A novel architecture and system for the provision of Reliability Centred Maintenance (RCM) for offshore wind power generation is presented. The architecture was developed by conducting a bottom-up analysis of the data required to support RCM within this specific industry, combined with a top-down analysis of the required maintenance functionality. The architecture and system consists of three integrated modules for intelligent condition monitoring, reliability and maintenance modelling, and maintenance scheduling that provide a scalable solution for performing dynamic, efficient and cost-effective preventative maintenance management within this extremely demanding renewable energy generation sector. The system demonstrates for the first time the integration of state-of-the-art advanced mathematical techniques: Random Forests, dynamic Bayesian networks and memetic algorithms in the development of an intelligent autonomous solution. The results from the application of the intelligent integrated system illustrated the automated detection of faults within a wind farm consisting of over 100 turbines, the modelling and updating of the turbines' survivability and creation of a hierarchy of maintenance actions, and the optimizing of the maintenance schedule with a view to maximizing the availability and revenue generation of the turbines.

Many renewable sources of energy can harness greater uptime and power output when located in remote and potentially hostile locations. One example of this is wind power, wherein turbines positioned at offshore locations can experience higher and more sustained windspeeds than their onshore counterparts. However, these traits also lead to increased load and degradation upon components, which in turn means that regular maintenance is required. While onshore maintenance costs are relatively trivial, the costs associated with offshore maintenance can be several orders-of-magnitude greater.Traditionally, the scheduling of these repairs is performed by hand using a set of pre-determined plans for specific fault-categories (e.g. trivial/minor/major component replacement). This paper formulates this problem as a PDDL domain which encapsulates all of the individual pre-defined plans in a single representation, such that multiple levels of response can be integrated in a single plan. The domain presented is complex in that it contains not only numeric and temporal planning aspects, but that a subset of the domain is heavily geared towards pure scheduling. We include performance results on how a state-of-the-art planner performs on various example scenarios.