【摘要】：為了高速、高效的測試和診斷模擬電路,提出一種將局部均值分解(LMD)多尺度熵和極限學(xué)習(xí)機(jī)相結(jié)合的模擬電路故障診斷的新方法。該方法中,首先采用LMD將故障信號分解為若干個(gè)乘積函數(shù)(production function,PF);然后,求出各PF分量的多尺度熵并構(gòu)造故障特征向量;最后,將特征向量輸入到極限學(xué)習(xí)機(jī)中進(jìn)行訓(xùn)練和測試。仿真實(shí)驗(yàn)結(jié)果顯示采用該方法診斷時(shí)間只需0.028 74 s,診斷精度達(dá)到了98.89%。相較于其他3種方法有效減少診斷時(shí)間,提高故障診斷精度。
[Abstract]:In order to test and diagnose analog circuits with high speed and efficiency, a new method for fault diagnosis of analog circuits is proposed, which combines the local mean decomposition of (LMD) multi-scale entropy with the ultimate learning machine. In this method, the fault signal is first decomposed into several product functions (production function,PF) by LMD, then the multi-scale entropy of each PF component is obtained and the fault eigenvector is constructed. Finally, the eigenvector is input into the extreme learning machine for training and testing. The simulation results show that the diagnostic time is only 0.028 74 s and the diagnostic accuracy is 98.89 s. Compared with the other three methods, the diagnosis time is reduced and the fault diagnosis accuracy is improved.
【作者單位】： 湖南師范大學(xué)物理與信息科學(xué)學(xué)院;合肥工業(yè)大學(xué)電氣工程博士后流動(dòng)站;合肥工業(yè)大學(xué)電氣與自動(dòng)化工程學(xué)院;國網(wǎng)湖南省邵陽供電公司;
【基金】：國家自然科學(xué)基金(51577046);國家自然科學(xué)基金重點(diǎn)項(xiàng)目(51637004) 國家重點(diǎn)研發(fā)計(jì)劃“重大科學(xué)儀器設(shè)備開發(fā)”項(xiàng)目(2016YFF0102200) 湖南省教育廳項(xiàng)目(17C0956)資助
【分類號】：TN710

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 陳建萍;多尺度熵方法用于電子器件噪聲分析[D];西安電子科技大學(xué);2007年

，

本文編號：2387798