[1]陈炳煌,缪希仁,江灏,等.融合粒子群与极限学习机的输电杆塔灾害分类方法[J].郑州大学学报(工学版),2021,42(04):77-83.
 A method for disaster status classification of transmission line towers by integrating particle swarm optimization and extreme learning machine[J].Journal of Zhengzhou University (Engineering Science),2021,42(04):77-83.
点击复制

融合粒子群与极限学习机的输电杆塔灾害分类方法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42
期数:
2021年04期
页码:
77-83
栏目:
出版日期:
2021-07-30

文章信息/Info

Title:
A method for disaster status classification of transmission line towers by integrating particle swarm optimization and extreme learning machine
作者:
陈炳煌缪希仁江灏吴俊钢
文献标志码:
A
摘要:
在无人机应急巡检架空输电线路的基础上,提出一种融合粒子群优化与极限学习机的输电线路铁塔灾害状态分类方法。先结合直线检测法和Harris角点检测法从架空输电线路铁塔图像中提取特征参数,再采用灰色关联分析法获取铁塔与灾害状态关联的主要特征参数,应用粒子群优化对极限学习机的输入隐藏权值和隐藏偏差阈值进行优化,将该分类方法应用于无人机铁塔图像数据集中。与其他算法的对比实验表明,融合粒子群优化和极限学习机模型的分类方法可更准确地区分正常、半倒塌和全倒塌等三种类型的输电线路铁塔状态。
Abstract:
On the basis of UAV emergency inspection of overhead transmission lines, this paper proposes a disaster status classification method of transmission line iron tower that integrates particle swarm optimization and extreme learning machine. First combined with line segment detection and Harris corner detection from an overhead transmission line tower image to extract the characteristic parameters, then adopts the grey relation analysis for the main features and disaster status of the iron tower. The input hidden weight and deviation threshold of extreme learning machine are optimized by the application of particle swarm optimization, and the image classification algorithm is applied to the dataset of iron tower by UAV. The comparison experiment with other algorithms shows that the classification method ba<x>sed on particle swarm optimization and extreme learning machine model can more accurately distinguish normal, semi-collapsed and fully collapsed transmission line tower states
更新日期/Last Update: 2021-08-26