基于金属磁记忆检测的正交异性钢桥面板疲劳应力检测  

Fatigue stress detection of orthotropic steel bridge decks based on metal magnetic memory testing

作　　者：司海飞 史震[1] 胡兴柳 SI Haifei;SHI Zhen;HU Xingliu(College of Intelligent Systems Science and Engineering,Harbin Engineering University,Harbin 150001,China;College of Intelligent Science and Control Engineering,Jinling Institute of Technology,Nanjing 211169,China)

机构地区：[1]哈尔滨工程大学智能科学与工程学院,黑龙江哈尔滨150001 [2]金陵科技学院智能科学与控制工程学院,江苏南京211169

出　　处：《南京工业大学学报（自然科学版）》2024年第4期472-478,共7页Journal of Nanjing Tech University(Natural Science Edition)

基　　金：江苏省自然科学基金面上项目(BK20171114);教育部“春晖计划”合作科研项目(HZKY20220122);江苏省产学研合作项目(BY2020445)。

摘　　要：钢箱梁作为被广泛应用的桥梁建设结构,正交异性钢桥面板的连接焊缝多,受到车轮载荷的影响,容易产生疲劳应力和疲劳裂纹,进而可能造成严重安全事故,针对此类涉及正交异性钢桥面板疲劳应力检测的问题,提出了一种基于金属磁记忆检测的正交异性钢桥面板疲劳应力检测方法。首先,通过建立一个金属磁记忆检测系统,实现正交异性钢桥面板的金属磁记忆信号的时域、频域和时频域特征的提取;然后,建立各个信号特征与材料疲劳应力的极限学习机模型;最后,通过极限学习机模型对材料的疲劳应力进行相关估算。结果表明:该系统和极限学习机模型对正交异性钢桥面板的疲劳应力检测是有效的,且疲劳应力估算精度较高。研究结果可作为正交异性钢桥面板应力检测的一种重要技术手段。Steel box girders,as widely used in bridge construction,are prone to fatigue stress and cracks due to the high number of weld joints and the impact of wheel loads,which can lead to serious safety accidents.To address the problem of fatigue stress detection in orthotropic steel bridge decks,a method based on metal magnetic memory detection was proposed.Firstly,the time-domain,frequency-domain,and time-frequency-domain characteristics of the metal magnetic memory signal from the decks were extracted by establishing a metal magnetic memory testing system.Then,an extreme learning machine model for each signal feature and material s fatigue stress was established.Finally,material s fatigue stress was estimated using the model.The results showed that the system and the model were effective for fatigue stress detection in orthotropic steel bridge decks,with high estimation accuracy.The research results can be used as an important technical means for stress detection in orthotropic steel bridge decks.

关 键 词：正交异性钢桥面板 金属磁记忆 疲劳应力 极限学习机 桥梁工程 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TG115.5[自动化与计算机技术—计算机科学与技术]