合肥工业大学学报(自然科学版)
閤肥工業大學學報(自然科學版)
합비공업대학학보(자연과학판)
JOURNAL OF HEFEI UNIVERSITY OF TECHNOLOGY(NATURAL SCIENCE)
2014年
2期
159-163
,共5页
小电流接地故障%选线%多小波%能量特征%神经网络
小電流接地故障%選線%多小波%能量特徵%神經網絡
소전류접지고장%선선%다소파%능량특정%신경망락
small current grounding fault%line selection%multiwavelet%energy feature%neural network
文章基于多小波的特性,提出了应用GHM多小波和神经网络相结合的方法实现小电流接地故障选线,根据故障前后各条线路的能量分布,利用GHM多小波变换构造出各条线路的能量特征,以此构成故障特征向量作为神经网络的输入向量,进而通过神经网络的训练给出选线结果。最后构造出小电流接地仿真实验模型,实验结果的对比验证了该方法的有效性、可行性。
文章基于多小波的特性,提齣瞭應用GHM多小波和神經網絡相結閤的方法實現小電流接地故障選線,根據故障前後各條線路的能量分佈,利用GHM多小波變換構造齣各條線路的能量特徵,以此構成故障特徵嚮量作為神經網絡的輸入嚮量,進而通過神經網絡的訓練給齣選線結果。最後構造齣小電流接地倣真實驗模型,實驗結果的對比驗證瞭該方法的有效性、可行性。
문장기우다소파적특성,제출료응용GHM다소파화신경망락상결합적방법실현소전류접지고장선선,근거고장전후각조선로적능량분포,이용GHM다소파변환구조출각조선로적능량특정,이차구성고장특정향량작위신경망락적수입향량,진이통과신경망락적훈련급출선선결과。최후구조출소전류접지방진실험모형,실험결과적대비험증료해방법적유효성、가행성。
In view of the characteristics of multiw avelet , the fault line selection method of small current grounding system based on the GHM multiwavelet and neural network is presented .According to the energy distribution of each line before and after the fault ,the energy features of every line are sent to the neural net-work with the use of GHM multiwavelet transformation .By training the neural network ,the last line selec-tion results are given directly by the neural network output .A simulation model of small current grounding is constructed and the experimental results verify the effectiveness and feasibility of the method .