The blade is a crucial part of wind turbine for generating electricity and prone to damage due to harsh external environment. Accurate damage detection of wind turbine blade (WTB) is still a prominent challenge. This paper presents an acoustical detection method for damage identification of the WTB based on pattern recognition. In the proposed method, sound pulse extraction of the WTB is first investigated through physical method in combination with the filter and sliding window. Subsequently, the wavelet packet energy ratios of acoustic signal are introduced to characterize the discrepancy between intact and cracked sound pulses, and the support vector data description (SVDD) model is built for WTB damage detection. Besides, an improved incremental learning method is presented and employed to adaptively update the SVDD model, which aims at simplifying calculation procedure. Finally, the performance of proposed method is evaluated using experimental data collected from the WTBs with both intact and damaged conditions in commercial wind farms. It is demonstrated that proposed method has improvement in prediction accuracy compared to previous incremental SVDD models and performs the best on training time. (C) 2020 Elsevier Ltd. All rights reserved.