基于構(gòu)造性神經(jīng)網(wǎng)絡(luò)的模擬電路故障診斷研究
發(fā)布時間：2019-05-19 19:15
【摘要】：模擬電路故障診斷研究已有數(shù)十年歷史,受元件容差、非線性、溫漂等因素影響,該課題一直是研究的難點(diǎn)和熱點(diǎn)。電子器件中,模擬電路所占比例不大,但故障問題出現(xiàn)最多,電子器件運(yùn)行可靠性很大程度上依賴于模擬電路的可靠性。傳統(tǒng)方法在電路規(guī)模日趨增大的背景下表現(xiàn)出數(shù)據(jù)處理能力弱、診斷時間長、診斷過程復(fù)雜等局限性,人工智能方法特別是神經(jīng)網(wǎng)絡(luò)方法為其提供了新的研究方向,能很好適應(yīng)非線性電路診斷,不依賴具體電路,降低診斷難度,但在診斷時間、診斷精度、糾錯容錯方面仍表現(xiàn)不足,并且建模過程復(fù)雜�；诟采w理論構(gòu)造性神經(jīng)網(wǎng)絡(luò)是近年來提出的新型神經(jīng)網(wǎng)絡(luò)方法,它相比于傳統(tǒng)神經(jīng)網(wǎng)絡(luò)具有建模簡單、魯棒性好、運(yùn)算能力強(qiáng)的優(yōu)點(diǎn),適用于海量數(shù)據(jù)、復(fù)雜環(huán)境等情況下的工業(yè)應(yīng)用,特別能大大降低運(yùn)算時間。本文以神經(jīng)網(wǎng)絡(luò)理論為基礎(chǔ),克服現(xiàn)有故障診斷系統(tǒng)需要提取故障特征,故障建模過程復(fù)雜,系統(tǒng)運(yùn)行中難以實(shí)現(xiàn)知識擴(kuò)充等問題,提出將構(gòu)造性神經(jīng)網(wǎng)絡(luò)方法應(yīng)用于模擬電路故障診斷中,取得良好的診斷結(jié)果。本文首先以M P神經(jīng)元球面模型為基礎(chǔ),建立基于球面領(lǐng)域的構(gòu)造性神經(jīng)網(wǎng)絡(luò),對模擬電路具有±4%擾動故障樣本進(jìn)行診斷能達(dá)到100%診斷精度;然后針對具有±15%擾動樣本某些故障無法診斷問題,通過設(shè)定拒識模式并通過增加神經(jīng)元方法對無法診斷故障進(jìn)行學(xué)習(xí)擴(kuò)充,重新訓(xùn)練神經(jīng)網(wǎng)絡(luò),能對新故障完全診斷并提升整體診斷精度;針對實(shí)際工業(yè)應(yīng)用中需要處理海量數(shù)據(jù),診斷系統(tǒng)存在優(yōu)化約簡的問題,本文采用領(lǐng)域覆蓋和模糊覆蓋算法對神經(jīng)網(wǎng)絡(luò)進(jìn)行優(yōu)化構(gòu)造,診斷范圍從最大軟故障擴(kuò)大為所有軟故障模式,診斷精度分別能達(dá)到89.3%和94.9%,并且能降低神經(jīng)元個數(shù),減小計(jì)算難度、計(jì)算量,降低診斷時間,同時使用模糊覆蓋算法對最大軟故障模式進(jìn)行診斷,單選診斷率為85.71%,三選能實(shí)現(xiàn)100%診斷。實(shí)驗(yàn)證明本文方法具有很強(qiáng)容錯能力,泛化能力好,特別適合復(fù)雜環(huán)境下電路故障診斷,具有良好發(fā)展前景。
[Abstract]:The research on fault diagnosis of analog circuits has been studied for decades. Affected by element tolerance, nonlinear, temperature drift and other factors, this subject has always been a difficult and hot research topic. Among electronic devices, analog circuits account for a small proportion, but the fault problems occur the most. The reliability of electronic devices depends on the reliability of analog circuits to a large extent. Under the background of the increasing size of the circuit, the traditional method shows the limitations of weak data processing ability, long diagnosis time and complex diagnosis process. Artificial intelligence method, especially neural network method, provides a new research direction for it. It can adapt to nonlinear circuit diagnosis, does not rely on specific circuits, and reduces the difficulty of diagnosis, but it is still insufficient in diagnosis time, diagnosis accuracy, error correction and fault tolerance, and the modeling process is complex. The constructive neural network based on coverage theory is a new neural network method proposed in recent years. Compared with the traditional neural network, it has the advantages of simple modeling, good robustness and strong computing ability, and is suitable for massive data. The industrial application in complex environment and so on can greatly reduce the operation time. In this paper, based on the theory of neural network, the existing fault diagnosis systems need to extract fault features, the process of fault modeling is complex, and it is difficult to expand the knowledge in the operation of the system. In this paper, the constructive neural network method is applied to analog circuit fault diagnosis, and good diagnosis results are obtained. In this paper, based on the spherical model of M 鈮，
本文編號：2480995
[Abstract]:The research on fault diagnosis of analog circuits has been studied for decades. Affected by element tolerance, nonlinear, temperature drift and other factors, this subject has always been a difficult and hot research topic. Among electronic devices, analog circuits account for a small proportion, but the fault problems occur the most. The reliability of electronic devices depends on the reliability of analog circuits to a large extent. Under the background of the increasing size of the circuit, the traditional method shows the limitations of weak data processing ability, long diagnosis time and complex diagnosis process. Artificial intelligence method, especially neural network method, provides a new research direction for it. It can adapt to nonlinear circuit diagnosis, does not rely on specific circuits, and reduces the difficulty of diagnosis, but it is still insufficient in diagnosis time, diagnosis accuracy, error correction and fault tolerance, and the modeling process is complex. The constructive neural network based on coverage theory is a new neural network method proposed in recent years. Compared with the traditional neural network, it has the advantages of simple modeling, good robustness and strong computing ability, and is suitable for massive data. The industrial application in complex environment and so on can greatly reduce the operation time. In this paper, based on the theory of neural network, the existing fault diagnosis systems need to extract fault features, the process of fault modeling is complex, and it is difficult to expand the knowledge in the operation of the system. In this paper, the constructive neural network method is applied to analog circuit fault diagnosis, and good diagnosis results are obtained. In this paper, based on the spherical model of M 鈮，
本文編號：2480995
本文鏈接：http://www.wukwdryxk.cn/kejilunwen/dianzigongchenglunwen/2480995.html
最近更新
教材專著
