陶洪峰,周超超,杨慧中.三电平逆变器的决策树SVM故障诊断[J].电子测量与仪器学报,2017,31(2):238-244
三电平逆变器的决策树SVM故障诊断
Fault diagnosis of three level inverter based on decision tree SVM
  
DOI:10.13382/j.jemi.2017.02.011
中文关键词:  逆变器  三电平  故障诊断  决策树支持向量机  粒子群聚类
英文关键词:inverter  three level  fault diagnosis  decision tree support vector machine  particle swarm clustering
基金项目:国家自然科学基金(61203092)、中央高校基本科研业务费专项资金(JUSRP51733B)、江苏省产学研前瞻性联合研究项目(BY2015019 21)资助
作者单位
陶洪峰 江南大学教育部轻工过程先进控制重点实验室无锡214122 
周超超 江南大学教育部轻工过程先进控制重点实验室无锡214122 
杨慧中 江南大学教育部轻工过程先进控制重点实验室无锡214122 
AuthorInstitution
Tao Hongfeng Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi 214122, China 
Zhou Chaochao Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi 214122, China 
Yang Huizhong Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi 214122, China 
摘要点击次数: 382
全文下载次数: 310
中文摘要:
      针对二极管箝位型三电平逆变器的开路故障诊断问题,提出一种基于决策树支持向量机(decision tree support vector machines, DT SVM)的故障诊断方法。以逆变状态为例,首先分析逆变器主电路的运行情况并进行故障分类,然后以中、上、下三种桥臂电压为测量信号,采用小波多尺度分解法提取特征信号,进而利用粒子群聚类算法(particle swarm clustering algorithm)生成决策树SVM分类模型,最终实现了三电平逆变器的多模式故障诊断。仿真结果表明,本方法在使用了较少分类模型的情况下完成故障诊断任务,相较于BP神经网络、一对一结构的支持向量机和极端学习机等方法,在10%白噪声扰动下对于三电平逆变器多模式开路故障的诊断精度可达98.46%,算法具有更好的准确性和鲁棒性。
英文摘要:
      Aiming at the problem of open circuit fault arising in diode clamped three level inverter, a new fault diagnosis method based on decision tree support vector machine (DT SVM) is proposed. Taking the inverter state as an example, firstly, the operation conditions of main circuit in inverter are analyzed to classify faults. Then, in terms of the multi scale decomposition of wavelet analysis, the middle, upper and down bridge voltages are selected to extract the fault features, respectively. Moreover, particle swarm clustering algorithm is built to construct the DT SVM classify model, and the multi model fault diagnosis of power component in three level inverter is finally accomplished. The simulation results show that this method in case of less classification model to complete fault diagnosis, comparing to other methods such as back propagation neural network, one versus one support vector machine and extreme learning machine, the diagnostic accuracy up to 98.46% for multi mode fault diagnosis of three level inverter in 10% white noise, which indicate that the algorithm has better accuracy and robustness.
查看全文  查看/发表评论  下载PDF阅读器