<address id="xrvvb"><listing id="xrvvb"></listing></address>

          <form id="xrvvb"></form>

          <address id="xrvvb"></address>

          華中科技大學學報(自然科學版) 2020, Vol. 48 Issue (12): 38-43 DOI10.13245/j.hust.201207

          欄目:機械工程
          基于SSD和1DCNN的滾動軸承故障診斷方法
          宋 霖 a , 宿 磊 a , 李 可 a , 蘇文勝 b
          a. 江南大學 1.機械工程學院;2. 江蘇省食品先進制造裝備技術重點實驗室,江蘇 無錫 214122
          b. 江蘇省特種設備安全監督檢驗研究院無錫分院,江蘇 無錫 214071
          摘要 針對滾動軸承故障診斷中振動信號易受強背景噪聲干擾,出現非平穩、非線性的特性,導致故障診斷精度較低等問題,提出了一種基于奇異譜分解(SSD)和一維卷積神經網絡(1DCNN)的滾動軸承故障診斷方法.首先,利用SSD將原始振動信號分解成若干個頻率尺度的奇異譜(SSC)分量,并根據峭度準則選取有效SSC分量對信號進行重構;然后,構建一維卷積神經網絡結構,先將重構后的信號輸入模型進行訓練,充分提取信號的特征,再由輸出層輸出診斷結果;最后,進行滾動軸承故障診斷實驗,結果表明:提出的診斷方法診斷準確率達到98.9%,比傳統方法具有更高的準確性和穩定性.
          關鍵詞 滾動軸承 ;故障診斷 ;奇異譜分解 ;峭度 ;一維卷積神經網絡
          Fault diagnosis method of rolling bearings based on SSD and 1DCNN
          SONG Lin a , SU Lei a , LI Ke a , SU Wensheng b
          a. School of Mechanical Engineering;Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment & Technology,Jiangnan University,Wuxi 214122,Jiangsu China
          b. Jiangsu Province Special Equipment Safety Supervision Inspection Institute Branch of Wuxi,Wuxi 214071,Jiangsu China
          Abstract The rolling bearing signal under strong background noise has non-stationary and nonlinear characteristics,resulting in the low accuracy of fault diagnosis.To solve the problem,a method based on singular spectrum decomposition (SSD) and 1D convolutional neural network (1DCNN) was proposed.In this method,the original vibration signal was decomposed into several singular spectrum components (SSC) with different frequency scales by SSD,and the SSC was selected according to the kurtosis criterion to reconstruct the signal.In addition,the 1D (one dimension) convolutional neural network was used to extract the fault feature from the reconstructed signal and obtain diagnosis results.Finally,the experimental results prove the effectiveness and superiority of the proposed method.The diagnosis accuracy is up to 98.9%,which is more accurate and stable than other traditional methods.
          Keywords rolling bearing ; fault diagnosis ; singular spectrum decomposition (SSD) ; kurtosis ; 1D convolutional neural network (1DCNN)
          基金資助國家自然科學基金資助項目(51705203,51775243);高等學校學科創新引智計劃資助項目(B18027).

          中圖分類號TH133.3;TP206.3
          文獻標志碼A
          文章編號1671-4512(2020)12-0038-06
          參考文獻
          [1]宿磊,黃海潤,李可,等.基于LCD-MCKD的滾動軸承故障特征提取方法[J].華中科技大學學報(自然科學版),2019,47(9):19-24.
          [2]萬齊楊,熊邦書,李新民,等.基于DCAE-CNN的自動傾斜器滾動軸承故障診斷[J].振動與沖擊,2020,39(11):273-279.
          [3]佘博,田福慶,湯健,等.基于自適應LTSA算法的滾動軸承故障診斷[J].華中科技大學學報(自然科學版),2017,45(1):91-96.
          [4]吳定海,王懷光,張培林,等.基于雙樹復小波包變換的空域和鄰域聯合降噪[J].華中科技大學學報(自然科學版),2015,43(4):17-21.
          [5]WANG H Q,LI K,SUN H,et al.Feature extraction method based on Pseudo-Wigner-Ville distribution for rotational machinery in variable operating conditions [J].Chinese Journal of Mechanical Engineering,2011,24(4):661-668.
          [6]劉進明,應懷樵.FFT譜連續細化分析的富里葉變換法[J].振動工程學報,1995,8(2):162-166.
          [7]BONIZZI P,KAREL J M H,MESTE O,et al.Singular spectrum decomposition:a new method for time series decomposition[J].Advances in Adaptive Data Analysis,2014,6(4):1450011.
          [8]JIA F,LEI Y,LU N,et al.Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J].Me- chanical Systems and Signal Processing,2018,110:349-367.
          [9]YAN H,BAOPING T,LEI D.Multi-level wavelet packet fusion in dynamic ensemble convolutional neural network for fault diagnosis [J].Measurement,2018,127:246-255.
          [10]INCE T,KIRANYAZ S,EREN L,et al.Real-time motor fault detection by 1-D convolutional neural networks [J]. IEEE Transactions on Industrial Electronics,2016,63(11):7067-7075.
          [11]鄧佳林,鄒益勝,張笑璐,等.一種改進CNN在軸承故障診斷中的應用[J].現代制造工程,2020(4):142-147.
          [12]LI H M,HUANG J Y,JI S W.Bearing fault diagnosis with a feature fusion method based on an ensemble con- volutional neural network and deep neural network [J].Sensors,2019,19(9):2034.DOI:10.3390/s19092034.
          文獻來源
          宋 霖, 宿 磊, 李 可, 蘇文勝. 基于SSD和1DCNN的滾動軸承故障診斷方法[J]. 華中科技大學學報(自然科學版), 2020, 48(12): 38-43
          DOI:10.13245/j.hust.201207
          澳门盘口