The development of condition monitoring systems often follows a modular scheme where some systems are already embedded in certain equipment by their manufacturers, and some are distributed across various equipment and instruments. This work introduces a framework for guiding the modular development of monitoring systems and integrating them into a comprehensive model that can handle uncertainty of predictions from the constituent modules. Furthermore, this framework improves the robustness of the modular condition monitoring systems as it provides a methodology for maintaining quality assurance and preventing unnecessary shutdowns in the event of some modules going off-line due to condition-based maintenance interventions.
Keywords: Bayesian; Condition Monitoring; Machine Learning; Modular; Probabilistic Programming.