Condition monitoring (CM) has long been recognised as one of the best methods of reducing the operation and maintenance (O&M) costs of wind turbines (WTs). However, its potential in the wind industry has not been fully exploited. One of the major reasons is due to the lack of an efficient tool to properly process the WT CM signals, which are usually non-stationary in both time and frequency domains owing to the constantly varying operational and loading conditions experienced by WTs. For this reason, S-transform and its potential contribution to WT CM are researched in this paper. Following the discussion of the superiorities of S-transform to the Short-Time Fourier Transform (STFT) and Wavelet Transform, two S-transform based CM techniques are developed, dedicated for use on WTs. One is for tracking the energy variations of those fault-related characteristic frequencies under varying operational conditions (the energy rise of these frequencies usually indicates the presence of a fault); another is for assessing the health condition of WT gears and bearings, which have shown significant reliability issues in both onshore and offshore wind projects. In the paper, both proposed techniques have been verified experimentally, showing that they are valid for detecting both the mechanical and electrical faults occurring in the WT despite its varying operational and loading conditions. (C) 2013 Elsevier Ltd. All rights reserved.