硅酸盐学报

基于生成对抗网络与声发射特征的超高性能混凝土填充钢管短柱轴压损伤阶段智能识别

PDF下载

陈正 ¹^,² , 陈展鹏 ¹^,² , 陈犇 ³^,⁴ , 杨正曦 ¹^,² , 陆彦菘 ¹^,² , 朱浩杰 ¹^,²

硅酸盐学报 | 第二十八届中国科协年会智能建造关键无机非金属材料–AI驱动水泥基材料创新专题-研究论文 2026,54(10): 3345-3360

收起

硅酸盐学报 |第二十八届中国科协年会智能建造关键无机非金属材料–AI驱动水泥基材料创新专题-研究论文 2026 , 54 (10) : 3345 -3360

基于生成对抗网络与声发射特征的超高性能混凝土填充钢管短柱轴压损伤阶段智能识别

全屏

陈正¹^,², 陈展鹏¹^,², 陈犇³^,⁴, 杨正曦¹^,², 陆彦菘¹^,², 朱浩杰¹^,²

作者信息

^1.广西大学土木建筑工程学院，南宁　530004

^2.广西大学广西防灾减灾与工程安全重点实验室，南宁　530004

^3.中国电建集团华东勘测设计研究院有限公司，杭州　311100

^4.浙江大学高性能结构研究所，杭州　310058

通讯作者:

陈犇（1997-），男，博士。

作者简介:

陈正（1982-），男，博士，教授。

Intelligent Identification of Axial Compression Damage Stages in Ultra-High-Performance Concrete-Filled Steel Tube Short Columns Based on Generative Adversarial Networks And Acoustic Emission Features

Zheng CHEN¹^,², Zhanpeng CHEN¹^,², Ben CHEN³^,⁴, Zhengxi YANG¹^,², Yansong LU¹^,², Haojie ZHU¹^,²

Affiliations

^1.School of Civil Engineering and Architecture, Guangxi University, Nanning 530004, China

^2.Guangxi Key Laboratory of Disaster Prevention and Structural Safety, Guangxi University, Nanning 530004, China

^3.Powerchina Huadong Engineering Corporation Limited, Hangzhou 311100, China

^4.College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China

Corresponding Author:

CHEN Ben (1997-), male, Ph.D. E-mail: chen_b13@hdec.com

CHEN Zheng (1982-), male, Ph. D, Professor. E-mail: chenzheng@gxu.edu.cn

出版时间: 2026-07-29 doi: 10.14062/j.issn.0454-5648.20260327

文章导航

摘要

收起

近年来，深远海区域的工程建设日益增多，极端荷载环境使得高耸塔架与海洋平台中钢管混凝土构件的损伤风险剧增。为实现对上述关键结构内部损伤程度的智能识别，本工作提出了一种融合带梯度惩罚的Wasserstein生成对抗网络（WGAN-GP）与一维残差网络（1D-ResNet）的超高性能混凝土填充钢管（UHP-CFST）短柱损伤阶段智能识别方法，以解决声发射（AE）数据类别不平衡导致的识别精度下降问题。通过对27根UHP-CFST短柱开展轴压试验，同步采集AE信号，并依据归一化累计撞击数（NCH）的演化规律，将损伤过程划分为轻微损伤阶段Ⅰ、中度损伤阶段Ⅱ和完全损伤阶段Ⅲ。选取上升时间、能量、持续时间、幅值、峰值频率、信号强度及约束系数等特征参数构建数据集，采用WGAN-GP对少数类样本进行增强，并结合统计特征分析、t-SNE降维可视化及最大均值差异（MMD）检验对生成数据质量进行评估。结果表明，WGAN-GP生成数据与原始数据在统计特征及高维特征空间分布上具有较高一致性，能够较好保持AE数据的整体分布趋势与主要特征结构。在此基础上，构建基于ResNet的三阶段损伤识别模型，并与支持向量机（SVM）、多层感知机（MLP）和卷积神经网络（CNN）模型进行对比。结果表明：ResNet在阶段Ⅰ、阶段Ⅱ和阶段Ⅲ的F1分数分别达到91.6%、93.8%和94.7%，整体识别性能优于SVM、MLP和CNN模型。研究表明：所提出的WGAN-GP与ResNet相结合的方法能够有效提升UHP-CFST短柱轴压损伤阶段的智能识别性能，为基于AE信号的结构损伤识别提供了新的思路。

关键词

超高性能混凝土填充钢管 / 声发射 / 带梯度惩罚的Wasserstein生成对抗网络 / 一维残差网络 / 损伤识别

Abstract

收起

Introduction

Ultra-high-performance concrete-filled steel tubular (UHP-CFST) members exhibit excellent overall performance; however, the opaque outer steel tube completely prevents direct observation of the damage evolution within the UHPC core. With the continuing development of deep and distant offshore regions, engineering structures are increasingly exposed to extreme loading conditions, which can cause irreversible damage to the core concrete of CFST members. Therefore, the introduction of structural health monitoring (SHM) techniques for accurate identification of structural damage severity is particularly important for these members. Acoustic emission (AE) technology, owing to its in situ passive monitoring capability and sensitivity to microscopic defects, is well suited to such harsh conditions and has become an ideal nondestructive evaluation tool for this type of member. However, although AE enables dynamic monitoring, conventional parameter-based analysis methods, such as the Ib-value and hit count, still rely heavily on manual experience and have limited capability in representing the complex nonlinear relationships embedded in AE signals, which makes it difficult to fully extract the latent damage information contained in high-dimensional AE data. In recent years, deep learning (DL) has been widely applied in pattern recognition, image classification, and regression tasks. Compared with conventional methods, DL methods can automatically extract high-dimensional features and establish nonlinear mappings among complex data, and have therefore attracted increasing attention in the field of structural health monitoring. Against this background, axial compression tests were conducted on 27 UHP-CFST short columns with synchronous AE data acquisition, and an intelligent classification framework was developed to identify damage stages in the specimens.

Methods

A total of 27 UHP-CFST short columns with an outer diameter of 152 mm and a height of 456 mm were tested under concentric axial compression. The test matrix included three steel grades (Q235, Q355, and Q420) and three wall thicknesses (4, 6 mm, and 8 mm), and all specimens were filled with UHPC and three replicate specimens were prepared for each group. The tests were conducted under displacement control, with a loading rate of 1.0 mm/min in the initial stage and 2.0 mm/min after the peak load was reached. The applied load and axial displacement were recorded synchronously by the built-in data acquisition module of the testing machine and external high-precision linear variable differential transformers (LVDTs), respectively. Meanwhile, a 16-channel MISTRAS acoustic emission monitoring system developed by Physical Acoustics Corporation (PAC), USA, was used to monitor crack development in the UHPC core throughout the test.

Based on the evolution of normalized cumulative hits (NCH) as a function of load percentage, the damage process was divided into three stages. AE feature parameters were subsequently extracted, and minority-class data were augmented using a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) to mitigate class imbalance. Based on the augmented data, a damage-stage identification model based on a one-dimensional residual network (1D-ResNet) was further established to classify different damage stages intelligently.

Results and discussion

The AE samples generated by WGAN-GP exhibited high similarity to the original samples in terms of both statistical characteristics and feature-space distribution. For Stage I damage identification, the developed ResNet model achieved a precision of 88.4%, a recall of 95.0%, and an F1-score of 91.6%. These results indicated that the model was able to identify most Stage I samples, with relatively few missed detections. The high recall suggested that the model was highly sensitive to the initial damage stage and could effectively capture early damage features. However, the relatively lower precision indicated that some Stage II samples were misclassified as Stage I, implying the presence of a limited number of false positives. For Stage II damage identification, the model achieved a precision of 92.7%, a recall of 95.0%, and an F1-score of 93.8%. All three metrics remained at a high level, and the precision and recall were relatively well balanced. These results indicated that the model was able to effectively extract the AE characteristics of Stage II and accurately distinguish them from those of the other stages, thereby yielding the best overall identification performance. For Stage III damage identification, the model achieved a precision of 100%, a recall of 90.0%, and an F1-score of 94.7%. These results indicated that the model exhibited extremely high identification accuracy for Stage III. When a sample was classified as belonging to Stage III, no misclassification occurred, indicating the absence of false positives. However, some true Stage III samples were assigned to other stages, which led to a slightly lower recall. The confusion matrix further showed that the model exhibited strong identification capability for all three damage stages. Among them, the classification performance for Stages II and III was particularly good. A small number of misclassifications were observed between Stages I and II, which could be attributed mainly to the continuity of the damage evolution process, as some late Stage I samples and early Stage II samples exhibited a certain degree of overlap in the AE feature space.

In addition, the comparison of identification results among different models showed that the ResNet model achieved high classification accuracy across all three damage stages, with overall performance markedly superior to that of the SVM, MLP, and CNN models. Overall, the results demonstrated that the ResNet model constructed on the basis of the augmented dataset could effectively learn the damage evolution patterns embedded in the AE features and achieve accurate identification of different damage stages in UHP-CFST short columns under axial compression.

Conclusions

The data generated by WGAN-GP show high consistency with the original data in terms of both statistical characteristics and the distribution in high-dimensional feature space, indicating that the overall distribution trend and the main feature structure of the AE data are well preserved. On this basis, a three-stage damage identification model based on ResNet is established and further compared with support vector machine (SVM), multilayer perceptron (MLP), and convolutional neural network (CNN) models. The results show that the F1-scores of the ResNet model for Stages I, II, and III reach 91.6%, 93.8%, and 94.7%, respectively, demonstrating overall identification performance superior to that of the SVM, MLP, and CNN models. Therefore, the proposed method combining WGAN-GP and ResNet effectively improves the intelligent identification of axial compression damage stages in UHP-CFST short columns and provides a new perspective for AE-based structural damage identification.

Key words

ultra-high-performance concrete-filled steel tubular / acoustic emission / wasserstein generative adversarial network with gradient penalty / 1D-residual network / damage identification

引用本文

陈正, 陈展鹏, 陈犇, 杨正曦, 陆彦菘, 朱浩杰. 基于生成对抗网络与声发射特征的超高性能混凝土填充钢管短柱轴压损伤阶段智能识别. 硅酸盐学报, 2026 , 54 (10) : 3345 -3360 . DOI: 10.14062/j.issn.0454-5648.20260327

Zheng CHEN, Zhanpeng CHEN, Ben CHEN, Zhengxi YANG, Yansong LU, Haojie ZHU. Intelligent Identification of Axial Compression Damage Stages in Ultra-High-Performance Concrete-Filled Steel Tube Short Columns Based on Generative Adversarial Networks And Acoustic Emission Features[J]. Journal of the Chinese Ceramic Society, 2026 , 54 (10) : 3345 -3360 . DOI: 10.14062/j.issn.0454-5648.20260327

基金

收起

国家自然科学基金面上项目(52478242)
广西科技重大专项(桂科AA23073017)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

韩林海, 牟廷敏, 王法承, 等. 钢管混凝土混合结构设计原理及其在桥梁工程中的应用[J]. 土木工程学报, 2020, 53(5): 1-24.

HAN Linhai, MU Tingmin, WANG Facheng, et al. China Civ Eng J, 2020, 53(5): 1-24.

[2]

钟善桐. 钢管混凝土结构在我国的应用和发展[J]. 建筑技术, 2001(2): 80-82.

ZHONG Shantong. Archit Technol, 2001(2): 80-82.

[3]

刘威. 钢管混凝土局部受压时的工作机理研究[D]. 福建: 福州大学, 2005.

LIU Wei. Research on mechanism of concrete-filled steel tubes subjected to local compression[D]. Fujian: Fuzhou University, 2005.

[4]

JASINDA C, KONO S, MUKAI D, et al. Experimental investigation and development of design equation for circular hollow precast high-strength concrete-filled steel tube piles under uniaxial compressive loading[J]. Eng Struct, 2025, 343: 121276.

[5]

GAO W, LIAO C, ZHANG L C, et al. Behaviour of concrete-filled steel tube subjected to truck impact considering failure with cohesive zone model[J]. Thin Walled Struct, 2026, 225: 114745.

[6]

XU N, LIU Y H. Integrated algorithm for identifying failure modes and assessing reliability of concrete-filled steel tubes under lateral impact[J]. Autom Constr, 2025, 173: 106118.

[7]

周侃. 钢管混凝土叠合柱-RC梁节点耐火性能研究[D]. 北京: 清华大学, 2017.

ZHOU Kan. Fire performance of concrete-encased concrete filled steel tubular column-RC beam joints[D]. Beijing: Tsinghua University, 2017.

[8]

ZHANG W J, CHEN X M, YUAN X H, et al. Investigation on concrete-filled double skin steel tube columns to impact resistance post-fire[J]. J Constr Steel Res, 2026, 238: 110200.

[9]

韦建刚, 罗霞, 陈宝春, 等. 圆高强钢管UHPC梁抗弯性能研究[J]. 工程力学, 2021, 38(1): 183-194.

WEI Jiangang, LUO Xia, CHEN Baochun, et al. Eng Mech, 2021, 38(1): 183-194.

[10]

ZAHRA H G, MAHMOUD N, BADR A, et al. Integrated experimental and numerical study with design code comparison for stiffened UHPC-filled steel tube columns under axial compression[J]. Structures, 2026, 88: 111917.

[11]

AMRAN M, HUANG S S, ONAIZI A M, et al. Recent trends in ultra-high performance concrete (UHPC): Current status, challenges, and future prospects[J]. Constr Build Mater, 2022, 352: 129029.

[12]

欧阳雪, 史才军, 史金华, 等. 超高性能混凝土受压力学性能及其弹性模量预测[J]. 硅酸盐学报, 2021, 49(2): 296-304.

OUYANG Xue, SHI Caijun, SHI Jinhua, et al. J Chin Ceram Soc, 2021, 49(2): 296-304.

[13]

史才军, 肖江帆, 曹张, 等. 材料组成对UHPC性能的影响[J]. 硅酸盐通报, 2013, 32(6): 1005-1011.

SHI Caijun, XIAO Jiangfan, CAO Zhang, et al. Bull Chin Ceram Soc, 2013, 32(6): 1005-1011.

[14]

张力伟. 混凝土损伤检测声发射技术应用研究[D]. 大连: 大连海事大学, 2012.

ZHANG Liwei. Research on concrete damage detection by using acoustic emission technology[D]. Dalian: Dalian Maritime University, 2012.

[15]

BEHNIA A, CHAI H K, SHIOTANI T. Advanced structural health monitoring of concrete structures with the aid of acoustic emission[J]. Constr Build Mater, 2014, 65: 282-302.

[16]

SAEEDIFAR M, ZAROUCHAS D. Damage characterization of laminated composites using acoustic emission: A review[J]. Compos Part B, 2020, 195: 108039.

[17]

XU Z W, SAMPATH S, WANG X J, et al. Review on structural health monitoring of pipeline: From perspective on acoustic based crack detection[J]. Measurement, 2026, 263: 120075.

[18]

杨瑞峰, 马铁华. 声发射技术研究及应用进展[J]. 中北大学学报(自然科学版), 2006, 27(5): 456-461.

YANG Ruifeng, MA Tiehua. J N Univ China Nat Sci Ed, 2006, 27(5): 456-461.

[19]

XIE K Z, HUANG K, LIANG D, et al. Axial compressive damage and failure early warning method of concrete-filled steel tube with defects based on acoustic emission[J]. Structures, 2026, 86: 111411.

[20]

SHEN W, BAI H, WANG F, et al. Acoustic Emission characteristics and damage evolution of Concrete-Encased CFST columns under compressive load[J]. Eng Fract Mech, 2024, 311: 110578.

[21]

GAO P, LIU J P, WANG X D, et al. Damage evaluation and failure mechanism analysis of axially compressed square concrete-filled steel tubular columns by acoustic emission techniques[J]. Measurement, 2023, 217: 113132.

[22]

SHEN W, WANG F, LI C, et al. Revealing evolution law and failure mechanism of interface damage in concrete-encased CFST columns by acoustic emission technology[J]. J Build Eng, 2024, 93: 109792.

[23]

ZOU Z L, WANG M S, SONG B, et al. Deep learning and digital twin driven structural health monitoring of masonry structures: Progress and challenges[J]. Autom Constr, 2026, 188: 106993.

[24]

ZHENG B, YANG J, LI J Y, et al. Advances in deep learning for intelligent non-destructive spectral analysis: From preprocessing and data augmentation to interpretability, fusion, and transfer learning[J]. Trac Trends Anal Chem, 2026, 197: 118741.

[25]

DU J B, ZENG J, WANG H, et al. Using acoustic emission technique for structural health monitoring of laminate composite: A novel CNN-LSTM framework[J]. Eng Fract Mech, 2024, 309: 110447.

[26]

郭福平. 基于深度学习的CFRP复合材料损伤声发射信号模式识别[D]. 黑龙江: 东北石油大学, 2023.

Guo Fuping. Pattern recognition of acoustic emissionsignals based on deep learning for CFRP composite damage[D]. Heilongjiang: Northeast Petroleum University, 2023.

[27]

XU D, LIU P F, CHEN Z P. A deep learning method for damage prognostics of fiber-reinforced composite laminates using acoustic emission[J]. Eng Fract Mech, 2022, 259: 108139.

[28]

BARILE C, CASAVOLA C, PAPPALETTERA G, et al. Damage monitoring of carbon fibre reinforced polymer composites using acoustic emission technique and deep learning[J]. Compos Struct, 2022, 292: 115629.

[29]

SIKDAR S, LIU D Z, KUNDU A. Acoustic emission data based deep learning approach for classification and detection of damage-sources in a composite panel[J]. Compos Part B Eng, 2022, 228: 109450.

[30]

石洪波, 陈雨文, 陈鑫. SMOTE过采样及其改进算法研究综述[J]. 智能系统学报, 2019, 14(6): 1073-1083.

SHI Hongbo, CHEN Yuwen, CHEN Xin. CAAI Trans Intell Syst, 2019, 14(6): 1073-1083.

[31]

王磊, 刘雨, 刘志中, 等. 处理不平衡数据的聚类欠采样加权随机森林算法[J]. 计算机应用研究, 2021, 38(5): 1398-1402.

WANG Lei, LIU Yu, LIU Zhizhong, et al. Appl Res Comput, 2021, 38(5): 1398-1402.

[32]

张家伟, 郭林明, 杨晓梅. 针对不平衡数据的过采样和随机森林改进算法[J]. 计算机工程与应用, 2020, 56(11): 39-45.

ZHANG Jiawei, GUO Linming, YANG Xiaomei. Comput Eng Appl, 2020, 56(11): 39-45.

[33]

Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Advances in neural information processing systems, 2014, 27.

[34]

Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks[C]//International conference on machine learning. Pmlr, 2017: 214-223.

[35]

HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016: 770-778.

2026年第54卷第10期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.14062/j.issn.0454-5648.20260327

接收时间：2026-05-15
首发时间：2026-10-22
出版时间：2026-07-29

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2026-05-15
修回日期：2026-05-29

基金

国家自然科学基金面上项目(52478242)

广西科技重大专项(桂科AA23073017)

作者信息

^1.广西大学土木建筑工程学院，南宁　530004

^2.广西大学广西防灾减灾与工程安全重点实验室，南宁　530004

^3.中国电建集团华东勘测设计研究院有限公司，杭州　311100

^4.浙江大学高性能结构研究所，杭州　310058

通讯作者:

陈犇（1997-），男，博士。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/gsyxb/CN/10.14062/j.issn.0454-5648.20260327

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT