A New Intelligent Fault Detection Approach for HVDC Based on Kernel Extreme Learning Machine
Yuanjin Li · Electric Switchgear · 2014
HVDC finds variant applications in industry. How to achieve high fault recognition accuracy is still received considerable attentions in this field. To address this issue,this paper presents a new method that uses the kernel extreme learning machine( KELM) for HVDC fault detection. The fault voltage signal was recorded firstly. Then KELM has been proposed to provide quick and accurate fault recognition. The only parameter need be determined in KELM is the neuron number of hidden layer. Literature review indicates that very limited work has addressed the optimization of this parameter. Hence,the PSO was used for the first time to optimize the KELM parameter in this paper. Experiments have been implemented to verify the efficiency of the proposed method.