As the core transmission component of wind turbine gearboxes, rolling bearings directly determine the power generation efficiency and operational costs of the units. Under complex operating conditions, these bearings are prone to failures caused by wear, fatigue, and impact. Moreover, vibration signals are often masked by strong background noise and multi-component coupled vibrations, making fault feature extraction challenging. To address this technical bottleneck, this study systematically explores rolling bearing fault feature extraction technology from three dimensions: vibration signal preprocessing, innovative fault feature extraction methods, and feature validity verification. The research aims to provide reliable technical support for fault diagnosis of rolling bearings in wind turbine gearboxes.