eprintid: 17547
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/75/47
datestamp: 2023-12-19 03:23:55
lastmod: 2023-12-19 03:23:55
status_changed: 2023-12-19 03:08:15
type: book
metadata_visibility: show
creators_name: Bingi, K.
creators_name: Prusty, B.R.
creators_name: Ibrahim, R.
title: Machine learning application to industrial control systems
ispublished: pub
note: cited By 0
abstract: This chapter focuses on the growth, development, and future of various machine learning techniques in industrial process control applications. However, the main focus is developing a neural network (NN)-based predictive controller to control the neutralization process using a continuous stirred tank reactor (CSTR). In the first stage of the proposed strategy, a nonlinear autoregressive moving average model will be developed to model the CSTR's nonlinearities, sensitive, and dynamic behavior. The training of the NN model is based on Levenberg-Marquardt algorithm. Then, for the developed model, a feedback linearization-based controller will be designed. The performance evaluation of the proposed modeling will be done on R2 and mean square errors. Moreover, the performance of the proposed control strategy will be evaluated and compared with the benchmark control law for set-point tracking. Furthermore, the numerical evaluation will be done using step-response characteristics such as rise, settling, and overshoot. © 2022 Elsevier Inc. All rights reserved.
date: 2022
publisher: Elsevier
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85137553296&doi=10.1016%2fB978-0-323-90789-7.00008-7&partnerID=40&md5=ac240fd2a5fc351e8e560de4dc2c7f1e
id_number: 10.1016/B978-0-323-90789-7.00008-7
full_text_status: none
publication: Smart Electrical and Mechanical Systems: An Application of Artificial Intelligence and Machine Learning
pagerange: 237-258
refereed: TRUE
isbn: 9780323907897; 9780323914413
citation:   Bingi, K. and Prusty, B.R. and Ibrahim, R.  (2022) Machine learning application to industrial control systems.     Elsevier, pp. 237-258.  ISBN 9780323907897; 9780323914413