基于无人机巡检的风机叶片机械冲击疲劳感知  

Mechanical impact fatigue perception of fan blades based on UAV inspection

作　　者：刘艳贵 傅望安 王海明 劳文欣 LIU Yan-gui;FU Wang-an;WANG Hai-ming;LAO Wen-xin(Clean Energy Branch of Huaneng(Zhejiang)Energy Development Co.,Ltd.,Hangzhou 310014,China;China Huaneng Clean Energy Research Institute,Beijing 102209,China)

机构地区：[1]华能(浙江)能源开发有限公司清洁能源分公司,杭州310014 [2]中国华能集团清洁能源技术研究院有限公司,北京102209

出　　处：《信息技术》2025年第3期186-191,共6页Information Technology

摘　　要：风机通常安装在复杂地形场所,且风机叶片较高,导致人工巡检困难,难以及时发现风机故障。为此,提出基于无人机巡检的风机叶片机械冲击疲劳感知方法。根据力学平衡关系计算叶片试件平均应力和应力变动关系,获取比例函数,得到应力损伤和机械冲击疲劳性同比例线性阈值。建立无人机巡检线路数字模拟空间,计算巡航最大距离与航线长度间的差值,约束叶片定位误差。结合卷积神经网络算法与映射法,得到风机叶片机械冲击疲劳感知结果。实验数据证明,所提方法巡检效率高,且对风机叶片机械冲击疲劳感知精度高。The fan is usually installed in complex terrain,and the fan blade is high,which makes manual inspection difficult and difficult to find the fan fault in time.Therefore,a mechanical impact fatigue sensing method for fan blades based on UAV inspection is proposed.According to the mechanical equilibrium relationship,the mean stress and stress variation of blade specimens were calculated,and the proportional function was obtained to obtain the proportional linear threshold of stress damage and mechanical impact fatigue.The digital simulation space of UAV inspection line was established,and the difference between cruise maximum distance and route length was calculated to constrain the blade positioning error.Combined with convolutional neural network algorithm and mapping method,the mechanical impact fatigue perception of fan blade is obtained.Experimental data show that the proposed method has high inspection efficiency and high sensing precision for mechanical impact fatigue of fan blades.

关 键 词：多旋翼无人机 风机风轮叶片 机械冲击疲劳性 无人机巡检 应力损伤 

分 类 号：TH11[机械工程—机械设计及理论] TP273.2[自动化与计算机技术—检测技术与自动化装置]