基于RVM和相空间重构的模拟电路PHM研究
|
摘要
针对模拟电路健康管理的特点,提出了一种基于RVM的模拟电路故障诊断和预测方法;首先对模拟电路作蒙特卡罗分析得到输出频域响应,然后利用小波分解方法提取模拟电路的故障特征,最后用相关向量机分别对电路进行了单一故障和双故障的诊断研究;接着,对电路进行参数分析,得到不同参数值下的输出响应,计算其与电路无故障标准响应的欧氏距离作为故障特征,并以此表征电路元件健康值,结合相空间重构方法,得到相关向量机的输入输出样本,随后训练学习并实现对各个时间点元件的健康值变化轨迹进行预测;仿真结果表明,该方法在小样本情况下,诊断和预测效果好,适用于健康管理中实时预测,具有较好的实用性。
Aimed at the characteristics of prognostic and health management(PHM)in analog circuits,a new method for analog circuit fault diagnostics and prediction based on relevance vector machine(RVM)is proposed in this paper.Firstly,getting frequency domain response by the Monte Carlo analysis of analog circuits,fault features are extracted by wavelet decomposition and reconstruction to make single-fault and double fault diagnosis utilizing relevance vector machine,combining the phase space reconstruction method,the health value of circuit components is represented through calculating the Euclidean distance between output of standard and different parameter analysis,and the trend of health value trajectory with respect to time points can be predicted by training samples of inputs and outputs of RVM,the proposed approach is appropriate for real time prediction in PHM.Simulation results validate the good practicability and effectiveness of the proposed method.
Aimed at the characteristics of prognostic and health management(PHM)in analog circuits,a new method for analog circuit fault diagnostics and prediction based on relevance vector machine(RVM)is proposed in this paper.Firstly,getting frequency domain response by the Monte Carlo analysis of analog circuits,fault features are extracted by wavelet decomposition and reconstruction to make single-fault and double fault diagnosis utilizing relevance vector machine,combining the phase space reconstruction method,the health value of circuit components is represented through calculating the Euclidean distance between output of standard and different parameter analysis,and the trend of health value trajectory with respect to time points can be predicted by training samples of inputs and outputs of RVM,the proposed approach is appropriate for real time prediction in PHM.Simulation results validate the good practicability and effectiveness of the proposed method.
引文
[1]Pecht M G.Prognostics and Health Management of Electronics[M].Hoboken:John Wiley&Sons,2008:2-82.
[2]胡鸿志,田书林,郭庆,等.面向三维空间的模拟电路故障建模与故障检测[J].仪表技术与传感器,2015(10):101-103.
[3]何星,王宏力,陆敬辉,等.基于优选小波包和ELM的模拟电路故障诊断[J].仪器仪表学报,2013,34(11):2614-2619.
[4]彭宇,刘大同,彭喜元.故障预测与健康管理技术综述[J].电子测量与仪器学报,2010,24(1):1-9.
[5]Hess A,Calvello G,Frith P.Challenges,issues,and lessons learned chasing the“Big P”.Real predictive prognostics.Part 1[A].IEEE Aerospace Conference[C].IEEE,2005:3610-3619.
[6]Baraldi P,Cadini F,Mangili F,et al.Model-based and datadriven prognostics under different available information[J].Probabilistic Engineering Mechanics,2013,32(4):66-79.
[7]彭宇,刘大同.数据驱动故障预测和健康管理综述[J].仪器仪表学报,2014,35(3):481-495.
[8]Eddahech A,Briat O,Bertrand N,et al.Behavior and state-of-health monitoring of Li-ion batteries using impedance spectroscopy and recurrent neural networks[J].International Journal of Electrical Power&Energy Systems,2012,42(1):487-494.
[9]Wang S,Zhao L,Su X,et al.Prognostics of Lithium-Ion Batteries Based on Battery Performance Analysis and Flexible Support Vector Regression[J].Energies,2014,7(10):6492-6508.
[10]Yu W X,Sui Y,Wang J.The Faults Diagnostic Analysis for Analog Circuit Based on FA-TM-ELM[J].Journal of Electronic Testing,2016,32(4):1-7.
[11]Tipping M E.The Relevance Vector Machine[A].Proc.of Conference on Neural Information Processing Systems[C].MIT Press,2000:652-658.
[12]Tipping M E.Sparse Bayesian Learning and the Relevance Vector Machine[J].Journal of Machine Learning Research,2001,3(1):211-244.
[13]Tipping M E.Bayesian Inference:An Introduction to Principles and Practice in Machine Learning[A].Proc.of Conference on Machine Learning[C].Springer,2004:41-62.
[14]段青,赵建国,马艳.优化组合核函数相关向量机电力负荷预测模型[J].电机与控制学报,2010,14(6):33
[15]雷亚国,陈吴,李乃鹏,等.自适应多核组合相关向量机预测方法及其在机械设备剩余寿命预测中的应用[J].机械工程学报,2016,52(1):87-93.
[16]张洋,陈浩,郭波,等.锂离子电池剩余寿命在线预测[J].机械科学与技术,2016,35(8):1286-1290.
[17]邴其春,龚勃文,杨兆升,等.一种组合核相关向量机的短时交通流局域预测方法[J].哈尔滨工业大学学报,2017,49(3):144-149.
[18]Vasan A S S,Long B,Pecht M.Diagnostics and Prognostics Method for Analog Electronic Circuits[J].IEEE Transactions on Industrial Electronics,2013,60(11):5277-5291.
[19]周靖宇,田书林,王厚军,等.采用电压特征的模拟电路单元件预测方法研究[J].微电子学与计算机,2015,32(12):44-48.
[20]刘张亮,邓芳明,郝勇,等.基于余弦距离和超限学习机的模拟电路故障预测方法[J].仪表技术与传感器,2016(8):84-86.
[21]张朝龙,何怡刚,邓芳明,等.一种基于QPSO-RVM的模拟电路故障预测方法[J].仪器仪表学报,2014,35(8):1751-1757.
[22]祁涛,张彦斌,邸凯,等.PSO优化LS-SVM在模拟电路故障预测中的应用[J].计算机测量与控制,2016,24(3):4-7.
[23]范庚,马登武,张继军,等.基于自适应RVM的电子系统缓变故障预测方法[J].北京航空航天大学学报,2013,39(10):1319-1324.
[24]廖剑,史贤俊,周绍磊,等.基于局部图嵌入加权罚SVM的模拟电路故障诊断方法[J].电工技术学报,2016,31(4):28-35.
[25]高明哲,许爱强,唐小峰,等.基于多核多分类相关向量机的模拟电路故障诊断方法[J].自动化学报,2008:1-11.
[26]Psorakis I,Damoulas T,Girolami M A.Multiclass relevance vector machines:sparsity and accuracy[J].IEEE Transactions on Neural Networks,2010,21(10):1588.
[2]胡鸿志,田书林,郭庆,等.面向三维空间的模拟电路故障建模与故障检测[J].仪表技术与传感器,2015(10):101-103.
[3]何星,王宏力,陆敬辉,等.基于优选小波包和ELM的模拟电路故障诊断[J].仪器仪表学报,2013,34(11):2614-2619.
[4]彭宇,刘大同,彭喜元.故障预测与健康管理技术综述[J].电子测量与仪器学报,2010,24(1):1-9.
[5]Hess A,Calvello G,Frith P.Challenges,issues,and lessons learned chasing the“Big P”.Real predictive prognostics.Part 1[A].IEEE Aerospace Conference[C].IEEE,2005:3610-3619.
[6]Baraldi P,Cadini F,Mangili F,et al.Model-based and datadriven prognostics under different available information[J].Probabilistic Engineering Mechanics,2013,32(4):66-79.
[7]彭宇,刘大同.数据驱动故障预测和健康管理综述[J].仪器仪表学报,2014,35(3):481-495.
[8]Eddahech A,Briat O,Bertrand N,et al.Behavior and state-of-health monitoring of Li-ion batteries using impedance spectroscopy and recurrent neural networks[J].International Journal of Electrical Power&Energy Systems,2012,42(1):487-494.
[9]Wang S,Zhao L,Su X,et al.Prognostics of Lithium-Ion Batteries Based on Battery Performance Analysis and Flexible Support Vector Regression[J].Energies,2014,7(10):6492-6508.
[10]Yu W X,Sui Y,Wang J.The Faults Diagnostic Analysis for Analog Circuit Based on FA-TM-ELM[J].Journal of Electronic Testing,2016,32(4):1-7.
[11]Tipping M E.The Relevance Vector Machine[A].Proc.of Conference on Neural Information Processing Systems[C].MIT Press,2000:652-658.
[12]Tipping M E.Sparse Bayesian Learning and the Relevance Vector Machine[J].Journal of Machine Learning Research,2001,3(1):211-244.
[13]Tipping M E.Bayesian Inference:An Introduction to Principles and Practice in Machine Learning[A].Proc.of Conference on Machine Learning[C].Springer,2004:41-62.
[14]段青,赵建国,马艳.优化组合核函数相关向量机电力负荷预测模型[J].电机与控制学报,2010,14(6):33
[15]雷亚国,陈吴,李乃鹏,等.自适应多核组合相关向量机预测方法及其在机械设备剩余寿命预测中的应用[J].机械工程学报,2016,52(1):87-93.
[16]张洋,陈浩,郭波,等.锂离子电池剩余寿命在线预测[J].机械科学与技术,2016,35(8):1286-1290.
[17]邴其春,龚勃文,杨兆升,等.一种组合核相关向量机的短时交通流局域预测方法[J].哈尔滨工业大学学报,2017,49(3):144-149.
[18]Vasan A S S,Long B,Pecht M.Diagnostics and Prognostics Method for Analog Electronic Circuits[J].IEEE Transactions on Industrial Electronics,2013,60(11):5277-5291.
[19]周靖宇,田书林,王厚军,等.采用电压特征的模拟电路单元件预测方法研究[J].微电子学与计算机,2015,32(12):44-48.
[20]刘张亮,邓芳明,郝勇,等.基于余弦距离和超限学习机的模拟电路故障预测方法[J].仪表技术与传感器,2016(8):84-86.
[21]张朝龙,何怡刚,邓芳明,等.一种基于QPSO-RVM的模拟电路故障预测方法[J].仪器仪表学报,2014,35(8):1751-1757.
[22]祁涛,张彦斌,邸凯,等.PSO优化LS-SVM在模拟电路故障预测中的应用[J].计算机测量与控制,2016,24(3):4-7.
[23]范庚,马登武,张继军,等.基于自适应RVM的电子系统缓变故障预测方法[J].北京航空航天大学学报,2013,39(10):1319-1324.
[24]廖剑,史贤俊,周绍磊,等.基于局部图嵌入加权罚SVM的模拟电路故障诊断方法[J].电工技术学报,2016,31(4):28-35.
[25]高明哲,许爱强,唐小峰,等.基于多核多分类相关向量机的模拟电路故障诊断方法[J].自动化学报,2008:1-11.
[26]Psorakis I,Damoulas T,Girolami M A.Multiclass relevance vector machines:sparsity and accuracy[J].IEEE Transactions on Neural Networks,2010,21(10):1588.