A new time-domain analysis method that uses second generation wavelettransform (SGWT) for weak fault feature extraction is proposed. To extract incipient fault feature,a biorthogonal wavelet with the characteristics o...A new time-domain analysis method that uses second generation wavelettransform (SGWT) for weak fault feature extraction is proposed. To extract incipient fault feature,a biorthogonal wavelet with the characteristics of impact is constructed by using SGWT. Processingdetail signal of SGWT with a sliding window devised on the basis of rotating operation cycle, andextracting modulus maximum from each window, fault features in time-domain are highlighted. To makefurther analysis on the reason of the fault, wavelet package transform based on SGWT is used toprocess vibration data again. Calculating the energy of each frequency-band, the energy distributionfeatures of the signal are attained. Then taking account of the fault features and the energydistribution, the reason of the fault is worked out. An early impact-rub fault caused by axismisalignment and rotor imbalance is successfully detected by using this method in an oil refinery.展开更多
In order to make trend analysis and prediction to acquisition data in amechanical equipment condition monitoring system, a new method of trend feature extraction andprediction of acquisition data is proposed which con...In order to make trend analysis and prediction to acquisition data in amechanical equipment condition monitoring system, a new method of trend feature extraction andprediction of acquisition data is proposed which constructs an adaptive wavelet on the acquisitiondata by means of second generation wavelet transform ( SGWT), Firstly, taking the vanishing momentnumber of the predictor as a constraint, the linear predictor and updater are designed according tothe acquisition data by using symmetrical interpolating scheme. Then the trend of the data isobtained through doing SGWT decomposition , threshold processing and SGWT reconstruction. Secondly,under the constraint of the vanishing moment number of the predictor, another predictor based on theacquisition data is devised to predict the future trend of the data using a non-symmetricalinterpolating scheme, A one-step prediction algorithm is presented to predict the future evolutiontrend with historical data. The proposed method obtained a desirable effect in peak-to-peak valuetrend analysis for a machine set in an oil refinery.展开更多
In literature, features based on First and Second Order Statistics that characterizes textures are used for classification of images. Features based on statistics of texture provide far less number of relevant and dis...In literature, features based on First and Second Order Statistics that characterizes textures are used for classification of images. Features based on statistics of texture provide far less number of relevant and distinguishable features in comparison to existing methods based on wavelet transformation. In this paper, we investigated performance of texture-based features in comparison to wavelet-based features with commonly used classifiers for the classification of Alzheimer’s disease based on T2-weighted MRI brain image. The performance is evaluated in terms of sensitivity, specificity, accuracy, training and testing time. Experiments are performed on publicly available medical brain images. Experimental results show that the performance with First and Second Order Statistics based features is significantly better in comparison to existing methods based on wavelet transformation in terms of all performance measures for all classifiers.展开更多
文摘A new time-domain analysis method that uses second generation wavelettransform (SGWT) for weak fault feature extraction is proposed. To extract incipient fault feature,a biorthogonal wavelet with the characteristics of impact is constructed by using SGWT. Processingdetail signal of SGWT with a sliding window devised on the basis of rotating operation cycle, andextracting modulus maximum from each window, fault features in time-domain are highlighted. To makefurther analysis on the reason of the fault, wavelet package transform based on SGWT is used toprocess vibration data again. Calculating the energy of each frequency-band, the energy distributionfeatures of the signal are attained. Then taking account of the fault features and the energydistribution, the reason of the fault is worked out. An early impact-rub fault caused by axismisalignment and rotor imbalance is successfully detected by using this method in an oil refinery.
文摘In order to make trend analysis and prediction to acquisition data in amechanical equipment condition monitoring system, a new method of trend feature extraction andprediction of acquisition data is proposed which constructs an adaptive wavelet on the acquisitiondata by means of second generation wavelet transform ( SGWT), Firstly, taking the vanishing momentnumber of the predictor as a constraint, the linear predictor and updater are designed according tothe acquisition data by using symmetrical interpolating scheme. Then the trend of the data isobtained through doing SGWT decomposition , threshold processing and SGWT reconstruction. Secondly,under the constraint of the vanishing moment number of the predictor, another predictor based on theacquisition data is devised to predict the future trend of the data using a non-symmetricalinterpolating scheme, A one-step prediction algorithm is presented to predict the future evolutiontrend with historical data. The proposed method obtained a desirable effect in peak-to-peak valuetrend analysis for a machine set in an oil refinery.
文摘In literature, features based on First and Second Order Statistics that characterizes textures are used for classification of images. Features based on statistics of texture provide far less number of relevant and distinguishable features in comparison to existing methods based on wavelet transformation. In this paper, we investigated performance of texture-based features in comparison to wavelet-based features with commonly used classifiers for the classification of Alzheimer’s disease based on T2-weighted MRI brain image. The performance is evaluated in terms of sensitivity, specificity, accuracy, training and testing time. Experiments are performed on publicly available medical brain images. Experimental results show that the performance with First and Second Order Statistics based features is significantly better in comparison to existing methods based on wavelet transformation in terms of all performance measures for all classifiers.
