针对大型设备的齿轮运行环境噪声干扰大和缺少故障样本的特点,提出了基于奇异值分解和支持向量机相结合的齿轮故障诊断方法。分析了奇异值分解法在信号特征提取中的应用与优势、支持向量机的原理与算法,并通过试验验证了基于奇异值分解和支持向量机的齿轮故障诊断方法可以实现对齿轮进行快速、准确的故障诊断。 Aiming at the characteristics of large equipment noise and disturbance of gear running environment and lack of fault samples, a gear fault diagnosis method based on singular value decomposition and support vector machine is proposed. The application and advantage of singular value decomposition in signal feature extraction and the principle and algorithm of support vector machine are analyzed. The method of gear fault diagnosis based on singular value decomposition and support vector machine is proved to be effective in fast and accurate gear detection Fault diagnosis.