摘要
提出了一种基于支持向量机的机械故障诊断模型,该模型建立在VC维理论和结构风险最小原理基础上,根据有限的样本信息在模型的复杂性和学习能力之间寻求最佳折中,以期获得最好的推广能力。在选取诊断模型输入向量时,对故障信号功率谱进行小波分解,简化了故障特征向量的提取。仿真结果验证了该模型的有效性。
A machinery fault diagnosis model based on support vector machine （SVM） was proposed. The model was built on Vapnik-Chervonenkis dimension and structural risk minimization principle. According to limited sample information, the model seeks the optimal approach between complexity and study ability of the model so that it can obtain good extending ability. In selecting input vectors, the power spectrum of fault signals are decomposed by wavelet analysis, which predigests choosing meth- od of fault eigenvectors. The simulation results show the validity of the model.
出处
《河北工业科技》
CAS
2007年第1期37-39,42,共4页
Hebei Journal of Industrial Science and Technology
基金
中国博士后科学基金资助项目(2005038515)
关键词
小波包分析
故障诊断
支持向量机
核函数
wavelet packet analysis
fault diagnosis
support vector machine
kernel function
