1. Home
  2. Honda R&D Technical Review Vol.29 N...
  3. Vehicle Performance Design System U...

Technical Review e-Book: Summary

Vehicle Performance Design System Using Data Mining Techniques towards Model-based Development

Article of Honda R&D Technical Review Vol.29 No.1

Summary

A vehicle performance design system has been developed that makes it possible to assign target values for different performance demands at the initial stage of the vehicle development process. Based on the concept of model-based development, this system determines appropriate target values through the application of data mining techniques.
The system uses the data available at the time of vehicle development, and comprises the following three techniques:
(1) A response surface generation technique that helps enable high-accuracy predictions based on small amounts of data;
(2) A decision-making technique that helps enable high-efficiency data searches that reflect the user’s intentions; and
(3) An impact analysis technique that makes it possible to identify specifications that have the great effect on performance from the relationships between performance and specifications.
It was demonstrated that the application of this system to vehicle dynamic performance simulations enables determination of target performance values and specification values simply and at high speed.

Reference

(1) Fukushige, T., Ariyoshi, T., Uda, Y., Okuma, Y., Okabe, T., Yamamoto, K., Graening, L., Menzel, S., Olhofer, M.: Development of Real-time Aerodynamic Design System, Honda R&D Technical Review, Vo. 24, No. 2, p. 107-116
(2) Tuno, K., Takafumi Kotani, T., Dobashi, M., Koide, F., Fukushige, T., Ariyoshi, T.: Development of Honda Smart Home System, Honda R&D Technical Review, Vol.26, No.1, p.11-17
(3) Hastie, T., Tibshirani, R. Freidman, J. :The Elements of Statistical Learning: Data mining, Inference, and Prediction, Springer Series in Statistics, p. 369-370, (2009)
(4) Blatman, G., Sudret, B.: Adaptive sparse polynomial Chaos expansion based on least angle regression, Journal of Computational Physics, Vol. 230, p. 2345-2367, (2011)
(5) Schobi, R. Sudret, B. Wiart, J.: Polynomial Chaos-based Kriging, ETH Zurich Project Report RSUQ-2015-002, February 13th, (2015)
(6) Bezdek, J. C., Ehrlich R., Full, W.: FCN: THE FUZZY c-MEANS CLUSTERING ALGORITHM, Computers & Geosciences, vol. 10, p. 2-3, (1984)

Author (organization or company)

Tokitomo ARIYOSHI(Automobile R&D Center)、Masatoshi HARUMATSU(Automobile R&D Center)、Kazushige YANO(Automobile R&D Center)、Takahiro FUKUSHIGE(Automobile R&D Center)、Kentaro YAMADA(Automobile R&D Center)、Kaname NARUKAWA(Fundamental Technology Research Center)

We would like to get your opinion on this research paper. (This is only applicable to registered members.)

The readers of this research paper have also selected these research papers.

Proposal of Development Process Using DSM and Simulation
Article of Honda R&D Technical Review Vol.29 No.1
Development of Chassis Performance Design Technologies for MBD of Mass-production Vehicles
Article of Honda R&D Technical Review Vol.29 No.1
Technique for Simulating Vehicle Handling in Very Low Speed Range for Model Based Development
Article of Honda R&D Technical Review Vol.30 No.2