本文關(guān)鍵詞：基于自組織映射與受限玻爾茲曼機(jī)的滾動(dòng)軸承健康評(píng)估　出處：《機(jī)械傳動(dòng)》2017年06期 　論文類型：期刊論文

  更多相關(guān)文章： 序列前向算法 自組織映射 受限玻爾茲曼機(jī) 健康評(píng)估 滾動(dòng)軸承

【摘要】：為了對(duì)滾動(dòng)軸承進(jìn)行動(dòng)態(tài)健康評(píng)估,準(zhǔn)確描述其性能退化的動(dòng)態(tài)過程,采用自組織映射(SOM)與受限玻爾茲曼機(jī)(RBM)相結(jié)合的方法進(jìn)行軸承健康評(píng)估。考慮軸承健康狀態(tài)的變化引起響應(yīng)特征的相應(yīng)變化,利用SOM的無監(jiān)督學(xué)習(xí)特點(diǎn),通過序列前向排序算法(SFS)篩選時(shí)域、頻域和時(shí)頻域特征,進(jìn)而建立最優(yōu)特征域,獲得特征向量與軸承健康狀態(tài)間的映射關(guān)系。為了避免傳統(tǒng)神經(jīng)網(wǎng)絡(luò)在處理上述高維特征數(shù)據(jù)時(shí)出現(xiàn)的易陷入局部最優(yōu)、參數(shù)調(diào)整困難、訓(xùn)練時(shí)間過長(zhǎng)問題,將映射后的特征向量與軸承健康狀態(tài)分別作為RBM的輸入與輸出,建立健康評(píng)估模型。試驗(yàn)數(shù)據(jù)分析的結(jié)果表明,所提方法可準(zhǔn)確識(shí)別滾動(dòng)軸承性能退化過程中的不同健康狀態(tài),對(duì)于滾動(dòng)軸承健康評(píng)估具有較好的工程適用性。
[Abstract]:For the rolling bearing dynamic health assessment, to accurately describe the dynamic process of the performance degradation of the self-organizing map (SOM) and restricted Boltzmann machine (RBM) method combined with the bearing health assessment. Considering the changes caused by the corresponding response characteristics change of the health status of the bearing, unsupervised learning using SOM algorithm to. Through the sorting sequence (SFS) screening in time domain, frequency domain and time-frequency domain features, and then establish the best feature domain, obtain mapping between the feature vector and the bearing health status. In order to avoid easy to fall into local optimum traditional neural network in dealing with the high dimensional feature data, parameter adjustment difficulties, long training time. The feature vector and the bearing health status after mapping were used as input and output of RBM, the establishment of health assessment model. The experimental data analysis results show that the proposed method can accurately It can identify the different health state in the process of the performance degradation of the rolling bearing, and it has good engineering applicability for the health evaluation of rolling bearings.

【作者單位】： 上海大學(xué)機(jī)械自動(dòng)化工程系;
【基金】：國家自然科學(xué)基金(50876057) 上海高校青年教師培養(yǎng)資助計(jì)劃(14203) 上海大學(xué)(理工類)創(chuàng)新基金(13007)
【分類號(hào)】：TH133.33
【正文快照】： 0引言大型風(fēng)電、盾構(gòu)機(jī)、高速軋鋼機(jī)等高端裝備的工作特點(diǎn)使其實(shí)現(xiàn)功能輸出的核心部件——轉(zhuǎn)子-軸承系統(tǒng)承受了比以往更為嚴(yán)苛的工作載荷,因零部件損傷而引起的整機(jī)失效時(shí)有發(fā)生[1]。軸承是機(jī)械設(shè)備的“關(guān)節(jié)”,由于受到復(fù)雜載荷作用,往往成為設(shè)備可靠性的薄弱環(huán)節(jié)[2]。因此,針，

本文編號(hào)：1370675