| 郭乙龙,陈春梅,朱宏伟,汪顶攀,李明俊,张婷.隧道超前钻探下的围岩裂隙检测算法[J].电子测量与仪器学报,2025,39(12):300-309 |
| 隧道超前钻探下的围岩裂隙检测算法 |
| Detection algorithm of surrounding rock defects under tunnel advance drilling |
| |
| DOI： |
| 中文关键词: 地质超前预报 围岩缺陷检测 YOLOv8n CSCM注意力机制 |
| 英文关键词:geological advance prediction surrounding rock defect detection YOLOv8n CSCM attention mechanism |
| 基金项目: |
|
|
| Author | Institution |
| Guo Yilong | 1.School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang 621010, China;
2.Robot Technology Used for Special Environment Key Laboratory of Sichuan Province, Mianyang 621010, China |
| Chen Chunmei | 1.School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang 621010, China;
2.Robot Technology Used for Special Environment Key Laboratory of Sichuan Province, Mianyang 621010, China |
| Zhu Hongwei | School of Environment and Resource, Southwest University of Science and Technology, Mianyang 621010, China |
| Wang Dingpan | Sichuan Zhentong Inspection Co. Ltd., Mianyang 621000, China |
| Li Mingjun | Sichuan Zhentong Inspection Co. Ltd., Mianyang 621000, China |
| Zhang Ting | 1.School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang 621010, China;
2.Robot Technology Used for Special Environment Key Laboratory of Sichuan Province, Mianyang 621010, China |
|
| 摘要点击次数: 465 |
| 全文下载次数: 404 |
| 中文摘要: |
| 在隧道钻探地质超前预报中，为了更好地指导隧道掘进作业，需对钻探岩层内壁上存在的缺陷、裂隙和渗漏情况进行检测。在真实工程环境中采集了超前钻探岩层内壁图像，通过针对性处理，形成了钻孔内壁缺陷数据集，并提出一种基于YOLOv8n的孔洞内壁缺陷检测模型。首先，提出一种融合坐标注意力机制的坐标通道 空间卷积模块(CSCM)，通过建立通道维度与空间坐标的交互关系，以增强模型特征提取能力；其次，设计快速空间金字塔池化卷积模块，以提升网络浅层特征与深层特征融合传递的能力；最后，引入幻影卷积算子改进C2f模块，采用残差连接结构提升多尺度特征提取的效果，以进一步提高模型检测性能，并实现模型轻量化。验证结果表明，相比于原始的YOLOv8n模型，改进后的算法在自制钻孔数据集中的检测精度提升了5.5%，而计算负载降低了0.1 GFLOPs，相较于YOLOv11、RT-DETR等主流检测模型，平均检测精度提升了7%。改进后算法有效提升了检测精度，实现了实时高效超前预报，展现出良好的工程应用前景。 |
| 英文摘要: |
| In tunnel advance drilling for geological forecasting, the detection of defects, cracks, and seepage within borehole walls is crucial to guide safe and efficient tunneling operations. This study addresses this challenge by constructing a borehole wall defect dataset from real-world drilling images and proposing an optimized YOLOv8n-based detection model. The technical advancements are threefold:Firstly, coordinate channel-spatial convolutional module with attention mechanism:A novel module integrating coordinate attention is designed to enhance feature extraction by establishing interdependencies between channel dimensions and spatial coordinates. Secondly, rapid spatial pyramid pooling convolutional module:A lightweight hierarchical architecture is developed to improve the fusion and transmission of shallow and deep network features. Lastly, ghost convolution-enhanced C2f module:A residual-connected C2f structure incorporating ghost convolution operators is proposed to refine multi-scale feature extraction while achieving model lightweighting. Experimental results demonstrate that the proposed algorithm achieves a 5.5% improvement in mean average precision (mAP) over the baseline YOLOv8n model on the custom dataset, with a computational load reduction of 0.1 GFLOPs. Compared to state-of-the-art models such as YOLOv11 and RT-DETR, it exhibits a 7% superiority in average detection accuracy. The improved algorithm effectively enhances detection accuracy, enabling real-time, efficient, and advance forecasting, demonstrating promising prospects for engineering applications. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
