本文關(guān)鍵詞： 轉(zhuǎn)子系統(tǒng) 信息熵 混合雜草優(yōu)化算法 神經(jīng)網(wǎng)絡(luò)　出處：《蘭州理工大學(xué)》2012年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來，隨著現(xiàn)代機械設(shè)備的大型化、復(fù)雜化、自動化和連續(xù)化，開展機械設(shè)備的故障診斷技術(shù)的研究具有重要的現(xiàn)實意義。目前，國內(nèi)外學(xué)者在此方面做了大量的工作，使得相關(guān)的理論與應(yīng)用取得的迅猛的發(fā)展。機械故障診斷是通過研究故障與征兆之間的關(guān)系來判斷設(shè)備故障的，而故障與征兆之間表現(xiàn)出的非常復(fù)雜的非線性關(guān)系，很難用數(shù)學(xué)模型加以精確的描述，給機械的故障診斷帶來很大的不便。人工神經(jīng)網(wǎng)絡(luò)是一種重要的人工智能行為，是一個非線性計算系統(tǒng)，可以實現(xiàn)故障與征兆之間復(fù)雜的非線性映射關(guān)系，因此在機械故障診斷領(lǐng)域得到了極大的應(yīng)用潛力。 本文構(gòu)建的混合雜草優(yōu)化算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)預(yù)測模型，以轉(zhuǎn)子試驗臺模擬的大量的故障數(shù)據(jù)為支持，采用信息熵方法來定量的對故障數(shù)據(jù)進(jìn)行特征提取，混合的雜草優(yōu)化算法優(yōu)化神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)。主要工作內(nèi)容和研究成果如下： （1）在轉(zhuǎn)子實驗臺上模擬了四種典型故障，對信息熵的性質(zhì)和時域的奇異譜熵、頻域的功率譜熵、時頻域的小波能譜熵和小波空間譜熵進(jìn)行了較為系統(tǒng)的研究和探討。 （2）以四類譜熵為原始數(shù)據(jù)，對數(shù)據(jù)進(jìn)行歸一化處理，并建立訓(xùn)練樣本庫和測試樣本庫。 （3）在分析遺傳算法、粒子群算法優(yōu)點的基礎(chǔ)上，將遺傳算法中的交叉算子、粒子群算法的矢量操作引入IWO，提出了HIWO。 （4）建立了HIWO優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型，由HIWO算法訓(xùn)練BP網(wǎng)絡(luò)訓(xùn)練的初始最優(yōu)權(quán)值和閾值，然后在訓(xùn)練好的BP神經(jīng)網(wǎng)絡(luò)中對測試樣本進(jìn)行預(yù)測，并且與遺傳算法、粒子群算法及IWO優(yōu)化的神經(jīng)網(wǎng)絡(luò)進(jìn)行了對比分析。 （5）基于HIWO算法流程開發(fā)了一套MATLAB GUI的轉(zhuǎn)子故障診斷系統(tǒng)，，子系統(tǒng)一實現(xiàn)對振動信號的消噪分析，頻譜分析，軸心軌跡分析等；子系統(tǒng)二實現(xiàn)熵值數(shù)據(jù)的歸一化；子系統(tǒng)三實現(xiàn)四種算法優(yōu)化神經(jīng)網(wǎng)絡(luò)的初始權(quán)值和閾值；子系統(tǒng)四根據(jù)樣本特點對分類器進(jìn)行參數(shù)尋優(yōu)，實現(xiàn)對未知故障的判別，實驗證明了該系統(tǒng)的有效性。
[Abstract]:In recent years, with the large-scale, complex, automation and continuity of modern mechanical equipment, it is of great practical significance to carry out the research on fault diagnosis technology of mechanical equipment. At present, many scholars at home and abroad have done a lot of work in this field. Mechanical fault diagnosis is based on the study of the relationship between the fault and the symptoms to judge the fault of the equipment, and the relationship between the fault and the symptoms shows a very complex nonlinear relationship. It is difficult to describe accurately by mathematical model, which brings great inconvenience to the fault diagnosis of machinery. Artificial neural network is an important artificial intelligence behavior and a nonlinear computing system. The complex nonlinear mapping relationship between fault and symptom can be realized, so it has great application potential in the field of mechanical fault diagnosis. In this paper, a hybrid weed optimization algorithm is constructed to optimize BP neural network prediction model. Based on a large number of fault data simulated by the rotor test-bed, the information entropy method is used to quantitatively extract the fault data. The hybrid weed optimization algorithm is used to optimize the neural network structure. The main work and research results are as follows:. In this paper, four typical faults are simulated on the rotor test bench. The properties of information entropy and singular spectral entropy in time domain, power spectrum entropy in frequency domain, wavelet spectrum entropy in time-frequency domain and wavelet space spectral entropy in time-frequency domain are systematically studied and discussed. (2) taking four kinds of spectral entropy as raw data, the data are normalized, and the training sample database and test sample database are established. On the basis of analyzing the advantages of genetic algorithm and particle swarm optimization algorithm, the crossover operator and the vector operation of particle swarm optimization algorithm in genetic algorithm are introduced into IWO.The HIWO is proposed. (4) the HIWO optimized BP neural network model is established. The initial optimal weights and thresholds of BP network training are trained by HIWO algorithm, and then the test samples are predicted in the trained BP neural network and compared with genetic algorithm. Particle swarm optimization (PSO) and IWO neural network are compared and analyzed. 5) based on HIWO algorithm flow, a rotor fault diagnosis system based on MATLAB GUI is developed. Subsystem 1 realizes noise reduction analysis, spectrum analysis, axis locus analysis, etc. Subsystem 2 realizes normalization of entropy value data. Subsystem 3 implements four algorithms to optimize the initial weights and thresholds of neural networks, subsystem 4 optimizes the classifier parameters according to the characteristics of samples, and realizes the identification of unknown faults. The experiment proves the effectiveness of the system.
【學(xué)位授予單位】：蘭州理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：TH165.3;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 駱德漢,陳偉海;基于 ANN 的故障診斷專家系統(tǒng)的應(yīng)用研究[J];北京航空航天大學(xué)學(xué)報;1998年05期

2 楊維,李歧強;粒子群優(yōu)化算法綜述[J];中國工程科學(xué);2004年05期

3 張氫;陳丹丹;秦仙蓉;高倩;;雜草算法收斂性分析及其在工程中的應(yīng)用[J];同濟大學(xué)學(xué)報(自然科學(xué)版);2010年11期

相關(guān)碩士學(xué)位論文 前6條

1 霍天龍;基于支持向量機的轉(zhuǎn)子系統(tǒng)故障診斷方法研究[D];蘭州理工大學(xué);2011年

2 崔慧敏;基于神經(jīng)網(wǎng)絡(luò)的旋轉(zhuǎn)機械故障診斷方法研究[D];燕山大學(xué);2007年

3 王慧;結(jié)合遺傳算法的粒子群優(yōu)化模型及其應(yīng)用研究[D];山東師范大學(xué);2008年

4 黃志輝;人工神經(jīng)網(wǎng)絡(luò)優(yōu)化算法研究[D];中南大學(xué);2009年

5 徐雅香;粒子群算法及在神經(jīng)網(wǎng)絡(luò)分類器中的應(yīng)用[D];西安電子科技大學(xué);2008年

6 楊娟;轉(zhuǎn)子故障信號的量化特征提取方法研究[D];蘭州理工大學(xué);2010年

本文編號：1523381