|
|
Learning strategies for wet clutch control Host Publication: 15th International Conference on System Theory, Control and Computing - ICSTCC 2011 Authors: G. Pinte, J. Stoev, W. Symens, A. Dutta, Y. Zhong, B. Wyns, R. De Keyser, B. Depraetere, J. Swevers, M. Gagliolo and A. Nowé Publisher: IEEE Publication Date: Oct. 2011 Number of Pages: 8 ISBN: 978-973-621-322-9
Abstract: This paper presents an overview of model-based
(Iterative Learning Control, Model Predictive Control and
Iterative Optimization) and non-model-based (Genetic-based
Machine Learning and Reinforcement Learning) learning
strategies for the control of wet clutches. Based on theoretical
considerations and a validation on an experimental test bench
containing wet clutches, the benefits and drawbacks of the
different strategies are compared. Although after convergence
a good engagement quality can be obtained by all strategies,
only model-based strategies are suited for online applicability.
The convergence time for non-model-based strategies is too long
such that they can only be applied during an offline calibration
phase.
|
|
