2025 AIChE Annual Meeting

Session: 10B: AI/ML and Data-Driven Estimation and Optimization for Control

This session highlights techniques that use data, AI, and ML to conduct tasks such as state/parameter estimation and optimization in the context of control. Emerging techniques from data science and machine learning as well as approaches that combine data with first-principles models are encouraged.

Chair

Co-Chairs

Vivek Saini, West Virginia University
Angan Mukherjee, West Virginia University
Styliani Avraamidou, Texas A&M University

Presentations

08:00 AM

(644a) Sample Complexity Bounds for Linear System Identification without Sub-Gaussianity and Iid Assumptions
Xiaomian Yang, Sungho Shin

08:18 AM

(644b) Neural Luenberger Observer for Nonlinear Systems with External Inputs (Neural LOX)
Jarod Morris, Moritz Woelk, Cormak Weeks, Wentao Tang

08:36 AM

(644c) A Simultaneous Approach for Training Neural Differential-Algebraic Systems of Equations
Laurens Lueg, Victor Alves, John Kitchin, Carl Laird, Lorenz Biegler

08:54 AM

(644d) Graph Convolutional Network (GCN)-Based Adaptive Distributed Model Predictive Control
Elliot Cooper, Andrew Allman

09:12 AM

(644e) Deep-Learning-Aided Modifier Adaptation for Real-Time Optimization
Gabriel Patron, Calvin Tsay, Luis Ricardez-Sandoval

09:30 AM

(391a) Dynamic Simulation and Control of a Dry Reforming Plant for Methanol Production: Dual Effects of Feedstock Variability and Operational Turndown
Omar Almaraz, Md Mizanur Rahman, Srinivas Palanki

09:48 AM

(644g) Data-Driven Synthesis of Nonlinear State Observer through Estimation of Koopman Eigenfunctions
Angela Ni, Wentao Tang

10:06 AM

(644h) Development of a Framework for Automatic Discovery of Optimal Hybrid First Principles - Machine Learning Models
Angan Mukherjee, Nishant Vinayak Giridhar, Debangsu Bhattacharyya