OperAItor: An Agentic Framework for Fault-Tolerant Operation of Chemical Processes
eess.SY, cs.AI, cs.SY
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/AISL-at-Imperial-College-London/operAItor
Project page: https://aisl-at-imperial-college-london.github.io/operAItor
License: http://creativecommons.org/licenses/by/4.0/
The gist: OperAItor, an open-source framework for developing and evaluating large language model agents for supervisory fault management in chemical processes.
Terminology
Abstract
OperAItor, an open-source framework for developing and evaluating large language model agents for supervisory fault management in chemical processes. The framework is demonstrated on a dynamic reactor-distillation process representing isopropanol dehydrogenation, with physically based thermodynamics and modified reaction kinetics to permit liquid-phase operation. The process is represented by a 113-variable differential-algebraic model and operates at a nominal feed rate of 100kmol/h, producing approximately 4t/h of acetone. The simulated plant includes 8 PI control loops, 22 process alarms, 5 duty-standby pump trains, and 11 independent safety instrumented functions. The agent architecture integrates multivariate statistical process monitoring, fault diagnosis, knowledge-graph retrieval, action planning, and supervisory action generation. Five action-validation configurations are investigated, comprising operation without validation, an LLM-based judge, digital-twin simulation, and deterministic admissibility checks with and without consequence projection. The framework is evaluated using four LLMs across 20 scenarios involving single and multiple simultaneous faults. Without agent intervention, 18 scenarios result in plant stops, corresponding to an economic loss of 399,000 relative to fault-free operation under the assumed benchmark economics. For GPT-5 nano, Qwen3 8B, and Mistral 7B, validated agent configurations reduce the number of stops to 5-8 and recover 265,000 of the loss. The study provides a reproducible benchmark for comparing agent architectures, language models, and action-validation methods for supervisory fault management in chemical processes.
Sources
- The Llama 3 Herd of Models
- Mistral 7B
- ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories
- From Detection to Action: Using LLM Agents for Fault-Tolerant Control
- Autonomous Industrial Control using an Agentic Framework with Large Language Models
- Qwen3 Technical Report
Related papers
- Industrial Load Modeling and Optimization for Market-Based Interaction with Power Systems
- Exact and Approximate Convex Reformulation of Linear Stochastic Optimal Control with Chance Constraints
- Certified Set Convergence for Piecewise Affine Systems
- Symbolic Control for Stochastic Systems via Finite Parity Games
- Multiobjective optimization-based design and dispatch of islanded, hybrid microgrids for remote, off-grid communities in sub-Saharan Africa
- Physiology-informed layered sensing for intelligent human-exoskeleton interaction