Integrating Artificial Intelligence/Machine Learning in Failure Reporting, Analysis, and Corrective Action Systems

This paper introduces a novel concept aimed at using Artificial Intelligence and Machine Learning (AI / ML) to enhance operational efficiency using a Failure Reporting, Analysis, and Corrective Action system (FRACA). Over a few decades, failure data, with root cause, and the associated corrective actions have been collected in several databases and spreadsheets. This paper will explore the critical role of a FRACA system in enhancing operational reliability and efficiency across various industries. Our theory is that by systematically capturing failure data, analyzing root causes, and implementing corrective actions, a FRACA system combined with AI /ML can not only mitigate the risk of future failures but also fosters a culture of continuous improvement and efficiency. The proposed idea is currently in the exploration phase, with the potential to evolve into a practical tool designed to streamline the process of utilizing the associated data collected when managing failures. In the current process, there are repetitive steps that require human interaction as part of the process. Those steps have been identified as candidates that AI / ML would be beneficial. A proof-of-concept project has been established to implement an AI /ML solution that will address the identified inefficiencies of these repetitive tasks. Plans have been established to continue fully enhancing capability. It is important to note that, as of now, no empirical testing or validation has been conducted to assess its effectiveness. Developing AI / ML solutions for unique products and systems takes significant effort to plan out. Future research and experimentation is necessary to determine its viability, practical application, and solve challenging implementation. Developing automated capabilities, predictive models, and best practices will aide in realizing efficiency, accuracy, and early detection with product failures. Iterations of this paper will include results and updates from that experimentation to assess the effectiveness of the tool.