车用发动机
車用髮動機
차용발동궤
2015年
1期
81-86
,共6页
司景萍%牛家骅%郭丽娜%马继昌
司景萍%牛傢驊%郭麗娜%馬繼昌
사경평%우가화%곽려나%마계창
故障诊断%振动信号%总体平均经验模态分解%相关系数%支持向量机
故障診斷%振動信號%總體平均經驗模態分解%相關繫數%支持嚮量機
고장진단%진동신호%총체평균경험모태분해%상관계수%지지향량궤
fault diagnosis%vibration signal%ensemble empirical mode decomposition%correlation coefficient%support vector machine
针对发动机缸盖振动信号的非线性非平稳特征，提出一种总体平均经验模态分解（EEM D ）和支持向量机相结合的信号分析及故障诊断方法，该方法利用EEMD算法以及IMF序列和原始振动信号之间的相关系数，有效放大故障诊断特征向量的差异。对原始振动信号进行EEMD分解，得到各阶特征模态函数（IMF），求各阶IMF分量对应于原始信号的相关系数并组成故障分类特征向量。分别将IM F相关系数法和IM F能量分布法得到的特征向量作为输入，建立BP神经网络和支持向量机，判断发动机工作状态和故障类型。分析表明，对IM F求相关系数的方法简便易行，能有效放大不同工况下特征向量的差异，结合支持向量机能够对既定机型的配气机构和点火系常见故障进行准确识别。
針對髮動機缸蓋振動信號的非線性非平穩特徵，提齣一種總體平均經驗模態分解（EEM D ）和支持嚮量機相結閤的信號分析及故障診斷方法，該方法利用EEMD算法以及IMF序列和原始振動信號之間的相關繫數，有效放大故障診斷特徵嚮量的差異。對原始振動信號進行EEMD分解，得到各階特徵模態函數（IMF），求各階IMF分量對應于原始信號的相關繫數併組成故障分類特徵嚮量。分彆將IM F相關繫數法和IM F能量分佈法得到的特徵嚮量作為輸入，建立BP神經網絡和支持嚮量機，判斷髮動機工作狀態和故障類型。分析錶明，對IM F求相關繫數的方法簡便易行，能有效放大不同工況下特徵嚮量的差異，結閤支持嚮量機能夠對既定機型的配氣機構和點火繫常見故障進行準確識彆。
침대발동궤항개진동신호적비선성비평은특정，제출일충총체평균경험모태분해（EEM D ）화지지향량궤상결합적신호분석급고장진단방법，해방법이용EEMD산법이급IMF서렬화원시진동신호지간적상관계수，유효방대고장진단특정향량적차이。대원시진동신호진행EEMD분해，득도각계특정모태함수（IMF），구각계IMF분량대응우원시신호적상관계수병조성고장분류특정향량。분별장IM F상관계수법화IM F능량분포법득도적특정향량작위수입，건립BP신경망락화지지향량궤，판단발동궤공작상태화고장류형。분석표명，대IM F구상관계수적방법간편역행，능유효방대불동공황하특정향량적차이，결합지지향량궤능구대기정궤형적배기궤구화점화계상견고장진행준학식별。
For the non‐linear and non‐stationary characteristics of cylinder head vibration signal ,the method of ensemble em‐pirical mode decomposition (EEMD) combined with support vector machine (SVM ) was proposed .The difference of feature vectors was amplified effectively by using EEMD algorithm and correlation coefficient of intrinsic mode function (IMF) se‐quence with original vibration signal .The IMFs were acquired by decomposing the original vibration signal with EEMD and then the feature vectors of fault classification was formed by calculating the correlation coefficients of IMF with original signal . Taking the feature vectors calculated with IMF correlation coefficient and energy distribution method as the input ,BP neural network and SVM models were established to analyze engine working status and fault type .The result shows that the method of IMF correlation coefficient is feasible and can magnify the difference between feature vectors .With the help of SVM ,the common faults of valve mechanism and ignition system can be identified accurately .
