文档介绍：第 25 卷第 9 期中国电机工程学报 May 2005 2005 年 5 月 Proceedings of the CSEE ?2005 . 文章编号: 0258-8013 (2005) 09-0035-05 中图分类号: TM935 文献标识码: A 学科分类号: 470 ? 40 基于 FFT 和神经网络的非整数次谐波检测方法 向东阳, 王公宝, 马伟明, 张文博(海军工程大学,湖北省武汉市 430033 ) A NEW METHOD FOR NON-INTEGER HARMONICS MEASUREMENT BASED ON FFT ALGORITHM AND WORK XIANG Dong-yang, WANG Gong-bao, MA Wei-ming, ZHANG Wen-bo (Naval University of Engineering, Wuhan 430033, Hubei Province, China) ABSTRACT: By using an artificial work (ANN) model, high measurement accuracy of integer harmonics can be obtained. The invalidation of an ANN model being used in non-integer harmonics analysis is pointed out. In order to detect non-integer harmonics precisely, an improved ANN model is presented in this paper. bining the windowed fast Fourier transform (FFT) algo rithm with the improved ANN model, we provide a new me thod for measurement of non-integer harmonics. The following approach is adopted. Firstly, the Hanning-windowed FFT algorithm processes the sampled signal. By this time, the number of harmonics and the orders of harmonics are obtained. Secondly, choose the number of neural nodes according to the number of harmonics. Thirdly, choose the initial values of orders of harmonics according to the result obtained from the Hann ing-windowed FFT algorithm. Finally, by using the