|
|
|
| SHAFT CRACK FAULT DIAGNOSIS BASED ON GRID SUPPORT VECTOR MACHINES |
| YUAN Shengfa li xiu qiong |
| （School of Material Science and Engineering, Wuhan University of Technology, Wuhan 430070, China) |
|
|
|
Abstract Support vector machines is a general machine-learning tool that exhibits good generalization when fault samples are few. Since basic support vector machines is originally designed for two-class classification, a new multi-class classification algorithm named grid support vector machines is presented to solve the pattern recognition problems in fault diagnosis which is typical multi-class classification case. With this rid support vector machines, every class constructs two-class SVM classifiers with less than 4 other classes, and the total number of two-class SVM classifiers is less. The rid support vector machines is simpler and more extensible compared with other methods of multi-class support vector machines. The cracks in different positions of the shaft are regarded as different classes of fault, and are diagnosed by the grid support vector machines. The result shows the new methods distinctly improves the fault recognition accuracy and the diagnosis speed, and it is more suitable for practical application of multi-class fault diagnosis.
|
|
Received: 05 September 2008
|
|
Corresponding Authors:
YUAN Shengfa li xiu qiong
|
|
|
|
|
|
|
2009, Vol. 28 
