Damage Assessment of Transmission Tower Members Based on Image Recognition and Finite Element Analysis
-
摘要: 提出一种基于图像识别与有限元分析的输电塔杆件损伤评估方法,针对受损杆件,利用现场巡检获取的图像,结合边缘检测和线性拟合等步骤来定位杆件轮廓,对杆件的弯曲程度和状态进行定量评估,该方法在杆件交叉和节点板等复杂情况下也表现出较好的鲁棒性。针对未受损杆件,在有限元模型中设定损伤工况,构建了一种杆件重要性分析方法,可准确定位损伤杆件的牵连杆件位置。输电塔倒塌计算与失效路径分析表明,杆件的初始损伤会改变输电塔倒塌的失效路径,损伤杆件的牵连杆件存在提前失效的风险,进一步验证了杆件重要性分析方法的准确性。Abstract: A damage assessment method for transmission tower members based on image recognition and finite element analysis was proposed. For damaged members, based on the images obtained from on-site inspection, combined with edge detection and curve fitting to locate the member contour, the bending and state of members could be quantitatively assessed. This method showed good robustness in complex conditions such as members crossing and existence of gusset plates. For undamaged members, a member importance analysis method was proposed by setting the damage conditions in the finite element model, which could accurately locate the position of associated element. Transmission tower collapse calculation and failure path analysis showed that initial damage to the tower member would change the failure path of transmission tower collapse. The associated elements of damaged elements had the risk of early failure, which further verified the accuracy of the member importance analysis method.
-
Key words:
- transmission tower /
- image recognition /
- importance of member /
- damage assessment /
- failure path
-
[1] CERÓN A, MONDRAGÓN I, PRIETO F. Real-time transmission tower detection from video based on a feature descriptor[J]. IET Computer Vision, 2017, 11(1): 33-42. [2] 卞荣, 陈科技, 张柏岩, 等. 基于改进Canny算法的输电导线覆冰冰形视觉识别[J]. 高压电器, 2021, 57(11): 131-138. [3] HUANG M, ZHANG B, LOU W, et al. A deep learning augmented vision-based method for measuring dynamic displacements of structures in harsh environments[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2021, 217, 104758. [4] VEERAKUMAR R, HU H, TIAN L, et al. An experimental study of rime ice accretion on bundled conductors[J]. Experimental Thermal and Fluid Science, 2023, 147, 110962. [5] 桂常清. 基于集成卷积神经网络的钢结构锈蚀识别[D]. 天津:天津大学, 2019. [6] 逯鹏, 赵天淞, 王剑, 等.基于计算机视觉的钢结构表面损伤识别与健康监测综述[J]. 工业建筑, 2022, 52(10): 22-27. [7] 逯鹏, 赵天淞, 王剑, 等. 基于计算机视觉的钢结构表面锈蚀程度检测方法[J]. 工业建筑, 2024, 54(8):133-139. [8] 王雯瑶. 基于图像处理的输电线路故障诊断系统研究[D].北京: 华北电力大学, 2020. [9] 姚志东, 卢佳祁, 熊梦雅, 等. 基于计算机视觉的钢结构表面缺陷智能识别研究综述[J]. 建筑结构, 2023, 53(24): 126-135. [10] 蔡建国, 王蜂岚, 冯健, 等.新广州站索拱结构屋盖体系连续倒塌分析[J].建筑结构学报, 2010, 31(7):103-109. [11] 张雷明, 刘西拉. 框架结构能量流网络及其初步应用[J]. 土木工程学报, 2007, 40(3): 45-49. [12] 吴刚, 张晓辉, 李殿亮, 等. 特高压长悬臂输电塔鲁棒性分析[J]. 空间结构, 2023, 29(2): 80-87, 96. [13] 何启巧. 基于检测状态的输电杆塔结构随机分析与可靠性评估[D]. 重庆:重庆大学, 2022. [14] HE K, GKIOXARI G, DOLLlÁR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 2961-2969. [15] KIRILLOV A, MINTUN E, RAVI N, et al. Segment anything[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 4015-4026. [16] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986 (6): 679-698. [17] 中华人民共和国住房和城乡建设部. 钢结构设计标准: GB 50017—2017[S]. 北京: 中国建筑工业出版社, 2018. [18] LI Y, CHEN Y, SHEN G, et al. Member capacity-based progressive collapse analysis of transmission towers under wind load[J]. Wind and Structures, 2021, 33(4): 317-329. [19] 刘智健. 输电铁塔风致响应的在线监测与状态评估方法研究[D]. 广州:华南理工大学, 2020. [20] 国家能源局. 架空输电线路运行状态评估技术导则: DL/T 1249—2013[S]. 北京: 中国电力出版社, 2013. [21] 国家能源局. 架空输电线路荷载规范: DL/T 5551—2018[S]. 北京: 中国计划出版社, 2018. [22] 范存新, 葛义娇, 谢丽宇. 基于概率可靠度的输电塔风灾易损性分析[J]. 工业建筑, 2015, 45(7): 84-88, 94. [23] 胡鹏瑞. 长横担输电塔的等效静力风荷载及抗风承载力研究[D]. 杭州:浙江大学, 2023.
点击查看大图
计量
- 文章访问数: 52
- HTML全文浏览量: 6
- PDF下载量: 12
- 被引次数: 0