風(fēng)機(jī)軸承故障診斷中的振動(dòng)信號(hào)特征提取方法研究

隨著風(fēng)電產(chǎn)業(yè)的快速發(fā)展以及對(duì)風(fēng)機(jī)系統(tǒng)高可靠性、易維護(hù)性等的各方面要求，風(fēng)機(jī)狀態(tài)監(jiān)測(cè)與故障診斷技術(shù)引起了學(xué)術(shù)界和工業(yè)界的廣泛關(guān)注。軸承作為風(fēng)機(jī)機(jī)械傳動(dòng)系統(tǒng)和發(fā)電機(jī)系統(tǒng)的核心部件，其運(yùn)行狀態(tài)的實(shí)時(shí)監(jiān)測(cè)和準(zhǔn)確分析，對(duì)整個(gè)風(fēng)機(jī)的故障診斷和運(yùn)行維護(hù)均具有重要的意義。本文針對(duì)風(fēng)機(jī)軸承故障診斷中的振動(dòng)信號(hào)特征提取問(wèn)題展開研究，運(yùn)用局部均值分解(Local Mean Decomposition, LMD)瞬態(tài)信號(hào)分解技術(shù)、信息熵和非線性動(dòng)力學(xué)參數(shù)分析，分別從瞬態(tài)特征描述和非線性特征分析兩個(gè)角度，對(duì)風(fēng)機(jī)軸承振動(dòng)信號(hào)特征提取方法進(jìn)行理論研究和實(shí)驗(yàn)驗(yàn)證，為軸承狀態(tài)監(jiān)測(cè)和故障診斷提供了有效的理論方法。論文主要工作如下：
(1)  在分析風(fēng)機(jī)軸承運(yùn)行特點(diǎn)、故障機(jī)理及其振動(dòng)故障特征的基礎(chǔ)上，針對(duì)復(fù)雜工況下風(fēng)機(jī)軸承振動(dòng)信號(hào)非平穩(wěn)、非線性特征難以提取及量化問(wèn)題，研究基于 LMD的瞬態(tài)信號(hào)分解技術(shù)和基于信息熵的信號(hào)特征定量描述方法，實(shí)現(xiàn)風(fēng)機(jī)軸承振動(dòng)信號(hào)特征的有效提取和準(zhǔn)確描述。
(2)  研究基于 LMD 和信息熵的 Wigner-Ville 譜熵的振動(dòng)信號(hào)瞬態(tài)能量特征提取方法，用于定量刻畫軸承不同狀態(tài)下振動(dòng)信號(hào)的時(shí)頻能量分布的規(guī)律，并設(shè)計(jì)基于LS-SVM 的智能故障診斷模型，實(shí)現(xiàn)軸承狀態(tài)和故障類型的自動(dòng)分類與識(shí)別。仿真分析和風(fēng)機(jī)軸承診斷實(shí)驗(yàn)驗(yàn)證了該方法和模型較好的特征提取與故障診斷效果。
(3)  從非線性動(dòng)力學(xué)角度出發(fā)，提出基于 LMD 的多尺度排序熵的軸承振動(dòng)信號(hào)非線性特征提取方法，有效刻畫軸承振動(dòng)信號(hào)的非線性復(fù)雜度特征，實(shí)現(xiàn)了軸承內(nèi)不同故障程度的有效識(shí)別。仿真分析和風(fēng)機(jī)軸承故障診斷實(shí)驗(yàn)驗(yàn)證了該方法的有效性。 
關(guān)鍵詞：振動(dòng)信號(hào)；特征提取；風(fēng)機(jī)軸承；局部均值分解；排序熵；故障診斷

石家莊風(fēng)機(jī)廠石家莊風(fēng)機(jī)石家莊風(fēng)機(jī)銷售石家莊風(fēng)機(jī)維修

Abstract
With  the  rapid  development  of  wind  power  industry,  the  reliability  and maintainability of the wind turbine system are very urgent. Condition monitoring and fault diagnosis technology of wind turbine system cause the extensive concern of the academia and  industry.  Bearings  are  as  the  core  components  of  wind  turbine  mechanical transmission  system  and  generator  system,  there  has  a  realistic  significance  to  make  a condition monitoring and fault diagnosis to them. In this paper, aimed at feature extraction methods  of  wind  turbine  bearing  diagnosis, applied  Local  Mean  Decomposition  (LMD), Shannon  entropy  and  nonlinear  dynamic  parameters,  in  view  of  the  transient characteristics description and nonlinear feature analysis research, the proposed methods are verified by simulation experiment and experimental platform. The proposed methods provide a solution for wind turbine bearing condition monitoring and fault diagnosis. The specific research ways are as follows: Firstly, the wind turbine bearing operation characteristics and the failure mechanism are  discussed,  besides,  aiming  at  nonstationary  and  nonlinear  characteristics  of  bearings, the transient signal decomposition technique based on LMD are studied; the quantitative description method based on information entropy are analyzed. Both of that is in order toeffective extraction and accurate description of wind turbine bearing vibratory signals.Secondly,  a  transient  characteristic  extraction  method  based  on  LMD  and Wigner-Ville  spectral  entropy  is  proposed,  in  order  to  quantitatively  describe  thetime-frequency energy distribution of bearing vibratory signals under different condition. After  that,  a  intelligent  fault  diagnosis  model  based  on  LS-SVM  is  used  for  automaticclassification  and  recognition  of  bearing  faults.  Simulation  experiment  and  experimental platform verified the proposed method and diagnosis model. Finally, in view of nonlinear dynamics, a nonlinear feature extraction method named a multi-scale permutation entropy based on LMD is proposed. The proposed method can effectively represent nonlinear complexity characteristics of bearing vibratory signals and identify  different  fault  degree  of  bearing.  Simulation  experiment  and  experimental  III platform verified the proposed method.
Keywords:  vibratory  signals;  feature  extraction;  wind  turbine  bearings;  local  mean decomposition (LMD); permutation entropy; fault diagnosis