基于神经网络的电力谐波检测方法  

Power Harmonic Detection Approach Based on Neurnal Network

作　　者：张文嘉 卢惠辉 苏成悦[2] 潘永雄[2] 刘力斌[2] 

机构地区：[1]广州供电局有限公司,广东广州510730 [2]广东工业大学,广东广州510006

出　　处：《陕西电力》2015年第6期67-70,共4页Shanxi Electric Power

基　　金：2014年广东省高等学校学科建设专项资金资助项目(2014KTSCX058)

摘　　要：非线性用电负载产生的大量谐波对输入电网造成极大危害,已有的传统检测方法由于自身技术的限制,难以满足目前谐波检测对精确性的要求。针对电力谐波表现形式,分析神经网络结构和计算算法,提出一种结合神经网络的谐波检测方法,并与快速傅里叶加Hanning窗函数双谱线插值方法进行试验数据对比,验证了该方法的有效性,有效提高了电力谐波的检测精度。Nnnlinear loads create a large number of harmonic which cause great harm to the input power grid. The existing traditional detection methods are difficuh to meet the accuracy requirements of harmonic detection due to the limitation of their own Ieehnology. In view of the power harmonic forms, this paper analyzes the principle of neural network（NN）structure and algorithm, and then puts forward a detection method based on neural network . Finally,the experimental results verify the effectiveness of the proposed method and the effective improvement of power harmonic detection aeeuracy by comparing with double-spectrum-line interpolation base on ltanning window fast fourier transform（FFT）.

关 键 词：电力谐波 快速傅里叶变换 神经网络 窗函数 谐波检测 

分 类 号：TM711[电气工程—电力系统及自动化]