东南大学学报（自然科学版）2024，Vol.54Issue(2)：285-293,9.DOI:10.3969/j.issn.1001-0505.2024.02.005
基于声发射的钢桥面板焊接气孔缺陷在线识别
Online detection of welding pore defects in steel bridge decks based on acoustic emission
摘要
Abstract
To achieve online monitoring of defects in the robot intelligent welding process of orthogonal aniso-tropic steel bridge decks,a pore defect acoustic emission detection method was proposed based on fast Fourier transform(FFT)and support vector machine(SVM).The acoustic emission characteristics of the welding and defect generation processes in steel bridge decks were explored by conducting robotic welding experi-ments.The parameters of acoustic emission signals,such as amplitude,counts,peak frequency,and center frequency,in the non-damage and pore defect cases behave with significant overlaps and low correlations.However,the Fourier spectrums of signals from the pore defect case exhibit more high-frequency energy distri-butions.Therefore,taking spectrums as the input,a radial basis kernel SVM model was established for classif-ying the two cases.Experimental results demonstrate that the proposed method outperforms other machine learning models,including naive Bayes,random forest,and linear kernel SVM models,in terms of accuracy(95.4％)and recall(94.3％).It can be used for online detection of pore defects in the welding process,ex-hibiting strong robustness and practicality.关键词
钢桥面板/焊接缺陷/在线识别/声发射/频谱分析/支持向量机Key words
steel bridge decks/welding defects/online detection/acoustic emission/spectral analysis/sup-port vector machine(SVM)分类
建筑与水利引用本文复制引用
李丹,陈燕秋,王浩,聂佳豪,刘洋,王建国..基于声发射的钢桥面板焊接气孔缺陷在线识别[J].东南大学学报（自然科学版）,2024,54(2):285-293,9.基金项目
国家自然科学基金资助项目(52378290,52338011)、中央高校基本科研业务费专项资金资助项目(RF1028623228)、江苏省科技成果转化专项资金资助项目(BA2023059). （52378290,52338011）
