Ming Liu

To effectively extract fault characteristics from complex vibration signals and improve the diagnostic performance of deep learning networks, this paper introduces a wind turbine blade fault diagnosis method that combines Multi-scale Enhanced Hierarchical Fuzzy Entropy (MEHFE), Isolation Forest, and the Grey Wolf Optimization (GWO) algorithm for optimizing the Gated Recurrent Unit (GRU). Initially, the MEHFE algorithm is applied to decompose and reconstruct three-directional vibration signals at the blade root, thereby extracting “scale-frequency” dual-dimensional features that represent the evolution of fault frequency structure and complexity across multiple scales. Subsequently, Isolation Forest is employed to assess and filter feature importance, constructing an optimal feature subset to mitigate redundancy and noise interference. Finally, the optimal features are fed into the GRU network for fault pattern recognition, and the GWO algorithm is utilized to adaptively optimize network hyperparameters, thereby enhancing classification accuracy and noise resilience. Simulation experiments on typical wind turbine blade faults reveal that when GRU serves as the classifier, the diagnostic accuracy of MEHFE exceeds 76%. After feature optimization with Isolation Forest and network parameter optimization with GWO, the diagnostic accuracy surpasses 93%, demonstrating notable advantages in both classification capability and stability. Even under conditions of noise interference, the accuracy remains above 90%. The research substantiates that the proposed method can effectively extract pattern information indicative of blade structural damage from vibration data, achieving high fault recognition accuracy and robustness.

Oxidative degradation stands as the principal cause of gear oil failure and transmission system malfunctions in wind turbines. Electrochemical impedance spectroscopy (EIS) offers a novel technical avenue for the condition monitoring of gear oil. This research centers on the evolution mechanism of electrochemical properties during the oxidative degradation process, utilizing high-viscosity gear oil commonly employed in wind turbines as the research subject. Through a combination of accelerated oxidation tests, broadband EIS measurements, and equivalent circuit fitting, the study examines the variations in the electrochemical response of gear oil with respect to oxidation temperature and duration. The findings reveal that oxidative degradation does not modify the single-relaxation dielectric characteristics of the gear oil; however, various electrochemical parameters undergo systematic evolution. Following oxidation at temperatures ranging from 90 to 120 °C, the charge transfer resistance escalates by approximately 5.9-fold; the base resistance diminishes by 10% to 20%; both the admittance constant and dispersion index of the constant phase element (CPE) exhibit changes of less than 5%, indicating that the system retains its capacitive properties. During constant-temperature oxidation at 90 °C for durations spanning 50 to 175 h, the charge transfer resistance increases in an approximately linear fashion with oxidation time, while the base resistance continues to decline, and the CPE parameters remain largely stable. Various electrochemical parameters evolve monotonically with the extent of oxidation, with charge transfer resistance demonstrating the highest sensitivity to thermal oxidation and thus serving as a pivotal indicator for evaluating the degree of thermal oxidative degradation in gear oil. This study lays an experimental foundation for the application of EIS technology in the realm of online gear oil monitoring.

Electrochemical impedance spectroscopy (EIS), a rapid and non-destructive detection technique, offers a novel technical pathway for monitoring the degradation and assessing the quality of gear oil. This research delves into the electrochemical response characteristics and the underlying evolution mechanism of high-viscosity gear oil specifically formulated for wind turbines during its oxidative degradation process. Utilizing Mobil SHC™ Gear Oil 320 WT as the research subject, oil samples with varying degrees of degradation were prepared through accelerated oxidation experiments. Broadband frequency-sweep EIS testing was employed to acquire impedance spectra. The EIS data were subsequently analyzed using the equivalent circuit (ECM) method to extract electrochemical fingerprint parameters, enabling a systematic analysis of the variation patterns in the electrochemical response of gear oil with respect to oxidation temperature and time. Concurrently, the impact of test temperature on measurement results was evaluated. The findings reveal that EIS can dissect the intricate oxidative degradation process of gear oil into quantifiable interfacial electrochemical responses, with the characteristic parameters derived from ECM demonstrating consistent trends. Through a comprehensive analysis of the evolution patterns of electrochemical fingerprints, the oxidative degradation state of gear oil can be effectively evaluated. This research provides empirical evidence supporting the application of EIS technology in monitoring oxidative degradation and assessing the quality of gear oil for wind turbines.