Offshore wind turbines (OWTs) operate under harsh marine conditions involving strong winds, waves, and salt-laden air, which increase the risk of excessive vibrations and structural failures such as tower collapse. To ensure structural safety and achieve effective vibration control, accurate modal parameter identification is essential. In this study, a vibration monitoring system was developed, and the Bayesian Spectral Decomposition (BSD) method was applied for the operational modal analysis of a 5.5 MW monopile OWT. The monitoring system consisted of ten uniaxial accelerometers mounted at five elevations along the tower, with two orthogonally oriented sensors at each level to capture horizontal vibrations. Due to continuous nacelle yawing, the measured accelerations were projected onto the structural fore–aft (FA) and side–side (SS) directions prior to modal analysis. Two days of vibration and SCADA data were collected: one under rated rotor speed and another including one hour of idle state. Data preprocessing involved outlier removal, low-pass filtering, and directional projection. The obtained data were divided into 20-min segments, and the BSD approach was applied to extract the primary modal parameters in both FA and SS directions. Comparison with results from the Stochastic Subspace Identification (SSI) technique showed strong consistency, verifying the reliability of the BSD method and its advantage in uncertainty quantification. The results indicate that the identified modal frequencies remain relatively stable under both rated and idle conditions, whereas the damping ratios increase with wind speed, with a more significant growth observed in the FA direction.

Tower bolts play a crucial role as connecting components in wind turbines and are of great interest for health monitoring systems. Non-contact monitoring techniques offer superior efficiency, convenience, and intelligence compared to contact-based methods. However, the precision and robustness of the non-contact monitoring process are significantly impacted by suboptimal lighting conditions within the wind turbine tower. To address this problem, this article proposes an automated detection method for the bolt detachment of wind turbines in low-light scenarios. The approach leverages the deep convolutional generative adversarial network (DCGAN) to expand and augment the small-sample bolt dataset. Transfer learning is then applied to train the Zero-DCE++ low-light enhancement model and the bolt defect detection model, with the experimental verification of the proposed method’s effectiveness. The results reveal that the deep convolutional generative adversarial network can generate realistic bolt images, thereby improving the quantity and quality of the dataset. Additionally, the Zero-DCE++ light enhancement model significantly increases the mean brightness of low-light images, resulting in a decrease in the error rate of defect detection from 31.08% to 2.36%. In addition, the model’s detection performance is affected by shooting angles and distances. Maintaining a shooting distance within 1.6 m and a shooting angle within 20° improves the reliability of the detection results.