基于GMKL-SVM的模擬電路故障診斷方法
發(fā)布時間：2019-03-07 08:27
【摘要】：提出了一種新穎的基于廣義多核支持向量機(GMKL-SVM)的模擬電路故障診斷方法。首先,應用Haar小波分析提取被測電路時域響應信號的小波系數(shù)作為特征參量,并生成樣本數(shù)據(jù);然后,基于樣本數(shù)據(jù),應用量子粒子群算法對GMKL-SVM的參數(shù)進行優(yōu)化,并以此建立基于GMKL-SVM的故障診斷模型,用于區(qū)分模擬電路的各個故障。實例電路的單故障和雙故障診斷實驗結(jié)果表明,所提出的GMKL-SVM方法能較好地實現(xiàn)模擬電路故障診斷,與傳統(tǒng)的GMKL-SVM方法相比,表現(xiàn)出了更好的性能,獲得了更高的故障診斷正確率。
[Abstract]:A novel fault diagnosis method for analog circuits based on generalized multi-kernel support vector machine (GMKL-SVM) is proposed. Firstly, the wavelet coefficients of the time-domain response signal of the tested circuit are extracted by Haar wavelet analysis as the characteristic parameter, and the sample data are generated. Then, based on the sample data, quantum particle swarm optimization (QPSO) is applied to optimize the parameters of GMKL-SVM, and then a fault diagnosis model based on GMKL-SVM is established to distinguish the faults of analog circuits. The experimental results of single-fault and double-fault diagnosis show that the proposed GMKL-SVM method can realize analog circuit fault diagnosis better than the traditional GMKL-SVM method, and the performance of the proposed method is better than that of the traditional fault diagnosis method. A higher accuracy rate of fault diagnosis is obtained.
【作者單位】： 合肥工業(yè)大學電氣與自動化工程學院;安慶師范大學物理與電氣工程學院;
【基金】：國家自然科學基金重點項目(51637004);國家自然科學基金(51577046,51607004) 國家重點研發(fā)計劃“重大科學儀器設備開發(fā)”(2016YFF0102200) 安徽省科技計劃重點項目(1301022036) 安徽省自然科學基金(1608085QF157) 安徽省高校優(yōu)秀青年人才支持計劃重點項目(gxyq ZD2016207) 安徽省高等學校自然科學研究重點項目(KJ2016A431)資助
【分類號】：TN710
，
本文編號：2435943
[Abstract]:A novel fault diagnosis method for analog circuits based on generalized multi-kernel support vector machine (GMKL-SVM) is proposed. Firstly, the wavelet coefficients of the time-domain response signal of the tested circuit are extracted by Haar wavelet analysis as the characteristic parameter, and the sample data are generated. Then, based on the sample data, quantum particle swarm optimization (QPSO) is applied to optimize the parameters of GMKL-SVM, and then a fault diagnosis model based on GMKL-SVM is established to distinguish the faults of analog circuits. The experimental results of single-fault and double-fault diagnosis show that the proposed GMKL-SVM method can realize analog circuit fault diagnosis better than the traditional GMKL-SVM method, and the performance of the proposed method is better than that of the traditional fault diagnosis method. A higher accuracy rate of fault diagnosis is obtained.
【作者單位】： 合肥工業(yè)大學電氣與自動化工程學院;安慶師范大學物理與電氣工程學院;
【基金】：國家自然科學基金重點項目(51637004);國家自然科學基金(51577046,51607004) 國家重點研發(fā)計劃“重大科學儀器設備開發(fā)”(2016YFF0102200) 安徽省科技計劃重點項目(1301022036) 安徽省自然科學基金(1608085QF157) 安徽省高校優(yōu)秀青年人才支持計劃重點項目(gxyq ZD2016207) 安徽省高等學校自然科學研究重點項目(KJ2016A431)資助
【分類號】：TN710
，
本文編號：2435943
本文鏈接：http://www.sikaile.net/kejilunwen/dianzigongchenglunwen/2435943.html
教材專著
