Lee, Won Je Na, Jonggeol Kim, Kyeongsu Lee, Chul-Jin Lee, Younggeun Lee, Jong Min 2024-01-19T22:04:58Z 2024-01-19T22:04:58Z 2021-09-03 2018-07-12 0098-1354 https://pubs.kist.re.kr/handle/201004/121153 This study considers the Nonlinear Autoregressive eXogenous Neural Net model (NARX NN) based real-time optimization (RTO) for industrial-scale air & gas compression system in a commercial terephthalic acid manufacturing plant. NARX model is constructed to consider time-dependent system characteristics using actual plant operation data. The prediction performance is improved by extracting the thermodynamic characteristics of the chemical process as a feature of this model. And a systematic RTO method is suggested for calculating an optimal operating condition of compression system by recursively updating the NARX model. The performance of the proposed NARX model and RTO methodology is exemplified with a virtual plant that simulates the onsite commercial plant with 99.6% accuracy. NARX with feature extraction model reduces mean squared prediction error with the actual plant data 43.5% compared to that of the simple feed-forward multi-perceptron neural networks. The proposed RTO method suggests optimal operating conditions that reduce power consumption 4%. (c) 2018 Elsevier Ltd. All rights reserved. English PERGAMON-ELSEVIER SCIENCE LTD NEURAL-NETWORK SUPERSTRUCTURE PREDICTION NARX modeling for real-time optimization of air and gas compression systems in chemical processes Article 10.1016/j.compchemeng.2018.04.026 1 COMPUTERS & CHEMICAL ENGINEERING, v.115, pp.262 - 274 COMPUTERS & CHEMICAL ENGINEERING 115 262 274 scie scopus 000439701900022 2-s2.0-85046680781 Computer Science, Interdisciplinary Applications Engineering, Chemical Computer Science Engineering Article NEURAL-NETWORK SUPERSTRUCTURE PREDICTION NARX NN Real time optimization Multi-stage compressor Industrial scale plant Process systems engineering