Truncated backpropagation through time and Kalman filter training for neurocontrol

作者: G.V. Puskorius , L.A. Feldkamp

DOI: 10.1109/ICNN.1994.374611

关键词:

摘要: We have recently established the feasibility of training recurrent neural networks by parameter-based decoupled extended Kalman filter (DEKF) algorithms for control nonlinear dynamical systems. In this paper we investigate use truncated backpropagation through time (BPTT) approximating required dynamic derivatives that are used DEKF algorithm. The approximation allows gradient calculations and weight updates algorithm to be performed asynchronously with application signals, thereby leading a scalable, real-time, online demonstrate in simulation effectiveness BPTT-based problem automotive engine idle speed control. >

参考文章(17)
J. A. Cook, B. K. Powell, Nonlinear Low Frequency Phenomenological Engine Modeling and Analysis american control conference. ,vol. 24, pp. 332- 340 ,(1987) , 10.1109/ACC.1987.4172371
G. V. Puskorius, L. A. Feldkamp, Automotive Engine Idle Speed Control with Recurrent Neural Networks 1993 American Control Conference. pp. 311- 316 ,(1993) , 10.23919/ACC.1993.4792864
L.A. Feldkamp, G.V. Puskorius, L.I. Davis, F. Yuan, Neural control systems trained by dynamic gradient methods for automotive applications international joint conference on neural network. ,vol. 2, pp. 798- 804 ,(1992) , 10.1109/IJCNN.1992.226889
J.A. Cook, B.K. Powell, Modeling of an internal combustion engine for control analysis IEEE Control Systems Magazine. ,vol. 8, pp. 20- 26 ,(1988) , 10.1109/37.7726
Ronald J. Williams, Jing Peng, An efficient gradient-based algorithm for on-line training of recurrent network trajectories Neural Computation. ,vol. 2, pp. 490- 501 ,(1990) , 10.1162/NECO.1990.2.4.490
B. Fernandez, A.G. Parlos, W.K. Tsai, Nonlinear dynamic system identification using artificial neural networks (ANNs) international joint conference on neural network. pp. 133- 141 ,(1990) , 10.1109/IJCNN.1990.137706
Fuzzy logic control of an automotive engine IEEE Control Systems Magazine. ,vol. 13, pp. 62- 68 ,(1993) , 10.1109/37.214946
L.A. Feldkamp, G.V. Puskorius, Trainable fuzzy and neural-fuzzy systems for idle-speed control ieee international conference on fuzzy systems. pp. 45- 51 ,(1993) , 10.1109/FUZZY.1993.327465
Derrick Nguyen, Bernard Widrow, The truck backer-upper: an example of self-learning in neural networks Neural networks for control. pp. 287- 299 ,(1990) , 10.1016/B978-0-444-88400-8.50006-6
G.V. Puskorius, L.A. Feldkamp, Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks IEEE Transactions on Neural Networks. ,vol. 5, pp. 279- 297 ,(1994) , 10.1109/72.279191