This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Neural Network-Based Model Reference Adaptive Control for Electronic Throttle Systems
Technical Paper
2007-01-1628
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
The purpose of this paper is to use a multilayer perceptron neural network model to identify and control a non-linear electronic throttle system. The neural network model, which represents the dynamic behaviour of the non-linear throttle servo system, was first identified at different operating conditions. The neural network controller model was then designed (or trained) with the throttle identifier network model, so that the tracking control position of the throttle system follows a reference model. The neural network controller training is computationally expensive and requires the use of the dynamic backpropagation algorithm, which is significantly time consuming during on-line implementation. For this reason, the throttle identifier network model is used to assist in training the neural controller in off-line mode. The neural network controller was trained with the same inputs that are fed to the actual throttle system to produce the same output. An adaptation algorithm was used to reduce the difference between the outputs by adjusting the weights and biases parameters of the controller network model. The tracking control performance of the throttle control system using the neural network controller was compared to the classical adaptive PID controller [1]. The simulation results reveal that, tracking control was achieved with the neural network controller, which satisfied all the requirements for the control performance.
Recommended Content
Citation
Al-Assadi, S., "Neural Network-Based Model Reference Adaptive Control for Electronic Throttle Systems," SAE Technical Paper 2007-01-1628, 2007, https://doi.org/10.4271/2007-01-1628.Also In
SAE 2007 Transactions Journal of Passenger Cars: Electronic and Electrical Systems
Number: V116-7; Published: 2008-08-15
Number: V116-7; Published: 2008-08-15
References
- Al-Assadi S. Breitinger J. Murphy N. “Tuning An Electronic Throttle Controllers using Computer-Aided Calibration Methodology” SAE2006-World Congress , 2006-01-0307
- Chowdhury F.N. Wahi F. Raina R. Kaminedi S. “A Survey of Neural Networks Applications in Automatic Control” Proceedings of the 33rd Southeastern Symposium on System Theory 2001 349 353
- Quilliard J. Achaichia N “Adaptive Comfort Control” SAE2005-World Congress , 2006-01-2017
- Norgard, M. Ravn O. Poulsen N.K. Hansen L.K. “Neural Networks for Modelling and Control of Dynamic Systems” Springer-Verlag London 2000
- Yang H. Liu L.Y. Wasacz B. “Neural Network Based Feedforward Control for Electronic Throttles” SAE20002-World Congress , 2002-01-1149
- MathWorks “Neural Network Toolbox- Version 4.0.6 (R14)” July 2005
- Schultz R.L Hagan M. T. Jesus O D. “Training multi-loop networks” IJCNN'99 International Joint Conference on Neural Networks 1999 3 1580 1585
- Chen, L. Narendra K. “Nonlinear Adaptive Control Using Neural Networks and Multiple Models” Automatica, Special Issue on Neural Network Feedback Control 2001 37 8 1245 1255
- Al-Assadi S. Breitinger J. Murphy N. “Model-Based Friction and Limp-Home Compensation in Electronic Throttle Control Systems” SAE2006 World Congress , 2006-01-0857
- Al-Assadi S. Breitinger J. Traver M. “Electronic Throttle Simulation Using Nonlinear Hammerstein Model” SAE2006 World Congress , 2006-01-0112
- Eriksson L. Nielsen “Non-Linear Model-Based Throttle Control” SAE2000 World Congress , 2000-01-0261
- Ayeb M. Lichtenthaler D. Winsel T. Theuerkauf H.J. “Model-Based Analysis and Tuning An Electronic Throttle Controllers” SAE1998-World Congress , 980790
- Hornik, K. M. Stinchcombe M. White H. “Multilayer Feedforward Networks are Universal Approximators” Neural Networks 1989 2 5 359 366
- Pinkus A. “Approximation Theory of the MLP Model in Neural Networks,” Acta Numerica 1999 143 195
- Narendra K.S. Mukhopadhyay S. “Adaptive Control Using Neural Networks and Approximate Models,” IEEE Transactions on Neural Networks 1997 8 475 485
- Charalambous C. “Conjugate Gradient Algorithm for Efficient Training of Artificial Neural Networks,” IEEE Proceedings 1992 139 3 301 310
- Hagan M. T. Menhaj M “Training Feedforward Networks with the Marquardt Algorithm,” IEEE Transactions on Neural Networks 1995 5 6 989 993
- Hagan M. Demuth H. Beale M. “Neural Network Design” Boston PWS 1996
- De Jesus, O. Hagan M.T. “Backpropagation Through Time for a General Class of Recurrent Network,” Proceedings of the International Joint Conference on Neural Networks 2001 4 2638 2643
- Dennis J. E. Schnabel R.B. “Numerical Methods for Unconstrained Optimization and Nonlinear Equations” Englewood Cliffs NJ Prentice-Hall 1983
- Al-Assadi S. Breitinger J. Murphy N. “Engine Torque Mapping Using Computer-Aided Calibration” SAE2005 World Congress , 2005-01-0055
- Al-Assadi S. Breitinger J. Murphy N. “Computer-Aided Calibration Methodology” IAC2005 MathWorks International Automotive Conference Detroit, Michigan June 21-22 2005
- Al-Assadi S. Breitinger J. Murphy N. “On-Line Optimization Using Computer-Aided Engine Calibration Method” ETAS North America (Connection 2005) Conference Plymouth, Michigan October 19 2005