Condition based maintenance optimization for offshore wind turbine considering opportunities based on neural network approach

Abstract

A well-established condition-based maintenance (CBM) method based on condition monitoring information can be used to reduce maintenance costs by decimating unnecessary maintenance actions, reducing system downtime, and minimizing unexpected failures. In this paper, we propose an opportunistic CBM optimization approach for offshore wind turbines (OWTs) in which economic dependence exists among the components that are subjected to condition monitoring. An artificial neural network is used to predict life percentage by leveraging the condition monitoring information. A conditional failure probability value that is derived from the predicted failure-time distribution of the component was adopted to represent the deterioration of OWTs. Our maintenance method can be defined by a threshold with two-level failure probability. We propose a simulation method that can be used to calculate the optimal threshold values to minimize the long-term maintenance cost. Failure information and maintenance cost of OWTs are collected from existing articles to illustrate the proposed approach. Results show that the opportunistic CBM strategy can be effective and is established in the wind power industry. Moreover, the expense comparison between onshore and offshore WTs demonstrates the importance of this method.