A review of failure prognostics for predictive maintenance of offshore wind turbines

Abstract

Offshore wind turbines (OWTs) are important facilities for wind power generation because of their low land use and high electricity output. However, the harsh environment and remote location of offshore sites make it difficult to conduct maintenance on turbines. To upkeep OWTs cost-effectively, predictive maintenance (PdM) is an appealing strategy for offshore wind industry. The heart of PdM is failure prognostics, which aims to predict an asset’s remaining useful life (RUL) based on condition monitoring (CM). To provide references to PdM of OWTs, this paper presents a systematic review of failure prognostic models for wind turbines. In this review, data-driven models, model-based models, and hybrid models are classified and presented for model selection. The findings reveal that it is promising to develop hybrid models in the future and combine the advantages of data-driven and model-based models. Currently, the internal combinations of machine learning methods and statistical approaches in data-driven models are more common than exterior linkages between data-driven models and model-based models. The limitations and strengths of different models are discussed, and opportunities for developing hybrid models are highlighted in the conclusion.

Challenges on prognostics and health management for wind turbine components

“…Hybrid models represent a combination of the aforementioned approaches. According to Zhang et al [8], these combinations can be classified in three main types: machine learning (ML)stats model, stats-physics model and other hybrid models. They get the positive aspects of each type of model while minimizing their respective limitations.…”

“…They get the positive aspects of each type of model while minimizing their respective limitations. Results obtained from hybrid models have shown higher interpretability and intuitiveness compared to data-driven models [8], which are often considered as black boxes due to their lack of explainability. In this context, explainable artificial intelligence algorithms have raised to explain the predictions, such as local interpretable model-agnostic explanations or Shapley additive explanation methods, which help hybrid models to gain explainability [49].…”

Limitations and Opportunities in PHM for Offshore Wind Farms: A Socio-Technical-Ecological System Perspective

“…These data sources, combined with diverse analytics and machine learning (ML) techniques, facilitate fault detection, diagnosis, prognosis, and health management across OWFs. Recent years have witnessed notable progress in deploying various methodologies, including stochastic modeling (Cao, L., Qian, Z., Zareipour, H., Wood, D., Mollasalehi, E. A comprehensive evaluation of these techniques, encompassing an assessment of their strengths, limitations, and potential for hybrid models, has been meticulously presented by (Zhang, W., Vatn, J., & Rasheed, A. (2022)).…”