本文關(guān)鍵詞：柴油機(jī)故障的集成診斷方法研究　出處：《西安石油大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 集成學(xué)習(xí) 支持向量機(jī) 遺傳算法 柴油機(jī) 故障診斷

【摘要】：柴油機(jī)作為一種動(dòng)力設(shè)備,在車輛、船舶、電站、工程機(jī)械和農(nóng)用機(jī)械等領(lǐng)域都有著廣泛的應(yīng)用。柴油機(jī)具有零部件多、運(yùn)動(dòng)復(fù)雜、工作環(huán)境惡劣等特點(diǎn),因此其出現(xiàn)故障的概率相對(duì)較高,故障診斷的研究在保證整個(gè)設(shè)備正常運(yùn)行中具有非常重要的意義。隨著智能化技術(shù)的發(fā)展,故障診斷方法也日益完善。論文在學(xué)習(xí)和總結(jié)現(xiàn)有方法和技術(shù)的基礎(chǔ)上,基于集成學(xué)習(xí)理論,對(duì)柴油機(jī)故障診斷方法進(jìn)行深入探討。以支持向量機(jī)為子學(xué)習(xí)器的集成學(xué)習(xí)理論應(yīng)用于柴油機(jī)故障模式識(shí)別中,并綜合采用BP神經(jīng)網(wǎng)絡(luò)、遺傳算法和單個(gè)支持向量機(jī)就柴油機(jī)故障診斷中運(yùn)行狀態(tài)的分類識(shí)別這一關(guān)鍵環(huán)節(jié)進(jìn)行系統(tǒng)的對(duì)比分析研究。針對(duì)柴油機(jī)正常狀態(tài)以及出油閥磨損、供油多等六種故障狀態(tài)下的振動(dòng)信號(hào)提取了時(shí)域信號(hào)特征和子帶能量特征,結(jié)合不同方法在故障模式識(shí)別上的優(yōu)勢(shì),論文在重點(diǎn)研究單個(gè)支持向量機(jī)和支持向量機(jī)集成學(xué)習(xí)算法故障診斷技術(shù)的基礎(chǔ)上,研究了BP神經(jīng)網(wǎng)絡(luò)和遺傳算法在柴油機(jī)故障診斷中的應(yīng)用。建立了支持向量機(jī)故障診斷模型,并利用交叉驗(yàn)證方法得出最優(yōu)參數(shù);基于Boosting算法建立支持向量機(jī)集成故障診斷模型;同時(shí)分析研究了BP神經(jīng)網(wǎng)絡(luò)和遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)故障診斷模型,并與基于集成學(xué)習(xí)構(gòu)建的強(qiáng)學(xué)習(xí)器診斷模型對(duì)比分析。研究結(jié)果表明,基于集成學(xué)習(xí)的支持向量機(jī)模型診斷結(jié)果正確率高于單個(gè)支持向量機(jī)方法和支持向量機(jī)參數(shù)優(yōu)化以后故障診斷結(jié)果正確率,且明顯高于BP神經(jīng)網(wǎng)絡(luò)和遺傳優(yōu)化BP神經(jīng)網(wǎng)絡(luò)在柴油機(jī)故障診斷中的應(yīng)用結(jié)果。成功驗(yàn)證了基于集成學(xué)習(xí)構(gòu)建強(qiáng)可學(xué)習(xí)的構(gòu)想,即集成學(xué)習(xí)應(yīng)用于柴油機(jī)故障診斷的可行性。
[Abstract]:As a kind of power equipment, diesel engine has been widely used in the fields of vehicle, ship, power station, construction machinery and agricultural machinery. Therefore, the probability of failure is relatively high, the study of fault diagnosis is very important to ensure the normal operation of the whole equipment. With the development of intelligent technology. The method of fault diagnosis is becoming more and more perfect. This paper studies and summarizes the existing methods and techniques, and based on the integrated learning theory. The integrated learning theory based on support vector machine (SVM) is applied to diesel engine fault pattern recognition, and BP neural network is used comprehensively. Genetic algorithm (GA) and single support vector machine (SVM) are used to compare and analyze the key link of diesel engine fault diagnosis in classification and recognition, aiming at the normal state of diesel engine and the wear of oil delivery valve. The vibration signals in six kinds of fault states, such as oil supply, extracted the time domain signal characteristics and sub-band energy characteristics, and combined with the advantages of different methods in fault pattern recognition. This paper focuses on the single support vector machine and support vector machine integrated learning algorithm fault diagnosis technology. The application of BP neural network and genetic algorithm in diesel engine fault diagnosis is studied. The support vector machine integrated fault diagnosis model is established based on Boosting algorithm. At the same time, BP neural network and genetic algorithm optimized BP neural network fault diagnosis model are analyzed and compared with the strong learning model based on integrated learning. The diagnostic accuracy of SVM model based on ensemble learning is higher than that of single SVM method and SVM parameters optimization. The application results of BP neural network and genetic optimization BP neural network in diesel engine fault diagnosis are obviously higher than that of BP neural network. That is, integrated learning is feasible for diesel engine fault diagnosis.
【學(xué)位授予單位】：西安石油大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TK428;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 曹龍漢,曹長(zhǎng)修,孫穎楷,景有泉,郭振;柴油機(jī)故障診斷技術(shù)的現(xiàn)狀及展望[J];重慶大學(xué)學(xué)報(bào)(自然科學(xué)版);2001年06期

2 李業(yè)波;李秋紅;黃向華;趙永平;;航空發(fā)動(dòng)機(jī)傳感器故障與部件故障診斷技術(shù)[J];北京航空航天大學(xué)學(xué)報(bào);2013年09期

3 呂鋒;李翔;杜文霞;;基于MultiBoost的集成支持向量機(jī)分類方法及其應(yīng)用[J];控制與決策;2015年01期

4 劉世元,杜潤(rùn)生,楊叔子;柴油機(jī)缸蓋振動(dòng)信號(hào)的小波包分解與診斷方法研究[J];振動(dòng)工程學(xué)報(bào);2000年04期

5 趙宏,夏哲雷;優(yōu)化遺傳神經(jīng)網(wǎng)絡(luò)及其在機(jī)械故障診斷中的應(yīng)用[J];中國(guó)計(jì)量學(xué)院學(xué)報(bào);2004年02期

相關(guān)博士學(xué)位論文 前1條

1 李敏通;柴油機(jī)振動(dòng)信號(hào)特征提取與故障診斷方法研究[D];西北農(nóng)林科技大學(xué);2012年

相關(guān)碩士學(xué)位論文 前1條

1 張北鷗;基于小波包變換和Elman人工神經(jīng)網(wǎng)絡(luò)的電機(jī)故障診斷系統(tǒng)的研究[D];武漢理工大學(xué);2010年

，

本文編號(hào)：1427100