TY - JOUR
T1 - Deep Learning-Based Model Predictive Control for Continuous Stirred-Tank Reactor System
AU - Wang, Gongming
AU - Jia, Qing Shan
AU - Qiao, Junfei
AU - Bi, Jing
AU - Zhou, Mengchu
N1 - Funding Information:
Manuscript received August 12, 2019; revised November 16, 2019, March 3, 2020, and June 16, 2020; accepted August 8, 2020. Date of publication September 9, 2020; date of current version August 4, 2021. This work was supported in part by the Major Project of the Ministry of Science and Technology of China under Grant 2018ZX07111005, in part by the Major Project for New Generation Artificial Intelligence under Grant 2018AAA0101600, in part by the National Natural Science Foundation of China under Grant 61703011, and in part The Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, under Grant RG-48-135-40. (Corresponding author: Junfei Qiao.) Gongming Wang and Qing-Shan Jia are with the Center for Intelligent and Networked Systems (CFINS), Department of Automation, Tsinghua University, Beijing 100084, China (e-mail: wanggm@tsinghua.edu.cn; jiaqs@tsinghua.edu.cn).
Publisher Copyright:
© 2012 IEEE.
PY - 2021/8
Y1 - 2021/8
N2 - A continuous stirred-tank reactor (CSTR) system is widely applied in wastewater treatment processes. Its control is a challenging industrial-process-control problem due to great difficulty to achieve accurate system identification. This work proposes a deep learning-based model predictive control (DeepMPC) to model and control the CSTR system. The proposed DeepMPC consists of a growing deep belief network (GDBN) and an optimal controller. First, GDBN can automatically determine its size with transfer learning to achieve high performance in system identification, and it serves just as a predictive model of a controlled system. The model can accurately approximate the dynamics of the controlled system with a uniformly ultimately bounded error. Second, quadratic optimization is conducted to obtain an optimal controller. This work analyzes the convergence and stability of DeepMPC. Finally, the DeepMPC is used to model and control a second-order CSTR system. In the experiments, DeepMPC shows a better performance in modeling, tracking, and antidisturbance than the other state-of-the-art methods.
AB - A continuous stirred-tank reactor (CSTR) system is widely applied in wastewater treatment processes. Its control is a challenging industrial-process-control problem due to great difficulty to achieve accurate system identification. This work proposes a deep learning-based model predictive control (DeepMPC) to model and control the CSTR system. The proposed DeepMPC consists of a growing deep belief network (GDBN) and an optimal controller. First, GDBN can automatically determine its size with transfer learning to achieve high performance in system identification, and it serves just as a predictive model of a controlled system. The model can accurately approximate the dynamics of the controlled system with a uniformly ultimately bounded error. Second, quadratic optimization is conducted to obtain an optimal controller. This work analyzes the convergence and stability of DeepMPC. Finally, the DeepMPC is used to model and control a second-order CSTR system. In the experiments, DeepMPC shows a better performance in modeling, tracking, and antidisturbance than the other state-of-the-art methods.
KW - Continuous stirred-tank reactor (CSTR) system
KW - growing deep belief network (GDBN) model
KW - model predictive control
KW - optimal controller
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85112002681&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112002681&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2020.3015869
DO - 10.1109/TNNLS.2020.3015869
M3 - Article
C2 - 32903185
AN - SCOPUS:85112002681
SN - 2162-237X
VL - 32
SP - 3643
EP - 3652
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 8
M1 - 9189864
ER -