Picture of neon light reading 'Open'

Discover open research at Strathprints as part of International Open Access Week!

23-29 October 2017 is International Open Access Week. The Strathprints institutional repository is a digital archive of Open Access research outputs, all produced by University of Strathclyde researchers.

Explore recent world leading Open Access research content this Open Access Week from across Strathclyde's many research active faculties: Engineering, Science, Humanities, Arts & Social Sciences and Strathclyde Business School.

Explore all Strathclyde Open Access research outputs...

Time series semi-Markov decision process with variable costs for maintenance planning

Dawid, R. and McMillan, D. and Revie, M. (2016) Time series semi-Markov decision process with variable costs for maintenance planning. In: European Safety and Reliability Conference ESREL 2016, 2016-09-25 - 2016-09-29.

Other (Dawid-etal-Esrel2016-Time-series-semi-markov-decision-process)
Dawid_etal_Esrel2016_Time_series_semi_markov_decision_process.PDF - Accepted Author Manuscript

Download (169kB) | Preview


Deciding when and how to maintain offshore wind turbines is becoming even more complex as the size of wind farms increases, while accessibility is challenging compared to onshore wind farms. Planning future maintenance actions requires the wind farm operator to consider factors such as the current condition of the turbine, the cost of a given maintenance action, revenue generated by the asset, weather factors and vessel availability. Rather than making case-by-case decisions for each turbine, the approach described in this paper allows the wind farm operators to automate the process of short to-medium term maintenance planning through application of a Semi-Markov Decision Process (SMDP). The model proposed here is capable of suggesting the cost-optimal maintenance policy given weather forecast, future vessel costs and availability and the current condition of the turbine. Using the semi-Markov approach, allows the user to implement time varying failure rate. As the model is capable of utilising time-series data, future weather and vessel constraints can be applied depending on the information available to the user at the time, which will be reflected in the optimal policy suggested by the model. The model proposed here facilitates maintenance decision making in wind farms and will lead to cost reduction through more efficient planning. In addition to that, the model can be used to carry out a cost-benefit analysis of using vessels with different properties.