Motor Control using Adaptive Time-Delay Learning
This paper presents the application of time-delay learning to motor control. An extended version of the Adaptive Time-Delay Neural Network is used guaranteeing a more precise delay learning. This approach is applied to motor control by supporting a traditional PI-controller when controlling a combustion engine as a neural co-controller showing that it outperforms the traditional Adaptive Time-Delay Neural Network.
KeywordsMotor Control Combustion Engine Feedforward Neural Network Nonlinear Control System Network Input
Unable to display preview. Download preview PDF.
- D.-T. Lin, J. Dayhoff, P. Ligomedes, “A learning algorithm for adaptive time-delays in a temporal neural network”, tech. rep., University of Maryland, 1992.Google Scholar
- C. Ungerer, A. Radan, “Identifying time delays using neural networks”, in Proc. of the Int. Conf. on Engineering Applic. of Neural Networks (D. Tsaptsinos, ed., pp. 237–244, 2000.Google Scholar
- C. Ungerer, D. Stübener, C. Kirchmair, M. Sturm, “Supporting traditional controllers of combustion engines by means of neural networks”, in Proceedings of the 6th Fuzzy Days (B. Reusch, ed.), pp. 132–141, Springer, 1999.Google Scholar
- C. Ungerer, “Identifying time-delays in nonlinear control systems: An application of the adaptive time-delay neural network”, in CIMCA 99 — Neural Networks & Andvanced Control Strategies (M. Mohammadian, (ed.), pp. 99–104, IOS Press, 1999.Google Scholar