Trajectory optimization and positioning control for batch process using learning control

Abstract Efficiency and accuracy are critical in the motion control of a batch process. This paper proposes a new intelligent motion control method for a batch process based on reinforcement learning (RL) and iterative learning control (ILC). The proposed learning-based motion control method enables the system to learn from its previous experience. The motion control method can be divided into two parts: (1) RL-based trajectory optimization and (2) ILC-based positioning control. Experiments were conducted to demonstrate the effectiveness of the proposed method. The results indicate that the proposed method not only reduces the process time effectively while ensuring system stability, but also achieves excellent positioning accuracy.

[1]  Ben J. A. Kröse,et al.  Learning from delayed rewards , 1995, Robotics Auton. Syst..

[2]  Michel Zasadzinski,et al.  Trajectory tracking control for perturbed robot manipulators using iterative learning method , 2016 .

[3]  Cong Wang,et al.  Design of arbitrary-order robust iterative learning control based on robust control theory , 2017 .

[4]  Cheng Shao,et al.  Robust iterative learning control with applications to injection molding process , 2001 .

[5]  Dimitry Gorinevsky,et al.  Distributed Loop-shaping for Iterative Control of Batch Processes , 2002 .

[6]  Furong Gao,et al.  Predictive Functional Control for Linear Systems under Partial Actuator Faults and Application on an Injection Molding Batch Process , 2014 .

[7]  A.G. Alleyne,et al.  A survey of iterative learning control , 2006, IEEE Control Systems.

[8]  Harald Aschemann,et al.  Robust guaranteed cost ILC with dynamic feedforward and disturbance compensation for accurate PMSM position control , 2017 .

[9]  Suguru Arimoto,et al.  Bettering operation of Robots by learning , 1984, J. Field Robotics.

[10]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[11]  Rong-Fong Fung,et al.  Energy-saving trajectory planning for a toggle mechanism driven by a PMSM , 2014 .

[12]  X. Chen,et al.  Model-Free Quality Optimization Strategy for a Batch Process with Short Cycle Time and Low Operational Cost , 2014 .

[13]  Limin Wang,et al.  Iterative learning fault-tolerant control for injection molding processes against actuator faults , 2017 .

[14]  Weihai Chen,et al.  A Robust Adaptive Iterative Learning Control for Trajectory Tracking of Permanent-Magnet Spherical Actuator , 2016, IEEE Transactions on Industrial Electronics.

[15]  Gheorghe Mogan,et al.  Neural networks based reinforcement learning for mobile robots obstacle avoidance , 2016, Expert Syst. Appl..

[16]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[17]  Rong-Jong Wai,et al.  Recurrent-fuzzy-neural-network sliding-mode controlled motor-toggle servomechanism , 2001 .

[18]  Yu-Ping Tian,et al.  Consensus of Data-Sampled Multi-Agent Systems With Random Communication Delay and Packet Loss , 2010, IEEE Transactions on Automatic Control.

[19]  Jay H. Lee,et al.  ITERATIVE LEARNING CONTROL APPLIED TO BATCH PROCESSES: AN OVERVIEW , 2006 .

[20]  Svante Gunnarsson,et al.  Experimental comparison of some classical iterative learning control algorithms , 2002, IEEE Trans. Robotics Autom..

[21]  L. Turng,et al.  A review of current developments in process and quality control for injection molding , 2005 .

[22]  Rong-Fong Fung,et al.  Key design parameters and optimal design of a five-point double-toggle clamping mechanism , 2011 .

[23]  Martin A. Riedmiller,et al.  Reinforcement learning for robot soccer , 2009, Auton. Robots.

[24]  Nariman Sepehri,et al.  Internal Leakage Detection in Hydraulic Actuators Using Empirical Mode Decomposition and Hilbert Spectrum , 2012, IEEE Transactions on Instrumentation and Measurement.

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