Real-time maintenance prioritization with learning capability

This paper presents a radical approach for real-time maintenance prioritization where the main idea is drawn from neuroscience studies. In this approach, maintenance prioritization is a product of a learning process. Failures and maintenance experiences are learned from and applied through “habituation” and “gist generation”. During real-time operations, the knowledge is retrieved when maintenance prioritization is demanded. The brain's “dual-process” model is applied as the basic framework for conducting maintenance prioritization. The central processing unit, e.g., the “slow brain”, conducts high-fidelity analyses and prioritizes equipment according to their “criticality”. The distributed processing units, e.g., the “fast brain”, provide efficient reactions in real time. These two processes work in parallel to ensure the performance of the real-time maintenance prioritization. A prototyping tool has been developed to demonstrate the concepts.