摘要
提出了一种基于麻雀搜索算法优化BP人工神经网络(SSA-BP)的湍流预报模式。首先,采用BP人工神经网络作为湍流预报模型的基础框架。通过对温度、湿度、风速等气象因素的采集和处理,将其作为输入层的特征。然后,利用麻雀搜索算法对BP人工神经网络的权重和偏置进行优化。为了验证该方法的有效性,采用了来自地面气象站的大气湍流数据及气象数据进行实验。实验结果表明,SSA-BP人工神经网络能够成功预测大气湍流的发展趋势,并具有较高的预测精度和稳定性,能够充分利用大气湍流数据中的非线性特征,为湍流预测研究和实际应用提供了有力支持。
A turbulence prediction model based on sparrow search algorithm optimized BP artificial neural network(SSA-BP)has been proposed.Firstly,the BP artificial neural network is adopted as the basic framework for turbulence prediction models.By collecting and processing meteorological factors such as temperature,humidity,and wind speed,they are used as input layer features.Then,the sparrow search algorithm is used to optimize the weights and biases of the BP artificial neu-ral network.To verify the effectiveness of this method,experiments were conducted using atmospheric turbulence data and meteorological data from ground meteorological stations.The experimental results indicate that the SSA-BP artificial neural network can successfully predict the development trend of atmospheric turbulence,and has high prediction accuracy and stability.Being able to fully utilize the nonlinear features in atmospheric turbulence data provides strong support for turbulence prediction research and practical applications.
作者
张恒
张雷
姚海峰
佟首峰
曹玉玺
ZHANG Heng;ZHANG Lei;YAO Haifeng;TONG Shoufeng;CAO Yuxi(School of Opto-Electronic Engineering,Changchun University of Science and Technology,Changchun 130022;School of Optics and Photonics,Beijing Institute of Technology,Beijing 100081)
出处
《长春理工大学学报（自然科学版）》
2024年第2期58-65,共8页
Journal of Changchun University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金(62105029)
博士后特别资助项目(2021TQ0035)
博士后面上项目(2021M700415)
应用光学国家重点实验室资助(SKLA02022001A11)
吉林省教育厅科学技术研究项目(JJKH20220743KJ)。
关键词
BP人工神经网络
麻雀搜索算法
气象参数
大气湍流预测
BP artificial neural network
sparrow search algorithm
seteorological parameters
atmospheric turbulence prediction
