【摘要】：針對(duì)大型風(fēng)機(jī)葉片裂紋故障聲學(xué)診斷問(wèn)題,提出一種非接觸式的葉片狀態(tài)遠(yuǎn)程在線聲學(xué)監(jiān)測(cè)系統(tǒng),給出了葉片裂紋故障的聲學(xué)特征自適應(yīng)提取方法.首先設(shè)計(jì)了面向復(fù)雜環(huán)境噪聲的原始聲信號(hào)預(yù)處理算法,然后采用1/6倍頻程粗略刻畫(huà)葉片聲信號(hào)的頻譜總體變化趨勢(shì),提取無(wú)量綱的倍頻程能量比構(gòu)造支持向量機(jī)分類器的輸入特征向量,最后引入主成分分析法自適應(yīng)的優(yōu)化高維特征空間.風(fēng)場(chǎng)實(shí)測(cè)數(shù)據(jù)驗(yàn)證了該算法的有效性.
[Abstract]:Aiming at the acoustic diagnosis of large fan blade crack fault, a non-contact on-line acoustic monitoring system for blade state is proposed, and the adaptive acoustic feature extraction method for blade crack fault is presented. In this paper, the preprocess algorithm of the original acoustic signal for complex ambient noise is designed, and then the frequency spectrum variation trend of the blade acoustic signal is roughly described by using 1 ~ 6 octave. The input feature vector of support vector machine classifier is constructed by extracting dimensionless octave energy ratio. At last, principal component analysis is introduced to optimize the high-dimensional feature space adaptively. The experimental data of wind field show the effectiveness of the algorithm.
【作者單位】： 北京郵電大學(xué)自動(dòng)化學(xué)院;廣東德風(fēng)科技有限公司工程部;
【分類號(hào)】：TM315
，

本文編號(hào)：2446078