【摘要】：齒輪箱是機(jī)械設(shè)備中重要的傳動(dòng)部件，，對(duì)齒輪箱進(jìn)行故障診斷研究有著非�，F(xiàn)實(shí)的意義。本文將EMD(Empirical Mode Decomposition)近似熵和LSSVM(Least SquareSupport Vector Machine)相結(jié)合來實(shí)現(xiàn)對(duì)齒輪箱的故障診斷。 EMD方法對(duì)信號(hào)處理具有良好的局域化特性，同時(shí)針對(duì)非線性、非平穩(wěn)的信號(hào)有著非常好的分解效果。近似熵在表征信號(hào)動(dòng)力學(xué)特性方面能包含更多的信息，對(duì)提取信號(hào)的故障特征有著先天的優(yōu)勢(shì)。LSSVM是針對(duì)SVM(Support Vector Machine)作為分類算法中存在著運(yùn)行時(shí)間過長(zhǎng)和計(jì)算量過大的弊端做出的改進(jìn)和變形，實(shí)驗(yàn)證明LSSVM在齒輪箱故障診斷中能準(zhǔn)確而快速的實(shí)現(xiàn)故障識(shí)別。 本文首先闡述了齒輪箱故障診斷的意義、目的及國(guó)內(nèi)外研究現(xiàn)狀，同時(shí)對(duì)目前的故障診斷技術(shù)進(jìn)行了概述。其次介紹了齒輪箱振動(dòng)機(jī)理和故障類型，接著重點(diǎn)研究了EMD方法在分解信號(hào)中存在著端點(diǎn)效應(yīng)這樣的弊端，提出了鏡像延拓以及在信號(hào)序列上進(jìn)行了加窗函數(shù)相結(jié)合的辦法對(duì)EMD方法的改進(jìn)。實(shí)驗(yàn)證明經(jīng)過改進(jìn)之后的EMD方法在信號(hào)分解上取得了非常好的效果。然后應(yīng)用EMD和近似熵相結(jié)合的方法完成了對(duì)齒輪箱故障特征的提取，分別從理論上和具體實(shí)驗(yàn)中對(duì)SVM和LSSVM進(jìn)行了對(duì)比，突出LSSVM在故障識(shí)別上的優(yōu)勢(shì)。最后利用改進(jìn)后的EMD方法結(jié)合近似熵完成對(duì)故障特征的提取，利用LSSVM對(duì)提取的故障特征進(jìn)行識(shí)別，然后通過對(duì)比其他幾種不同的故障診斷方法，表明EMD近似熵和LSSVM能夠提高齒輪箱故障診斷的準(zhǔn)確率和效率。
[Abstract]:Gearbox is an important transmission component in mechanical equipment, so it is of great practical significance to study the fault diagnosis of gearbox. In this paper, EMD (Empirical Mode Decomposition) approximate entropy and LSSVM (Least SquareSupport Vector Machine) are combined to realize the fault diagnosis of gearbox. The EMD method has good localization characteristics for signal processing, and has a very good decomposition effect for nonlinear and non-stationary signals. Approximate entropy can contain more information in describing the dynamic characteristics of the signal. LSSVM has inherent advantages in extracting fault features of signals. LSSVM is an improvement and deformation for the disadvantages of SVM (Support Vector Machine) as a classification algorithm, which has too long running time and too much computation. The experimental results show that LSSVM can realize fault identification accurately and quickly in gearbox fault diagnosis. This paper first expounds the significance, purpose and research status of gearbox fault diagnosis at home and abroad, and summarizes the current fault diagnosis technology. Secondly, the vibration mechanism and fault type of gearbox are introduced, and then the end-point effect of EMD method in decomposing signal is studied. The mirror image extension and the combination of windowing function on the signal sequence are proposed to improve the EMD method. The experimental results show that the improved EMD method has achieved very good results in signal decomposition. Then the fault features of gearbox are extracted by using the method of EMD and approximate entropy. SVM and LSSVM are compared theoretically and in specific experiments to highlight the advantages of LSSVM in fault identification. Finally, the improved EMD method combined with approximate entropy is used to extract the fault features, LSSVM is used to identify the extracted fault features, and then several other fault diagnosis methods are compared. It is shown that EMD approximate entropy and LSSVM can improve the accuracy and efficiency of gearbox fault diagnosis.
【學(xué)位授予單位】：中北大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TH165.3;TH132.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 許寶杰;張建民;徐小力;李建偉;;抑制EMD端點(diǎn)效應(yīng)方法的研究[J];北京理工大學(xué)學(xué)報(bào);2006年03期

2 郭輝;劉賀平;王玲;;最小二乘支持向量機(jī)參數(shù)選擇方法及其應(yīng)用研究[J];系統(tǒng)仿真學(xué)報(bào);2006年07期

3 楊建文;賈民平;;希爾伯特-黃譜的端點(diǎn)效應(yīng)分析及處理方法研究[J];振動(dòng)工程學(xué)報(bào);2006年02期

4 舒忠平;楊智春;;抑制經(jīng)驗(yàn)?zāi)７纸膺吘壭?yīng)的極值點(diǎn)對(duì)稱延拓法[J];西北工業(yè)大學(xué)學(xué)報(bào);2006年05期

5 丁康，王延春;傳動(dòng)箱齒輪和軸故障的振動(dòng)診斷方法的研究[J];振動(dòng)與沖擊;1994年02期

6 鄭勇濤,劉玉樹;支持向量機(jī)解決多分類問題研究[J];計(jì)算機(jī)工程與應(yīng)用;2005年23期

相關(guān)博士學(xué)位論文 前2條

1 楊宇;基于EMD和支持向量機(jī)的旋轉(zhuǎn)機(jī)械故障診斷方法研究[D];湖南大學(xué);2005年

2 程軍圣;基于Hilbert-Huang變換的旋轉(zhuǎn)機(jī)械故障診斷方法研究[D];湖南大學(xué);2005年

相關(guān)碩士學(xué)位論文 前5條

1 成瓊;基于小波分析的齒輪故障診斷研究[D];湖南大學(xué);2001年

2 顧小軍;面向旋轉(zhuǎn)機(jī)械的支持向量機(jī)方法及智能故障診斷系統(tǒng)研究[D];浙江大學(xué);2006年

3 魏于凡;支持向量機(jī)在智能故障診斷中的應(yīng)用研究[D];華北電力大學(xué)（北京）;2007年

4 許昕;齒輪箱故障診斷在安全生產(chǎn)中的應(yīng)用[D];中北大學(xué);2007年

5 楊皓;分形理論應(yīng)用于齒輪箱滾動(dòng)軸承故障診斷的研究[D];長(zhǎng)沙理工大學(xué);2007年

本文編號(hào)：2482905