|
|||||
|
|
| 永磁直流电机故障模式识别方法对比研究 | |
| 引用本文： | 刘曼兰,崔淑梅,郭斌.永磁直流电机故障模式识别方法对比研究[J].微电机,2011,44(3):9-12. |
| 作者姓名： | 刘曼兰 崔淑梅 郭斌 |
| 作者单位： | 1. 哈尔滨工业大学,机电工程学院,哈尔滨,150001;哈尔滨工业大学,材料科学与工程学院,哈尔滨,150001 2. 哈尔滨工业大学,电气工程学院,哈尔滨,150001 3. 哈尔滨工业大学,材料科学与工程学院,哈尔滨,150001 |
| 摘 要： | 构建了两种基于BP神经网络和支持向量机的的永磁直流电机故障模式识别分类器,并对该两种模式识别分类器在永磁直流电机故障诊断中的应用进行了实验研究与理论分析。研究结果表明:基于支持向量机的永磁直流电机故障模式识别方法在小样本情况下的诊断正确率高于基于BP神经网络,最好能达到94.6667%,且不存在局部极小值问题和过学习问题。 |
| 关 键 词： | 永磁直流电机 支持向量机 BP神经网络 模式识别 故障诊断 |
Compared Study on the Method of Failure Recognition for Permanent Magnetic DC Motor |
|
| LIU Manlan,CUI Shumei,GUO Bin.Compared Study on the Method of Failure Recognition for Permanent Magnetic DC Motor[J].Micromotors,2011,44(3):9-12. | |
| Authors: | LIU Manlan CUI Shumei GUO Bin |
| Affiliation: | LIU Manlan1,2,CUI Shumei3,GUO Bin2 (1.School of Mechanical and Electrical Engineering,Harbin Institute of Technology,Harbin 150001,China,2.School of Material Science and Engineering,Harbin150001,3.School of Electric Engineering,China) |
| Abstract: | Fault diagnosis method based on SVM(Support Vector Machine) and BP were developed for permanent magnetic DC motor.The fault diagnosis results of this method in cases where only limited training samples are available were compared with that of another classification algorithm BP ANN.It shows that SVM have better performance than ANN both in training speed and recognition rate and its greatest rate gets to 94.6667%.SVM can also avoid over-fitting and trapping in local extreme which often happened in the neura... |
| Keywords: | permanent magnetic DC Motor support vector machines BP failure recognize failure diagnosis |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |