Advances in Constructional Engineering
Advances in Constructional Engineering. 2025; 5: (4) ; 10.12208/j.ace.2025000146 .
总浏览量: 118
杭州英大智信科技有限公司 浙江杭州
*通讯作者： 赵馨,单位：杭州英大智信科技有限公司 浙江杭州；
针对智能建筑弱电井设备检测难度大、缺陷识别效率低的问题，本文提出了一种基于改进YOLOv7的缺陷检测方法。通过引入注意力机制和多尺度特征融合技术，提升模型对弱电井设备细节的捕捉能力，实现高精度、实时的缺陷识别。实验结果表明，该方法在检测准确率和速度上均优于传统算法，具备良好的工程应用价值。
To address the challenges of high detection difficulty and low defect recognition efficiency in intelligent building weak current shaft equipment, this paper proposes a defect detection method based on an improved YOLOv7. By introducing attention mechanisms and multi-scale feature fusion techniques, the model's ability to capture fine details of weak current shaft equipment is enhanced, achieving high-precision and real-time defect identification. Experimental results demonstrate that this method outperforms traditional algorithms in both detection accuracy and speed, showing strong practical engineering value.
[1] 王建.公共建筑弱电井火灾危险分析与预防措施[J].中国应急救援,2015,(01):31-34.
[2] 王建.公共建筑弱电井火灾危险分析与预防措施[J].中国应急救援,2015,(01):31-34.
[3] 贾世杰,殷永浩,田丹云,等.基于YOLOv7-tiny改进的铁轨表面损伤检测算法[J].大连交通大学学报,2025,46(03): 107-113.
[4] 柏扬.基于改进YOLOv7的煤矿井下运输系统异物在线检测方法设计[J].自动化应用,2025,66(11):105-108.
[5] 吴铁钰.基于改进YOLO算法的道路缺陷识别研究[D].大连交通大学,2025.
[6] 张文广,曾祥玖,刘重阳.基于改进YOLOv7的电力调度控制系统图元识别方法研究[J].电气技术,2025,26(05):1-9.
[7] 朱贵威.基于改进YOLOv7的带钢缺陷检测算法研究[D].大连交通大学,2025.
[8] 郭晓阳.基于YOLOv7的火焰目标检测的改进与应用[D].大连交通大学,2025.