Machine Learning-Based Dynamic Modeling for Process Engineering Applications: A Guideline for Simulation and Prediction from Perceptron to Deep Learning

Carine M. Rebello; Paulo H. Marrocos; Erbet A. Costa; Vinicius V. Santana; Alírio E. Rodrigues; Ana M. Ribeiro; Idelfonso B. R. Nogueira

LAPSE:2023.2927

Published Article

LAPSE:2023.2927

Machine Learning-Based Dynamic Modeling for Process Engineering Applications: A Guideline for Simulation and Prediction from Perceptron to Deep Learning

Carine M. Rebello, Paulo H. Marrocos, Erbet A. Costa, Vinicius V. Santana, Alírio E. Rodrigues, Ana M. Ribeiro, Idelfonso B. R. Nogueira

February 21, 2023

Abstract
A misusage of machine learning (ML) strategies is usually observed in the process systems engineering literature. This issue is even more evident when dynamic identification is performed. The root of this problem is the gradient explode and vanishing issue related to the recurrent neural networks training. However, after the advent of deep learning, these issues were mitigated. Furthermore, the problem of data structuration is often overlooked during the machine learning model identification in this field. In this scenario, this work proposes a guideline for identifying ML models for the different applications in process systems engineering, which are usually for simulation or prediction purposes. While using the proposed guideline, the work also identifies a virtual analyzer for a pressure swing adsorption unit. In these types of adsorption separations, it is usual that the measurement of the main properties is not done online. Therefore, the virtual analyzer is another contribution of this manuscript. The overall results demonstrate that even though the test provides good performance during the ML model identification, its quality might degenerate over the application domain if the model application is overlooked.

Record ID

LAPSE:2023.2927

Keywords

deep learning, Dynamic Modelling, Machine Learning, pressure swing adsorption

Subject

Modelling and Simulations

Suggested Citation

Rebello CM, Marrocos PH, Costa EA, Santana VV, Rodrigues AE, Ribeiro AM, Nogueira IBR. Machine Learning-Based Dynamic Modeling for Process Engineering Applications: A Guideline for Simulation and Prediction from Perceptron to Deep Learning. (2023). LAPSE:2023.2927

Author Affiliations

Rebello CM: Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; Departamento de Engenharia Química, Escola [ORCID]
Marrocos PH: Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
Costa EA: Departamento de Engenharia Química, Escola Politécnica (Polytechnic School), Universidade Federal da Bahia, Salvador 40210-630, Brazil [ORCID]
Santana VV: Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
Rodrigues AE: Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal [ORCID]
Ribeiro AM: Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
Nogueira IBR: Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE/LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal [ORCID]

Journal Name

Processes

Volume

10

Issue

2

First Page

250

Year

2022

Publication Date

2022-01-27