The Experts below are selected from a list of 50706 Experts worldwide ranked by ideXlab platform
Ping Liang - One of the best experts on this subject based on the ideXlab platform.
-
turbine generator set vibration faults diagnosis based on wavelet Packet Analysis and information fusion technology
International Conference on Electrical and Control Engineering, 2010Co-Authors: Jingpei Gu, Ping LiangAbstract:According to the four typical fault signals of turbine vibration including: mass unbalance, misalignment, rubbing and loosing from the Bently experiment table, Analysis and symptom extraction are carried out by wavelet Packet Analysis. The fault symptom parameters extracted by wavelet Packet compose the framework of the D-S evidence theory; get turbine rotor vibration faults types by the information fusion technology. The results of diagnosis indicate that the faults diagnosis method based on wavelet Analysis and information fusion technology can improve the accuracy of fault diagnosis.
-
Turbine Rotor Vibration Faults Diagnosis based on Wavelet Packet Analysis and the Largest Lyapunov Exponent
2010 Asia-Pacific Power and Energy Engineering Conference, 2010Co-Authors: Ping LiangAbstract:According to the four typical fault signals of turbine rotor vibration, including rubbing, loosening, misalignment and mass unbalance which are collected from the Bently experiment set, the method which combines wavelet Packet and the largest Lyapunov exponent is adopted to diagnose the faults. First, use wavelet Packet Analysis for filtering the fault signals, extracting useful signal frequency segments from original signals. Then calculate the largest Lyapunov exponent of the signals which is adopted as the basis of diagnosis. The results indicate that wavelet Packet Analysis is of good ability of filtering and extracting of nonstationary signal; the largest Lyapunov exponent of vibration time series can distinguish different fault conditions, and is of good discriminability in turbine rotor faults diagnosis.
-
Target extraction from clutter images using wavelet Packet Analysis
Proceedings of the 1998 IEEE Radar Conference RADARCON'98. Challenges in Radar Systems and Solutions (Cat. No.98CH36197), 1Co-Authors: Hyungjun Kim, Ping LiangAbstract:We present a wavelet shrinkage method that yields high clutter suppression by using a best-tree wavelet Packet Analysis. An integrated automatic target recognition processor utilizing a wavelet Packet transform and a shape extraction method is introduced to demonstrate the feasibility of using wavelet Packet Analysis for automatic target extraction from synthetic aperture radar (SAR) images. Two Analysis procedures are processed independently and the two outputs from each process are combined to increase the detection performance. Experimental demonstrations of target extraction are also provided. The preliminary experiments show that target extraction using wavelet Packet Analysis has high detection performance as well as low false detection performance.
Marimuthu Palaniswami - One of the best experts on this subject based on the ideXlab platform.
-
Classification of sleep apnea types using wavelet Packet Analysis of short-term ECG signals
Journal of Clinical Monitoring and Computing, 2012Co-Authors: Jayavardhana Gubbi, Ahsan Khandoker, Marimuthu PalaniswamiAbstract:Objective Obstructive sleep apnea (OSA) causes a pause in airflow with reduced breathing effort. In contrast, central sleep apnea (CSA) event is not accompanied with breathing effort. The aim of this study is to differentiate CSA and OSA events using wavelet Packet Analysis and support vector machines of ECG signals over 5 s period. Methods Eight level wavelet Packet Analysis was performed on each 5 s clip using Daubechies (DB3) mother wavelet and for comparison discrete wavelet Analysis was performed using Symlet (SYM3) wavelets. The choice of wavelet basis function was based on a grid search using Daubechies, Symlet and biorthogonal wavelets with decomposition levels varying between 2 and 5. Support vector machine is used for two-class classification. Out of 29 overnight polysomnographic studies, 23 of them were used in the training phase and 6 patients were used for independent testing. Results The proposed algorithm is shown to perform better in classifying CSA and OSA with wavelet Packet features (accuracy—91%, sensitivity—88.14% and specificity—91.11%) than with the traditional wavelet decomposition based features (accuracy—83.79%, sensitivity—89.18% and specificity—83.59%). The independent test resulted in overall classification accuracy, sensitivity and specificity of 91.08, 91.02 and 91.09% respectively using wavelet Packet Analysis. Conclusions The classification result indicates the possibility of non-invasively classifying CSA and OSA events based on shorter segments of ECG signals.
-
Classification of obstructive and central sleep apnea using wavelet Packet Analysis of ECG signals
2009Co-Authors: Jayavardhana Gubbi, Ahsan Khandoker, Marimuthu PalaniswamiAbstract:Obstructive sleep apnea (OSA) causes a pause in air-flow with continuing breathing effort. In contrast, central sleep apnea (CSA) event is not accompanied with breathing effort. The aim of this study is to differentiate characteristics of CSA and OSA using wavelet Packet Analysis of ECG signal over 5 second period and support vector machines. Six patients were used in the study that contained both CSA and OSA events. Eight level wavelet Packet Analysis was performed on each 5 sec clip using Daubechies (DB3) mother wavelet. Two features namely the best tree and the entropy of the best wavelet tree were extracted from each clip. One patient was used for testing at a time while all other patients' data was used for training. The accuracy range was between 82% and 92% with best tree as features. Entropy of best tree resulted in improved accuracies ranging between 87% and 94.5%.
Yuan Yun-long - One of the best experts on this subject based on the ideXlab platform.
-
Fault Diagnosis of Rolling Bearing Based on Kurtosis-Wavelet Packet Analysis
New Technology & New Process, 2008Co-Authors: Yuan Yun-longAbstract:Theoretical Analysis and examination were made and it indicates that present statistical parameters of time domain of rolling bearing vibration like kurtosis index,can only provide the type information about a rolling bearing in normal instead of more information.The feature spectrum of fault rolling bearing can be obtained by decomposing the vibration signal through wavelet Packet Analysis and then reconstructing the signal which including fault feature spectrum,Thus,the information effectively helps the fault diagnosis of rolling bearing.
-
Study on Fault Diagnosis of Rolling Bearing Based on Wavelet Packet Analysis
Modular Machine Tool & Automatic Manufacturing Technique, 2008Co-Authors: Yuan Yun-longAbstract:Theoretical Analysis and examination were made and it is indicated that the present statistical parameters of time domain of rolling bearing vibration,such as the kurtosis index,can only provide the type information about a rolling bearing in normal or not.The feature spectrum of fault rolling bearing can be obtained by decomposing the vibration signal through wavelet Packet Analysis and then reconstructing the signal which including fault feature spectrum,Thus,the information effectively helps the fault diagnosis of rolling bearing.
Jayavardhana Gubbi - One of the best experts on this subject based on the ideXlab platform.
-
Classification of sleep apnea types using wavelet Packet Analysis of short-term ECG signals
Journal of Clinical Monitoring and Computing, 2012Co-Authors: Jayavardhana Gubbi, Ahsan Khandoker, Marimuthu PalaniswamiAbstract:Objective Obstructive sleep apnea (OSA) causes a pause in airflow with reduced breathing effort. In contrast, central sleep apnea (CSA) event is not accompanied with breathing effort. The aim of this study is to differentiate CSA and OSA events using wavelet Packet Analysis and support vector machines of ECG signals over 5 s period. Methods Eight level wavelet Packet Analysis was performed on each 5 s clip using Daubechies (DB3) mother wavelet and for comparison discrete wavelet Analysis was performed using Symlet (SYM3) wavelets. The choice of wavelet basis function was based on a grid search using Daubechies, Symlet and biorthogonal wavelets with decomposition levels varying between 2 and 5. Support vector machine is used for two-class classification. Out of 29 overnight polysomnographic studies, 23 of them were used in the training phase and 6 patients were used for independent testing. Results The proposed algorithm is shown to perform better in classifying CSA and OSA with wavelet Packet features (accuracy—91%, sensitivity—88.14% and specificity—91.11%) than with the traditional wavelet decomposition based features (accuracy—83.79%, sensitivity—89.18% and specificity—83.59%). The independent test resulted in overall classification accuracy, sensitivity and specificity of 91.08, 91.02 and 91.09% respectively using wavelet Packet Analysis. Conclusions The classification result indicates the possibility of non-invasively classifying CSA and OSA events based on shorter segments of ECG signals.
-
Classification of obstructive and central sleep apnea using wavelet Packet Analysis of ECG signals
2009Co-Authors: Jayavardhana Gubbi, Ahsan Khandoker, Marimuthu PalaniswamiAbstract:Obstructive sleep apnea (OSA) causes a pause in air-flow with continuing breathing effort. In contrast, central sleep apnea (CSA) event is not accompanied with breathing effort. The aim of this study is to differentiate characteristics of CSA and OSA using wavelet Packet Analysis of ECG signal over 5 second period and support vector machines. Six patients were used in the study that contained both CSA and OSA events. Eight level wavelet Packet Analysis was performed on each 5 sec clip using Daubechies (DB3) mother wavelet. Two features namely the best tree and the entropy of the best wavelet tree were extracted from each clip. One patient was used for testing at a time while all other patients' data was used for training. The accuracy range was between 82% and 92% with best tree as features. Entropy of best tree resulted in improved accuracies ranging between 87% and 94.5%.
Liang Ping - One of the best experts on this subject based on the ideXlab platform.
-
Wavelet Packet Analysis for Vibration Fault Diagnosis of Turbine Rotor
Guangdong Electric Power, 2007Co-Authors: Liang PingAbstract:A fault diagnosis method based on wavelet Packet Analysis for turbine rotor vibration has been put forward according to the vibration frequency spectrum characteristics of turbo-generator units.It can reflect the frequency spectrum ingredients and energy contained in vibration signals more exactly than wavelet transformation.Based on the four typical fault signals of turbine rotor vibration collected from the Bently experiment set,energy Analysis and symptom extraction are carried out by wavelet Packet Analysis.The experimental Analysis indicates that the conditions of turbine rotor vibration faults can be obtained by the extraction method of mechanical fault symptoms based on wavelet Packet Analysis and signal energy decomposition.According to the character in both the time domain and the frequency domain of faults,the fault types can be identified,and then the turbine rotor vibration faults can be diagnosed.This method is more effective than the extraction method of fault symptoms based on the Fourier transformation,and it is fit for mechanical fault diagnosis.
