本文關(guān)鍵詞： 旋轉(zhuǎn)機(jī)械 流形學(xué)習(xí) Laplacian雙聯(lián)最小二乘支持向量機(jī) 半監(jiān)督學(xué)習(xí) 故障診斷　出處：《振動(dòng)與沖擊》2017年16期 　論文類型：期刊論文

【摘要】：提出基于Laplacian雙聯(lián)最小二乘支持向量機(jī)(Laplacian Twin Least Squares Support Vector Machine,LapTLSSVM)半監(jiān)督模式識(shí)別的新型早期故障診斷方法。用時(shí)、頻域特征集廣泛收集旋轉(zhuǎn)機(jī)械不同早期故障的特征信息,再用提升半監(jiān)督局部Fisher判別分析(Enhanced Semi-Supervised Local Fisher Discriminant Analysis,ESSLFDA)將高維時(shí)、頻域特征集約簡(jiǎn)為具有更好類區(qū)分度的低維特征向量,并輸入到Lap-TLSSVM中進(jìn)行早期故障診斷。Lap-TLSSVM引入了包含大量無標(biāo)簽數(shù)據(jù)信息的流形規(guī)則實(shí)現(xiàn)半監(jiān)督學(xué)習(xí);其目標(biāo)函數(shù)只含等式約束條件,且用共軛梯度法求解目標(biāo)函數(shù)的線性方程組以加速訓(xùn)練過程。所提出的方法在訓(xùn)練樣本非常稀少的情況下具有較高的診斷精度和計(jì)算效率。深溝球軸承早期故障診斷實(shí)驗(yàn)驗(yàn)證了該方法的有效性。
[Abstract]:A dual least squares support vector machine (LS-SVM) based on Laplacian is proposed. Laplacian Twin Least Squares Support Vector Machine. A new method of early fault diagnosis based on LapTLS SSVM (Semi-supervised pattern recognition). The feature set of frequency domain is widely used to collect the feature information of different early faults of rotating machinery. Then the Fisher discriminant analysis was used to promote the semi-supervision department (. Enhanced Semi-Supervised Local Fisher Discriminant Analysis. ESSLFDA reduces the feature set in high dimensional time and frequency domain to a low dimensional feature vector with better classification. And input into Lap-TLSSVM for early fault diagnosis. Lap-TLSSVM introduces manifold rule which contains a lot of untagged data to realize semi-supervised learning. The objective function contains only equality constraints. The conjugate gradient method is used to solve the linear equations of the objective function to accelerate the training process. The proposed method has high diagnostic accuracy and computational efficiency in the case of very few training samples. The effectiveness of this method is verified by diagnostic experiments.
【作者單位】： 四川大學(xué)制造科學(xué)與工程學(xué)院;重慶大學(xué)機(jī)械傳動(dòng)國(guó)家重點(diǎn)實(shí)驗(yàn)室;四川航天技術(shù)研究院總體設(shè)計(jì)部;
【基金】：國(guó)家自然科學(xué)基金青年基金(51305283) 中國(guó)博士后科學(xué)基金第60批面上資助項(xiàng)目(2016M602685)
【分類號(hào)】：TH17
【正文快照】： 軸承、轉(zhuǎn)子、齒輪等旋轉(zhuǎn)部件是機(jī)械裝備的重要組成部分,起到支撐載荷、傳遞運(yùn)動(dòng)和動(dòng)力的關(guān)鍵作用。然而這些旋轉(zhuǎn)部件一旦出現(xiàn)故障得不到及時(shí)診斷和處理,任由其發(fā)展、擴(kuò)大,將會(huì)引起整臺(tái)機(jī)械裝備的重大事故以及代價(jià)高昂的長(zhǎng)期停工。因此,及時(shí)準(zhǔn)確地診斷出處于早期發(fā)生階段的微弱

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 李鋒;湯寶平;宋濤;丁行武;;歸一Laplacian矩陣有監(jiān)督最優(yōu)局部保持映射故障辨識(shí)[J];機(jī)械工程學(xué)報(bào);2013年13期

，

本文編號(hào)：1454792