<strong>3D</strong>打印混凝土界面孔隙智能检测方法研究

doi:10.3785/j.issn.1006-754X.2025.04.109

工程设计学报

2025, Vol. 32

Issue (1): 11-22 DOI: 10.3785/j.issn.1006-754X.2025.04.109

机械设计理论与方法

3D打印混凝土界面孔隙智能检测方法研究

曾妮(

),马宗方(

),宋琳,段明

西安建筑科技大学信息与控制工程学院，陕西西安 710055

Research on intelligent detection method of 3D printed concrete interface pore

Ni ZENG(

),Zongfang MA(

),Lin SONG,Ming DUAN

College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China

全文: PDF(6320 KB) HTML

摘要：

目前，3D打印混凝土领域仍存在诸多问题，严重制约了其大规模工业化生产与应用。其中，孔隙为最常见缺陷，亟须发展相关检测技术，以提高混凝土的打印质量。针对现有3D打印混凝土界面孔隙检测方法主要依赖人的主观经验，且存在耗时长、成本高和计算资源耗费量大等缺陷，引入基于深度学习的目标检测算法，提出了一种轻量级的孔隙智能检测方法。首先，利用传统图像处理算法对3D打印混凝土界面孔隙图像进行预处理，并构建适用于目标检测算法的孔隙图像数据集；同时，基于所构建数据集的特点对锚框计算方法进行优化，以获取更适合界面孔隙目标的锚框，从而提升检测准确度。然后，在检测方法的主干网络中，利用ShuffleNetv2网络进行多尺度特征提取，并去掉部分网络以降低网络深度和减少计算参数量，从而提高孔隙检测效率。最后，在特征提取网络中融合极化自注意力机制模块，在保持高分辨率的同时增强对孔隙目标的关注度，以提高检测精度。实验结果表明，所提出的方法能够有效完成3D打印混凝土界面孔隙的智能化检测，通过与多种检测算法对比，发现该方法的多个性能指标均有所提升，检测效率提升显著。研究结果可为后续混凝土的质量控制和性能评估提供一定的数据支持。

关键词： 3D打印混凝土; 孔隙检测; ShuffleNetv2; 自注意力机制; 多尺度特征融合

Abstract:

At present, the 3D printed concrete field is still hampered by numerous issues that impede its large-scale industrial production and application. Among these, pores stand out as the most prevalent defect. Consequently, there is an urgent imperative to develop pertinent detection technologies for enhancing the printing quality of concrete. Aiming at the existing 3D printed concrete interface pore detection methods that mainly rely on subjective experience of individuals, and have disadvantages such as long-time consumption, high cost and large computational resource consumption, a lightweight intelligent pore detection method is proposed by introducing a deep learning-based object detection algorithm. Firstly, the traditional image processing algorithms were employed to preprocess the 3D printed concrete interface pore images, and the pore image dataset suitable for the target detection algorithm was constructed. At the same time, based on the characteristics of the constructed dataset, the anchor-box calculation method was optimized to acquire anchor boxes that were better suited to the interface pore targets, so as to improve the detection accuracy. Then, within the backbone network of the detection method, the ShuffleNetv2 network was utilized for multi-scale feature extraction, and part of the network was removed to reduce the network depth and the number of calculation parameters, thereby enhancing the pore detection efficiency. Finally, in order to improve detection precision, the polarized self-attention mechanism module was incorporated into the feature extraction network to enhance the attention to the pore target while maintaining high resolution. Experimental results demonstrated that the proposed method could effectively complete the intelligent detection of 3D printed concrete interface pores. Through comparing with various detection algorithms, it was found that multiple performance indicators of the method were improved, and the detection efficiency was significantly boosted. The research results can provide some data support for the subsequent quality control and performance evaluation of concrete.

Key words: 3D printed concrete pore detection ShuffleNetv2 self-attention mechanism multi-scale feature fusion

收稿日期: 2024-01-31 出版日期: 2025-03-04

CLC:

TP 391

基金资助: 国家自然科学基金面上项目(62276207)

通讯作者: 马宗方 E-mail: 1220863996@qq.com;zongfangma@xauat.edu.cn

作者简介: 曾　妮（2000—），女，硕士生，从事3D打印混凝土界面孔隙智能检测方法研究，E-mail: 1220863996@qq.com，https://orcid.org/0000-0001-5829-7052

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	曾妮
	马宗方
	宋琳
	段明

引用本文:

曾妮,马宗方,宋琳,段明. 3D打印混凝土界面孔隙智能检测方法研究[J]. 工程设计学报, 2025, 32(1): 11-22.

Ni ZENG,Zongfang MA,Lin SONG,Ming DUAN. Research on intelligent detection method of 3D printed concrete interface pore[J]. Chinese Journal of Engineering Design, 2025, 32(1): 11-22.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2025.04.109 或 https://www.zjujournals.com/gcsjxb/CN/Y2025/V32/I1/11

图1 3D打印混凝土界面孔隙检测方法的网络结构

图2 ShuffleNetv2网络结构

图3 不同尺寸的孔隙特征图

图4 PSA机制模块结构

图5 融合PSA机制模块前后的孔隙特征图对比

图6 多尺度特征融合检测的网络结构

图7 3D打印混凝土界面孔隙检测流程

图8 3D打印混凝土构件界面孔隙图像

表1 实验环境配置

表2 锚框优化的结果对比

图9 锚框优化前后的mAP对比

图10 锚框优化前后的孔隙检测结果对比

表3 融合不同注意力机制的结果对比

图11 融合不同注意力机制的mAP对比

图12 融合不同注意力机制的孔隙检测结果对比

表4 消融实验结果对比

图13 各组消融实验对应的孔隙检测结果对比

表5 综合对比实验结果

图14 不同算法的计算资源对比

1	张大旺，王栋民. 3D打印混凝土材料及混凝土建筑技术进展［J］. 硅酸盐通报， 2015， 34（6）： 1583-1588. ZHANG D W， WANG D M. Progress of 3D print of concrete materials and concrete construction technology［J］. Bulletin of the Chinese Ceramic Society， 2015， 34（6）： 1583-1588.
2	陈权要，周燕，周诚. 混凝土3D打印的机器视觉检测研究现状与展望［J］. 土木建筑工程信息技术， 2023， 15（5）： 1-8. CHEN Q Y， ZHOU Y， ZHOU C. The research status and prospect of machine vision inspection for 3D concrete printing［J］. Journal of Information Technology in Civil Engineering and Architecture， 2023， 15（5）： 1-8.
3	杨敏，来猛刚，窦艳宁，等. 混凝土3D打印质量影响因素及控制方法［J］. 混凝土与水泥制品， 2021（4）： 11-16. YANG M， LAI M G， DOU Y N， et al. Influencing factors and control measures of concrete 3D printing quality［J］. China Concrete and Cement Products， 2021（4）： 11-16.
4	刘化威，刘超，白国良，等. 基于孔结构缺陷的3D打印粗骨料混凝土力学性能试验研究［J］. 土木工程学报， 2022， 55（12）： 54-64. doi：10.1016/j.addma.2022.102843 LIU H W， LIU C， BAI G L， et al. Experimental study on mechanical properties of 3D printed coarse aggregate concrete based on the pore structure defects［J］. China Civil Engineering Journal， 2022， 55（12）： 54-64. doi: 10.1016/j.addma.2022.102843
5	王超，王川婴，王益腾，等. 基于孔壁光学图像的岩石孔隙结构识别与分析方法研究［J］. 岩石力学与工程学报， 2021， 40（9）： 1894-1901. WANG C， WANG C Y， WANG Y T， et al. Research on identification and analysis method of rock pore structure based on optical images of borehole walls［J］. Chinese Journal of Rock Mechanics and Engineering， 2021， 40（9）： 1894-1901.
6	马宗方，杨兴伟，宋琳，等. 基于层间信息熵的混凝土3D打印构件精细分割［J］. 激光与光电子学进展， 2022， 59（4）： 101-108. MA Z F， YANG X W， SONG L， et al. Fine segmentation of concrete 3D-printed elements based on information entropy between layers［J］. Laser & Optoelectronics Progress， 2022， 59（4）： 101-108.
7	陈雁，李祉呈，程超，等. FLU-net：用于表征页岩储层微观孔隙的深度全卷积网络［J］. 海洋地质前沿， 2021， 37（8）： 34-43. CHEN Y， LI Z C， CHENG C， et al. FLU-net： a deep fully convolutional neural network for shale reservoir micro-pore characterization［J］. Marine Geology Frontiers， 2021， 37（8）： 34-43.
8	REN Y P， HUANG J S， HONG Z Y， et al. Image-based concrete crack detection in tunnels using deep fully convolutional networks［J］. Construction and Building Materials， 2020， 234： 117367.
9	LIANG H， LEE S C， SEO S. UAV-based low altitude remote sensing for concrete bridge multi-category damage automatic detection system［J］. Drones， 2023， 7（6）： 386.
10	苗新法，刘宝莲，李晓琴，等. 改进YOLOv5s的铁轨裂纹目标检测算法［J］. 计算机工程与应用， 2024， 60（12）： 216-224. MIAO X F， LIU B L， LI X Q， et al. Improved YOLOv5s railway crack target detection algorithm［J］. Computer Engineering and Applications， 2024， 60（12）： 216-224.
11	ZHANG S H， YANG H K， YANG C H， et al. Edge device detection of tea leaves with one bud and two leaves based on ShuffleNetv2-YOLOv5-lite-E［J］. Agronomy， 2023， 13（2）： 577.
12	WANG X F， WU Z W， JIA M， et al. Lightweight SM-YOLOv5 tomato fruit detection algorithm for plant factory［J］. Sensors， 2023， 23（6）： 3336.
13	CAO M L， FU H， ZHU J Y， et al. Lightweight tea bud recognition network integrating GhostNet and YOLOv5［J］. Mathematical Biosciences and Engineering， 2022， 19（12）： 12897-12914.
14	ZHANG Y， SUN Y P， WANG Z， et al. YOLOv7-RAR for urban vehicle detection［J］. Sensors， 2023， 23（4）： 1801.
15	REN S Q， HE K M， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（6）： 1137-1149.
16	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： unified， real-time object detection［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas， NV， Jun. 27-30， 2016.
17	LIU W， ANGUELOV D， ERHAN D， et al. SSD： single shot MultiBox detector［M］//Lecture Notes in Computer Science. Cham： Springer， 2016： 21-37.
18	YAN J H， ZHOU Z， ZHOU D J， et al. Underwater object detection algorithm based on attention mechanism and cross-stage partial fast spatial pyramidal pooling［J］. Frontiers in Marine Science， 2022， 9： 1056300.
19	GAO G， LEE S H. Design and implementation of fire detection system using new model mixing［J］. International Journal of Advanced Culture Technology， 2021， 9（4）： 260-267.
20	JIANG K L， XIE T Y， YAN R， et al. An attention mechanism-improved YOLOv7 object detection algorithm for hemp duck count estimation［J］. Agriculture， 2022， 12（10）： 1659.
21	ZHENG J F， WU H， ZHANG H， et al. Insulator-defect detection algorithm based on improved YOLOv7［J］. Sensors， 2022， 22（22）： 8801.
22	TENG S， LIU Z C， LI X D. Improved YOLOv3-based bridge surface defect detection by combining high-and low-resolution feature images［J］. Buildings， 2022， 12（8）： 1225.
23	ZHANG Y X， HUANG J， CAI F H. On bridge surface crack detection based on an improved YOLOv3 algorithm［J］. IFAC-PapersOnLine， 2020， 53（2）： 8205-8210.
24	WU P R， LIU A R， FU J Y， et al. Autonomous surface crack identification of concrete structures based on an improved one-stage object detection algorithm［J］. Engineering Structures， 2022， 272： 114962.
25	MA N N， ZHANG X Y， ZHENG H T， et al. ShuffleNet V2： practical guidelines for efficient CNN architecture design［C］//European Conference on Computer Vision. Munich， Sep. 8-14， 2018.
26	LIU H J， LIU F Q， FAN X Y， et al. Polarized self-attention： towards high-quality pixel-wise regression［EB/OL］. （2021-07-08）［2024-01-20］. .
27	YANG R J， LI W F， SHANG X N， et al. KPE-YOLOv5： an improved small target detection algorithm based on YOLOv5［J］. Electronics， 2023， 12（4）： 817.
28	LIU S， QI L， QIN H F， et al. Path aggregation network for instance segmentation［C］//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， UT， Jun. 18-23， 2018.
29	WOO S， PARK J， LEE J Y， et al. CBAM： convolutional block attention module［C］//European Conference on Computer Vision. Munich， Sep. 8-14， 2018.
30	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， UT， Jun. 18-23， 2018.
31	HOU Q B， ZHOU D Q， FENG J S. Coordinate attention for efficient mobile network design［C］//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville， TN， Jun. 20-25， 2021.
32	LIU Y C， SHAO Z R， HOFFMANN N. Global attention mechanism： retain information to enhance channel-spatial interactions［EB/OL］. （2021-12-10）［2024-01-20］. .
33	HAN K， WANG Y H， TIAN Q， et al. GhostNet： more features from cheap operations［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， WA， Jun. 13-19， 2020.

[1]	金晶,王京,周奕辰,潘文明. 电力数据驱动的电池剩余寿命预测研究[J]. 工程设计学报, 2024, 31(6): 757-765.

Viewed

Full text

Abstract

Cited

Shared

Discussed