Augmenting the Existing CBPM Maintenance Philosophy Currently in Use in the Marine Sector with Intelligent Predictive—CBPM Philosophy

Abstract

The maintenance philosophy of equipment/system used in maritime environment which is highly corrosive follows CBPM (Condition-Based Predictive Maintenance) philosophy, where the maintenance of any equipment/system is based on the existing running condition of the same. Based on the running condition of the equipment/system, they are subjected to maintenance so as to have enhanced exploitation of the equipment/system. Among the various maintenance philosophy of equipment/system in our ecosystem, predictive maintenance has become a widely used term and the same is finding deep roots in maritime applications. The concept of predictive maintenance is being constantly updated by engineers and researchers based on monitoring historical data, modelling, simulation, and failure probabilities to predict fault and system deterioration over their useful life. Leveraging on various existing data science techniques and thereby sensor adaptation(s), the current paper proposes real-time predictive analytical techniques using R/PYTHON/JULIA and its associated libraries, such that the source of defect is localized thereby resulting in enhanced and better exploitation of the equipment/system with minimal downtime. The authors et al. are of the opinion that the real-time (existing) CBPM techniques that are currently being followed in maritime environment are time-consuming and require enhanced level of human monitoring and intervention for enhanced exploitation of the same. The authors et al. have also designed a customized self-healing RS (Recommender System) that liquidates majority of problems onboard a marine vessel utilizing advanced ML concepts and the same also recommending to the watchkeeper/EOW/Bridge in audio/video mode of possible upcoming defects on any maritime equipment/system.