Proactive and Predictive Maintenance of Cyber-Physical Systems

Abstract

The following chapter describes a concept model for proactive decision support system based on (real-time) predictive analytics and designed for maintenance of cyber-physical systems (CPSs) in order to optimize its downtime. This concept later is referred to as proactive and predictive maintenance decision support systems or P2M for short. The concept is based on (i) the axioms of predictive decisions making, (ii) the proactive computing principles and (iii) models and methods for intelligent data processing. The aforementioned concept extends an idea of data-driven intelligent systems by using two approaches. The first approach implements predictive analytics, i.e. detection of a pre-failure event (called a proactive event) over a certain time period. This approach is based on the sequence of the following operational processes: to detect–to predict–to decide–to act. The second approach helps to automate maintenance decisions, which allows to exclude operational roles and move to supervisory level positions in the operational management structure. The concept includes the following primary components: ontology, a data warehouse (data lake), data factory as a set of data processing methods, flexible pipelines for data handling and processing and business processes with predictive decision logic for cyber-physical systems maintenance. This concept model is considered as the platform for the design of cyber-physical asset performance management systems.