Unified automatic extraction method for pipeline geometric features based on point cloud data and its application

doi:10.11996/JG.j.2095-302X.2026040812

Abstract

Abstract:

To address the issue that upstream design data formats in the manufacturing process of pipeline products are inconsistent, making it difficult to efficiently extract key geometric features for precise processing and assembly, a method was proposed that converted pipeline models in different formats into point-cloud data and then uniformly extracted key geometric features. First, design models in various formats were converted into point clouds to unify the data with physically scanned models. Second, a method based on boundary extraction and point-cloud segmentation was designed to obtain the boundary-circle features in the model, and the center point coordinates and radius parameters were optimized. Finally, the threshold parameters in the subsequent point-cloud processing algorithm were adaptively adjusted according to the size of the boundary circle. The pipeline model skeleton was extracted through region growing and local median iteration, and the optimization was completed in combination with cylindrical segmentation to output the axis feature parameters. Experimental results showed that compared with common skeleton-generation and geometric-segmentation algorithms, the proposed feature-extraction scheme had a wider range of applications and relatively higher accuracy. It could extract complete key geometric features from both pipeline design models with multiple branches and low-quality point-cloud models, meeting the precision requirements for calculating tooling-control commands in aviation pipeline pre-welding assembly.

Key words: pipeline assembly, point cloud, data format conversion, feature extraction, axis generation

CLC Number:

TP391

ZHANG Zhibo, ZHENG Lianyu. Unified automatic extraction method for pipeline geometric features based on point cloud data and its application[J]. Journal of Graphics, 2026, 47(4): 812-819.

Figures/Tables 16

Fig. 1 Unified feature extraction process for pipeline models

Fig. 2 CAD model data conversion process ((a) CATIA design model; (b) STL model; (c) Sampled point cloud; (d) Filtered point cloud)

Fig. 3 Boundary circle extraction process

Fig. 4 Boundary circle extraction results (1-4: Converted from design models; 5-8: Scanned models)

Fig. 5 Axis points generated by ordinary L1 median method and interpolated axis

Fig. 6 Region growing segmentation results and main axis of pipeline model

Fig. 7 Pipeline axis completed by part-aware

Fig. 8 Cylindrical point cloud segmented by RANSAC

Fig. 9 Axis extraction results of cylindrical segments by improved cylinder segmentation method

Fig. 10 Axis extraction process of pipeline

Fig. 11 Axis extraction results of different pipeline models

Fig. 12 Axis extraction results of special pipeline models

Fig. 13 Boundary circle feature parameter errors ((a) Distance error; (b) Angular error)

Table 1 Points of axis distance errors/mm

序号	提取算法	平均误差	极误差值	均方根误差
1	圆柱分割插补	3.158	24.133/0.638	4.571
1	L1中值骨架	4.955	19.330/1.104	4.620
1	改进方法	3.412	7.196/0.147	2.247
3	圆柱分割插补	3.110	10.128/0.586	2.015
3	L1中值骨架	4.350	8.926/1.261	2.374
3	改进方法	3.002	6.931/0.654	1.962

Fig. 14 Simulation verification and field application

Table 2 Simulation positioning error

管路序号	支撑位置	距离误差/mm	角度误差/(°)
1	管接头1	1.902	0
1	管接头2	0.698	0.513
1	管接头3	0.411	0.412
1	直管段1中心	1.214	0.725
1	直管段2中心	1.627	0.818
3	管接头1	1.154	0.106
3	管接头2	0.800	0.073
3	直管段1中心	1.541	0.701
3	直管段2中心	1.711	0.418

References 22

[1]	LIU S L, LIU J H, JIN P, et al. Tube measurement based on stereo-vision: a review[J]. The International Journal of Advanced Manufacturing Technology, 2017, 92(5): 2017-2032. DOI URL
[2]	夏芝玮, 钱进, 陈果. 带装配偏差下的飞机管路连接件密封性能分析[J]. 中国工程机械学报, 2024, 22(3): 341-345.
	XIA Z W, QIAN J, CHEN G. Sealing performance analysis of aircraft pipe connectors with assembly deviation[J]. Chinese Journal of Construction Machinery, 2024, 22(3): 341-345 (in Chinese).
[3]	李光俊, 兰勇, 孙林, 等. 柔性组合夹具在飞机导管数字化快速制造中的应用[J]. 航空制造技术, 2012(9): 58-61.
	LI G J, LAN Y, SUN L, et al. Application of flexible combine-clamp in digital rapid production for aircraft tube[J]. Aeronautical Manufacturing Technology, 2012(9): 58-61 (in Chinese).
[4]	SUN H T, NIU W T, NIU Y X, et al. Pipe-assembly approach for ships using modified NSGA-Ⅱ algorithm[J]. Computer Aided Drafting, Design and Manufacturing, 2016, 26(2): 34-42.
[5]	王超凡. 基于MBD的航空发动机管路设计系统研究与开发[J]. 航空制造技术, 2025, 68(7): 117-123.
	WANG C F. Research and development of MBD based aero-engine pipeline design system[J]. Aeronautical Manufacturing Technology, 2025, 68(7): 117-123 (in Chinese).
[6]	张德乾, 徐锋, 杨龙, 等. 基于MBD的管路三维工艺设计技术研究[J]. 数字制造科学, 2024, 22(3): 183-187.
	ZHANG D Q, XU F, YANG L, et al. Study on three-dimensional process design technology of pipeline based on MBD[J]. Digital Manufacture Science, 2024, 22(3): 183-187 (in Chinese).
[7]	ZHENG L, JI A H, CHENG Y, et al. Design and development of automatic pipe cutting and welding robot for fusion reactor[J]. Fusion Engineering and Design, 2024, 205: 114555. DOI URL
[8]	樊伟, 郑联语, 王亚辉, 等. 管路组件可重构装配工装系统的定位器自动配置与性能分析[J]. 航空学报, 2018, 39(5):248-261.
	FAN W, ZHENG L Y, WANG Y H, et al. Automatic configuration and performance analysis of locators for reconfigurable assembly fixture system of pipeline components[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(5):248-261 (in Chinese).
[9]	李尚强. 基于管网特性的飞机总装管路装配工序规划研究[C]// 第六届中国航空科学技术大会论文集. 北京: 北京航空航天大学出版社, 2023: 1112-1117.
	LI S Q. Research on assembly process planning of aircraft assembly pipeline based on pipe network characteristics[C]// Proceedings of the 6th China Aviation Science and Technology Conference. Beijing: Beihang University Press, 2023: 1112-1117 (in Chinese).
[10]	徐中平, 王海宽, 李徐辉, 等. 基于图割的多相机管路三维重建测量[J]. 自动化与仪表, 2023, 38(12): 43-47.
	XU Z P, WANG H K, LI X H, et al. Graph cut based 3D reconstruction and measurement of tube using multi-camera[J]. Automation & Instrumentation, 2023, 38(12): 43-47 (in Chinese).
[11]	张天, 刘少丽, 唐承统, 等. 基于形状特征的管路接头测量和三维重建方法[J]. 计算机集成制造系统, 2015, 21(1): 123-134.
	ZHANG T, LIU S L, TANG C T, et al. Measurement and 3D reconstruction method for pipeline’s joints based on shape features[J]. Computer Integrated Manufacturing Systems, 2015, 21(1): 123-134 (in Chinese).
[12]	施腾芮. 基于双目视觉的管路数字化测量研究及实现[D]. 南京: 南京大学, 2020.
	SHI T R. Research and realization of pipeline digital measurement based on binocular vision[D]. Nanjing: Nanjing University, 2020 (in Chinese).
[13]	冯彦淏, 邓志杰, 刘维, 等. 基于改进PointNet++的船舶管路重建方法[J]. 机械设计与研究, 2025, 41(5): 86-92.
	FENG Y H, DENG Z J, LIU W, et al. A Ship pipeline reconstruction method based on improved PointNet++[J]. Machine Design & Research, 2025, 41(5): 86-92 (in Chinese).
[14]	刘检华, 黄浩, 金鹏, 等. 基于自适应基元的导管测量方法[J]. 机械工程学报, 2021, 57(22): 71-79. DOI
	LIU J H, HUANG H, JIN P, et al. Tube measurement method based on adaptive primitives[J]. Journal of Mechanical Engineering, 2021, 57(22): 71-79 (in Chinese). DOI
[15]	ARAÚJO A M C, OLIVEIRA M M. Connectivity-based cylinder detection in unorganized point clouds[J]. Pattern Recognition, 2020, 100: 107161. DOI URL
[16]	LARI Z, HABIB A. An adaptive approach for the segmentation and extraction of planar and linear/cylindrical features from laser scanning data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93: 192-212. DOI URL
[17]	李恺洋, 王立忠, 常志文, 等. 基于自适应圆柱点云分割的弯管弯曲段测量方法[J]. 激光与光电子学进展, 2025, 62(4):107-117.
	LI K Y, WANG L Z, CHANG Z W, et al. Measurement method for tube bending sections based on adaptive cylindrical point cloud segmentation[J]. Laser & Optoelectronics Progress, 2025, 62(4):107-117 (in Chinese).
[18]	时坤伟, 谢晓尧, 刘嵩. 基于三维点云骨架的点云曲面分割[J]. 自动化应用, 2025, 66(2): 88-92, 95.
	SHI K W, XIE X Y, LIU S. Point cloud surface segmentation based on 3D point cloud skeleton[J]. Automation Application, 2025, 66(2): 88-92, 95 (in Chinese).
[19]	黄浩, 刘少丽, 刘检华, 等. 基于局部轮廓形状特征的复杂管路结构识别方法[J]. 计算机集成制造系统, 2019, 25(3): 598-606.
	HUANG H, LIU S L, LIU J H, et al. Recognition method for complex tube structures based on local shape feature[J]. Computer Integrated Manufacturing Systems, 2019, 25(3): 598-606 (in Chinese).
[20]	LI X J, LIU B, SHI Y G, et al. Efficient three-dimensional reconstruction and skeleton extraction for intelligent pruning of fruit trees[J]. Computers and Electronics in Agriculture, 2024, 227: 109554. DOI URL
[21]	关柏良, 周凡, 林淑金, 等. 面向三维模型分割的边界感知点云神经网络[J]. 计算机辅助设计与图形学学报, 2020, 32(1): 147-155.
	GUAN B L, ZHOU F, LIN S J, et al. Boundary-aware point based deep neural network for shape segmentation[J]. Journal of Computer-Aided Design & Computer Graphics, 2020, 32(1): 147-155 (in Chinese).
[22]	LI C H, ZHOU M Q, GENG G H, et al. EPCS: endpoint-based part-aware curve skeleton extraction for low-quality point clouds[J]. Computers & Graphics, 2023, 117: 209-221. DOI URL