Bridging Data and Diagnostics: A Systematic Review and Case Study on Integrating Trend Monitoring and Change Point Detection for Wind Turbines

Abstract

Wind turbines face significant operational challenges due to their complex electromechanical systems, exposure to harsh environmental conditions, and high maintenance costs. Reliable structural health monitoring and condition monitoring are therefore essential for early fault detection, minimizing downtime, and optimizing maintenance strategies. Traditional approaches typically rely on either Trend Monitoring (TM) or Change Point Detection (CPD). TM methods track the long-term behaviour of process parameters, using statistical analysis or machine learning (ML) to identify abnormal patterns that may indicate emerging faults. In contrast, CPD techniques focus on detecting abrupt changes in time-series data, identifying shifts in mean, variance, or distribution, and providing accurate fault onset detection. While each approach has strengths, they also face limitations: TM effectively identifies fault type but lacks precision in timing, while CPD excels at locating fault occurrence but lacks detailed fault classification. This review critically examines the integration of TM and CPD methods for wind turbine diagnostics, highlighting their complementary strengths and weaknesses through an analysis of widely used TM techniques (e.g., Fast Fourier Transform, Wavelet Transform, Hilbert–Huang Transform, Empirical Mode Decomposition) and CPD methods (e.g., Bayesian Online Change Point Detection, Kullback–Leibler Divergence, Cumulative Sum). By combining both approaches, diagnostic accuracy can be enhanced, leveraging TM’s detailed fault characterization with CPD’s precise fault timing. The effectiveness of this synthesis is demonstrated in a case study on wind turbine blade fault diagnosis. Results shows that TM–CPD integration enhances early detection through coupling vibration and frequency trend analysis with robust statistical validation of fault onset.