Optimizing resource allocation for wind turbine maintenance through process and fault data fusion

Huiling Li, Cong Liu, Qinjun Du, Qingtian Zeng, Haobing Liu, Qingle Wang, Long Cheng

Abstract: Highlights•Wind turbine maintenance process (WTMP) data are fused with fault data to construct a comprehensive fault-process data. Using this fused fault-process data, a Petri net-based WTMP resource model is discovered.•A cost- and time-aware resource allocation strategy is proposed and a resource-time model is established to allocate the most suitable resources for each maintenance task.•Four state-of-the-art deep learning models (LSTM, GRU, BiLSTM, BiGRU) are implemented on top of the proposed allocation strategy to predict the time and cost of maintenance tasks.•Based on the experimental results, the BiGRU model combined with the proposed allocation strategy achieves the optimized resource allocation.

External IDs:dblp:journals/inffus/LiLDZLWC26