非线性复合FSVM在设备故障诊断中的应用

Nonlinear FSVM with Multi-kernel Function for Equipment Fault Diagnosis

为了提高设备故障诊断的精度和准确性,利用模糊支持向量机(fuzzy support vector machine,FSVM),处理设备故障样本中的噪声数据。单个核函数构成的FSVM可以处理单一特征的样本集,但不能满足现有设备故障分析实际应用的需求。本文在现有核函数的基础上,进行复合核函数构建,可以有效解决设备故障样本集异构和分布不规则的特征,并可以对于故障进行有效分析,得到较为诊断准确的研究结果。通过对滚动轴承故障实验数据的分析,证明基于复合核函数的FSVM方法,可以有效提高故障诊断的准确度。该方法相比传统FSVM的分析结果,其故障数据信息利用更加充分,故障诊断准确性有效提高,具有较好的有效性和可行性。

A fuzzy support vector machine （FSVM） is proposed to improve the accuracy of equipment fault diagnosis. FSVM is good at dealing with an equipment fault system or data with ambiguous characters. When equipment fault data have heterogeneous or irregular and uneven distribution characteristics, satisfactory results cannot be obtained by using a traditional FSVM based on single kernel. To overcome this drawback, a FSVM algorithm based on multi-kernel function is proposed to deal with equipment fault diagnosis. By applying this method to the rolling bearing fault diagnosis, the test result shows that this method is superior to an original FSVM and can identify rolling bearing fault patterns more effectively.