基于敲击声信号和一维卷积神经网络的钢管混凝土脱空缺陷识别

梁学文; 陈天宇; 田明东; 廖飞宇; 余焜明; 骆勇鹏

doi:10.13206/j.gjgS26051701

基于敲击声信号和一维卷积神经网络的钢管混凝土脱空缺陷识别

doi: 10.13206/j.gjgS26051701

1. 广东省建科建筑设计院有限公司, 广州 510145;
2. 福建农林大学交通与土木工程学院, 福州 350108;
3. 南平市公路事业发展中心, 福建南平 350008

基金项目:

福建省自然科学基金面上项目（2024J01424）；福建农林大学科技创新专项基金项目（KFB23168）；福建省交通运输科技项目（YB202412）；福建省住房与城乡建设科学技术计划项目（2025-K-23）。

详细信息

作者简介:
梁学文，高级工程师，主要从事工程结构设计与检测方面的研究工作。

通讯作者:
骆勇鹏，副教授，主要从事工程结构智能检测与监测技术方面的研究工作，yongpengluo@fafu.edu.cn。

计量
- 文章访问数: 2
- HTML全文浏览量: 0
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2026-05-17
- 网络出版日期: 2026-07-06

Void Defect Identification in Concrete-Filled Steel Tubes Using Percussion Acoustic Signals and a One-Dimensional Convolutional Neural Network

1. Guangdong Jianke Architectural Design Institute Company, Guangzhou 510145, China;
2. School of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou 350108, China;
3. Nanping Highway Development Center, Nanping 350008, China

摘要

摘要: 受施工工艺、材料收缩徐变及服役环境等多重因素影响，钢管混凝土易产生脱空缺陷，导致承载能力下降，长期服役安全性受到威胁。传统人工敲击检测具有方便快捷的优势，但该方法依赖检测人员的主观经验，易出现误判漏判问题。为此，提出一种基于敲击声信号和一维卷积神经网络的钢管混凝土脱空缺陷识别方法。采用一维卷积神经网络构建钢管混凝土脱空缺陷识别模型，以敲击声压信号为输入，通过多层卷积操作自动提取声音信号中的缺陷特征进行缺陷识别。采用试验和有限元数据构建涵盖不同脱空位置、脱空深度等因素影响的数据集，并用于验证所提方法的可行性及可靠性。结果表明：所构建的缺陷识别模型在测试集上的平均识别准确率达到97.44%，具有训练时间较短、收敛速度较快的优势。
- 钢管混凝土 /
- 脱空缺陷 /
- 声音信号 /
- 一维卷积神经网络
Abstract: Influenced by multiple factors such as construction technology， material shrinkage and creep， and service environment， concrete-filled steel tubes are prone to void defects， which lead to a decrease in bearing capacity and pose a threat to long-term service safety. Traditional manual percussion detection is convenient and fast. However， this method relies on the subjective experience of inspectors and is prone to misjudgment and missed detection. Therefore， a method for identifying void defects in concrete-filled steel tubes using percussion sound signals and a one-dimensional convolutional neural network is proposed. A one-dimensional convolutional neural network is used to construct a model for identifying void defects in concrete-filled steel tubes. With the percussion sound pressure signal as input， defect features in the sound signal are automatically extracted through multi-layer convolution operations for defect identification. A dataset covering the influence of factors such as void position and void depth was constructed using experimental and finite-element data， and was used to verify the feasibility and reliability of the proposed method. The results showed that the average identification accuracy of the constructed defect identification model on the test set was 97.44%. Furthermore， the model offered the advantages of short training time and fast convergence.
- concrete-filled steel tube /
- void defect /
- acoustic signal /
- one-dimensional convolutional neural network

HTML全文

参考文献(15)

[1]	朱宏平, 余璟, 张俊兵. 结构损伤动力检测与健康监测研究现状与展望[J]. 工程力学, 2011, 28（2）:1-11.
[2]	Chen H, Nie X, Gan S, et al. Interfacial imperfection detection for steel-concrete composite structures using NDT techniques:a state-of-the-art review[J]. Engineering Structures, 2021, 245:112778.
[3]	凌干展, 解威威, 秦大燕, 等. 密实状态下拱桥管内混凝土超声波波速的时变规律及多因素模型[J]. 铁道科学与工程学报, 2023, 20（10）:3851-3860.
[4]	Xu B, Chen H, Xia S. Numerical study on the mechanism of active interfacial debonding detection for rectangular CFSTs based on wavelet packet analysis with piezoceramics[J]. Mechanical Systems and Signal Processing, 2017, 86:108-121.
[5]	许斌, 李冰, 宋刚兵, 等. 基于压电陶瓷的钢管混凝土柱剥离损伤识别研究[J]. 土木工程学报, 2012, 45（7）:86-96.
[6]	Liu H, Liao J, Chen Z, et al. Impact acoustic inspection of interfacial debonding defects in concrete-filled steel tubes[J]. Mechanical Systems and Signal Processing, 2023, 200:110641.
[7]	Zhou Y, Pei Y L, Liu M. Non-contact diagnosis for interface debonding of steel-concrete composited structure by using impact resonance test with microphone[J]. Earthquake Engineering and Engineering Dynamics, 2020, 40（1）:67-79.
[8]	Chen D, Montano V, Huo L, et al. Detection of subsurface voids in concrete-filled steel tubular（CFST）structure using percussion approach[J]. Construction and Building Materials, 2020, 262:119761.
[9]	Li Y, Yue Q, Li H, et al. Multi-damage index-based interfacial debonding prediction for steel-concrete composite structures with percussion method[J]. Journal of Building Engineering, 2024, 94:109964.
[10]	Chen D, Shen Z, Huo L, et al. Percussion-based quasi real-time void detection for concrete-filled steel tubular structures using dense learned features[J]. Engineering Structures, 2023, 274:115197.
[11]	Pan P, Yang W, Zhang Y. Detection of steel-concrete interface defects in concrete-filled steel tubular columns using the percussion method and dual-branch CNN with multi-modal feature fusion[J]. Advances in Engineering Software, 2025, 207:103952.
[12]	Cao H, Li J, Chen X. Investigation of interfacial debonding identification for concrete filled steel tube columns based on acoustic signals[J]. Measurement, 2025, 240:115511.
[13]	张镇涛. 基于小波变换和深度学习的电能质量扰动信号去噪与识别研究[D]. 南昌:南昌大学, 2021.
[14]	张瑞程, 王新颖, 胡磊磊, 等. 基于一维卷积神经网络的燃气管道泄漏声发射信号识别[J]. 中国安全生产科学技术, 2021, 17（2）:104-109.
[15]	Abdeljaber O, Avci O, Kiranyaz S, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks[J]. Journal of Sound and Vibration, 2017, 388:154-170.