摘要
HVDC已经被应用于输电配电网络。如何实现准确的电力故障检测是目前该领域的研究热点问题。针对这个难点,提出了一种基于核极端学习机(KELM)的HVDC故障检测方法。首先,采集到HVDC故障时段的电压数字信号;然后提出PSO-KELM模型来以提供快速而准确的故障识别,其中PSO实现了KELM参数优化,即隐层的神经元数目的全局优化。试验结果表明,所提出的PSO-KELM新方法能够有效识别系统不同故障,具有较好的工程应用前景。
HVDC finds variant applications in industry. How to achieve high fault recognition accuracy is still receivedconsiderable attentions in this field. To address this issue,this paper presents a new method that uses the kernel extremelearning machine （KELM） for HVDC fault detection. The fault voltage signal was recorded firstly. Then KELM has beenproposed to provide quick and accurate fault recognition. The only parameter need be determined in KELM is the neuronnumber of hidden layer. Literature review indicates that very limited work has addressed the optimization of this parame-ter. Hence, the PSO was used for the first time to optimize the KELM parameter in this paper. Experiments have been im-plemented to verify the efficiency of the proposed method.
出处
《电气开关》
2014年第4期36-38,共3页
Electric Switchgear
