【摘要】 将支持向量机(SVMs)用于机械设备振动信号趋势预测中,研究了SVMs参数及核函数类型对SVMs预测能力的影响.试验显示,在短期预测中4种核函数有着基本相同的预测能力,而在长期预测中,径向基函数核和多项式核表现出了相对较高的预测能力,同线性核和神经网络核相比,它们的归一化均方误差约降低了20%.SVMs与向后传播神经网络、径向基函数网络和广义回归神经网络预测能力的对比表明,实现了结构风险最小化原理的SVMs具有更好的预测能力,在长期预测中,其归一化均方误差约降低了15%.更多还原

【Abstract】 Support vector machines (SVMs) were used for trend prediction of vibration signal of mechanical equipment. The influence of kernel functions and parameters on SVMs prediction performance was studied. Analysis of the experimental results shows that four kernel functions have the same prediction performance in short term prediction and radial basis function (RBF) kernel has better prediction performance than other kernels in long term prediction. The normalized mean square error (NMSE) of RBF kernel decreases by about 20% compared with other kernels. In comparison with conventional back propagation neural network (BP), radial basis function network (RBF) and generalized regression neural network (GRNN), the results show that SVMs, which implement the structure risk minimization principle, obtain the best prediction performance and the NMSE of SVMs decreases by about 15% in long term prediction.更多还原