A batch-wise LSTM-encoder decoder network for batch process monitoring

•Proposed a multi-layer recurrent neural network in the encoder–decoder structure and the corresponding monitoring method for batch process monitoring.•The proposed network can simultaneously capture the between and within batch dynamic features in the nonlinear batch process.•The proposed model out...

Full description

Saved in:
Bibliographic Details
Published in:Chemical engineering research & design Vol. 164; pp. 102 - 112
Main Authors: Ren, Jiayang, Ni, Dong
Format: Journal Article
Language:English
Published: Rugby Elsevier B.V 01.12.2020
Elsevier Science Ltd
Subjects:
Coders
Control limits
Density
Encoder–decoder structure
Feature extraction
Fermentation
Kernel density estimation
Monitoring
Monitoring systems
Multi-layer LSTM
Multilayers
Nonlinear batch processes
Nonlinear dynamics
Nonlinear systems
Nonlinearity
Occupational safety
Penicillin
Process monitoring
Recurrent neural networks
Statistical methods
Process monitoring
Nonlinear batch processes
Kernel density estimation
Encoder–decoder structure
Multi-layer LSTM
ISSN:0263-8762, 1744-3563
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Proposed a multi-layer recurrent neural network in the encoder–decoder structure and the corresponding monitoring method for batch process monitoring.•The proposed network can simultaneously capture the between and within batch dynamic features in the nonlinear batch process.•The proposed model outperforms the AutoEncoder and Sub-PCA model in fault detection. Process monitoring is essential to keep quality consistency and operation safety in the batch process. However, the existence of multiphase, nonlinearity and dynamic features in the batch process makes the batch process monitoring a complicated task. In this work, a multi-layer recurrent neural network in the encoder–decoder structure called batch-wise LSTM-encoder decoder network is proposed to solve the difficulties mentioned above in batch process monitoring. The LSTM-encoder extracts the nonlinear dynamic features in both between and within batch direction, then projects the high dimensional input space to a low dimensional hidden state space. The decoder part regenerates the samples from hidden states. Control statistics H2 and SPE are designed for process monitoring, and the corresponding control limits are estimated by kernel density estimation. A case study on an extensive reference penicillin fermentation dataset suggests that the proposed method can detect the fault samples more effectively than previous methods while keeping the same robustness in normal conditions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0263-8762
1744-3563
DOI:10.1016/j.cherd.2020.09.019