针对强噪声背景下风力机齿轮箱振动信号易被掩盖、难以提取的难题，基于频域谱负熵（Frequency-domain Spectral Negentropy,FSN）改进经验小波变换（Empirical Wavelet Transform,EWT）提出优化经验小波变换方法（Improved Empirical Wavelet Transform，IEWT），并采用改进灰狼算法（Improved Grey Wolf Optimization,IGWO）优化支持向量机（Support Vector Machine,SVM）惩罚系数α及核参数σ。基于NREL GRC风力机齿轮箱数据验证所提方法的有效性。结果表明：IEWT-IGWO-SVM可有效提取故障信息并进行故障识别，分类准确率高达99.66%。

In order to solve the problem that the wind turbine gearbox vibration signal is easily masked and difficult to extract in a strong noise background, an improved empirical wavelet transform(IEWT) method is proposed based on the empirical wavelet transform (EWT) improved by the frequencydomain spectral negentropy (FSN).The improved grey wolf optimization (IGWO) is used to optimize the penalty coefficients and kernel parameters of the support vector machine (SVM). The effectiveness of the proposed method is verified based on NREL GRC wind turbine gearbox data. The results show that IEWTIGWOSVM can effectively extract fault information and perform fault identification with the classification accuracy up to 99.66%.

TH132.41

国家自然科学基金（52006148,51976131,52106262）；上海“科技创新行动计划”地方院校能力建设项目（19060502200）