本文關(guān)鍵詞： 支持向量機(jī)（SVM） 遺傳算法(GA) 模式識(shí)別 趨勢(shì)預(yù)測(cè) 小波變換 滾動(dòng)軸承 齒輪　出處：《北京化工大學(xué)》2012年碩士論文　論文類型：學(xué)位論文

【摘要】：本文開(kāi)展了基于支持向量機(jī)（Support Vector Machine—SVM）與遺傳算法(Genetic Algorithms—GA)的故障模式識(shí)別及趨勢(shì)預(yù)測(cè)方法研究，利用支持向量機(jī)對(duì)滾動(dòng)軸承典型故障進(jìn)行了模式識(shí)別，同時(shí)應(yīng)用預(yù)測(cè)模型對(duì)齒輪狀態(tài)趨勢(shì)進(jìn)行預(yù)測(cè)，并利用遺傳算法分別對(duì)支持向量機(jī)分類過(guò)程和趨勢(shì)預(yù)測(cè)過(guò)程進(jìn)行了優(yōu)化分析，主要工作如下： （1）基于SVM可以解決小樣本學(xué)習(xí)問(wèn)題這一優(yōu)點(diǎn)，提出利用SVM對(duì)滾動(dòng)軸承在正常、內(nèi)圈缺陷、外圈缺陷和滾動(dòng)體缺陷條件下工作的四種狀態(tài)信號(hào)進(jìn)行識(shí)別分類,為了提高分類識(shí)別率，利用遺傳算法具有優(yōu)良空間搜索性能的特點(diǎn)，對(duì)分類過(guò)程中的兩個(gè)重要核參數(shù)初始值進(jìn)行優(yōu)化，提出了基于GA算法的改進(jìn)SVM識(shí)別方法，研究結(jié)果表明：核參數(shù)初始值經(jīng)過(guò)GA優(yōu)化后SVM分類識(shí)別率得到了明顯提高，能較好地實(shí)現(xiàn)軸承典型故障類型的識(shí)別。 （2）為解決低轉(zhuǎn)速滾動(dòng)軸承故障特征難以提取的問(wèn)題，利用小波變換技術(shù)具有高低頻分離、局部細(xì)化和時(shí)頻域內(nèi)特征提取等性能優(yōu)點(diǎn)，提出基于小波變換技術(shù)的低轉(zhuǎn)速滾動(dòng)軸承故障特征提取方法，對(duì)低轉(zhuǎn)速軸承正常、外圈缺陷、內(nèi)圈缺陷和滾動(dòng)體缺陷等四種狀態(tài)下的振動(dòng)信號(hào)進(jìn)行診斷分析，并結(jié)合SVM對(duì)軸承典型故障進(jìn)行了分類識(shí)別，由分析結(jié)果可知，利用小波變換與支持向量機(jī)技術(shù)相結(jié)合的方法處理低轉(zhuǎn)速滾動(dòng)軸承故障問(wèn)題能夠取得很好的效果。 （3）為了預(yù)測(cè)齒輪狀態(tài)趨勢(shì)發(fā)展?fàn)顩r，，建立三階函數(shù)方程預(yù)測(cè)模型對(duì)齒輪趨勢(shì)發(fā)展進(jìn)行模擬分析研究，利用GA良好的空間搜索性，提出基于GA的預(yù)測(cè)模型函數(shù)優(yōu)化方法，將獲得的新預(yù)測(cè)模型函數(shù)與通過(guò)線性擬合原理獲得的二階、三階函數(shù)做了對(duì)比分析研究。研究結(jié)果顯示：經(jīng)過(guò)GA優(yōu)化后獲得的三階函數(shù)方程預(yù)測(cè)模型能夠?qū)崿F(xiàn)齒輪故障趨勢(shì)發(fā)展預(yù)測(cè)模擬。
[Abstract]:This paper carried out based on support vector machine (Support Vector Machine - SVM) and genetic algorithm (Genetic Algorithms GA) to study the fault pattern recognition and prediction method based on support vector machine for pattern recognition of typical faults of rolling bearings, and applied to the prediction of the gear state trend, and the support vector forecasting classification process and trend analysis process was optimized by genetic algorithm, the main work is as follows:
(1) the advantages of SVM can solve small sample learning problems based on the proposed for rolling bearings in normal, inner defects with SVM outer defects and four kinds of rolling state signals of defects under the working conditions of the recognition and classification, in order to improve the classification accuracy, algorithm has excellent performance characteristics using the genetic search space, the two important parameters in the process of classification of the initial nuclear value optimization, this paper proposes an improved SVM recognition method based on GA algorithm, the results show that: the kernel parameter initial value GA optimized SVM classification rate has been significantly improved, can achieve better recognition of typical bearing fault types.
(2) to solve the problem of low speed rolling bearing fault feature extraction difficult problem, using wavelet transform technology with high frequency separation, local refinement and time-frequency domain feature extraction performance advantages, the low speed of wavelet transform technique of rolling bearing fault feature extraction method based on the low speed bearing outer ring inner ring is normal, defects, defects and the rolling defects diagnosis and analysis of vibration signals under four conditions, combined with the SVM classification of typical bearing faults, according to the analysis results, combined with the method of using wavelet transform and support vector machine technology with low speed rolling bearing fault problem can achieve good results.
(3) in order to predict the trend of gear fault, the establishment of three order function equation prediction model was simulated and analyzed to study the development trend of gear, the use of GA good space search, optimization method is proposed to predict the model function based on GA function, a new prediction model will be obtained by linear fitting with the principle of order two, order three the function to do the comparative analysis. The research results show that: three order function equation obtained by optimized GA prediction model can simulate the development trend of gear fault prediction.

【學(xué)位授予單位】：北京化工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TH165.3

【引證文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 李卓文;基于粗糙分類的路徑不精確研究及應(yīng)用[D];河南師范大學(xué);2013年

本文編號(hào)：1515622