中国机械工程
中國機械工程
중국궤계공정
CHINA MECHANICAl ENGINEERING
2014年
16期
2219-2224
,共6页
模式识别%正交局部保持映射%特征提取%故障诊断
模式識彆%正交跼部保持映射%特徵提取%故障診斷
모식식별%정교국부보지영사%특정제취%고장진단
pattern recognition%orthogonal locality preserving projection%feature extraction%fault diagnosis
为了改善故障模式识别的分类性能，提出了一种基于正交局部保持映射算法的多流形特征提取方法。对于高维的非线性数据可以有效地提取低维流形特征向量，并且不会改变数据的内在属性。利用转子的振动信号构造一个高维多征兆矩阵，然后在应用正交局部保持映射将这个高维矩阵进行降维，提取低维特征向量矩阵，映射在可视空间里，从而可以有效地达到故障分类的效果，提高故障诊断的准确率。最后通过实验和数据降维仿真证明了正交局部保持映射算法的有效性和可行性。
為瞭改善故障模式識彆的分類性能，提齣瞭一種基于正交跼部保持映射算法的多流形特徵提取方法。對于高維的非線性數據可以有效地提取低維流形特徵嚮量，併且不會改變數據的內在屬性。利用轉子的振動信號構造一箇高維多徵兆矩陣，然後在應用正交跼部保持映射將這箇高維矩陣進行降維，提取低維特徵嚮量矩陣，映射在可視空間裏，從而可以有效地達到故障分類的效果，提高故障診斷的準確率。最後通過實驗和數據降維倣真證明瞭正交跼部保持映射算法的有效性和可行性。
위료개선고장모식식별적분류성능，제출료일충기우정교국부보지영사산법적다류형특정제취방법。대우고유적비선성수거가이유효지제취저유류형특정향량，병차불회개변수거적내재속성。이용전자적진동신호구조일개고유다정조구진，연후재응용정교국부보지영사장저개고유구진진행강유，제취저유특정향량구진，영사재가시공간리，종이가이유효지체도고장분류적효과，제고고장진단적준학솔。최후통과실험화수거강유방진증명료정교국부보지영사산법적유효성화가행성。
In order to improve the classification performance of fault pattern recognition,this paper proposes a local orthogonal locality preserving projection(OLPP)algorithm based on orthogonal mani-fold feature extraction method.For high dimensional nonlinear data,it can effectively extract the low dimensional manifold feature vector,and will not change the intrinsic attributes of data.Construct a high-dimensional symptom matrix with the vibration signal of the rotor,the orthogonal locality pre-serving projection was used to reduce the dimension of this high dimension matrix,extract the low di-mensional feature vector matrix,mapping in the visual space,this can achieve the result of fault classi-fication effectively,enhance the accuracy in fault diagnose.Finally,through experiment and data di-mension reduction simulation process shows that the orthogonal locality preserving projection is effec-tive and feasible.
