Anti-vibration hammer defect detection based on structural knowledge representation

Zhenbing Zhao, Guangxue Guo, Yitian Pan, Ke Zhang, Yongjie Zhai, Wenqing Zhao

Abstract: Anti-vibration hammer defects pose a significant risk to the safe operation of power transmission lines. Addressing the issues posed by the various manifestations of identical category defects and the similarities among different defects, this paper introduces a defect detection algorithm for anti-vibration hammers based on structural knowledge representation. Initially, a Structural Knowledge Enhancement (StKE) Module is proposed to conduct a statistical analysis of the aspect ratios of different defects in anti-vibration hammers, effectively extracting the structural features of the anti-vibration hammers and their corresponding defects. Subsequently, a Structural Knowledge Representation (StKR) Module is introduced, which bolsters the model’s ability to precisely locate defects that disrupt structural symmetry. The model incorporates the Coordinate Attention (CA) mechanism to acquire contextual information, thereby enhancing detection accuracy. Experimental results demonstrate that the improved model achieves a 6.1% increase in mean detection precision over the baseline model, and a notable improvement in detection accuracy compared to other advanced algorithms.

External IDs:dblp:journals/eaai/ZhaoGPZZZ25