【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。更多还原

【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.更多还原