This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
On-Line StatePrediction Of Engines Based On Fast Neural Network
Technical Paper
2001-01-0562
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Event:
SAE 2001 World Congress
Language:
English
Abstract
A flat neural network is designed for the on-line state prediction of engine. To reduce the computational cost of weight matrix, a fast recursive algorithm is derived according to the pseudoinverse formula of a partition matrix. Furthermore, the forgetting factor approach is introduced to improve predictive accuracy and robustness of the model. The experiment results indicate that the improved neural network is of good accuracy and strong robustness in prediction, and can apply for the on-line prediction of nonlinear multi input multi output systems like vehicle engines.
Recommended Content
Technical Paper | A Neural Model of Friction Material Behaviour |
Technical Paper | Development of a Fall Detection Algorithm for Powered Two Wheelers Application |
Technical Paper | An Electronic Throttle Simulation Model with Automatic Parameter Tuning |
Authors
Citation
Gang, X., Jianwu, Z., and Li, C., "On-Line StatePrediction Of Engines Based On Fast Neural Network," SAE Technical Paper 2001-01-0562, 2001, https://doi.org/10.4271/2001-01-0562.Also In
Electronic Engine Controls: Modeling, Controls, Obd and Neural Networks
Number: SP-1585; Published: 2001-03-05
Number: SP-1585; Published: 2001-03-05
References
- Chunghung Pan Moskwa John J. An analysis of the effects of torque, engine geometry and speed on choosing an engine inertia model to minimize prediction errors Abraham H H Proceedings of the 1993 American Control Conference, American Control Conference San Francisco 1993 California American Automatic Control Council 1993:1784∼1789
- Chonghuan Li Zhehao Xuan Dejie Xin Identification of engine's rotative velocity control system based on system identification method (in Chinese) Shanghai Automobile 1995 4 45 47
- Yonghong Tan Nonlinear dynamic system identification based on wavelet neural network Journal of Guilin Institute of Electronic Technology 1999 1 19 1 6
- Pao Y H Park G H Sobajic D J. Learning and generalization characteristics of the random vector functional-link net, in Neuro-computing Amsterdam, The Netherlands Elsevier 1994 6 163 180