Condition based maintenance is a very promising strategy for management of subsea facilities from a cost and safety perspective. The implementation of condition based maintenance relies on several interacting steps including data collection, data processing, prognostics and decision-making for optimization.

The aim of the project is to focus on the first steps dedicated to data collection and data processing, that is to say on inspection and condition monitoring. Currently, there is a lack of knowledge and methods for optimizing monitoring schedules and efficient use of available condition data in subsea systems.The research questions we propose to address are:

1. For a given condition monitoring and inspection programme, what is the value of added condition information for future decision making?
2. What are the most efficient ways to build models that utilize existing (even poor) data collected from subsea equipment for predictive decisions?
3. How can data intentionally not collected for condition monitoring (such as operating data) be utilised in such models?

In the initial phase the project has focused on a case study of Safety Instrumented Systems (SIS) in low demand mode. Such systems are submitted to periodic inspections (proof testing), that can degrade the condition of system components (a mild type of destructive testing). The goal for the case study is to find the optimum testing frequency, which balances the added value of frequent testing versus the negative effect on wear caused by the testing.The result of the case study can be used to optimize testing strategies for safety critical systems.

Further work will focus on prediction models and tools that integrate different levels and quality of monitoring information. This can be used to optimise systems for instrumentation, data collection and analysis/prediction.