Target remote damage assessment system for different vehicle models established based on artificial intelligence supervised learning decision tree method and target remote damage assessment method thereof

A supervised learning and artificial intelligence technology, applied in the field of vehicle damage assessment, to achieve the effect of improving accuracy

Inactive Publication Date: 2016-11-02
DALIAN ROILAND SCI & TECH CO LTD
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of detecting the target of the colliding vehicle after the collision, the present invention proposes a supervised learning decision tree method based on artificial inte

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Target remote damage assessment system for different vehicle models established based on artificial intelligence supervised learning decision tree method and target remote damage assessment method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] A supervised learning decision tree method based on artificial intelligence to establish a remote damage assessment system for different vehicle models, including:

[0026] The model selection subsystem selects the model data corresponding to the vehicle as the total data set;

[0027] The data classification subsystem reads CAE simulation data and real vehicle data, and classifies the data accordingly;

[0028] The collision detection subsystem judges whether the vehicle collides during driving; the collision detection subsystem learns the collision training data to generate a collision model, and the collision model is established using an intelligent supervised learning decision tree method;

[0029] The working condition detection subsystem judges all the working condition information of the collision; the working condition detection subsystem learns the working condition training data to generate a working condition model, and the working condition model is establi...

Embodiment 2

[0052] A supervised learning decision tree method based on artificial intelligence to establish a remote damage assessment method for different vehicle types with sub-targets, comprising the following steps:

[0053] Step 1. Select the model data corresponding to the vehicle as the total data set;

[0054] Step 2. Read the CAE simulation data and real vehicle data, and classify the data accordingly;

[0055] Step 3. Judging whether the vehicle collides during driving; the collision detection subsystem learns the collision training data to generate a collision model, and the collision model is established using an intelligent supervised learning decision tree method;

[0056] Step 4. Judging all the working condition information where the collision occurs; the working condition detection subsystem learns the working condition training data to generate a working condition model, and the working condition model is established using an intelligent supervised learning decision tree...

Embodiment 3

[0097] Have the technical scheme identical with embodiment 1 or 2, more specifically:

[0098] The overall data set in the above scheme: all are CAE simulation data and sports car data; it is divided into three parts as follows

[0099] 1. Training data set: it is used to train the model or determine the model parameters (CAE simulation data and sports car data).

[0100] 2. Verification data set: It is used for model selection (model selection), that is, for the final optimization and determination of the model (CAE simulation data and sports car data).

[0101] 3. Test data set: it is purely to test the generalization ability of the trained model. (CAE simulation data and sports car data).

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a target remote damage assessment system for different vehicle models established based on an artificial intelligence supervised learning decision tree method and a target remote damage assessment method thereof, belongs to the field of vehicle damage assessment, and aims at solving the problem of target detection of a collided vehicle after vehicle collision. The technical key points are that a target detection subsystem judges the object of collision of the vehicle, wherein the target detection subsystem learns target training data so as to generate a target model, and the intelligent supervised learning decision tree method is applied in establishing of the target model. The beneficial effects are that target detection of vehicle collision can be realized through the technical scheme, a machine learning method is applied in the technical field of remote damage assessment and the judgment accuracy is enhanced in the damage assessment process by the machine learning method.

Description

technical field [0001] The invention belongs to the field of vehicle damage assessment, and relates to a system and method for establishing a remote damage assessment system and method for different vehicle models based on a supervised learning decision tree method of artificial intelligence. Background technique [0002] Aiming at the problem of claim settlement disputes caused by frequent collisions of vehicles during low-speed movement (including low-speed road driving, vehicle parking, etc.), the remote damage assessment technology collects various signals (such as speed, acceleration, angular velocity, Sound, etc.) and analyzed with signal processing and machine learning techniques to determine whether a collision has occurred and the damage to the vehicle after the collision. [0003] After a vehicle collision accident, the front-end equipment can detect the occurrence of the collision and intercept the signal of the collision process, and send it to the cloud through ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/245
Inventor 田雨农刘俊俍
Owner DALIAN ROILAND SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap