郭杰榮+何怡剛
摘要提出一種基于多尺度小波分解及神經(jīng)網(wǎng)絡(luò)映射歸納的測(cè)試電流模電路故障缺陷的方法.針對(duì)CMOS器件典型故障建立了測(cè)試所需的故障模型,給電路節(jié)點(diǎn)加入故障模型進(jìn)行故障響應(yīng)測(cè)試.對(duì)故障信號(hào)進(jìn)行時(shí)域采樣,采用小波多尺度分解對(duì)故障相應(yīng)信號(hào)進(jìn)行頻域多尺度分解,然后將處理數(shù)據(jù)作為神經(jīng)網(wǎng)絡(luò)訓(xùn)練樣本,對(duì)各類缺陷響應(yīng)結(jié)果進(jìn)行分類、識(shí)別,最后根據(jù)可接受偏差范圍確定信號(hào)為故障或非故障.給出了6類故障的故障覆蓋率測(cè)試結(jié)果.
關(guān)鍵詞電流模;測(cè)試;小波分解;神經(jīng)網(wǎng)絡(luò)
中圖分類號(hào)TM315文獻(xiàn)標(biāo)識(shí)碼A文章編號(hào)1000-2537(2014)02-0051-05
與開關(guān)電容技術(shù)不同,電流模電路采用電流作為信號(hào)傳輸介質(zhì),因而呈現(xiàn)較低的電抗特性,具有較小的漂移電感(stray-inductance)[1-3],可以達(dá)到較高的速率.電流模電路基本單元如圖1所示.但是,將傳統(tǒng)的模擬電路測(cè)試方法應(yīng)用在電流模電路方面遇到了困難,電流模電路獨(dú)特的結(jié)構(gòu)及傳輸方式需要新的測(cè)試方法.可供選擇的方法是采用神經(jīng)網(wǎng)絡(luò)方法,相關(guān)文獻(xiàn)[4~9]表明,如果要達(dá)到較高的故障識(shí)別率,需要在神經(jīng)網(wǎng)絡(luò)訓(xùn)練過(guò)程中加大訓(xùn)練數(shù)據(jù)的數(shù)量以及神經(jīng)元數(shù)目,這將導(dǎo)致訓(xùn)練過(guò)程的復(fù)雜化及過(guò)長(zhǎng)的訓(xùn)練時(shí)間.本文在研究電流模電路特殊結(jié)構(gòu)與特性的前提下,提出了一種基于測(cè)試節(jié)點(diǎn)電壓的瞬態(tài)測(cè)試的多尺度小波分分解及神經(jīng)網(wǎng)絡(luò)非線性映射歸納的測(cè)試方法,可以在較少訓(xùn)練的前提下獲得較高的故障識(shí)別率.
4結(jié)束語(yǔ)
本文提出了一種針對(duì)電流模電路的預(yù)先采用多尺度小波分解,再使用神經(jīng)網(wǎng)絡(luò)訓(xùn)練測(cè)試的方法.即首先將各類故障模型加入電流模電路中,以電流模電路的電流輸出響應(yīng)信號(hào)為樣本,在正常提取測(cè)試信號(hào)特性的前提下,采用多尺度小波分解對(duì)各類響應(yīng)數(shù)據(jù)進(jìn)行預(yù)處理,在保留故障信號(hào)特性品質(zhì)的前提下降低分析的樣本數(shù)量,將預(yù)處理的結(jié)果作為神經(jīng)網(wǎng)絡(luò)模型訓(xùn)練樣本,訓(xùn)練完成后可對(duì)各類故障進(jìn)行識(shí)別.本文方法可以適用于電流模式信號(hào)傳輸測(cè)試并有效降低訓(xùn)練所需神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)復(fù)雜性.
參考文獻(xiàn):
[1]KIM H S, JEON J Y, LEE S W, et al. A compact-sized 9-bit switched-current DAC for AMOLED mobile display drivers[J]. IEEE Trans Circuits Syst Ⅱ: Express Briefs, 2012,58(12):887-891.
[2]SAETHER G E, TOUMAZOU C, TAYLOR G, et al. Concurrent self test of switched current circuits based on the S 2I-technique[J]. IEEE Int Symp Circuits Syst, 1995,12(2):841-844.
[3]戴力,莊奕琪,景鑫,等. 一種新型高性能CMOS電流模式的動(dòng)態(tài)規(guī)劃電路[J]. 西安交通大學(xué)學(xué)報(bào), 2012,46(6):29-35.
[4]劉美容,何怡剛,趙新民,等. 基于混沌的模擬電路故障診斷方法[J]. 湖南師范大學(xué)自然科學(xué)學(xué)報(bào), 2012,35(3):34-39.
[5]彭良玉, 禹旺兵. 基于小波分析和克隆選擇算法的模擬電路故障診斷[J]. 電工技術(shù)學(xué)報(bào), 2007,22(6):12-16.
[6]GU H Y, ZHANG F, WANG Z J, et al. Identification method for low-voltage Arc fault based on the loose combination of wavelet transformation and neural network[C]. IEEE Power Engineering and Automation Conference (PEAM), Wuhan, China, 2012.
[7]DAVANIPOOR M, ZEKRI M, SHEIHOLESLAM F. Fuzzy wavelet neural network with an accelerated hybrid learning algorithm[J]. IEEE Trans Fuzzy Sys, 2012,20(3):463-470.
[8]徐崇斌,趙志文,鄭慧芳.ELVQ算法實(shí)現(xiàn)寬參數(shù)偏移的多故障電路診斷[J]. 電子與信息學(xué)報(bào), 2011,33(6):1520-1524.
[9]ABOHAGAR A A, MUSTAFA M W. Back propagation neural network aided wavelet transform for high impedance fault detection and faulty phase selection[C]. IEEE International Conference on Power and Energy (PECon), Kota Kinabalu, Malaysia, 2012.
[10]CORDOVA J J, YU W, LI X O. Haar wavelet neural networks for nonlinear system identification[C]. 2012 IEEE International Symposium on Intelligent Control (ISIC), Dubrouk, Croatia, 2012.
[11]ESPINOZA-TREJO D R, CAMPOS-DELGADO D U, BRCENAS E, et al. Robust fault diagnosis scheme for open-circuit faults in voltage source inverters feeding induction motors by using non-linear proportional-integral observers[J]. IET Power Electr, 2012,5(7):1204-1216.
[12]REN S X, GAO L. Application of a wavelet packet transform based radial basis function neural network to analyze overlapping spectra [J]. Congress Image Signal Proc, 2008,5(2):228-232.
[13]IOKIBE K, AMANO T, OKAMOTO K, et al. Improvement of linear equivalent circuit model to identify simultaneous switching noise current in cryptographic integrated circuits[C]. IEEE International Symposium on Electromagnetic Compatibility (EMC), Denver, America, 2013.
[14]YAN Y Y, LEE F C, MATTAVELLI P. Analysis and design of average current mode control using a describing-function-based equivalent circuit model [J]. IEEE Trans Power Electr, 2013,28(10):4732-4741.
[15]KHANG H V, ARKKIO A. Eddy-current loss modeling for a form-wound induction motor using circuit model[J]. IEEE Trans Magnet, 2012,48(2):1059-1062.
[16]ARUMUGAM P, HAMITI T, GERADA C. Modeling of different winding configurations for fault-tolerant permanent magnet machines to restrain interturn short-circuit current [J]. IEEE Trans Energy Conver, 2012,27(2):351-361.
[17]郭杰榮,李長(zhǎng)生,劉長(zhǎng)青. 基于0.18 μm CMOS的電流模單元最優(yōu)化設(shè)計(jì)[J]. 湖南文理學(xué)院學(xué)報(bào):自然科學(xué)版, 2012,24(1):39-41,45.
(編輯陳笑梅)
[12]REN S X, GAO L. Application of a wavelet packet transform based radial basis function neural network to analyze overlapping spectra [J]. Congress Image Signal Proc, 2008,5(2):228-232.
[13]IOKIBE K, AMANO T, OKAMOTO K, et al. Improvement of linear equivalent circuit model to identify simultaneous switching noise current in cryptographic integrated circuits[C]. IEEE International Symposium on Electromagnetic Compatibility (EMC), Denver, America, 2013.
[14]YAN Y Y, LEE F C, MATTAVELLI P. Analysis and design of average current mode control using a describing-function-based equivalent circuit model [J]. IEEE Trans Power Electr, 2013,28(10):4732-4741.
[15]KHANG H V, ARKKIO A. Eddy-current loss modeling for a form-wound induction motor using circuit model[J]. IEEE Trans Magnet, 2012,48(2):1059-1062.
[16]ARUMUGAM P, HAMITI T, GERADA C. Modeling of different winding configurations for fault-tolerant permanent magnet machines to restrain interturn short-circuit current [J]. IEEE Trans Energy Conver, 2012,27(2):351-361.
[17]郭杰榮,李長(zhǎng)生,劉長(zhǎng)青. 基于0.18 μm CMOS的電流模單元最優(yōu)化設(shè)計(jì)[J]. 湖南文理學(xué)院學(xué)報(bào):自然科學(xué)版, 2012,24(1):39-41,45.
(編輯陳笑梅)
[12]REN S X, GAO L. Application of a wavelet packet transform based radial basis function neural network to analyze overlapping spectra [J]. Congress Image Signal Proc, 2008,5(2):228-232.
[13]IOKIBE K, AMANO T, OKAMOTO K, et al. Improvement of linear equivalent circuit model to identify simultaneous switching noise current in cryptographic integrated circuits[C]. IEEE International Symposium on Electromagnetic Compatibility (EMC), Denver, America, 2013.
[14]YAN Y Y, LEE F C, MATTAVELLI P. Analysis and design of average current mode control using a describing-function-based equivalent circuit model [J]. IEEE Trans Power Electr, 2013,28(10):4732-4741.
[15]KHANG H V, ARKKIO A. Eddy-current loss modeling for a form-wound induction motor using circuit model[J]. IEEE Trans Magnet, 2012,48(2):1059-1062.
[16]ARUMUGAM P, HAMITI T, GERADA C. Modeling of different winding configurations for fault-tolerant permanent magnet machines to restrain interturn short-circuit current [J]. IEEE Trans Energy Conver, 2012,27(2):351-361.
[17]郭杰榮,李長(zhǎng)生,劉長(zhǎng)青. 基于0.18 μm CMOS的電流模單元最優(yōu)化設(shè)計(jì)[J]. 湖南文理學(xué)院學(xué)報(bào):自然科學(xué)版, 2012,24(1):39-41,45.
(編輯陳笑梅)