论文部分内容阅读
短波信道由于受电离层的非线性变化影响而不能及时选到最佳频率,严重制约了短波通信系统的效能发挥。为了提高短波频率预测及选频的准确性,在总结前人关于短波频率预测经验的基础上,结合人工智能技术在非线性时间序列预测方面取得的成就,提出了一种短波通信频率的预测方法,该方法结合相空间重构技术和模糊小波神经网络技术,并在数据预处理阶段采用奇异值分解对历史数据进行降噪处理,实验结果表明,该方法比其他预测方法的精度有很大的提高。
Due to the influence of the non-linearity of the ionosphere, the short-wave channel can not select the best frequency in time and severely restricts the performance of the short-wave communication system. In order to improve the accuracy of shortwave frequency prediction and frequency selection, based on the previous experience of shortwave frequency prediction, combined with the achievements made by artificial intelligence in nonlinear time series prediction, a method of shortwave communication frequency prediction This method combines the technique of phase space reconstruction and fuzzy wavelet neural network, and uses the singular value decomposition in the data preprocessing stage to denoise the historical data. The experimental results show that this method has a higher accuracy than other prediction methods improve.