Hybrid data-driven and first principles monitoring applied to the Tennessee Eastman process

Eduardo Iraola, José M. Nougués, Dr. Ehecatl Antonio del Rio Chanona, Lluís Batet, Luis Sedano
January 2023
Cite DOI URL

Abstract

In this work we present a hybrid monitoring approach for fault detection using the Tennessee Eastman (TE) process. We benchmark our proposed approach against previous methods in the available literature and analyze the benefits and shortcomings. The hybrid monitoring approach contains two steps. First, from a model-based perspective, a dynamic model of the TE plant is constructed using commercial dynamic simulation software and data is generated from the TE plant and its model. In the second step, a data-driven analysis is conducted. This involves training different fault detection models with the previously obtained datasets to detect plant faults as early as possible. The results show that combining datasets can improve the traditional pure data-driven monitoring performance with only plant data. This work highlights the usefulness of combining process modeling and machine learning in the monitoring and prognostics fields when data availability from the actual process is limited.

Type
Book section
Publication
Computer Aided Chemical Engineering
Aspen HYSYS fault detection Machine learning monitoring Tennessee Eastman
Dr. Ehecatl Antonio del Rio Chanona
Dr. Ehecatl Antonio del Rio Chanona
Principal Investigator of OptiML

Antonio del Rio Chanona is the head of the Optimisation and Machine Learning for Process Systems Engineering group based in thee Department of Chemical Engineering, as well as the Centre for Process Systems Engineering at Imperial College London. His work is at the forefront of integrating advanced computer algorithms from optimization, machine learning, and reinforcement learning into engineering systems, with a particular focus on bioprocess control, optimization, and scale-up. Dr. del Rio Chanona earned his PhD from the Department of Chemical Engineering and Biotechnology at the University of Cambridge, where his outstanding research earned him the prestigious Danckwerts-Pergamon award for the best PhD dissertation of 2017. He completed his undergraduate studies at the National Autonomous University of Mexico (UNAM), which laid the foundation for his expertise in engineering.