Based on Lund and Shanklin’s work (1972), methods of calculating Probability of Cloud-Free Lines-of-Sight (PCFLOS), Persistence Probability of Cloud-Free Lines-of-Sight (PPCFLOS) and Recurrence Probability of Cloud-f...Based on Lund and Shanklin’s work (1972), methods of calculating Probability of Cloud-Free Lines-of-Sight (PCFLOS), Persistence Probability of Cloud-Free Lines-of-Sight (PPCFLOS) and Recurrence Probability of Cloud-free Lines-of-Sight (RPCFLOS) at given heights are presented. PCFLOS, PPCFLOS and RPCFLOS are calculated in Foshan, China by conventional observation data from 1961 to 1990. The conclusions are: (1) The higher the elevations, the smaller the PCFLOS and the larger the view angles, the larger the PCFLOS. (2) PPCFLOS and RPCFLOS decrease with the increase of elevation and the delay of time. (3) RPCFLOS is always equal to or larger than PPCFLOS at lag times.展开更多
Based on the monitoring data of cloud-to-ground( CG) lightning positioning network and Doppler weather radar as well as MICAPS1°× 1° objective analysis field,a squall line process outside of the subtrop...Based on the monitoring data of cloud-to-ground( CG) lightning positioning network and Doppler weather radar as well as MICAPS1°× 1° objective analysis field,a squall line process outside of the subtropical high in low-latitude plateau on May 7,2010 was analyzed. The results showed that wind direction shear between low and high levels and low-level convergence zones provided favorable circulation background for the strong thunderstorm process,while high energy and high humidity,strong thermal instability and ascending motion at low and middle levels offered beneficial environmental conditions for the formation of the thunderstorm. 9 620 return strokes of cloud-to-ground lightning were monitored by the lightning positioning network,and cloud-to-ground lightning was distributed like bands between 584 and 586 hP a. The occurrence of cloud-to-ground lightning was mainly related to echo top and echo intensity at-10 ℃ stratification height,and it mainly appeared in zones where echo top height was larger than 13 km and echo intensity at-10 ℃ stratification height was 35-40 dB Z. Wind convergence and maintaining of high radial velocity were favorable for the development of convective echoes and occurrence of cloud-to-ground lightning.展开更多
针对云端单一集中数据处理时效性低、架空线路上鸟巢检测精度不高、模型对边缘计算设备算力高消耗以及目标定位不准确的问题,提出了一种基于云边端协作的架空线路鸟巢检测与定位算法。该算法通过云、终、边缘3端的协作,解决了云端集中...针对云端单一集中数据处理时效性低、架空线路上鸟巢检测精度不高、模型对边缘计算设备算力高消耗以及目标定位不准确的问题,提出了一种基于云边端协作的架空线路鸟巢检测与定位算法。该算法通过云、终、边缘3端的协作,解决了云端集中处理效率低的问题,并通过云边数据可视化协作解决由于角度及光线引起的图像不清晰问题。为了提高架空线路鸟巢检测的精度,该算法在YOLOv5x模型基础上进行了优化。首先,通过将主干特征提取网络中的C3模块替换为C2f模块,并在最后一层加入SE(squeeze and excitation)注意力模块,以提升模型对小目标的检测能力。其次,将激活函数替换为Mish函数,解决训练梯度饱和导致神经元停止学习的问题。为了降低模型对边缘计算设备算力的消耗,对改进后的模型进行剪枝微调以降低模型参数规模。基于此优化模型,提出了三维目标定位算法,结合GIS(geographic information system)系统对定位结果进行修正,实现了对检测目标的精准定位。实验数据显示,改进后的模型平均精度均值达到93.25%,比原YOLOv5x模型提升了3.44%,优化后的模型剪枝率达到45%。检测目标经过三维空间建模计算并通过位置修正能够定位到相应的杆塔,有效指导工作人员快速准确排除隐患。展开更多
文摘Based on Lund and Shanklin’s work (1972), methods of calculating Probability of Cloud-Free Lines-of-Sight (PCFLOS), Persistence Probability of Cloud-Free Lines-of-Sight (PPCFLOS) and Recurrence Probability of Cloud-free Lines-of-Sight (RPCFLOS) at given heights are presented. PCFLOS, PPCFLOS and RPCFLOS are calculated in Foshan, China by conventional observation data from 1961 to 1990. The conclusions are: (1) The higher the elevations, the smaller the PCFLOS and the larger the view angles, the larger the PCFLOS. (2) PPCFLOS and RPCFLOS decrease with the increase of elevation and the delay of time. (3) RPCFLOS is always equal to or larger than PPCFLOS at lag times.
基金Supported by National Natural Science Foundation of China(No.41305002)Science and Technology Project of Yunnan Province(No.2014RA002,2016RA096)
文摘Based on the monitoring data of cloud-to-ground( CG) lightning positioning network and Doppler weather radar as well as MICAPS1°× 1° objective analysis field,a squall line process outside of the subtropical high in low-latitude plateau on May 7,2010 was analyzed. The results showed that wind direction shear between low and high levels and low-level convergence zones provided favorable circulation background for the strong thunderstorm process,while high energy and high humidity,strong thermal instability and ascending motion at low and middle levels offered beneficial environmental conditions for the formation of the thunderstorm. 9 620 return strokes of cloud-to-ground lightning were monitored by the lightning positioning network,and cloud-to-ground lightning was distributed like bands between 584 and 586 hP a. The occurrence of cloud-to-ground lightning was mainly related to echo top and echo intensity at-10 ℃ stratification height,and it mainly appeared in zones where echo top height was larger than 13 km and echo intensity at-10 ℃ stratification height was 35-40 dB Z. Wind convergence and maintaining of high radial velocity were favorable for the development of convective echoes and occurrence of cloud-to-ground lightning.
文摘针对云端单一集中数据处理时效性低、架空线路上鸟巢检测精度不高、模型对边缘计算设备算力高消耗以及目标定位不准确的问题,提出了一种基于云边端协作的架空线路鸟巢检测与定位算法。该算法通过云、终、边缘3端的协作,解决了云端集中处理效率低的问题,并通过云边数据可视化协作解决由于角度及光线引起的图像不清晰问题。为了提高架空线路鸟巢检测的精度,该算法在YOLOv5x模型基础上进行了优化。首先,通过将主干特征提取网络中的C3模块替换为C2f模块,并在最后一层加入SE(squeeze and excitation)注意力模块,以提升模型对小目标的检测能力。其次,将激活函数替换为Mish函数,解决训练梯度饱和导致神经元停止学习的问题。为了降低模型对边缘计算设备算力的消耗,对改进后的模型进行剪枝微调以降低模型参数规模。基于此优化模型,提出了三维目标定位算法,结合GIS(geographic information system)系统对定位结果进行修正,实现了对检测目标的精准定位。实验数据显示,改进后的模型平均精度均值达到93.25%,比原YOLOv5x模型提升了3.44%,优化后的模型剪枝率达到45%。检测目标经过三维空间建模计算并通过位置修正能够定位到相应的杆塔,有效指导工作人员快速准确排除隐患。
