Entity

Time filter

Source Type


Zhang X.,Power Technology Research Center | Huang R.,Power Technology Research Center | Yao S.,Power Technology Research Center | Li G.,Xian Jiaotong University | And 2 more authors.
Proceedings - International Conference on Natural Computation | Year: 2016

Mechanical fault is one of the main faults occurring during the life cycle of high-voltage circuit breakers (HVCBs), which has a significant influence on the reliability of the electrical power system. In this paper, the mechanical prediction algorithm for HVCBs based on support vector machine (SVM) was studied. Firstly, we used a sliding time window (STW) method to extract features of the travel curves of the movable contacts and coil current curves of HVCBs. Then the historic data were used to learn a support vector regression machine and finally to predict the new curves. In the end, the mechanical life experiment data of a HVCB were applied to validate the feasibility of the algorithm. The results showed that the proposed algorithm could predict the mechanical condition of HVCBs successfully. © 2015 IEEE. Source

Discover hidden collaborations