【摘要】：現(xiàn)代工業(yè)生產(chǎn)以及家用電器都離不開(kāi)各式各樣的電機(jī),人們?cè)谥匾曤姍C(jī)性能的同時(shí)也希望降低電機(jī)轉(zhuǎn)動(dòng)而產(chǎn)生的噪音。目前,工廠(chǎng)對(duì)異音電機(jī)識(shí)別是通過(guò)對(duì)產(chǎn)線(xiàn)工人進(jìn)行培訓(xùn),用人耳聽(tīng)音的方式實(shí)現(xiàn)對(duì)生產(chǎn)線(xiàn)上大批量小型電機(jī)的音質(zhì)檢測(cè),而大量單調(diào)、重復(fù)聽(tīng)音勞動(dòng)致使聽(tīng)覺(jué)疲勞影響主觀(guān)判斷,導(dǎo)致異音電機(jī)混入正常樣本流入市場(chǎng),對(duì)公司的經(jīng)濟(jì)和聲譽(yù)會(huì)造成不可挽回的損失。因此,實(shí)現(xiàn)產(chǎn)線(xiàn)異音電機(jī)的自動(dòng)化檢測(cè)對(duì)電機(jī)產(chǎn)業(yè)的發(fā)展具有十分重要的意義。 本文針對(duì)電機(jī)聲音信號(hào)的統(tǒng)計(jì)特性及其人工質(zhì)檢的特點(diǎn),利用聲傳感器技術(shù)代替人耳實(shí)現(xiàn)對(duì)電機(jī)聲音信號(hào)的采集,這種非接觸式的測(cè)量方式正符合產(chǎn)線(xiàn)測(cè)試設(shè)備簡(jiǎn)單、高效等要求。在電機(jī)平穩(wěn)運(yùn)行情況下采集聲信號(hào),根據(jù)人耳聽(tīng)覺(jué)特性,從電機(jī)聲音的平穩(wěn)性來(lái)分析電機(jī)的頻譜。因?yàn)槿硕鷮?duì)相位不敏感,只需要對(duì)幅度譜來(lái)分析電機(jī)異音的特性,為了突出特征差異的絕對(duì)化,本文采用主成分分析法對(duì)電機(jī)的聲信號(hào)進(jìn)行數(shù)據(jù)壓縮、維數(shù)來(lái)實(shí)現(xiàn)電機(jī)聲信號(hào)提取特征。又考慮電機(jī)聲信號(hào)中可能存在非平穩(wěn)成分,將小波變換引入電機(jī)異音檢測(cè)研究以更精確分析電機(jī)的時(shí)頻特性,利用小波包分解獲取電機(jī)聲信號(hào)的各頻段系數(shù),根據(jù)奇異值分解的特征矢量對(duì)特征的貢獻(xiàn)量進(jìn)行降噪、重構(gòu)并映射到特征矢量所張成的狀態(tài)空間,實(shí)現(xiàn)對(duì)電機(jī)聲信號(hào)的特征提取。同時(shí),電機(jī)聲信號(hào)進(jìn)行小波包分解得到相互正交的頻帶,其能量沒(méi)有損耗且蘊(yùn)含著豐富的特征信息,將電機(jī)的特征映射到能量分布的子空間中,并以歸一化能量構(gòu)建特征矩陣實(shí)現(xiàn)對(duì)異音電機(jī)的特征提取。文中根據(jù)上述方法分別實(shí)現(xiàn)對(duì)電機(jī)聲信號(hào)進(jìn)行特征提取送入分類(lèi)器進(jìn)行訓(xùn)練,取得了良好的效果。 考慮到產(chǎn)線(xiàn)上異音樣本量少、獲取困難,個(gè)體差異造成異音等問(wèn)題難以分析,且電機(jī)異音形成過(guò)程異常復(fù)雜,應(yīng)用支持向量機(jī)一類(lèi)學(xué)習(xí)這種新的機(jī)器學(xué)習(xí)方法實(shí)現(xiàn)對(duì)異音電機(jī)檢測(cè)。該方法以正常電機(jī)樣本為基礎(chǔ)建立的質(zhì)檢判別函數(shù),并不需要異音樣本,避免了其它分類(lèi)算法要求訓(xùn)練樣本類(lèi)別全面和覆蓋廣泛的條件。文章最后通過(guò)大量正常電機(jī)樣本訓(xùn)練并以異音電機(jī)樣本進(jìn)行驗(yàn)證,得出對(duì)異音電機(jī)的識(shí)別率能滿(mǎn)足工廠(chǎng)的需求,達(dá)到了預(yù)期目標(biāo)。
[Abstract]:Modern industrial production and household appliances can not be separated from a variety of motors, people pay attention to the performance of the motor, but also want to reduce the noise generated by motor rotation. At present, the factory to the abnormal sound motor identification is through the production line worker to carry on the training, uses the human ear to listen the sound way to realize to the production line massive batch small electric machine sound quality detection, but a large number of monotonous, Repeated hearing labor causes hearing fatigue to affect subjective judgment and leads to abnormal motor mixed into the normal sample into the market, which will cause irreparable loss to the company's economy and reputation. Therefore, it is very important for the development of the motor industry to realize the automatic detection of the production line abnormal sound motor. In this paper, according to the statistical characteristics of motor sound signal and the characteristics of artificial quality inspection, the sound sensor technology is used to replace the human ear to realize the acquisition of motor sound signal. This non-contact measurement method is in line with the simple testing equipment of the production line. High efficiency, etc. The sound signal is collected under the condition of the motor running smoothly, and the frequency spectrum of the motor is analyzed according to the hearing characteristics of the human ear and the stability of the motor sound. Because the ear is not sensitive to the phase, only the amplitude spectrum is needed to analyze the abnormal sound characteristics of the motor. In order to highlight the absolute characteristic difference, the principal component analysis (PCA) is used to compress the acoustic signal of the motor. Dimension to achieve motor acoustic signal extraction features. Considering that there may be non-stationary components in the motor acoustic signal, wavelet transform is introduced into the research of the abnormal sound detection of the motor to analyze the time-frequency characteristics of the motor more accurately, and the coefficients of each frequency band of the motor acoustic signal are obtained by wavelet packet decomposition. According to the feature vector of singular value decomposition (SVD), the noise is reduced, the feature is reconstructed and mapped to the state space of Zhang Cheng, and the feature extraction of the acoustic signal of the motor is realized. At the same time, the acoustic signal of the motor is decomposed by wavelet packet to obtain the orthogonal frequency band, which has no energy loss and contains abundant characteristic information. The characteristics of the motor are mapped to the subspace of the energy distribution. The feature matrix is constructed with normalized energy to extract the feature of the abnormal sound motor. According to the above methods, the feature extraction of the motor acoustic signal is carried out and sent to the classifier for training, and good results are obtained. Considering that it is difficult to analyze the problems such as the small sample size of abnormal sound on the production line, the difficulty of obtaining the abnormal sound, and the difficulty of analyzing the abnormal sound caused by individual differences, and the abnormal sound formation process of the motor is extremely complex, A new machine learning method, support vector machine (SVM), is applied to detect abnormal sound motors. Based on the normal motor samples, this method establishes the quality inspection discriminant function, and does not need the abnormal sound samples, thus avoiding the condition that other classification algorithms require the training samples to be comprehensive and have extensive coverage. In the end, through the training of a large number of normal motor samples and the verification of the abnormal sound motor samples, it is concluded that the recognition rate of the abnormal sound motor can meet the needs of the factory and achieve the expected goal.
【學(xué)位授予單位】：五邑大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TM301.4;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王建民;讓余奇;;電機(jī)噪聲分析及抑制措施[J];船電技術(shù);2010年08期

2 樊可清,倪一清,高贊明;基于SVM的橋梁狀態(tài)監(jiān)測(cè)方法[J];公路交通科技;2004年01期

3 王海清,蔣寧;主元空間中的故障重構(gòu)方法研究[J];化工學(xué)報(bào);2004年08期

4 張學(xué)工;關(guān)于統(tǒng)計(jì)學(xué)習(xí)理論與支持向量機(jī)[J];自動(dòng)化學(xué)報(bào);2000年01期

5 呂琛,王桂增,邱慶剛;基于聲信號(hào)小波包分析的故障診斷[J];自動(dòng)化學(xué)報(bào);2004年04期

6 邱天;丁艷軍;吳占松;;基于主元分析的故障可檢測(cè)性的統(tǒng)計(jì)指標(biāo)比較[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2006年08期

7 沈艷霞,紀(jì)志成,姜建國(guó);電機(jī)故障診斷的人工智能方法綜述[J];微特電機(jī);2004年02期

8 王鋒,屈梁生;用遺傳編程方法提取和優(yōu)化機(jī)械故障的聲音特征[J];西安交通大學(xué)學(xué)報(bào);2002年12期

9 溫廣瑞,張西寧,屈梁生;奇異值分解技術(shù)在聲音信息分離中的應(yīng)用[J];西安交通大學(xué)學(xué)報(bào);2003年01期

10 李常有;徐敏強(qiáng);郭聳;;利用聲信號(hào)對(duì)滾動(dòng)軸承進(jìn)行故障診斷的研究[J];應(yīng)用聲學(xué);2008年04期

，

本文編號(hào)：2374671