优化支持向量机及其在智能故障诊断中的应用
Optimization of Support Vector Machine and Its Application in Intelligent Fault Diagnosis

单一支持向量机在轴承齿轮故障诊断中精度较低，为了提高支持向量机在轴承齿轮故障诊断中的精度，对支持向量机的样本特征提取方法以及支持向量机参数优化的方法进行了研究。首先，通过核主成分分析方法构造支持向量机的输入样本，可以减少数据间的冗余，提取数据的高维信息；其次，通过粒子群优化算法优化支持向量机核函数参数和惩罚因子；最后，使用优化后的支持向量机模型进行故障诊断。通过实际轴承齿轮故障诊断对比实验，结果表明，所提方法相比一般的支持向量机诊断方法诊断精度大幅提高，验证了该混合智能诊断方法的有效性和优势。
Single support vector machine has low precision in fault diagnosis of bearing and gear system, the sample feature extraction method of support vector machine and the method of parameter optimization of support vector machine are studied to improve the accuracy of the support vector machine in the fault diagnosis of bearing gear system. The input samples of support vector machines are constructed by the kernel principal component analysis to reduce data redundancy, extract high dimension information of the data, then particle swarm optimization algorithm is used to optimize the kernel function parameter and penalty factor of SVM, finally, the optimized support vector machine model is used for fault diagnosis. A comparative experiment on the fault diagnosis of bearing gear is carried out in order to verify the effectiveness of the proposed method, the results show that the proposed method improves the diagnostic accuracy significantly in comparison with the general support vector machines，the effectiveness and advantages of the intelligent diagnosis method are verified.