Angan Mukherjee

Boiler Health Monitoring using a Hybrid First Principles - Artificial Intelligence Model

My primary research interests include process control, simulation and dynamic optimization. My PhD project seeks to exploit the advantages of first-principles and AI models by synergistically coupling them to construct stochastic, dynamic, physics-constrained neural network (NN) models that can be adapted online for dynamic modelling and control of highly complex nonlinear chemical processes. I will also explore the stability properties of data-driven learning algorithms and necessary and sufficient conditions for parameter estimation, without violating mass and energy balances as well as thermodynamic constraints. Nonlinear static-dynamic NN architectures will be constructed with desired approximation capabilities with the development of normalized Gaussian RBF network models and Bayesian ML algorithms for recursive learning.  

Dissertation: Development of Dynamic Mass-Energy-Thermodynamics Constrained Hybrid Neural Network Models for Process Systems Applications

• Mukherjee A, Bhattacharyya D, “Hybrid Series/Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes”, 62, 3221-3237, Industrial & Engineering Chemistry Research, 2023

• Mukherjee A, Bhattacharyya D, "On the Development of Steady-State and Dynamic Mass Constrained Neural Networks using Noisy Transient Data", 187, 108722, Computers & Chemical Engineering, 2024

• Mukherjee A, Bhattacharyya D, "Development of Steady-State and Dynamic Mass and Energy Constrained Neural Networks for Distributed Chemical Systems Using Noisy Transient Data", 63, 14211-14239, Industrial & Engineering Chemistry Research, 2024

• Mukherjee A, Bhattacharyya D, "Development of Steady-State and Dynamic Mass-Energy Constrained Neural Networks using Noisy Transient Data", 3, 330-337, CSChE Systems & Control Transactions, 2024

• Mukherjee A, Saini V, Adeyemo S, Bhattacharyya D, Purdy D, Parker J, Boohaker C, "Development of Hybrid First Principles - Artificial Intelligence Models for Transient Modeling of Power Plant Superheaters under Load-Following Operation", 262, 124795, Applied Thermal Engineering, 2025

• Mukherjee A, Adeyemo S, Bhattacharyya D, "All-Nonlinear Static-Dynamic Neural Networks versus Bayesian Machine Learning for Data-Driven Modelling of Chemical Processes", 103, 1139-1154, The Canadian Journal of Chemical Engineering, 2025

• Mukherjee A, Gupta D, Bhattacharyya D, "Mass-Constrained Hybrid Gaussian Radial Basis Neural Networks: Development, Training, and Applications to Modeling Nonlinear Dynamic Noisy Chemical Processes", 197, 109080, Computers & Chemical Engineering, 2025

• Mukherjee A, Bhattacharyya D, "Development of Mass, Energy, and Thermodynamics Constrained Steady-State and Dynamic Neural Networks for Interconnected Chemical Systems", 309, 121506, Chemical Engineering Science, 2025

• Mukherjee A, Bhattacharyya D, “Development of Steady-State and Dynamic Mass-Energy-Thermodynamics Constrained Neural Network (MET-CNN) Models for Interconnected Systems using Noisy Transient Data”, Paper 14i, AIChE Annual Meeting, San Diego, CA, October 27-31, 2024

• Mukherjee A, Bhattacharyya D, “Development of Steady-State and Dynamic Mass-Energy Constrained Neural Network Models using Noisy Temporal Data for Dynamic Optimization of Distributed Chemical Systems”, Paper 676g, AIChE Annual Meeting, San Diego, CA, October 27-31, 2024 

• Mukherjee A, Bhattacharyya D, “Hybrid Gaussian Radial Basis Neural Networks (GRAB-NN): Development, Training, and Applications to Modeling Nonlinear Dynamic Noisy Chemical Processes”, Paper 674d, AIChE Annual Meeting, San Diego, CA, October 27-31, 2024 

• Mukherjee A, Bhattacharyya D, "Physics-Constrained Machine Learning", Fall 2024 Texas-Wisconsin-California Control Consortium (TWCCC), University of Wisconsin - Madison, Madison, WI, September 23-24, 2024

• Mukherjee A, Bhattacharyya D, “Development of Steady-State and Dynamic Mass-Energy Constrained Neural Networks using Noisy Transient Data”, Foundations of Computer-Aided Process Design (FOCAPD) Conference, Breckenridge, CO, July 14-18, 2024 

• Mukherjee A, Bhattacharyya D, “Development of Algorithms for Mass and Energy Constrained Dynamic Neural Network Models”, 2024 Statler College Research Poster Symposium", West Virginia University, Morgantown, WV, April 5, 2024

• Mukherjee A, Saini V, Adeyemo S, Bhattacharyya D, “Development of Hybrid First Principles - Artificial Intelligence Models: Application to an Industrial Steam Superheater System”, Paper 374d, AIChE Annual Meeting, Orlando, FL, November 5-10, 2023

• Mukherjee A, Bhattacharyya D, “Hybrid Series/Parallel All-Nonlinear Dynamic-Static Stochastic Neural Networks: Development, Training and Application to Chemical Processes”, Paper 149x, AIChE Annual Meeting, Orlando, FL, November 5-10, 2023

• Mukherjee A, Bhattacharyya D, “Development of Algorithms for Mass and Energy Constrained Dynamic Neural Network Models”, Paper 59o, AIChE Annual Meeting, Orlando, FL, November 5-10, 2023

• Mukherjee A, “New Data-Driven Modeling Paradigms in Systems Engineering using Novel Neural Network Structures”, Paper 2dw, AIChE Annual Meeting, Orlando, FL, November 5-10, 2023

• Mukherjee A, Bhattacharyya D, “Development of Algorithms for Mass-Constrained Dynamic Neural Networks”, Foundations of Process/Product Analytics and Machine Learning (FOPAM) Conference, UC Davis, CA, July 30 - Aug 3, 2023

• Mukherjee A, Bhattacharyya D, “Hybrid Series and Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes”, AIChE Midwest Regional Conference, Chicago, IL, April 11 - 12, 2023

• Mukherjee A, Bhattacharyya D, "Modeling CO2 Capture Process using Hybrid Series/Parallel Neural Networks", 2023 Statler College Research Week Annual Open House Poster Symposium", West Virginia University, Morgantown, WV, March 24, 2023

• Mukherjee A, Bhattacharyya D, “Hybrid Series / Parallel All-Nonlinear Dynamic-Static Neural Networks: Development, Training, and Application to Chemical Processes”, Statler Research Forum for Artificial Intelligence, West Virginia University, Morgantown, WV, December 6, 2022

• Mukherjee A, Bhattacharyya D, “Development of Mass and Energy Constrained Neural Networks”, Paper 12b, AIChE Annual Meeting, Phoenix, AZ, November 13-18, 2022

• Mukherjee A, Bhattacharyya D, “Data-Driven Modeling of Complex Nonlinear Systems using Hybrid Series and Parallel Nonlinear Static - Nonlinear Dynamic Stochastic Neural Networks”, Paper 362p, AIChE Annual Meeting, Phoenix, AZ, November 13-18, 2022

• Mukherjee A, Bhattacharyya D, “Data-Driven Modeling of Complex Nonlinear Systems Using Hybrid Series and Parallel Nonlinear Static-Nonlinear Dynamic Neural Networks”, AIChE Advanced Manufacturing and Processing Conference, Bethesda, MD, June 1 - 3, 2022 

• Mukherjee A, Bhattacharyya D, “Modeling Complex Nonlinear Systems using Hybrid Static-Dynamic Neural Networks”, 2022 Research Week Open House Poster Session, West Virginia University, Morgantown, WV, April 12, 2022 

• Mukherjee A, Bhattacharyya D, “Modeling Complex Nonlinear Systems Using Concatenated Static-Dynamic Neural Networks”, Paper 415a, AIChE Annual Meeting, Boston, MA, November 7-19, 2021 

• Mukherjee A, Bhattacharyya D, “Development of a Hybrid First Principles–Artificial Intelligence Approach for Dynamic Modeling of Complex Systems”, Virtual AIChE Annual Meeting, November 16-20, 2020