To search, Click below search items.


All Published Papers Search Service


Fault Diagnosis Based on Wavelet Fuzzy Feature Extraction and Information Fusion


Mohammad Reza Vazifeh , Farzaneh Abbasi Hossein Abadi


Vol. 15  No. 10  pp. 58-64


With increasing demand for efficiency and product quality and progressing integration of automatic control systems in high cost and safety ?critical process the field of supervision or monitoring, fault detection and diagnosis plays important rules. The Fault diagnosis task consist of the determination of the fault type with as many details as possible such as the fault size, location and time of detection. Today, fault diagnosis is main research in world. We exposure new algorithm in this paper, this algorithm have 3 steps. In the First step used wavelet packet and fuzzy set for make wavelet tree with coefficient in each node. In second step using wavelet tree and fuzzy set fused data with maximum Entropy coefficient in wavelet tree and in step three with output of fusion function we classification this fusion data. This algorithm have best time study because the time of search algorithms is 2^D ,D is depth of wavelet tree. Our proposed fusion strategies take into account that a Wavelet-Fuzzy by finding the optimal hyper plane with maximal margin. Then a Support Vector Machine classifier is trained. In the distributed schemes, the individual data sources are processed separately and modeled by using the Support Vector Machine.


Fault diagnosis, Information Fusion, Wavelet-Packed Entropy, Fuzzy set