2025 AIChE Annual Meeting

Session: 10E Process Monitoring & Fault Detection

This session seeks novel contributions in the broad areas of process monitoring, fault detection, isolation, estimation and accommodation in process systems. Both data-driven and model-based approaches are welcome. Applications to industrial processes are encouraged.

Chair

Styliani Avraamidou, Texas A&M University

Co-Chairs

Ivan Castillo, The Dow Chemical Company
Yankai Cao, The University of British Columbia
Ravendra Singh, Rutgers, The State University of New Jer

Presentations

02:30 PM

(711a) Real-Time Risk-Based Control: Integrating Deterministic Risk Indicators and Probabilistic Safety Constraints for Safe and Efficient Hydrogen Production
Sahithi Srijana Akundi, Yuanxing Liu, Austin Braniff, Beatriz Dantas, Shayan Niknezhad, Yuhe Tian, Faisal Khan, Efstratios Pistikopoulos

02:51 PM

(711b) A Digital Twin Simulator of a Pastillation Process with Applications to Computer Vision-Based Control
Leonardo Gonzalez, Joshua Pulsipher, Shengli Jiang, Angan Mukherjee, Tyler Soderstrom, Victor M. Zavala

03:12 PM

(711c) Development of a Health Monitoring Framework to Predict Oxide Scale Formation in Boiler Components Using Hybrid First Principles-Artificial Intelligence Models
Vivek Saini, Debangsu Bhattacharyya

03:33 PM

(711d) Robust and Efficient Fault Diagnosis in Chemical Processes Via Model Ensemble and Neural Network Pruning
Jingkang Liang, Gurkan Sin

03:54 PM

(711e) Data-Based Estimation and Mitigation of Distributed Sensor Faults in Nonlinear Process Networks: Centralized Vs. Decentralized Implementation Strategies
Aatam Gajjar, Nael El-Farra

04:15 PM

(711f) A Graph-Based Modeling Framework for Cooling System Availability Analysis and Component Isolation in Modular Data Centers
Aniket Nitin Deore, Aatam Gajjar, Matthew Ellis

04:36 PM

(711g) Variable?Wise Autoencoder Framework for Real-Time Monitoring and Fault Diagnosis of Chemical Process Startups
Bahareh Hassani, Yajun Wang, Ankur Kumar, Jesus Flores-Cerrillo, Jin Wang, Q. Peter He