陈攀, 尚保佑, 李天匀, 等. 面向船舶轴系智能安装的法兰激光扫描点云分割研究[J]. 中国舰船研究, 2023, 18(6): 268–274. doi: 10.19693/j.issn.1673-3185.03114
引用本文: 陈攀, 尚保佑, 李天匀, 等. 面向船舶轴系智能安装的法兰激光扫描点云分割研究[J]. 中国舰船研究, 2023, 18(6): 268–274. doi: 10.19693/j.issn.1673-3185.03114
CHEN P, SHANG B Y, LI T Y, et al. Point cloud segmentation of flange laser scanning for ship shafting intelligent installation[J]. Chinese Journal of Ship Research, 2023, 18(6): 268–274. doi: 10.19693/j.issn.1673-3185.03114
Citation: CHEN P, SHANG B Y, LI T Y, et al. Point cloud segmentation of flange laser scanning for ship shafting intelligent installation[J]. Chinese Journal of Ship Research, 2023, 18(6): 268–274. doi: 10.19693/j.issn.1673-3185.03114

面向船舶轴系智能安装的法兰激光扫描点云分割研究

Point cloud segmentation of flange laser scanning for ship shafting intelligent installation

  • 摘要:
    目的 激光扫描技术用于船舶轴系智能安装,具有非接触式、高速率扫描、高精度成像的优势,其中激光点云数据包含空间物体的大小、位置和方向信息。点云分割能大幅减小数据的计算规模,提高对接法兰相对位姿的测量效率。
    方法 采用深度学习理论研究点云分割,制作法兰类零件的点云数据集,利用PointNet模型进行训练,分别从Dropout正则化、学习率衰减和点云数据增强3个方面制定优化策略,并在船舶轴系智能安装台架上进行实验验证。
    结果 模型的收敛结果趋于稳定,其中训练集的准确率为0.88,验证集的准确率为0.65,法兰点云分割实验呈现清晰的轮廓边缘。
    结论 表明该方法具有良好的收敛性能和泛化性能,提高了轴系智能安装的效率。

     

    Abstract:
    Objectives Laser scanning technology used in the intelligent installation of ship shafting has such advantages as non-contact, high-speed scanning and high-precision imaging. The laser point cloud data includes the size, position and direction information of space objects. Point cloud segmentation can greatly reduce the calculation scale of the data and improve the measurement efficiency of the relative pose of the butt flange.
    Methods In this paper, deep learning theory is used to study point cloud segmentation and obtain a point cloud dataset of flange parts. The PointNet model is used for training. Optimization strategies are formulated in three aspects, namely dropout regularization, learning rate attenuation and point cloud data enhancement, then tested on a ship shafting intelligent installation platform.
    Results The convergence results of the model tend to be stable, with the accuracy of the training set reaching 0.88 and that of the verification set reaching 0.65. The flange point cloud segmentation experiment shows clear contour edges.
    Conclusion The results of this study show that the proposed method has good convergence and generalization performance, and can improve the efficiency of ship shafting intelligent installation.

     

/

返回文章
返回