Gear Fault Diagnosis Based on Wavelet-Support Vector Machines

2010 ◽  
Vol 33 ◽  
pp. 450-453 ◽  
Author(s):  
Jie Zhao ◽  
Chun Hua Li
Keyword(s):  
Fault Diagnosis ◽  
Support Vector Machines ◽  
Classification Model ◽  
Fault Classification ◽  
Small Samples ◽  
Support Vector ◽  
Noise Interference ◽  
Vector Machines ◽  
Gear Fault ◽  
Vibration Noise

According to the characteristics of gear vibration noise large and fault diagnosis complex, the paper proposes the method of gear fault classification based on wavelet analysis - Support Vector Machines (SVM). This method effectively eliminates the noise interference of the gear signals. The classification model of gear diagnosis applicable to small samples is established and the result of simulation shows that the model can correctly realize gear fault.

Transformer Fault Diagnosis Based on Fuzzy Support Vector Machines

2011 ◽  
Vol 135-136 ◽  
pp. 1102-1107
Author(s):  
Yi Yan Liu ◽  
Shuan Hai He ◽  
Yong Feng Ju ◽  
Chen Dong Duan
Keyword(s):  
Fault Diagnosis ◽  
Support Vector Machines ◽  
Transformer Oil ◽  
Small Samples ◽  
Parameter Determination ◽  
Support Vector ◽  
Correct Judgment ◽  
Vector Machines ◽  
Fuzzy Support Vector Machines ◽  
Transformer Fault

Due to lack of typical damage samples in the transformer fault diagnosis, a new fault diagnosis method based on fuzzy support vector machines (FFSVMs) was presented. According to the method, the five characteristic gases dissolved in transformer oil were extracted by the K-means clustering (KMC) method as feature vectors, which were input to fuzzy optimal multi-classified SVMs for training. Then the FSVMs diagnosis model was established to implement fault samples classification. Experiment showed that by adopting facture extraction with KMC, the diagnosis information was concentrated and the consuming in parameter determination was solved effectively. The presented method enabled to detect transformer faults with a high correct judgment rate, and can be used as an automation approach for diagnosis under condition of small samples.

Structure Fault Diagnosis of Tower Crane Based on Wavelet Packet Analysis and Support Vector Machines

2013 ◽  
Vol 325-326 ◽  
pp. 294-298
Author(s):  
Sheng Chun Wang ◽  
Rong Sheng Shen ◽  
Shi Jun Song ◽  
Yan Tian
Keyword(s):  
Fault Diagnosis ◽  
Support Vector Machines ◽  
Structural Damage ◽  
Wavelet Packet ◽  
Fault Classification ◽  
Support Vector ◽  
Analysis Model ◽  
Element Analysis ◽  
Tower Crane ◽  
Vector Machines

First establish a dynamic model of tower crane in the load lifting process, the lifting load is solved under two work conditions.Then establish the FEM(finite element analysis) model of the tower crane under the normal and the damage condition. Get the dynamic displacement of the normal and the damage status under the lifting dynamic load. With wavelet packet decomposition and SVM(Support vector machines) multi-classification algorithm, a multi-fault classifier is constructed, and applied to the fault diagnosis of tower body. The results of the study show that the multi-fault classifier has such advantages as simple algorithm and excellent capability of fault classification, and it can not only diagnose the structural damage status, but also determine the positions of structural damage. This will be a new search on tower crane structural health diagnosis.

Sign in / Sign up

Export Citation Format

Share Document