"Where is My Troubleshooting Procedure?": Studying the Potential of RAG in Assisting Failure Resolution of Large Cyber-Physical System
For operators in complex industrial environments, this work explores a conversational AI tool to speed up incident response, though results are preliminary and domain-specific.
The paper investigates the use of Retrieval Augmented Generation (RAG) to help operators retrieve troubleshooting procedures from technical manuals in large cyber-physical systems, finding that RAG can assist prompt failure response but requires cross-validation of recommendations.
In today's complex industrial environments, operators must often navigate through extensive technical manuals to identify troubleshooting procedures that may help react to some observed failure symptoms. These manuals, written in natural language, describe many steps in detail. Unfortunately, the number, magnitude, and articulation of these descriptions can significantly slow down and complicate the retrieval of the correct procedure during critical incidents. Interestingly, Retrieval Augmented Generation (RAG) enables the development of tools based on conversational interfaces that can assist operators in their retrieval tasks, improving their capability to respond to incidents. This paper presents the results of a set of experiments that derive from the analysis of the troubleshooting procedures available in Fincantieri, a large international company developing complex naval cyber-physical systems. Results show that RAG can assist operators in reacting promptly to failure symptoms, although specific measures have to be taken into consideration to cross-validate recommendations before actuating them.