检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:徐达[1] 洪文慧 季天瑶 徐钰涵 李梦诗[1] XU Da;HONG Wenhui;JI Tianyao;XU Yuhan;LI Mengshi(School of Electric Power Engineering,South China University of Technology,Guangzhou,Guangdong 510641,China)
出 处:《广东电力》2021年第7期33-39,共7页Guangdong Electric Power
基 金:国家自然科学基金(52077081)。
摘 要:针对电能质量复合扰动的识别方法准确率较低、效率较慢、鲁棒性较差的问题,提出一种基于S变换和长短期记忆网络的混合方法,该方法能够高效准确地对电能质量复合扰动进行识别,并且鲁棒性高。S变换得到的二维模矩阵的行和列分别反映频域和时域特征,将模矩阵作为长短期记忆网络的输入。为了检验该混合方法的性能,首先对15种电能质量扰动信号进行数学建模并得到大量数据样本,然后进行识别实验。为验证有效性,将所提方法与其他常用方法进行对比实验;为验证鲁棒性,对所提方法在不同强度的高斯噪声信号干扰下进行分类实验。实验结果表明,所提混合方法具有很高的准确性和鲁棒性。Accurate identification of power quality disturbance is the premise of making targeted measures to reduce its harm.Aiming at the problems of current identification methods for composite disturbance of power quality such as low accuracy,slow efficiency and poor robustness,this paper proposes a hybrid method based on S transform and long and short term memory network(LSTM),which can identify composite disturbance of power quality efficiently and accurately with high robustness.The row and column of the two-dimensional module matrix obtained by S transformation reflect the frequency domain and time domain characteristics respectively,and the module matrix is taken as the input of LSTM.In order to test the performance of the hybrid method,15 kinds of power quality disturbance signals are modeled and a large number of data samples are obtained,and then identification experiments are carried out.To verify the effectiveness of the method,the paper compares it with other common methods.To verify the robustness of the method,the sample classification experiments are carried out under the interference of Gaussian noise signals of different intensity.The experimental results show that the hybrid method proposed has high accuracy and robustness.
分 类 号:TM93[电气工程—电力电子与电力传动] TP183[自动化与计算机技术—控制理论与控制工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.145