| 改进脉冲耦合神经网络及二维Otsu算法的光伏阵列阴影检测 |
| |
| 引用本文： | 胡蓓,隆霞,胡超,段盼,唐若笠,段其昌. 改进脉冲耦合神经网络及二维Otsu算法的光伏阵列阴影检测[J]. 应用科学学报, 2013, 31(6): 613-618. DOI: 10.3969/j.issn.0255-8297.2013.06.010 |
| |
| 作者姓名： | 胡蓓 隆霞 胡超 段盼 唐若笠 段其昌 |
| |
| 作者单位： | 1. 重庆大学自动化学院，重庆4000442. 国家电网重庆市电力工司南岸供电分公司，重庆400060 |
| |
| 基金项目： | 国家自然科学基金(No.51377187)；重庆市科技攻关项目基金(No.2011AB6054)资助 |
| |
| 摘 要： | 阴影对太阳能发电系统输出功率有极大的抑制作用，该文针对光伏阵列局部遮荫现象提出一种基于改进的脉冲耦合神经网络的阴影检测方法. 设置合适的初始参数，根据unit-linking PCNN（ULPCNN）算法进行阴影分割，利用二维Otsu算法自动选取迭代次数，以循环迭代过程中具有最优阈值的分割图像为最终分割结果. 仿真结果表明：该算法可检测出光伏阵列局部阴影，与传统的脉冲耦合神经网络算法及ULPCNN算法相比分割结果更好，操作更简洁.
|
| 关 键 词： | 阴影检测 脉冲耦合神经网络 unit-linking PCNN 二维Otsu算法 |
| 收稿时间： | 2012-05-06 |
| 修稿时间： | 2012-12-27 |
Shadow Detection for PV Array Using Improved PCNN and Two-Dimensional Otsu Algorithm |
| |
| HU Bei,LONG Xia,HU Chao,DUAN Pan,TANG Ruo-li,DUAN Qi-chang. Shadow Detection for PV Array Using Improved PCNN and Two-Dimensional Otsu Algorithm[J]. Journal of Applied Sciences, 2013, 31(6): 613-618. DOI: 10.3969/j.issn.0255-8297.2013.06.010 |
| |
| Authors: | HU Bei LONG Xia HU Chao DUAN Pan TANG Ruo-li DUAN Qi-chang |
| |
| Affiliation: | 1. Automation, Chongqing University, Chongqing 400044, China;2. Chongqing Nan0an Power Company, State Grid Electric Power Company, Chongqing 400060, China |
| |
| Abstract: | Shadows cause serious reduction of power generation in a photovoltaic (PV) power plant. This paper proposes a shadow detection method based on improved pulse coupled neural networks (PCNN) for partially shaded PV module images. Suitable initial parameters of unit-link PCNN are set. The ULPCNN is applied to the gray shading images, and the two-dimensional Otsu method is used to automatically determine the numbers of iterations. The segmentation that achieves the best threshold in the iteration is selected as an optimal result. Simulations verify that the test images are well segmented, and the method has better performance compared to the conventional PCNN and ULPCNN. |
| |
| Keywords: | shadow detection pulse coupled neural network (PCNN) unit-linking PCNN two-dimensional Otsu algorithm |
|
| 点击此处可从《应用科学学报》浏览原始摘要信息 |
|
点击此处可从《应用科学学报》下载全文 |
