Condition-Based Maintenance Scheduling Using Probability Distribution Function and Agglomerative Hierarchical Clustering Approaches: AI-Driven Predictive Maintenance Mapping

Advanced industries such as wind turbines aim for condition-based maintenance (CBM) to enhance system availability and reach higher revenue. Hence, decision making plays an essential role in optimizing the maintenance planning process and achieving a more reliable system. In this work, a hierarchical decision process using remaining useful life (RUL) information is introduced for the maintenance scheduling of wind farms. Real-time condition monitoring and failure prognosis are conducted through a Bayesian approach to obtain probability distribution functions (PDFs) for the faulty turbines/components and predict their associated RUL. Following that, an augmented probability model is built by adding the RULs to create a feature map for maintenance. Finally, hierarchical clustering is applied to schedule maintenance times by setting certain planning policy rules using a dendrogram chart along with the wind farm information. This work’s main contribution is that the proposed decision process includes PDFs of faulty turbines used to deliver an optimized maintenance schedule based on the suggested probability feature map. In addition, the hierarchical clustering using wind farm information enhances wind turbine availability and reduces maintenance costs. Field data from wind turbines located in Chile confirm the superior performance of the proposed hierarchical decision policy in comparison with the conventional corrective maintenance strategy.