Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning

The time cost of first-principles dynamic modelling and the complexity of nonlinear control strategies may limit successful implementation of advanced process control. The maximum return on fixed capital within the processing industries is thus compromised. This study introduces a neurocontrol methodology that uses partial system identification and symbiotic memetic neuro-evolution (SMNE) for the development of neurocontrollers. Partial system identification is achieved using singular spectrum analysis (SSA) to extract state variables from time series data. The SMNE algorithm uses a symbiotic evolutionary algorithm and particle swarm optimisation to learn optimal neurocontroller weights from the partially identified system within a reinforcement learning framework. A multi-effect batch distillation (MEBAD) pilot plant was constructed to demonstrate the real world application of the neurocontrol methodology, motivated by the nonsteady state operation and nonlinear process interaction between multiple distillation columns. Multi-loop proportional integral (PI) control was implemented as a reduced model, reflecting an approach involving no modelling or significant controller tuning. Rapid multiple input multiple out nonlinear controller development was achieved using SSA and the SMNE algorithm, demonstrating comparable time and cost to implementation in relation to the reduced model. The optimal neurocontroller reduced the batch time and therefore the energy consumption by 45% compared to conventional multi-loop SISO PI control.

[1]  G. P. Distefano,et al.  Mathematical modeling and numerical integration of multicomponent batch distillation equations , 1968 .

[2]  Sigurd Skogestad,et al.  Closed operation of multivessel batch distillation: Experimental verification , 2000 .

[3]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning through Symbiotic Evolution , 2004 .

[4]  V.M.L. Santos,et al.  Predictive control based on neural networks: an application to a fluid catalytic cracking industrial unit , 2000 .

[5]  G. P. King,et al.  Extracting qualitative dynamics from experimental data , 1986 .

[6]  Kemal Leblebicioglu,et al.  Nonlinear model predictive controller using neural network , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[7]  Ahmet Palazoglu,et al.  Studies on the analysis of nonlinear processes via functional expansions—III: controller design , 1998 .

[8]  J. A. Wilson,et al.  Neuro-fuzzy modeling and control of a batch process involving simultaneous reaction and distillation , 1997 .

[9]  Masaru Noda,et al.  On-line optimization system of pilot scale multi-effect batch distillation system , 2000 .

[10]  Wei Sun,et al.  A Proposal of Adaptive PID Controller Based on Reinforcement Learning , 2007 .

[11]  Eva Sorensen,et al.  Optimal operation of multivessel batch distillation columns , 1999 .

[12]  Lennart Ljung,et al.  Closed-loop identification revisited , 1999, Autom..

[13]  Mohamed Azlan Hussain,et al.  Review of the applications of neural networks in chemical process control - simulation and online implementation , 1999, Artif. Intell. Eng..

[14]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[15]  Chris Aldrich,et al.  Process system identification strategies based on the use of singular spectrum analysis , 2003 .

[16]  Fernando Tadeo,et al.  Model-free learning control of neutralization processes using reinforcement learning , 2007, Eng. Appl. Artif. Intell..

[17]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[18]  David M. Himmelblau,et al.  Process control via artificial neural networks and reinforcement learning , 1992 .

[19]  L. Tsimring,et al.  The analysis of observed chaotic data in physical systems , 1993 .

[20]  Stephen Piche,et al.  Nonlinear model predictive control using neural networks , 2000 .

[21]  Christiaan Aldrich,et al.  Development of neurocontrollers with evolutionary reinforcement learning , 2005, Comput. Chem. Eng..

[22]  Chris Aldrich,et al.  Intelligent process control utilising symbiotic memetic neuro-evolution , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).