Deep reinforcement learning approaches for process control

S.P.K. Spielberg, R.B. Gopaluni, P.D. Loewen
2017 2017 6th International Symposium on Advanced Control of Industrial Processes (AdCONIP)  
The conventional and optimization based controllers have been used in process industries for more than two decades. The application of such controllers on complex systems could be computationally demanding and may require estimation of hidden states. They also require constant tuning, development of a mathematical model (first principle or empirical), design of control law which are tedious. Moreover, they are not adaptive in nature. On the other hand, in the recent years, there has been
more » ... ere has been significant progress in the fields of computer vision and natural language processing that followed the success of deep learning. Human level control has been attained in games and physical tasks by combining deep learning with reinforcement learning. They were also able to learn the complex go game which has states more than number of atoms in the universe. Self-Driving cars, machine translation, speech recognition etc started to gain advantage of these powerful models. The approach to all of them involved problem formulation as a learning problem. Inspired by these applications, in this work we have posed process control problem as a learning problem to build controllers to address the limitations existing in current controllers. ii Preface The thesis consists of two parts. The first part which is discussed in Chapter 3, discusses about the new neural network architecture that was designed to learn the complex behaviour of Model Predictive Control (MPC). It overcomes some of the challenges of MPC. The contributions of this part have A deep learning architecture for predictive control, Canadian Chemical Engineering Conference, Alberta, 2017. The second part of the work explained in Chapter 4, discusses the learning based approach to design a controller to be able to control the plant. The motivation for this approach is to solve some of the limitations present in the conventional and optimization based controllers. The contributions of iv
doi:10.1109/adconip.2017.7983780 fatcat:oljnc7ufwbdolcpz27nhtirve4