Xn-C | ^2)/n
Wherein, bunch radius arrives a little the average distance of bunch barycenter in representing bunch, in CF storage be bunch in all data points
The statistics of characteristic and, the when that a data point being added certain bunch, the detailed features of this data point is lost, BIRCH cluster
With this, data set is compressed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610365676.XA CN106056152A (en) | 2016-05-27 | 2016-05-27 | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610365676.XA CN106056152A (en) | 2016-05-27 | 2016-05-27 | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106056152A true CN106056152A (en) | 2016-10-26 |
Family
ID=57174865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610365676.XA Pending CN106056152A (en) | 2016-05-27 | 2016-05-27 | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence semi-supervised learning BIRCH method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106056152A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109668573A (en) * | 2019-01-04 | 2019-04-23 | 广东工业大学 | A kind of vehicle path planning method for improving RRT algorithm |
| CN114418200A (en) * | 2021-12-31 | 2022-04-29 | 清华大学 | Vehicle type specific passenger damage prediction model training method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103303237A (en) * | 2013-06-21 | 2013-09-18 | 湖南大学 | Air bag detonation control method based on genetic neural network |
| 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 |
-
2016
- 2016-05-27 CN CN201610365676.XA patent/CN106056152A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103303237A (en) * | 2013-06-21 | 2013-09-18 | 湖南大学 | Air bag detonation control method based on genetic neural network |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| CADOR: "BIRCH算法学习", 《CADOR，URL：HTTPS://BLOG.CSDN.NET/U013524655/ARTICLE/DETAILS/41171565》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109668573A (en) * | 2019-01-04 | 2019-04-23 | 广东工业大学 | A kind of vehicle path planning method for improving RRT algorithm |
| 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 |
|---|---|---|
| US11544917B2 (en) | Power electronic circuit fault diagnosis method based on optimizing deep belief network | |
| 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 | |
| Pawlus et al. | Investigation of vehicle crash modeling techniques: theory and application | |
| CN106056150A (en) | System and method for establishing part division remote damage assessment of different vehicle types based on artificial intelligence random forest method | |
| 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 | |
| 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 | |
| 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 | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| CN106055779A (en) | Remote damage-assessment system and method established based on artificial intelligence semi-supervised learning logistic-regression method for different types of vehicles | |
| KR102404498B1 (en) | Industrial gearbox failure diagnosis apparatus and method using convolutional neural network based on adaptive time-frequency representation | |
| CN112462759B (en) | Evaluation method, system and computer storage medium of rule control algorithm | |
| CN117809458A (en) | Real-time assessment method and system for traffic accident risk | |
| Yong et al. | State reconstruction in a nonlinear vehicle suspension system using deep neural networks | |
| 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 | |
| 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 | |
| CN113642114A (en) | Modeling method for humanoid random car following driving behavior capable of making mistakes | |
| 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 | |
| CN106096624A (en) | The long-range loss assessment system of different automobile types divided working status and method is set up based on artificial intelligence | |
| Hao et al. | Aggressive lane-change analysis closing to intersection based on UAV video and deep learning | |
| 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 | |
| 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 | |
| CN106096626A (en) | The long-range loss assessment system in different automobile types subregion and method is set up based on artificial intelligence's unsupervised learning FuzzyC Means clustering algorithm | |
| CN106056148A (en) | System and method for establishing target division remote damage assessment of different vehicle types based on artificial intelligence unsupervised learning sparse coding method | |
| CN114863210A (en) | Method and system for resisting sample attack of bridge structure health monitoring data driving model |
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 |