AI-Enhanced Operator Assistance for UNICOS Applications
Bernard Tam, Jean-Charles Tournier, Fernando Varela Rodriguez
TL;DR
This work introduces an AI-enhanced operator assistant for CERN's UNICOS systems, addressing widget decoding, root-cause analysis, and datapoint tracing through a modular multi-agent architecture. The solution combines a UNICOS-side CTRL extension with a Python VM-based supervisor and three specialized agents, all backed by a vector database for operator documentation and animation code, enabling retrieval-augmented reasoning (RAG) and multi-modal inputs. Empirical results demonstrate automated widget decoding, live-data-informed root-cause analysis, and traceable DPE mapping to widget animations, reducing operator workload and speeding diagnostics. The approach provides a practical foundation for intelligent, assistive HMIs in accelerator operations, with clear avenues for CERN-specific model fine-tuning, broader vector-database applications, and CI/CD integration newly enabling up-to-date, scalable AI assistance.
Abstract
This project explores the development of an AI-enhanced operator assistant for UNICOS, CERN's UNified Industrial Control System. While powerful, UNICOS presents a number of challenges, including the cognitive burden of decoding widgets, manual effort required for root cause analysis, and difficulties maintainers face in tracing datapoint elements (DPEs) across a complex codebase. In situations where timely responses are critical, these challenges can increase cognitive load and slow down diagnostics. To address these issues, a multi-agent system was designed and implemented. The solution is supported by a modular architecture comprising a UNICOS-side extension written in CTRL code, a Python-based multi-agent system deployed on a virtual machine, and a vector database storing both operator documentation and widget animation code. Preliminary evaluations suggest that the system is capable of decoding widgets, performing root cause analysis by leveraging live device data and documentation, and tracing DPEs across a complex codebase. Together, these capabilities reduce the manual workload of operators and maintainers, enhance situational awareness in operations, and accelerate responses to alarms and anomalies. Beyond these immediate gains, this work highlights the potential of introducing multi-modal reasoning and retrieval augmented generation (RAG) into the domain of industrial control. Ultimately, this work represents more than a proof of concept: it provides a basis for advancing intelligent operator interfaces at CERN. By combining modular design, extensibility, and practical AI integration, this project not only alleviates current operator pain points but also points toward broader opportunities for assistive AI in accelerator operations.