基于分段加权最小二乘支持向量机故障诊断的实现.PDF
文本预览下载声明
第9 卷第10期 Vol.9 No.10
2016 年 5 月 May 2016
基于分段加权最小二乘支持向量机故障
诊断的实现
吕 宁 ,颜鲁齐*
(哈尔滨理工大学自动化学院,哈尔滨 150080 )
摘要:在啤酒发酵过程中,为建立精准的传感器温度故障诊断模型,在标准支持向量机(support vector machine ,
SVM )的基础上提出分段加权最小二乘支持向量机(weighted least square support vector machine ,WLS-SVM )
的方法。该方法首先利用模糊C 均值(fuzzy C-means ,FCM )聚类对样本进行聚类分析,达到划分发酵阶段
和建立局部模型的目的,然后应用 WLS-SVM 的方法对各类样本进行建模。实验结果表明,使用该方法建立
的啤酒发酵过程温度故障诊断模型具有较高的准确性。经过比较,该方法建立模型的泛化能力要强于其他SVM
方法建立的模型。
关键词: 自动控制理论;支持向量机;模糊C 均值聚类;加权最小二乘支持向量机;啤酒发酵;建模
中图分类号:TP206+.3 文献标识码:A 文章编号:1674-2850(2016)10-1048-07
Realization of fault diagnosis based on piecewise weighted
least squares support vector machine
LÜ Ning, YAN Luqi
(College of Automation, Harbin University of Science and Technology, Harbin 150080, China)
Abstract: In the process of beer fermentation, in order to establish the precise temperature sensor fault
diagnosis model, on the basis of standard support vector machine (SVM), we proposed piecewise weighted
least square support vector machine (WLS-SVM) method. The method was first using fuzzy C-means
clustering (FCM) of the sample of poly class analysis, to divide fermentation stage and the establishment of
local model. Then, using the WLS-SVM method is used for modeling of various types of samples. The
experimental results show that the model has a high accuracy in the process of temperature fault diagnosis of
beer fermentation process. After comparison, the proposed method establishes the m
显示全部