P. Salgado, M. Salgado, and P. Afonso (Portugal)
Optimal control; Fuzzy Machine Learning and Fuzzy Control
In this paper, a new scheme of fuzzy optimal control for control the liquid level and temperature in a pilot plant continuous stirred tank reactor (CSTR) is presented. The proposed control method, based on the Pontryagin’s Minimum Principle, back propagation from the final co state error and gradient descent, allows training an adaptive fuzzy inference system to estimate values for the optimal co-state variables. This approach allows finding a solution to the optimal control problem on-line by training the system, which can be used on a close-loop control strategy. The design of control system is developed by minimizing a quadratic performance index selected for the desired operating conditions. Successful simulations results of controlling the system are presented.
Important Links:
Go Back
