Machine learning and feedback control

Pratyush Kumar

Data science has become a part of large number of engineering applications. This project aims to identify the potential applications of machine learning for process control. We are investigating both the model-based and model-free approaches proposed in the literature.

Reinforcement learning is a type of model-free control algorithm, and it aims to solve the optimal control problem without using the model of the system. eg: For linear systems, it solves the linear quadratic regulator problem online without using the system model. We are analyzing the advantages/disadvantages of reinforcement learning and its applicability for process control applications.

Explicit model predictive control was developed for linear time invariant (LTI) systems with quadratic objective functions in order to reduce the online optimization burden. It gives us a good idea about the piecewise affine nature of MPC control law, but it has large storage requirements and longer implementation time for high dimensional states. Neural networks with the rectified linear unit (ReLU) as the activation function also represent piecewise affine functions defined on polyhedral regions. In this work we are trying to approximate the piecewise affine MPC control law for linear systems using neural networks.

References:

A. Bemporad, M. Morari, V. Dua, and E. N. Pistikopoulos.
The explicit linear quadratic regulator for constrained systems.
Automatica, 38(1):3-20, 2002.

S. J. Bradtke, B. E. Ydstie, and A. G. Barto.
Adaptive linear quadratic control using policy iteration.
American Control Conference, 1994, volume 3, pages 3475-3479. IEEE, 1994.