针对运行中的风力机叶片,提出一种基于机器视觉特征分类的故障诊断方法。通过对叶片叶尖进行圆形标记,利用工业相机周期性获取叶片尖端的图像,并在Halcon软件上对图像进行预处理,对大雾天气下采集的图像利用暗通道除雾算法进行清晰化处理。利用叶尖标记检测算法提取标记、计算区域圆度和区域中心等区域特征。对相邻叶片上标记计算位移差,并与系统预警阈值比较,判断叶片在扭转或偏摆方向的变形程度和故障趋势,从而实现风力机叶片变工况运行状态在线检测和自适应预警。
Abstract
A fault diagnosis method based on machine vision feature classification is proposed for wind turbine blades in operation. By circularly marking the blade tip, images of the blade tip are acquired periodically using an industrial camera and pre-processed on Halcon software, and images acquired in foggy weather are clarified using a dark channel defogging algorithm. A leaf tip marker detection algorithm is used to extract markers, calculation area features such as area roundness and area centre. The markers on the adjacent blades are then compared with the system's warning threshold to determine the degree of blade deformation and fault trend in the direction of torsion or deflection, thus enabling online detection and adaptive warning of the variable operating conditions of wind turbine blades.
关键词
风力机叶片 /
故障检测 /
图像处理 /
机器视觉 /
特征分类
Key words
wind turbine blades /
fault detection /
image processing /
machine vision /
feature classification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] JIA L Y, HAO J, HALL J.A reinforcement learning based blade twist angle distribution searching method for optimizing wind turbine energy power[J]. Energy, 215: 119148.
[2] 高峰. 风力发电机组的运行维护分析[J]. 电子技术, 2022, 51(1): 230-231.
GAO F.Operation and maintenance analysis of wind turbine units[J]. Electronic technology, 2022, 51(1): 230-231.
[3] 胡燕平, 戴巨川, 刘德顺. 大型风力机叶片研究现状与发展趋势[J]. 机械工程学报, 2013, 49(20): 140-151.
HU Y P, DAI J C, LIU D S.Research status and development trend of large wind turbine blades[J]. Journal of mechanical engineering, 2013, 49(20): 140-151.
[4] 张越. 风力发电机叶片表面损伤图像识别方法研究[D]. 昆明: 昆明理工大学, 2019.
ZHANG Y.Study on image recognition of wind turbine blade[D]. Kunming: Kunming University of Science and Technology, 2019.
[5] GUAN B L, SU Z L, YU Q F.Monitoring the blades of a wind turbine by using videogrammetry[J]. Optics and lasers in engineering, 2022, 152: 106901.
[6] 周勃, 陈长征, 赵新光, 等. 风力机叶片蒙皮初始裂纹的盲信号提取[J]. 仪器仪表学报, 2012, 33(7): 1483-1489.
ZHOU B,CHEN C Z,ZHAO X G,et al.Blind signalextraction of skin initial crack in wind turbine blade[J]. Chinese journal of scientific instrument, 2012,33(7):1483-1489.
[7] 豆红尧, 周华飞, 秦良忠, 等. 风电叶片全场三维变形测试及分析[J]. 太阳能学报, 2015, 36(9): 2257-2262.
DOU H Y, ZHOU H F, QING L Z,et al.Test andanalysis of full-field 3D deformation for a wind turbineblade[J]. Acta energiae solaris sinica, 2015, 36(9): 2257-2262.
[8] 刘双, 胡斌, 贺铸. 风机叶片缺陷的无损检测方法比较与评价[J]. 无损检测, 2015, 37(3): 47-51.
LIU S, HU B, HE Z.Comparison and evaluation of nondestructive detection methods for fan leaf defects[J]. Nondestructive testing, 2015,37(3): 47-51.
[9] 付德义, 薛扬, 秦世耀. MW级风力发电机组载荷测试方法研究[J]. 可再生能源, 2013, 31(3): 65-68.
FU D Y,XUE Y,QIN S Y.Research on load testing methods for MW-class wind turbines[J]. Renewable Energy Resources, 2013, 31(3): 65-68.
[10] 邓勇, 钟铭, 刘乐, 等. 风力机叶片及翼型变形分析[J]. 可再生能源, 2017, 35(5): 765-770.
DENG Y, ZHONG M, LIU L, et al.Analysis of wind turbine blade and wing type deformation[J]. Renewable energy resources, 2017, 35(5): 765-770.
[11] 张子雨. 发电设备变工况自适应故障预警方法研究[D]. 北京: 华北电力大学, 2021.
ZHANG Z Y.Research on adaptive fault warning method in variable working condition of power generation equipment[D]. Beijing: North China Electric Power University, 2021.
[12] 泮永朋. 单幅图像去雾算法研究[D]. 济南: 山东大学, 2012.
PAN Y P.Foogging algorithm of single image[D]. Ji'nan: Shandong University, 2012.
[13] HE K M.Single image based on the dark channel prior[J]. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(12): 2341-2351.
[14] 黄鑫祥, 郭小锋, 齐剑峰. 风力机叶片动态气弹变形及其对整机性能的影响[J]. 可再生能源, 2020, 38(7): 916-921.
HUANG X X, GUO X F, QI J F.Dynamic air elastic deformation of the wind turbine blade and its influence on the performance of the whole machine[J]. Renewable energy resources, 2020, 38(7): 916-921.
PDF(1804 KB)
