失效模式及影响分析
结构工程
剪切(地质)
螺栓连接
工程类
连接(主束)
随机森林
模式(计算机接口)
计算机科学
材料科学
人工智能
复合材料
有限元法
操作系统
作者
Samia Zakir Sarothi,Khondaker Sakil Ahmed,Nafiz Imtiaz Khan,Aziz Ahmed,Moncef L. Nehdi
标识
DOI:10.1016/j.engfailanal.2022.106471
摘要
• Failure modes of 455 tested double shear bolted connections of structural steel are categorized. • 10 machine learning models are employed to predict the failure modes of double shear bolted connections. • 10-fold cross-validations were adopted for the model’s performance evaluation. • RF, CatBoost, XGBoost, and GB attained an accuracy of 90–92% on the failure mode classification. • Edge distance to bolt diameter (e 2 /d 0 ) is the most influential in controlling the failure types. The design of double shear bolted connections in structural steel is governed by four different failure modes; tear out, splitting, net-section, and bearing. Ten machine learning (ML) approaches were explored on a comprehensive database of 455 experimental results for identifying the failure modes of double shear bolted connections. Among them, Random Forest (RF), CatBoost, XGBoost, and Gradient Boosting (GB) attained 90–92% accuracy on the testing dataset for classifying the failure modes. The best-performing models revealed that the ratio of the edge distance-to-bolt diameter ( e 2 /d 0 ) is the most important feature with an influence of nearly 30% on the failure mode of the connections. Interestingly, the number of bolt rows in a connection also influences the failure mode, which was not captured by existing equations and design codes. Finally, a user interface capturing all proposed ML models was developed to identify the failure modes of double shear bolted connections.
科研通智能强力驱动
Strongly Powered by AbleSci AI