轴承
軸承
축승
BEARING
2014年
5期
48-52
,共5页
崔得龙%张清华%肖明%王磊
崔得龍%張清華%肖明%王磊
최득룡%장청화%초명%왕뢰
滚动轴承%故障诊断%谱图%约束NMF%特征频谱
滾動軸承%故障診斷%譜圖%約束NMF%特徵頻譜
곤동축승%고장진단%보도%약속NMF%특정빈보
rolling bearing%fault diagnosis%spectrogram%CNMF%feature spectrum
为了克服传统时频分析中信号特征频谱提取技术中参数敏感问题，设计了一种基于谱图和约束NMF的特征频谱提取算法。该算法首先对振动信号进行归一化预处理和短时Fourier分析，获得代表原始非平稳信号特性的瞬时参数即谱图；然后对谱图进行约束NMF分解；最后由基矩阵获得原始振动信号的特征频谱。理论分析、仿真和工程试验验证了该算法的可行性和有效性。
為瞭剋服傳統時頻分析中信號特徵頻譜提取技術中參數敏感問題，設計瞭一種基于譜圖和約束NMF的特徵頻譜提取算法。該算法首先對振動信號進行歸一化預處理和短時Fourier分析，穫得代錶原始非平穩信號特性的瞬時參數即譜圖；然後對譜圖進行約束NMF分解；最後由基矩陣穫得原始振動信號的特徵頻譜。理論分析、倣真和工程試驗驗證瞭該算法的可行性和有效性。
위료극복전통시빈분석중신호특정빈보제취기술중삼수민감문제，설계료일충기우보도화약속NMF적특정빈보제취산법。해산법수선대진동신호진행귀일화예처리화단시Fourier분석，획득대표원시비평은신호특성적순시삼수즉보도；연후대보도진행약속NMF분해；최후유기구진획득원시진동신호적특정빈보。이론분석、방진화공정시험험증료해산법적가행성화유효성。
In order to solve the problem about sensitive parameters in signal feature spectrum extraction of traditional time-frequency analysis,a feature spectrum extraction algorithm is proposed based on spectrogram and Constrained Non-Negative Matrix Factorizations(CNMF).Firstly,the vibration signal is normalized,and then the short time Fou-rier analysis is carried out,obtaining the instantaneous parameters that represent original non-stationary signal charac-teristics.Secondly,the spectrogram is decomposed using CNMF.Finally,the feature spectrum of original vibration sig-nal is got by the basic matrix.The feasibility and effectively of the proposed method are verified by theoretical analysis, simulation and engineering experiment.
