基于最小偏差LS-SVR的模电系统多故障诊断

谢璐璐; 何玉珠; 李建宏

基于最小偏差LS-SVR的模电系统多故障诊断

1.
北京航空航天大学仪器科学与光电工程学院, 北京 100191
2. 北京航空航天大学可靠性与系统工程学院, 北京 100191

详细信息

中图分类号: TP 18
计量
- 文章访问数: 1712
- HTML全文浏览量: 243
- PDF下载量: 386
- 被引次数: 0
出版历程
- 收稿日期: 2012-08-01
- 网络出版日期: 2013-07-30

Analog electronic system multiple fault diagnosis based on minimizing-deviation LS-SVR

1.
School of Instrumentation Science and Opto-electronics Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
2. School of Reliability and Systems Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 为解决支持向量分类机多分类存在的样本重复训练、训练模型过多的问题,保证模拟电子系统在整体和局部多故障模式上的诊断正确率,提出基于最小偏差的最小二乘支持向量回归机多故障诊断方法.通过引进样本各维度拟合误差相对于平均拟合误差的偏差平方项,最小化维度间的拟合误差间距,得到能够输出多维变量及具有高分辨率的最小二乘支持向量回归机模型.将模型多维输出值与预设的各个多故障模式值相乘,所得结果集中最大值所对应的多故障模式即为最终诊断结果.仿真结果表明:提出的方法在简化训练过程的同时,能够保持良好的整体和局部多故障诊断正确率.
- 多故障诊断 /
- 最小二乘支持向量回归机 /
- 模拟电子系统
Abstract: Aiming at multi-duplicated samples training and excessive training models in the process of multi-classification with standard support vector machine, and insuring high integral and partial diagnosis accuracy for analog electronic system, a multiple fault diagnosis method based on minimizing-deviation least squares support vector regression (MDLS-SVR) was proposed. With the square of deviation between the dimension fitting error and the average fitting error of the sample introduced to mimize the spacing between each dimension of the output variable, a new multiple-output least squares support vector regression was finally obtained which had high resolution for prediction results. Then through multiplying the model output by pre-set multi fault modes, the corresponding multiple fault mode to which the maximum value in the result set mapped was just the final diagnosis result. The simulation results show that, the new method simplifies the training process and could keep high integral and partial diagnosis accuracy under small sample set.
- multiple fault diagnosis /
- least squares support vector regression (LS-SVR) /
- analog electronic system

HTML全文

参考文献(10)

[1]	Vapnik V N.统计学习理论的本质[M].北京: 电子工业出版社,2009 Vapnik V N.The nature of statistical learning theory [M].Beijing: Electronic Manufacture Press,2009(in Chinese)
[2]	Huang Jian,Hu Xiaoguang,Xin Gengan.An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine[J].Electric Power Systems Research,2011,81:400-407
[3]	万九卿,李行善.基于串行支持向量分类器的模拟电路故障诊断[J].北京航空航天大学学报,2003,29(9):789-792 Wan Jiuqing,Li Xingshan.Analog circuits fault diagnosis based on serial support vector multi-classifier[J].Journal of Beijing University of Aeronautics and Astronautic,2003,29(9):789-792(in Chinese)
[4]	连可,王厚军,龙兵.基于SVM的模拟电子系统多故障诊断研究[J].仪器仪表学报,2007,28(6):1029-1034 Lian Ke,Wang Houjun,Long Bing.Study on SVM-based analog electronic system multiple fault diagnosis[J].Chinese Journal of Scientific Instrument,2007,28(6):1029-1034(in Chinese)
[5]	胡昌华,蔡艳宁,张琪.基于多重回归LSSVM的并发故障诊断[J].华中科技大学学报:自然科学版,2009,37(增刊5):1-5 Hu Changhua,Cai Yanning,Zhang Qi.Simultaneous fault diagnosis based on multi-regression LSSVM[J].Journal of Huazhong University of Science an Technology: Nature Science Edition,2009,37(S5):1-5(in Chinese)
[6]	杨士元.数字系统的故障诊断与可靠性设计[M].北京: 清华大学出版社,2000 Yang Shiyuan.The fault diagnosis and reliable design of digital circuits system[M].Beijing:Tsinghua University Press,2000:117-120(in Chinese)
[7]	Aminian M,Aminian F.A modular fault-diagnostic system for analog electronic circuits using neural networks with wavelet transform as a preprocessor[J].IEEE Transactions on Instrumentation and Measurement,2007,56(5):1546-1554
[8]	Kalpana P,Gunavathi K.Wavelet based fault detection in analog VLSI circuits using neural networks[J].Applied Soft Computing,2008,8:1592-1598
[9]	Luo Hui,Wang Youren,Cui Jiang.A SVDD approach of fuzzy classification for analog circuit fault diagnosis with FWT as preprocessor[J].Expert Systems with Applications,2011,38(8):10554-10561
[10]	Suykens J A K,Van Gestel T,De Brabanter J,et al.Least squares support vector machines[M].Singapore: World Scie-ntific,2002