P&amp;IDSeg-Net：A Lightweight P&amp;ID Segmentation Network

WANG Chenxi; YANG Tingting; ZHANG Tao; ZOU Yuchen; SHAO Huikai; ZHONG Dexing

doi:10.7652/xjtuxb202605022

您当前的位置：

首页 >

文章列表页 >

P&IDSeg-Net：A Lightweight P&ID Segmentation Network

更新时间：2026-04-27

- P&IDSeg-Net：A Lightweight P&ID Segmentation Network
- Journal of Xi'an Jiaotong University Vol. 60, Issue 5, Pages: 226-236(2026)
- 作者机构：
  
  西安交通大学自动化科学与工程学院，710049，西安
  中国广核集团有限公司科技数字化部，518000，广东深圳
  中广核智能科技（深圳）有限责任公司，518000，广东深圳
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202605022
  CLC： TP39
- Received：25 June 2025，
  
  Published：10 May 2026
- 稿件说明：
移动端阅览
WANG Chenxi, YANG Tingting, ZHANG Tao, et al. P&IDSeg-Net：A Lightweight P&ID Segmentation Network[J]. Journal of Xi'an Jiaotong University, 2026, 60(5): 226-236.
DOI：

WANG Chenxi, YANG Tingting, ZHANG Tao, et al. P&IDSeg-Net：A Lightweight P&ID Segmentation Network[J]. Journal of Xi'an Jiaotong University, 2026, 60(5): 226-236. DOI： 10.7652/xjtuxb202605022.

摘要

为了提高管道和仪器图（P

ID）智能分割的性能，提出了一种用于图纸分割的轻量化网络P

IDSeg-Net。首先，设计了通道减半的非局部注意力模块，在深层特征空间建立全局依赖，解决了图纸中管道与仪器的结构混淆问题；其次，用特征加法融合代替通道拼接进行跳跃连接，进一步减少参数量，适应小规模数据集；然后，基于P

ID中管道区域的低灰度特性，构建了视觉提示词启发的灰度掩膜加权损失，使网络聚焦前景关键区域；最后，收集和手工标注了P

ID_Pipe数据集，并在该数据集上进行了大量的实验。结果表明：所提出的P

IDSeg-Net网络仅需2.181×10

的参数量，轻量化优势突出，同时平均交并比达到77.40%，相比于主流的分割方法，能够获得更优的性能。

Abstract

To enhance the performance of intelligent segmentation for piping and instrumentation diagrams (P

IDs)

a lightweight segmentation network named P

IDSeg-Net is proposed. First

a channel-halved non-local attention module was designed to establish global dependencies in deep feature space

addressing the structural confusion between pipelines and instruments. Second

feature addition fusion was employed instead of channel concatenation for skip connections

further reducing the parameter count and adapting to small-scale datasets. Then

based on the lowgrayness characteristic of pipeline regions in P

IDs

a visual prompt-inspired grayscale mask weighted loss was constructed to focus the network on key foreground areas. Finally

the P

ID_Pipe dataset was collected and manually a

nnotated

and extensive experiments were conducted on this dataset. The results show that the proposed P

IDSeg-Net requires only 2.181×10

parameters

demonstrating significant lightweight advantages

while achieving a mean intersection over union of 77.40%. Compared with mainstream segmentation methods

it achieves superior performance.

关键词

Keywords

references

ISHII M，ITO Y，YAMAMOTO M，et al.An automatic recognition system for piping and instrument diagrams [J].Systemsand Computersin Japan，1989，20（3）：32-46.

ELYAN E，GARCIA C M，JAYNE C.Symbols classification in engineering drawings [C]//2018 International Joint Conference on Neural Networks（IJCNN）. Piscataway，NJ，USA：IEEE，2018：1-8.

KUCHUGANOV V N，KUCHUGANOV A V，KASIMOV D R.Clustering algorithm for a set of machine parts on the basis of engineering drawings [J].Programming and Computer Software，2020，46（1）：25-34.

MORENO-GARCÍA C F，ELYAN E，JAYNE C.New trends on digitisation of complex engineering drawings [J]. Neural Computing and Applications，2019，31（6）：1695-1712.

范家斌，王宝会，陈继轩.基于文本-图像多模态融合的变电所布局图纸图符检测方法[J/OL].计算机科学.（2025-05-15）[2025-06-01].https：//link.cnki. net/urlid/50.1075.tp.20250514.1843.016.

FAN Jiabin，WANG Baohui，CHEN Jixuan.Method for symbol detection in substation layout diagrams based on text-image multimodal fusion[J/OL].Computer Science.（2025-05-15）[2025-06-01].https：//link. cnki.net/urlid/50.1075.tp.20250514.1843.016.

章喻龙，罗壮强，石凌峰.基于YOLOX算法的工程图纸标题栏识别[J].数字技术与应用，2024，42（3）：198-202.

ZHANG Yulong，LUO Zhuangqiang，SHI Lingfeng.外文标题[J].Digital Technology and Application，2024，42（3）：198-202.

侯凯，梅诗妍.基于特征提取和模板匹配的电网工程图纸字符识别技术[J].沈阳工业大学学报，2025，47（2）：176-182.

HOU Kai，MEI Shiyan.Character recognition technology of power engineering drawings based on feature extraction and template matching[J].Journal of Shenyang University of Technology，2025，47（2）：176-182.

RICA E，ÁLVAREZ S，SERRATOSA F.Group of components detection in engineering drawings based on graph matching [J].Engineering Applications of Artificial Intelligence，2021，104：104404.

XIE Liuyue，LU Yao FURUHATA T，et al.Graph neural network-enabled manufacturing method classification from engineering drawings [J].Computers in Industry，2022，142：103697.

汪伟.基于人工智能的机械图纸图像切割技术的研究[J].精密制造与自动化，2025（1）：23-27.

WANG Wei.Research on mechanical drawing image segmentation technology based on artificial intelligence[J]. Precise Manufacturing & Automation，2025（1）：23-27.

ZHANG Wentai，JOSEPH J，YIN Yue，et al.Component segmentation of engineering drawings using Graph Convolutional Networks [J].Computers in Industry，2023，147：103885.

OTSU N.A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems，Man and Cybernetics，1979，9（1）：62-66.

HOJJATOLESLAMI S A，KITTLER J. Region growing：a new approach [J].IEEE Transactions on Image Processing，1998，7（7）：1079-1084.

LONG J，SHELHAMER E，DARRELL T. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Piscataway，NJ，USA：IEEE，2015：3431-3440.

NO H H，HONG S，HAN B.Learning deconvolution network for semantic segmentation [C]//2015 IEEE International Conference on Computer Vision（ICCV）. Piscataway，NJ，USA：IEEE，2015：1520-1528.

RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation [C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.Cham，Switzerland： Springer International Publishing，2015：234-241.

CHEN L C，PAPANDREOU G，KOKKINOS I，et al.DeepLab：semantic image segmentation with deep convolutional Nets，atrous convolution，and fully connected CRFs [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40（4）：834-848.

ZHAO Hengshuang，SHI Jianping，QI Xiaojuan，et al.Pyramid scene parsing network [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Piscataway，NJ，USA：IEEE，2017：6230-6239.

LIU Ze，LIN Yutong，CAO Yue，et al.Swin transformer：hierarchical vision transformer using shifted windows [C]//2021 IEEE/CVF International Conference on Computer Vision（ICCV）.Piscataway，NJ，USA：IEEE，2021 ：9992-10002.

XIE Enze，WANG Wenhai，YU Zhiding，et al.Seg-Former：simple and efficient design for semantic segmentation with transformers [C]//Proceedings of the 35th International Conference on Neural Information Processing Systems.Red Hook，NY，USA：Curran Associates Inc.，2021：12077-12090.

KIRILLOV A，MINTUN E，RAVI N，et al.Segment anything [C]//2023 IEEE/CVF International Conference on Computer Vision（ICCV）.Piscataway，NJ，USA：IEEE，2023：3992-4003.

RAVI N，GABEUR V，HU Y T，et al.SAM 2：segment anything in images and videos [EB/OL].（2024-10-28）[2025-06-25].https：//arxiv.org/abs/2408.00714.

CHEN Tianrun，ZHU Lanyun，DING Chaotao，et al. SAM-adapter：adapting segment anything in underperformed scenes [C]//2023 IEEE/CVF International Conference on Computer Vision Workshops（ICCVW）. Piscataway，NJ，USA：IEEE，2023：3359-3367.

WANG Xiaolong，GIRSHICK R，GUPTA A，et al. Non-local neural networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway，NJ，USA：IEEE，2018：7794-7803.

JIA Menglin，TANG Luming，CHEN B C，et al.Visual prompt tuning [C]//Computer Vision-ECCV 2022.Cham，Switzerland：Springer Nature Switzerland，2022：709-727.

MEI Jie，LI Roujing，GAO Wang，et al.CoANet：connectivity attention network for road extraction from satellite imagery [J]. IEEE Transactions on Image Processing，2021，30：8540-8552.

CHEN Jieneng，LU Yongyi，YU Qihang，et al.TransUNet：transformers make strong encoders for medical image segmentation [C]//2021 Interpretable Machine Learning in Healthcare.San Diego，CA，USA：ICML，2021 ：1-13.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

P&IDSeg-Net: A Lightweight P&ID Segmentation Network

Influence of Structural Parameters on the Summer Operational Characteristics of a Three-Tower-in-One Indirect Air-Cooling System

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

Related Author

WANG Chenxi

ZHANG Tao

ZOU Yuchen

SHAO Huikai

ZHONG Dexing

Related Institution

School of Automation Science and Engineering, Xi’an Jiaotong University

CGN Intelligent Technology (Shenzhen) Co., Ltd

⁰

P&IDSeg-Net：A Lightweight P&ID Segmentation Network

DOI：10.7652/xjtuxb202605022

摘要

Abstract

关键词

Keywords

references