|本期目录/Table of Contents|

[1]王少洁,陈丽娟,吴青琳,等.基于机器视觉的混凝土人工振捣质量监测研究[J].建筑科学与工程学报,2026,(01):56-66.[doi:10.19815/j.jace.2025.04029]
　WANG Shaojie,CHEN Lijuan,WU Qinglin,et al.Research on monitoring construction quality of manually vibrated concrete based on machine vision[J].Journal of Architecture and Civil Engineering,2026,(01):56-66.[doi:10.19815/j.jace.2025.04029]
点击复制

基于机器视觉的混凝土人工振捣质量监测研究(PDF)
分享到：

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

卷:
期数:
2026年01期
页码:
56-66
栏目:
智能检测与建造技术专栏
出版日期:
2026-01-20

文章信息/Info

Title:
Research on monitoring construction quality of manually vibrated concrete based on machine vision
文章编号:
1673-2049(2026)01-0056-11
作者:
王少洁1,2，陈丽娟1,2，吴青琳1，史培新1,2，陈蕾1,2
1. 苏州大学 轨道交通学院，江苏 苏州 215000； 2. 江苏省智慧城轨工程研究中心，江苏 苏州 215000
Author(s):
WANG Shaojie, CHEN Lijuan, WU Qinglin, SHI Peixin, CHEN Lei
1. School of Rail Transportation, Soochow University, Suzhou 215000, Jiangsu, China;?
2. Intelligent Urban Rail Engineering Research Center of Jiangsu Province, Suzhou 215000, Jiangsu, China
关键词:
混凝土; 人工振捣质量; 电子旁站; 机器视觉; 行为识别
Keywords:
concrete;  manual vibration quality;  digital superintendent;  machine vision;  action recognition
分类号:
TU375；TP181
DOI:
10.19815/j.jace.2025.04029
文献标志码:
A
摘要:
针对混凝土人工振捣施工过程中质量判断高度依赖作业人员经验，且人工旁站监督存在局限性，无法实时监控风险等问题，提出一种基于机器视觉的混凝土人工振捣质量智能监测方法。首先，建立基于EfficientNet的混凝土表面状态自动识别方法，通过图像分类实现对不合格、中等与合格3类混凝土产品表面质量的精准判定；其次，提出基于STGCN++的工人振捣行为自动识别方法，通过骨骼关键点序列对振捣、移动振捣棒、休息3类工人行为进行动态识别与跟踪；最后，对混凝土表面状态与工人振捣行为的识别结果进行联动分析，集成2类自动识别模型输出结果，设计可视化监测接口，构建面向现场施工的电子旁站监测流程，满足振捣时间与表面状态的协同控制要求，实现混凝土振捣的产品质量与工作质量的同步识别与智能反馈。结果表明：振捣中混凝土表面状态自动识别方法的全局准确度为99.89%，工人振捣行为自动识别方法的全局准确度为96.93%；提出的方法可有效补充甚至部分替代人工旁站，实现智能化的动态质量监测，对施工过程中可能存在的欠振或漏振风险进行实时判断与提示；该研究在苏州某地铁车站项目进行现场应用，成果具有较好的工程应用价值。
Abstract:
Aiming at the problems that the quality judgment in the process of concrete manual vibration construction is highly dependent on the experience of operators, and the manual supervision has limitations and cannot monitor the risk in real time, an intelligent monitoring method of concrete manual vibration quality based on machine vision was proposed. First, a recognition model base on EfficientNet was developed to classify target concrete surface into “unqualified”, “medium”, and “qualified” categories with site images from live feed. Then, a STGCN++based pose recognition model was designed to dynamically identify and track 3 actions “vibrating”, “moving vibrator”, and “resting” by using skeleton key point sequences method. The outputs of the 2 models were incorporated for analysis and assessment on vibration time and surface state. A visual monitoring interface and workflow were presented for automatic simultaneous assessment and feedback of both product quality and workmanship quality. The results show that the global accuracy of the automatic identification method of concrete surface state in vibration is 99.89%, and the global accuracy of the automatic identification method of worker vibration behavior is 96.93%. The proposed method can effectively complement and even partially replace manual supervision, providing realtime detection and alerts for undervibration or missedvibration risks. The research has been applied in a metro station at Suzhou, and the results have good engineering application value.

参考文献/References:

［ 1 ］ WANG D, REN B Y, CUI B, et al. Real-time monitoring for vibration quality of fresh concrete using convolutional neural networks and IoT technology ［ J ］ . Automation in Construction, 2021, 123: 103510.

［ 2 ］ REN B Y, WANG H D, WANG D, et al. Vision method based on deep learning for detecting concrete vibration quality ［ J ］ . Case Studies in Construction Materials, 2023, 18: e02132.

［ 3 ］ LI T, WANG H, PAN D X, et al. A machine vision approach with temporal fusion strategy for concrete vibration quality monitoring ［ J ］ . Applied Soft Computing, 2024, 160: 111684.

［ 4 ］ 王 栋 , 关 涛 , 杨 帅 , 等 . 空天地一体化感知下的混凝土振捣质量智能监控［ J ］ . 硅酸盐学报 ,2023, 51(5) :1219-1227.

WANG Dong, GUAN Tao, YANG Shuai, et al. Intelligent monitoring of concrete vibration quality based on space-air-ground integrated perception ［ J ］ . Journal of the Chinese Ceramic Society, 2023, 51(5) : 1219-1227.

［ 5 ］ GONG J, YU Y, KRISHNAMOORTHY R, et al. Real-time tracking of concrete vibration effort for intelligent concrete consolidation ［ J ］ . Automation in Construction, 2015, 54: 12-24.

［ 6 ］ TIAN Z H, SUN X, SU W H, et al. Development of real-time visual monitoring system for vibration effects on fresh concrete ［ J ］ . Automation in Construction, 2019, 98: 61-71.

［ 7 ］ QUAN Y H, WANG F L. Machine learning-based real-time tracking for concrete vibration ［ J ］ . Automation in Construction, 2022, 140: 104343.

［ 8 ］ 田正宏 , 边 策 , 毛 龙 , 等 . 混凝土振捣动态可视化监测系统开发研究［ J ］ . 建筑材料学报 ,2013,16(3):508-513.

TIAN Zhenghong, BIAN Ce, MAO Long, et al. Development research on visual kinematic monitoring system of concrete vibrating process ［ J ］ . Journal of Building Materials, 2013, 16(3): 508-513.

［ 9 ］ TIAN Z H, BIAN C. Visual monitoring method on fresh concrete vibration ［ J ］ . KSCE Journal of Civil Engineering, 2014, 18(2): 398-408.

［ 10 ］刘亚洁 . 基于立体视觉的混凝土振捣质量监测系统的开发［ D ］ . 哈尔滨 : 哈尔滨工业大学 ,2018.

?LIU Yajie. Develop of concrete vibration monitoring system based on stereo vision ［ D ］ . Harbin: Harbin Institute of Technology, 2018.

［ 11 ］ LI J J, TIAN Z H, MA Y S, et al. Feedback control system for vibration construction of fresh concrete ［ J ］ . Mechanical Systems and Signal Processing, 2024, 216: 111461.

［ 12 ］LEE S G, SKIBNIEWSKI M J. Monitoring of concrete placement and vibration for real-time quality control ［ C ］ //CCC. Proceedings of the Creative Construction Conference 2019. Budapest: Budapest University of Technology and Economics, 2019: 67-76.

［ 13 ］ LEE S, SKIBNIEWSKI M J. Automated monitoring and warning solution for concrete placement and vibration workmanship quality issues ［ J ］ . AI in Civil Engineering, 2022, 1(1): 4.

［ 14 ］ 边 策 , 崔海涛 , 田正宏 , 等 . 基于受振能量密度的新拌混凝土密实性实时监控方法［ J ］ . 水电能源科学 ,2025,43(5):116-120.

BIAN Ce, CUI Haitao, TIAN Zhenghong, et al. Real-time monitoring method for compactness of fresh concrete based on vibration energy density ［ J ］ .Water Resources and Power, 2025, 43(5):116-120.

［ 15 ］ LI T, WANG H, TAN J S, et al. Intelligent quality assessment of concrete vibration using computer vision and large language models ［ J ］ . Automation in Construction, 2025, 180: 106507.

［ 16 ］ JIANG D Q, KONG L J, WANG H, et al. Precise control mode for concrete vibration time based on attention-enhanced machine vision ［ J ］ . Automation in Construction, 2024, 158: 105232.

［ 17 ］ 李梓巍 , 张少朋 , 牛远志 , 等 . 高铁预制箱梁混凝土振捣技术及智能化发展［ J ］ . 铁道科学与工程学报 ,2024,21(12):4851-4860.

LI Ziwei, ZHANG Shaopeng, NIU Yuanzhi, et al. Concrete vibrating technology and intelligent development of prefabricated box girders for high speed railway ［ J ］ . Journal of Railway Science and Engineering, 2024, 21(12): 4851-4860.

［ 18 ］ 姜林峰 , 田正宏 , 王开贵 , 等 . 基于电阻率法的混凝土振捣离析程度研究［ J ］ . 混凝土 ,2023(1):41-44.

JIANG Linfeng, TIAN Zhenghong, WANG Kaigui, et al. Estimating the segregation of concrete under vibration based on electrical method ［ J ］ . Concrete, 2023(1): 41-44.

［ 19 ］ FAN S, HE T, LI W H, et al. Machine learning-based classification of quality grades for concrete vibration behaviour ［ J ］ . Automation in Construction, 2024, 167: 105694.

［ 20 ］ 田正宏 , 马元山 , 李佳杰 . 混凝土振捣密实性研究进展［ J ］ . 建筑材料学报 ,2024,27(1):46-57.

TIAN Zhenghong, MA Yuanshan, LI Jiajie. Research progress on vibration compaction of concrete ［ J ］ . Journal of Building Materials, 2024, 27(1): 46-57.

［ 21 ］ 钟登华 , 沈子洋 , 王佳俊 , 等 . 基于实时监控的混凝土坝振捣施工质量动态评价研究［ J ］ . 水利学报 ,2018,49(7):775-786.

ZHONG Denghua, SHEN Ziyang, WANG Jiajun, et al . Study on dynamic evaluation of vibration quality of concrete dam based on real-time monitoring ［ J ］ .Journal of Hydraulic Engineering, 2018, 49(7): 775-786.

［ 22 ］ ZHAO X K, HUANG Y M, DONG W, et al. A review of compaction mechanisms, influencing factors,and advanced methods in concrete vibration technology ［ J ］ . Journal of Building Engineering, 2024, 93: 109847.

［ 23 ］ 王晓玲 , 王栋 , 任炳昱 , 等 . 高拱坝混凝土振捣机器人系统研发及应用［ J ］ . 水利学报 ,2022,53(6):631-643,654.

WANG Xiaoling, WANG Dong, REN Bingyu, et al. Development and application of concrete vibrating robot system for high arch dam ［ J ］ .Journal of Hydraulic Engineering, 2022, 53(6): 631-643, 654.

［ 24 ］ 混凝土结构工程施工规范 :GB 50666 — 2011 ［ S ］ . 北京 : 中国建筑工业出版社 ,2012.

Code for construction of concrete structures: GB 50666 — 2011 ［ S ］ . Beijing: China Architecture & Building Press, 2012.

［ 25 ］ 陈洛轩 , 林成创 , 郑招良 , 等 .Transformer 在计算机视觉场景下的研究综述［ J ］ . 计算机科学 ,2023,50(12):130-147.

CHEN Luoxuan, LIN Chengchuang, ZHENG Zhao-liang, et al. Review of transformer in computer vision ［ J ］ . Computer Science, 2023, 50(12): 130-147.

［ 26 ］ 张应军 , 江永全 , 杨 燕 , 等 . 基于深度卷积神经网络的未知复合故障诊断［ J ］ . 中国科技论文 ,2019, 14(2) :204-209.

ZHANG Yingjun, JIANG Yongquan, YANG Yan, et al. Unknown compound fault diagnosis based on deep convolutional neural network ［ J ］ . China Sciencepaper, 2019, 14(2): 204-209.

［ 27 ］ 杨 铄 , 许清风 , 王卓琳 . 基于卷积神经网络的结构损伤识别研究进展［ J ］ . 建筑科学与工程学报 ,2022, 39(4) :38-57.

YANG Shuo, XU Qingfeng, WANG Zhuolin. Research progress on structural damage detection based on convolutional neural networks ［ J ］ . Journal of Architecture and Civil Engineering, 2022, 39(4): 38-57.

［ 28 ］ TAN M X, LE Q V. EfficientNet: rethinking model scaling for convolutional neural networks ［ EB/OL ］ . (2019-05-28) ［ 2025-03-06 ］ . https://arxiv.org/abs/1905.119046.

［ 29 ］ DUAN H D, WANG J Q, CHEN K, et al. PYSKL: towards good practices for skeleton action recognition ［ C ］ //ACM. Proceedings of the 30th ACM International Conference on Multimedia. Lisbon: ACM, 2022: 7351-7354.

［ 30 ］ 张 宗 , 石 林 . 基于 STGCN 算法的视频图像人体动作轮廓动态识别［ J ］ . 现代电子技术 ,2024,47(18):144-148.

ZHANG Zong, SHI Lin. STGCN algorithm based dynamic recognition of human motion contour in video image ［ J ］ . Modern Electronics Technique, 2024, 47(18) : 144-148.

相似文献/References:

[1]单炜,张绍逸.BFRP筋与混凝土的粘结-滑移本构关系[J].建筑科学与工程学报,2013,30(02):15.
　SHAN Wei,ZHANG Shao-yi.[J].Journal of Architecture and Civil Engineering,2013,30(01):15.
[2]马志鸣,赵铁军,巴光忠,等.冻融环境下引气混凝土的抗钢筋锈蚀能力研究[J].建筑科学与工程学报,2014,31(03):85.
　MA Zhi-ming,ZHAO Tie-jun,BA Guang-zhong,et al.Study on Ability of Resistance to Steel Corrosion of Air Entraining Concrete Under Freezethaw Environment[J].Journal of Architecture and Civil Engineering,2014,31(01):85.
[3]李苹,任晓丹,李 杰.基于隐式梯度理论的混凝土细观随机断裂模型[J].建筑科学与工程学报,2014,31(03):90.
　LI Ping,REN Xiao-dan,LI Jie.Meso Stochastic Fracture Model for Concrete Based on Implicit Gradient Theory[J].Journal of Architecture and Civil Engineering,2014,31(01):90.
[4]翟 越,赵均海,艾晓芹,等.基于统一强度理论的巴西圆盘劈裂强度分析[J].建筑科学与工程学报,2015,32(03):46.
　ZHAI Yue,ZHAO Jun-hai,AI Xiao-qin,et al.Analysis on Splitting Strength of Brazilian Disc Based on Unified Strength Theory[J].Journal of Architecture and Civil Engineering,2015,32(01):46.
[5]王 钧,任靖豪,郭大鹏.短切玄武岩纤维混凝土基本力学性能的尺寸效应[J].建筑科学与工程学报,2015,32(05):96.
　WANG Jun,REN Jing-hao,GUO Da-peng.Size Effect of Basic Mechanical Properties of Chopped Basalt Fiber Reinforced Concrete[J].Journal of Architecture and Civil Engineering,2015,32(01):96.
[6]吴方伯,张 航,李 钧,等.不同箱体形式混凝土密肋空心楼盖受力性能试验[J].建筑科学与工程学报,2016,33(02):7.
　WU Fang-bo,ZHANG Hang,LI Jun,et al.Experiment on Mechanical Behavior of Concrete Hollow-ribbed Floor with Different Box[J].Journal of Architecture and Civil Engineering,2016,33(01):7.
[7]孙 昊,李继超,甘 丹.肋间距超限钢筋与混凝土间粘结强度试验[J].建筑科学与工程学报,2016,33(02):107.
　SUN Hao,LI Ji-chao,GAN Dan.Experiment on Bond Strength Between Steel and Concrete with Overrun Rib Spacing[J].Journal of Architecture and Civil Engineering,2016,33(01):107.
[8]乔宏霞,路承功,李 宇,等.宁夏盐渍土地区现场暴露混凝土耐久性损伤评价试验[J].建筑科学与工程学报,2016,33(06):44.
　QIAO Hong-xia,LU Cheng-gong,LI Yu,et al.Experiment on Durability Damage Assessment of Concrete Field Exposed in Saline Soil Area of Ningxia[J].Journal of Architecture and Civil Engineering,2016,33(01):44.
[9]肖 杰,屈文俊,朱 鹏.不同粗细骨料组合下的混凝土耐硫酸腐蚀研究[J].建筑科学与工程学报,2016,33(06):81.
　XIAO Jie,QU Wen-jun,ZHU Peng.Research on Concrete Sulfuric Acid Resistance with Different Types of Coarse and Fine Aggregates[J].Journal of Architecture and Civil Engineering,2016,33(01):81.
[10]刘汉昆,孙超,李杰.基于CT扫描的混凝土三维细观数值模拟[J].建筑科学与工程学报,2010,27(01):54.
　LIU Han-kun,SUN Chao,LI Jie.Three-demensional Mesoscopic Numerical Simulation of Concrete Based on CT Scan[J].Journal of Architecture and Civil Engineering,2010,27(01):54.

备注/Memo

备注/Memo:
中国高校产学研创新基金项目（2022BC040）
更新日期/Last Update: 2026-01-20