Affiliations: [a] School of Information Science and Engineering, Zhejiang University Ningbo Institute of Technology, Ningbo, Zhejiang 315100, China | [b] School of Mechanical Engineering and Automation, College of Science and Technology, Ningbo University, Ningbo, Zhejiang 315212, China | [c] Department of Chemical Engineering and Materials Science, University of California, Davis, CA 95616, USA
Correspondence:
[*]
Corresponding author: Feifan Shen, School of Information Science and Engineering, Zhejiang University Ningbo Institute of Technology, Ningbo, Zhejiang 315100, China. E-mail: ffshen@nit.net.cn.
Abstract: 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.
Keywords: Batch process, long short-term memory, data-driven modeling, trajectory prediction, just-in-time learning, multivariate quality control
