發(fā)布時(shí)間：2018-01-11 10:37

  本文關(guān)鍵詞：基于GA-BP神經(jīng)網(wǎng)絡(luò)的內(nèi)燃機(jī)系統(tǒng)故障診斷研究　出處：《昆明理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 內(nèi)燃機(jī) 故障診斷 神經(jīng)網(wǎng)絡(luò) 遺傳算法 BP算法

【摘要】：內(nèi)燃機(jī)在諸多領(lǐng)域都起到十分重要的作用。例如,大型農(nóng)業(yè)裝備、工程機(jī)械設(shè)備、軍工重裝武器設(shè)備、軍艦船舶等,內(nèi)燃機(jī)是名副其實(shí)的工業(yè)動(dòng)力。搗固車是大型鐵路養(yǎng)護(hù)設(shè)備,是典型的大機(jī)。其動(dòng)輒百噸的自重工作時(shí)完全依靠?jī)?nèi)燃機(jī)為其提供動(dòng)力,包括車載衛(wèi)星小車的全部動(dòng)力和系統(tǒng)供電等。因此,針對(duì)搗固車而言,內(nèi)燃機(jī)系統(tǒng)是整個(gè)設(shè)備的核心之一。當(dāng)內(nèi)燃機(jī)出現(xiàn)故障時(shí),如果不能被及時(shí)發(fā)現(xiàn)這可能導(dǎo)致內(nèi)燃機(jī)持續(xù)受損,給社會(huì)生產(chǎn)帶來隱患,而機(jī)械設(shè)備自身也會(huì)帶傷運(yùn)行,影響機(jī)械壽命。采用定期入庫檢修雖然可以緩解這一現(xiàn)象,但是在內(nèi)燃機(jī)運(yùn)轉(zhuǎn)良好的情況下進(jìn)行檢修既浪費(fèi)了人力物力,又降低了工作效率。倘若內(nèi)燃機(jī)已經(jīng)發(fā)生故障,而此時(shí)按計(jì)劃未到檢修時(shí)間,機(jī)械設(shè)備將帶病工作。因而,對(duì)內(nèi)燃機(jī)系統(tǒng)進(jìn)行故障診斷分析,及時(shí)發(fā)現(xiàn)問題及時(shí)處理,這顯得重要而有意義。本文通過分析當(dāng)前故障診斷的常用手段和方法發(fā)現(xiàn),有些診斷模型始終圍繞機(jī)械振動(dòng)進(jìn)行研究、而有些則簡(jiǎn)單的利用單一算法進(jìn)行分析。這些都或多或少的存在一些不足和局限。受仿生技術(shù)的啟發(fā),本文的研究對(duì)象和研究手段都進(jìn)行了改進(jìn)。鑒于醫(yī)生對(duì)病人的檢查方法,本文選取內(nèi)燃機(jī)的排放物作為研究對(duì)象,通過內(nèi)燃機(jī)排出的碳氧化物、氮氧化物、碳?xì)浠衔铩⒁约芭欧盼锏臏貪穸�、排出物的速率等相關(guān)數(shù)據(jù)進(jìn)行分析研究。因?yàn)閮?nèi)燃機(jī)的故障形成都通過其機(jī)械狀況、氣缸內(nèi)部燃燒情況反映了出來。例如,內(nèi)燃機(jī)燃油系統(tǒng)的噴油嘴堵塞,會(huì)造成進(jìn)入燃燒室的油料偏少,這會(huì)導(dǎo)致混合氣過稀,燃燒不充分,在排出物中直接反應(yīng)就是碳氧化物含量增多。本文結(jié)合生物神經(jīng)網(wǎng)絡(luò)介紹了人工神經(jīng)網(wǎng)絡(luò),經(jīng)過分析,BP神經(jīng)網(wǎng)絡(luò)在某些區(qū)域容易陷入極優(yōu)狀態(tài),故提出引入動(dòng)量項(xiàng)和自適應(yīng)學(xué)習(xí)率進(jìn)行改進(jìn)。改良優(yōu)化后的BP神經(jīng)網(wǎng)絡(luò)表現(xiàn)出良好的訓(xùn)練性能,但其缺陷不能被徹底消除。而遺傳算法GA在全局搜尋方面性能很強(qiáng),所以將兩者進(jìn)行融合。融合手段即優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的權(quán)值和閾值,還可以用遺傳算法優(yōu)化其網(wǎng)絡(luò)架構(gòu)。BP算法在網(wǎng)絡(luò)訓(xùn)練過程中,通過誤差反向修正,獲得網(wǎng)絡(luò)待輸入的權(quán)值和閾值。如此,兩種者優(yōu)點(diǎn)互相補(bǔ)償,就能充分發(fā)揮彼此的算法優(yōu)點(diǎn)。在建模和實(shí)驗(yàn)過程中,基于改良遺傳算法優(yōu)化的BP神經(jīng)網(wǎng)絡(luò),本論文構(gòu)建了內(nèi)燃機(jī)故障診斷模型,利用DEUTZ的F12L413F風(fēng)冷柴油機(jī)排出物的數(shù)據(jù)進(jìn)行研究,并利用MATLAB對(duì)故障診斷模型進(jìn)行仿真分析。對(duì)比BP神經(jīng)網(wǎng)絡(luò)和優(yōu)化后的GA-BP神經(jīng)網(wǎng)絡(luò)模型的仿真結(jié)果可以發(fā)現(xiàn),BP神經(jīng)網(wǎng)絡(luò)大致經(jīng)過342步訓(xùn)練完成收斂,而優(yōu)化后的GA-BP神經(jīng)網(wǎng)絡(luò)經(jīng)過約60步訓(xùn)練完成收斂。實(shí)驗(yàn)數(shù)據(jù)表明,新改良的GA-BP神經(jīng)網(wǎng)絡(luò)結(jié)合新的故障診斷對(duì)象(內(nèi)燃機(jī)排出物),使內(nèi)燃機(jī)系統(tǒng)的故障診斷精確度有顯著提升。
[Abstract]:Internal combustion engines play a very important role in many fields, such as large-scale agricultural equipment, construction machinery equipment, military heavy weapons equipment, warships, and so on. Internal combustion engine is a real industrial power. Tamping car is a large railway maintenance equipment, is a typical large machine. Its 100 tons of deadweight work is completely dependent on the internal combustion engine to provide power for it. Therefore, for tamper, the internal combustion engine system is one of the core of the whole equipment. If it can not be detected in time, it may cause continuous damage to the internal combustion engine, bring hidden trouble to the social production, and the mechanical equipment itself will also run with injury. Although this phenomenon can be alleviated by the use of periodic storage maintenance, it is a waste of manpower and material resources to carry out maintenance under the condition of good operation of internal combustion engine. If the internal combustion engine has broken down and the time of maintenance is not up to schedule, the mechanical equipment will work with malfunction. Therefore, the fault diagnosis and analysis of the internal combustion engine system will be carried out. It is important and meaningful to find problems in time and deal with them in time. By analyzing the common methods and methods of fault diagnosis at present, this paper finds that some diagnosis models are always focused on mechanical vibration. Some are simple to use a single algorithm for analysis. These are more or less there are some shortcomings and limitations. Inspired by the bionic technology. In view of the doctor's examination method of patients, this paper selects the emission of internal combustion engine as the research object, the carbon oxide, nitrogen oxide discharged through the internal combustion engine. Data on hydrocarbons, temperature and humidity of emissions, rate of exhaust, etc., are analyzed because the failure of the internal combustion engine is reflected by its mechanical condition, combustion inside the cylinder, for example. The blockage of fuel injection nozzle in internal combustion engine fuel system will result in less oil entering the combustion chamber, which will lead to the mixture being too thin and the combustion is not sufficient. The direct reaction in the exhaust is the increase of carbon oxides. This paper introduces the artificial neural network combined with the biological neural network. The BP neural network is easy to fall into the optimal state in some areas. Therefore, it is proposed to introduce momentum term and adaptive learning rate to improve the improved BP neural network with good training performance. But its defects can not be completely eliminated. Genetic algorithm (GA) has a strong performance in global search, so the fusion method is to optimize the weight and threshold of BP neural network. Genetic algorithm can also be used to optimize its network architecture .BP algorithm in the process of network training, through the error reverse correction, to obtain the network input weights and thresholds, so that the advantages of the two kinds of compensation each other. In the process of modeling and experiment, based on BP neural network optimized by improved genetic algorithm, the fault diagnosis model of internal combustion engine is constructed. Using DEUTZ's F12L413F air-cooled diesel engine exhaust data were studied. The simulation results of BP neural network and optimized GA-BP neural network model can be found by using MATLAB to simulate the fault diagnosis model. The BP neural network is approximately trained to complete convergence in 342 steps, while the optimized GA-BP neural network has been trained to complete convergence in about 60 steps. The improved GA-BP neural network combined with the new fault diagnosis object (internal combustion engine exhaust) can improve the accuracy of fault diagnosis of internal combustion engine system.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U216.631;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 謝春麗;張繼洲;;基于遺傳BP神經(jīng)網(wǎng)絡(luò)的電控發(fā)動(dòng)機(jī)故障診斷研究[J];湖北汽車工業(yè)學(xué)院學(xué)報(bào);2016年02期

2 馮長(zhǎng)寶;韓忠偉;孫沫莉;;遺傳算法和神經(jīng)網(wǎng)絡(luò)在船舶柴油機(jī)故障診斷中的應(yīng)用[J];艦船科學(xué)技術(shù);2016年06期

3 余發(fā)山;康洪;;基于GA優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的液壓鉆機(jī)故障診斷[J];電子測(cè)量技術(shù);2016年02期

4 瞿紅春;黃遠(yuǎn)強(qiáng);;基于遺傳-BP神經(jīng)網(wǎng)絡(luò)的航空發(fā)動(dòng)機(jī)氣路故障診斷研究（英文）[J];機(jī)床與液壓;2015年18期

5 王萬玉;陶孫杰;馮旭祥;馬彬彬;;遙感衛(wèi)星接收系統(tǒng)故障診斷專家系統(tǒng)設(shè)計(jì)[J];電訊技術(shù);2015年05期

6 張秦嶺;郭宏;姜旭;;大型無人機(jī)電源系統(tǒng)故障診斷專家系統(tǒng)[J];北京航空航天大學(xué)學(xué)報(bào);2013年08期

7 劉罡;王興成;李放文;吳文慶;蔣一然;;基于遺傳神經(jīng)算法與證據(jù)理論的柴油機(jī)燃油系統(tǒng)故障診斷[J];大連海事大學(xué)學(xué)報(bào);2012年02期

8 李磊;楊峰;趙鵬鵬;;基于故障樹和虛擬儀器的故障診斷系統(tǒng)研究[J];飛航導(dǎo)彈;2011年07期

9 高陽;李國璋;;基于尾氣分析和免疫原理的內(nèi)燃機(jī)故障診斷法[J];車用發(fā)動(dòng)機(jī);2011年03期

10 馬良民;;淺談大型養(yǎng)路機(jī)械搗固裝置總成試驗(yàn)臺(tái)的開發(fā)[J];液壓與氣動(dòng);2011年05期

相關(guān)博士學(xué)位論文 前5條

1 宋志雄;鐵路大型養(yǎng)路機(jī)械若干智能化關(guān)鍵技術(shù)應(yīng)用研究[D];西南交通大學(xué);2013年

2 吳震宇;內(nèi)燃機(jī)故障診斷若干理論與相關(guān)技術(shù)的研究[D];東北大學(xué);2010年

3 李國勇;電控汽油機(jī)智能控制策略及故障診斷的研究[D];太原理工大學(xué);2007年

4 閆兵;基于曲軸角振動(dòng)信號(hào)的內(nèi)燃機(jī)故障診斷系統(tǒng)關(guān)鍵技術(shù)研究[D];西南交通大學(xué);2005年

5 馬笑瀟;智能故障診斷中的機(jī)器學(xué)習(xí)新理論及其應(yīng)用研究[D];重慶大學(xué);2002年

相關(guān)碩士學(xué)位論文 前10條

1 張偉;基于專家系統(tǒng)的故障診斷在汽車發(fā)動(dòng)機(jī)上的應(yīng)用[D];太原理工大學(xué);2011年

2 劉立恒;基于LabVIEW的電噴發(fā)動(dòng)機(jī)的故障分析與仿真[D];重慶交通大學(xué);2011年

3 李虎;BP算法的改進(jìn)及其在PID優(yōu)化控制中的應(yīng)用研究[D];西安科技大學(xué);2012年

4 張龍;汽油機(jī)車載診斷系統(tǒng)的診斷策略和標(biāo)定研究[D];西華大學(xué);2014年

5 李俊松;基于神經(jīng)網(wǎng)絡(luò)的混合動(dòng)力汽車故障診斷研究[D];武漢理工大學(xué);2003年

6 陳浩華;分布式神經(jīng)計(jì)算平臺(tái)的設(shè)計(jì)與實(shí)現(xiàn)[D];浙江大學(xué);2005年

7 郎敏峰;遺傳算法的改進(jìn)及其在組合優(yōu)化中的應(yīng)用[D];華東師范大學(xué);2005年

8 榮立燁;基于神經(jīng)網(wǎng)絡(luò)的航空發(fā)動(dòng)機(jī)控制研究[D];西北工業(yè)大學(xué);2007年

9 趙偉;船舶柴油機(jī)監(jiān)測(cè)與故障診斷技術(shù)研究[D];大連海事大學(xué);2006年

10 苗君明;基于神經(jīng)網(wǎng)絡(luò)的汽車發(fā)動(dòng)機(jī)智能故障診斷研究[D];沈陽航空工業(yè)學(xué)院;2006年

，

本文編號(hào)：1409221