| 基于卷积神经网络的非多普勒激光雷达测风系统 |
| |
| 引用本文： | 张平慧,胡淼,许蒙蒙,应娜,贺文迪,金益文,赵喻晓,周雪芳,杨国伟,毕美华,李齐良.基于卷积神经网络的非多普勒激光雷达测风系统[J].光电子．激光,2021,32(10):1039-1045. |
| |
| 作者姓名： | 张平慧 胡淼 许蒙蒙 应娜 贺文迪 金益文 赵喻晓 周雪芳 杨国伟 毕美华 李齐良 |
| |
| 作者单位： | 杭州电子科技大学通信工程学院,浙江杭州310018;杭州电子科技大学通信工程学院,浙江杭州310018;国民核生化灾害防护国家重点实验室,北京102205 |
| |
| 基金项目： | 国家自然科学基金(61705055)、2020年度浙江省重点研发计划项目(2019C01G1121168)、2020年国家级大学生创新创业训练项目(202010336054)、 2020年浙江省大学生科技创新活动计划暨新苗人才计划(2020R407073) 和本课题由杭州电 子科技大学研究生科研创新基金资助项目 (1.杭州电子科技大学 通信工程学院,浙江 杭州 310018； 2.国民核生化灾害防护国家重 点实验室,北京 102205) |
| |
| 摘 要： | 提出了一种基于卷积神经网络技术的非多普勒激光雷达测风系统.该系统利用半导体感光元件(charge coupled device,CCD)拍摄气溶胶颗粒物的激光雷达后向散射图,针对不同风速气溶胶颗粒物的运动轨迹特征,实现定量的风速测量.卷积神经网络对经过图像预处理的气溶胶颗粒物运动轨迹图,进行特征提取并生成风速测量模型,第100次训练样本和验证样本的准确率分别为0.92和0.93.利用生成的风速测量模型对测试样本进行实验,准确率达到0.84.这种低成本、操作简便的非多普勒激光雷达测风系统,能够解决当前多普勒频移测风激光雷达成本高的痛点,具有很强的现实意义.
|
| 关 键 词： | 大气光学 非多普勒激光雷达 卷积神经网络(CNN) |
| 收稿时间： | 2021/1/23 0:00:00 |
Non-doppler lidar wind measurement system based on convolutional neural networ k |
| |
| ZHANG Pinghui,HU Miao,XU Mengmeng,YING N,HE Wengdi,JIN Yiwen,ZHAO Yuxiao,ZHOU Xuefang,YANG Guowei,BI Meihua and LI Qiliang.Non-doppler lidar wind measurement system based on convolutional neural networ k[J].Journal of Optoelectronics·laser,2021,32(10):1039-1045. |
| |
| Authors: | ZHANG Pinghui HU Miao XU Mengmeng YING N HE Wengdi JIN Yiwen ZHAO Yuxiao ZHOU Xuefang YANG Guowei BI Meihua and LI Qiliang |
| |
| Affiliation: | College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China ;State Key Laboratory of NBC Protection for Civilian,Beijing 102205,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China,College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China and College of Communication Engineering,Hangzhou Dianzi University,Hangzhou,Zhej iang 310018,China |
| |
| Abstract: | A Non-Doppler lidar wind measurement system based on convolutional neu ral network technology is proposed.The system uses (charge coupled device, CCD) to capture the lidar backsca tter map of aerosol particles,and realizes quantitative wind speed measurement according to the movement trajectory of aerosol particles at different wind speeds.The convolutional neur al network extracts the features of the aerosol particle movement trajectory after lidar im age preprocessing and generates a wind speed measurement model.The accuracy of the 100th training sample and verification sample are 0.92and 0.93,respectively.The wind speed measurem ent model is used on the test sample,and the accuracy rate reaches 0.84.This low-cost, easy-to-operate non-Doppler lidar wind measurement system can effectively reduce the cost of wi nd measurement and has strong practical significance. |
| |
| Keywords: | atmospheric optics non-Doppler lidar convolution neural network (CNN) |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
