Email the Author

About the Book

This book is designed to help readers gain a working-level knowledge of machine learning-based dynamic process modeling techniques that have proven useful in process industry. Readers can leverage the concepts learned to build advanced solutions for process monitoring, soft sensing, inferential modeling, predictive maintenance, and process control for dynamic systems. The application-focused approach of the book is reader friendly and easily digestible to the practicing and aspiring process engineers, and data scientists. The authors of this book have drawn from their years of experience in developing data-driven industrial solutions to provide a guided tour along the wide range of available ML methods and declutter the world of machine learning for dynamic process modeling. Applications on time series analysis, process disturbance modeling, system identification, and process fault detection are illustrated with examples. Upon completion, readers will be able to confidently navigate the system identification literature and make judicious selection of modeling approaches suitable for their problems.

This book has been divided into three parts. Part 1 of the book provides perspectives on the importance of ML for dynamic process modeling and lays down the basic foundations of ML-DPM (machine learning for dynamic process modeling). Part 2 provides in-detail presentation of classical ML techniques (such as ARX, FIR, OE, ARMAX, ARIMAX, CVA, NARX, etc.) and has been written keeping in mind the different modeling requirements and process characteristics that determine a model’s suitability for a problem at hand. These include, amongst others, presence of multiple correlated outputs, process nonlinearity, need for low model bias, need to model disturbance signal accurately, etc. Part 3 is focused on artificial neural networks and deep learning.

The following topics are broadly covered:

·       Exploratory analysis of dynamic dataset

·       Best practices for dynamic modeling

·       Linear and discrete-time classical parametric and non-parametric models

·       State-space models for MIMO systems

·       Nonlinear system identification and closed-loop identification

·       Neural networks-based dynamic process modeling 

If you do not have a PayPal account, you can purchase the book at Google Play.

About the Authors

Ankur Kumar

Ankur Kumar holds a PhD degree (2016) in Process Systems Engineering from the University of Texas at Austin and a bachelor’s degree (2012) in Chemical Engineering from the Indian Institute of Technology Bombay. He currently works at Linde in the Advanced Digital Technologies & Systems Group in Linde’s Center of Excellence, where he has developed several in-house machine learning-based monitoring and process control solutions for Linde’s hydrogen and air-separation plants. Ankur’s tools have won several awards both within and outside Linde. One of his tools, PlantWatch (a plantwide fault detection and diagnosis tool), received the 2021 Industry 4.0 Award by the Confederation of Industry of the Czech Republic. Ankur has authored or co-authored several peer-reviewed journal papers (in the areas of data-driven process modeling and monitoring), is a frequent reviewer for many top-ranked Journals, and has served as Session Chair at several international conferences. Ankur served as an Associate Editor of the Journal of Process Control from 2019 to 2021. Most recently, he was included in the ‘Engineering Leaders Under 40, Class of 2023‘ by Plant Engineering Magazine.

Jesus Flores Cerrillo

Jesus Flores-Cerrillo is currently an Associate Director - R&D at Linde and manages the Advanced Digital Technologies & Systems Group in Linde’s Center of Excellence. He has over 20 years of experience in the development and implementation of monitoring technologies and advanced process control & optimization solutions. Jesus holds a PhD degree in Chemical Engineering from McMaster University and has authored or co-authored more than 40 peer-reviewed journal papers in the areas of multivariate statistics and advanced process control among others. His team develops and implements novel plant monitoring, machine learning, IIOT solutions to improve the efficiency and reliability of Linde’s processes. Jesus’s team received the Artificial Intelligence and Advanced Analytics Leadership 2020 award from the National Association of Manufacturers’ Manufacturing Leadership Council.