基于多域特征提取和自适应神经-模糊推理系统的电能质量扰动识别  被引量:6

Power quality disturbances recognition based on multi-domain feature extraction and ANFIS

在线阅读下载全文

作  者:张明[1] 李开成[1] 胡益胜[1] 

机构地区:[1]华中科技大学电气与电子工程学院,湖北武汉430074

出  处:《电力系统保护与控制》2010年第24期6-13,共8页Power System Protection and Control

基  金:国家自然科学基金项目(51077058)~~

摘  要:基于多域特征提取(multi-domain feature extraction)和自适应神经-模糊推理系统(Adaptive Neuro-Fuzzy Inference system,ANFIS)提出了电能质量扰动类型识别的一种新方法。基于波形包络阈值线对扰动进行检测;在时域、频域和小波域进行多域特征提取,选取扰动信号的基波均方根(RMS)幅值、总谐波畸变率、次谐波幅值和小波包能量熵共同组成输入特征矢量;通过自适应神经-模糊推理系统对电能质量扰动类型进行识别。仿真结果表明,该方法与BP神经网络和最小二乘支持向量机相比平均识别准确率高,对特征不规则的待检电能质量扰动信号具有良好的柔性和适应性。Based on multi-domain feature extraction and adaptive neuro-fuzzy inference system (ANFIS),a new method for the identification of power quality disturbances is proposed.First ,t he waveform envelope threshold is used to detect power quality disturbances and then the feature vectors are extracted in multi-domain including time-domain, frequency-domain and wavelet-domain, and fundamental component RMS amplitude,total harmonic distortion (THD),subharmonic amplitude and wavelet energy entropy of disturbance signal are selected to constitute input feature vector.The ANFIS is used in the identification of power quality disturbance types. Simulation results confirm the aptness and the capability of the proposed system in irregular power quality disturbance signal recognition and indicate that the ANFIS classifier is more accurate compared with back-propagation artificial neural networks (BP-ANN) and least square support vector machines (LS-SVM).

关 键 词:电能质量 多域特征提取 自适应神经-模糊推理系统 BP神经网络 最小二乘支持向量机 

分 类 号:TM711[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象