Just-in-time learning based integrated MPC-ILC control for batch processes

This paper deals with the online sample trajectory prediction problem of batch processes considering complex data characteristics and batch-to-batch variations. Although some methods have been proposed to implement the trajectory interpolation problem for quality prediction and monitoring applications, the accuracy and reliability are not ensured due to data nonlinearity, dynamics and other complicated feature. To improve the data interpolation performance, an improved JITL-LSTM approach is designed in this work. Firstly, an improved trajectory-based JITL strategy is developed to extract similar local trajectories. Then the LSTM neural network is used on the basis of the extracted trajectories with a modified network structure. Therefore, trajectory prediction and interpolation can be achieved according to the local JITL-LSTM model at each time index. A simulated fed-batch reactor process is presented to demonstrate the effectiveness of the proposed method.

Download Full-text

Quadratic-Criterion-Based Model Predictive Iterative Learning Control for Batch Processes Using Just-in-Time-Learning Method

IEEE Access ◽

10.1109/access.2019.2934474 ◽

2019 ◽

Vol 7 ◽

pp. 113335-113344

Author(s):

Liuming Zhou ◽

Li Jia ◽

Yu-Long Wang

Keyword(s):

Iterative Learning Control ◽

Learning Control ◽

Iterative Learning ◽

Batch Processes ◽

Just In Time ◽

Learning Method

Download Full-text

A Novel Dynamic Just-in-Time Learning Framework for Modeling of Batch Processes

Industrial & Engineering Chemistry Research ◽

10.1021/acs.iecr.0c02979 ◽

2020 ◽

Vol 59 (43) ◽

pp. 19334-19344

Author(s):

Tanuja Joshi ◽

Vishesh Goyal ◽

Hariprasad Kodamana

Keyword(s):

Batch Processes ◽

Just In Time ◽

Learning Framework

Download Full-text

Just-in-Time-Learning based Extended Prediction Self-Adaptive Control for batch processes

Journal of Process Control ◽

10.1016/j.jprocont.2016.04.009 ◽

2016 ◽

Vol 43 ◽

pp. 1-9 ◽

Cited By ~ 19

Author(s):

Qing-Lin Su ◽

Martin Wijaya Hermanto ◽

Richard D. Braatz ◽

Min-Sen Chiu

Keyword(s):

Adaptive Control ◽

Batch Processes ◽

Just In Time ◽

Self Adaptive

Download Full-text

Soft Sensor Framework Based on Semisupervised Just-in-Time Relevance Vector Regression for Multiphase Batch Processes with Unlabeled Data

Industrial & Engineering Chemistry Research ◽

10.1021/acs.iecr.0c03806 ◽

2020 ◽

Vol 59 (44) ◽

pp. 19633-19642

Author(s):

Kepeng Qiu ◽

Jianlin Wang ◽

Xinjie Zhou ◽

Yongqi Guo ◽

Rutong Wang

Keyword(s):

Soft Sensor ◽

Unlabeled Data ◽

Batch Processes ◽

Just In Time ◽

Relevance Vector Regression

Download Full-text

Phase division and transition modeling based on the dominant phase identification for multiphase batch process quality prediction

Transactions of the Institute of Measurement and Control ◽

10.1177/0142331219881343 ◽

2019 ◽

Vol 42 (5) ◽

pp. 1022-1036 ◽

Cited By ~ 1

Author(s):

Xiaochu Tang ◽

Yuan Li

Keyword(s):

Cumulative Effect ◽

Batch Process ◽

Batch Processes ◽

Just In Time ◽

Phase Identification ◽

Quality Prediction ◽

Time Model ◽

Transition Modeling ◽

Dominant Phase ◽

Prediction Strategy

Batch processes are carried out from one steady phase to another one, which may have multiphase and transitions. Modeling in transitions besides in the steady phases should also be taken into consideration for quality prediction. In this paper, a quality prediction strategy is proposed for multiphase batch processes. First, a new repeatability factor is introduced to divide batch process into different steady phases and transitions. Then, the different local cumulative models that considered the cumulative effect of process variables on quality are established for steady phases and transitions. Compared with the reported modeling methods in transitions, a novel just-in-time model can be established based on the dominant phase identification. The proposed method can not only consider the dynamic characteristic in the transition but also improve the accuracy and the efficiency of transitional models. Finally, online quality prediction is performed by accumulating the prediction results from different phases and transitions. The effectiveness of the proposed method is demonstrated by penicillin fermentation process.

Download Full-text