中文摘要：

针对风电齿轮箱易出现齿轮断齿、点蚀、磨损等故障问题，提取风电齿轮箱非平稳非线性振动信号的提升小波包能量熵，利用支持向量机（SVM）进行故障诊断。为提高算法的分类精度，利用遗传算法对参数进行优化处理，试验结果表明，优化后获得的最佳参数能够提高 SVM 测试样本的预测精度。

英文摘要：

In a wind turbine gearbox,gear teeth produced frequently the problems such as broken, pitting and wear failure.This paper will extract non-stationary nonlinear vibration signals of wind power gear box and enhance wavelet packet energy entropy with using SVM to fault diagnosis process-ing.To improve the classification accuracy of the algorithm,genetic algorithms was used to optimize of parameters.Tests show that the best parameters can improve the prediction accuracy of the SVM to test samples.