Citation: Zhao, L.; Yang, J. Batch
Process Monitoring Based on
Quality-Related Time-Batch 2D
Evolution Information. Sensors 2022,
22, 2235. https://doi.org/10.3390/
s22062235
Academic Editors: Hamed Badihi,
Ningyun Lu and Tao Chen
Received: 17 February 2022
Accepted: 11 March 2022
Published: 14 March 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Batch Process Monitoring Based on Quality-Related Time-Batch
2D Evolution Information
Luping Zhao * and Jiayang Yang
College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;
20194179@stu.neu.edu.cn
* Correspondence: zhaolp@ise.neu.edu.cn; Tel.: +86-188-4255-2385
Abstract:
This paper proposed a quality-related online monitoring strategy based on time and batch
two-dimensional evolution information for batch processes. In the direction of time, considering
the difference between each phase and the steady part and the transition part in the same phase,
the change trend of the regression coefficient of the PLS model is used to divide each batch into
phases, and each phase into parts. The phases, the steady parts, and the transition parts are finally
distinguished and dealt with separately in the subsequent modeling process. In the batch direction,
considering the slow time-varying characteristics of batch evolution, sliding windows are used to
perform mode division by analyzing the evolution trend of the score matrix
T
in the PLS model on
the base of phase division and within-phase part division. Finally, an online monitoring model that
comprehensively considers the evolution information of time and batch is obtained. In a typical
batch operation process, injection molding is used as an example for experimental analysis. The
results show that the proposed algorithm takes advantage of mixing the time-batch two-dimensional
evolution information. Compared with the traditional methods, the proposed method can overcome
the shortcomings caused by the single dimension analysis and has better monitoring results.
Keywords: batch process; partial least squares; online monitoring; evolution information
1. Introduction
The batch process is an important mode of production in the modern manufacturing
industry. It refers to the manufacturing process in which the input raw materials are
transformed into one or a batch of desired products in a limited phase by predetermined
procedures and repeated. Finally, more of the same products are obtained. In today’s
society, market demand changes rapidly, and high value-added products are produced by
batch processing, so the operation safety issue has aroused people’s attention [1–4].
It is expected that the batch process can be monitored efficiently; that is, the actual
running state of the production process can be sensitively sensed, and whether the whole
or part of the system is running properly can be analyzed. Early detection of abnormal
production conditions affecting the quality of products; corresponding countermeasures
can be given for different abnormal situations [
5
]; the monitoring of batch processes plays
an important role in maintaining safety and ensuring the high quality of products. It
can be divided into two aspects: condition monitoring and fault diagnosis. Condition
monitoring [
6
] refers to the perception, analysis, and evaluation of the operating status of
the production process, analysis based on the collected data, understanding of the historical
situation and operating status of the system, fully considering the impact of external factors,
including the environment, to judge whether it is normal and evaluating the operating level.
Fault diagnosis [
6
] is used to analyze the detected abnormal state further, to understand the
internal causes and influencing factors, and use the mining and understanding of historical
faults and maintenance records. On the one hand, it analyzes and judges the existing
faults; on the other hand, it forecasts the possible faults of the equipment in advance.
Sensors 2022, 22, 2235. https://doi.org/10.3390/s22062235 https://www.mdpi.com/journal/sensors
