Enabling cognitive predictive maintenance using machine learning: Approaches and design methodologies

Abstract

Asset reliability and 100% availability of machines are a competitive business advantage in complex industrial environment as they play a vital role in improving productivity. Preventive maintenance models help to identify the performance degradation or failure of machines well ahead to prevent unscheduled breakdown of machines. However, lack of knowledge in identifying the root cause or the lack of knowledge to fix the problem may delay the corrective actions, which in turn impacts the productivity. To overcome this problem, cognitive predictive maintenance model is proposed which helps in classifying and recommending corrective actions along with predicting time to failure of machine. We discussed in detail about building a cognitive system using rule-based bottom-up approaches. We also presented the high-level design of a system to build a software solution using open-source technologies.