电子测量与仪器学报

邓有为,李刚,辛怡,张生鹏,郝翊杰.隧道围岩沉降自适应实时识别及测量[J].电子测量与仪器学报,2023,37(2):236-243

隧道围岩沉降自适应实时识别及测量

Adaptive real-time recognition and measurement of tunnel rock settlement

DOI：

英文关键词:tunnel rock settlement monitoring object detection attention mechanism

基金项目:广西重点研发计划(桂科 AB20159032)、陕西省重点研发计划项目(2020ZDLGY09-03)、广西新恒通高速公路有限公司技术合作项目(XHT-KXB-2021-006)资助

作者	单位
邓有为	1. 长安大学电子与控制工程学院
李刚	2. 长安大学能源与电气工程学院
辛怡	1. 长安大学电子与控制工程学院
张生鹏	1. 长安大学电子与控制工程学院
郝翊杰	1. 长安大学电子与控制工程学院

Author	Institution
Deng Youwei	1. School of Electronic and Control Engineering, Chang′an University
Li Gang	2. School of Energy and Electrical Engineering, Chang′an University
Xin Yi	1. School of Electronic and Control Engineering, Chang′an University
Zhang Shengpeng	1. School of Electronic and Control Engineering, Chang′an University
Hao Yijie	1. School of Electronic and Control Engineering, Chang′an University

摘要点击次数: 678

全文下载次数: 610

中文摘要:

针对传统隧道围岩沉降监测方法鲁棒性较差、难以及时有效的监测隧道围岩沉降值的问题,提出将坐标注意力结合目标检测算法的隧道围岩沉降自适应识别测量算法。利用工业相机拍摄不同环境靶标图像建立数据集,训练具有坐标注意力的目标检测模型,在测试集中验证模型预测精度为 97. 9%。使用图像中靶标的数字以及 LED 灯点的像素坐标标定测量算法模型并计算沉降值。结果表明在 25 m 范围内测量误差小于 1 cm,在 10 m 范围内的靶标测量误差小于 5 mm。

英文摘要:

Aiming at the problems of poor robustness and are difficult to monitor the settlement value of tunnel timely and effectively. An adaptive recognition and measurement algorithm of tunnel settlement is proposed by combining coordinate attention with object detection algorithm. Using industrial camera to get object images in different environment to build datasets, then training object detection model with coordinate attention, prediction accuracy of the model is 97. 9% in the test sets. Using the target figures and LED lights of the pixel coordinates in images to do the camera calibration and calculate settlement value. The results show that the measurement error of tunnel surrounding rocks is less than 1 centimeter within 25 meters, less than 5 millimeters within 10 meters.

查看全文查看/发表评论下载PDF阅读器