Metals and Materials International ( IF 3.3 ) Pub Date : 2021-09-02 , DOI: 10.1007/s12540-021-01024-4 Abdelmoumin Ouladbrahim 1 , Idir Belaidi 1 , Samir Khatir 2 , Erica Magagnini 3 , Roberto Capozucca 3 , Magd Abdel Wahab 4, 5
|
Abstract
The Gurson–Tvergaard–Needleman damage model (GTN) describes the three stages of ductile tearing of steel: nucleation, growth and coalescence of micro-voids. This work is divided into two main parts. In the first part, based on the inverse analysis and the comparison between the experimental and numerical data, the parameters of the GTN damage model in conjunction with the hardening law are determined. The identification is broadened to include a considerable number of experimental tests drawn from our previous works and other works done at ALFAPIPE Ghardaia laboratory. In the second part, an Artificial Neural Network model is developed to predict the parameters of the (GTN) model coupled with the hardening law that goes through the prediction of traction and impact properties of API X70 steel pipe depending on its chemical composition. The weight of the chemical elements in percentages is considered as the inputs and the GTN parameters are considered as the outputs. In order to validate the obtained ANNGTN parameters, traction and impact tests are simulated. The numerical results are compared with the experimental ones and revealed that the developed model is very precise and has the potential to capture the interaction of GTN parameters coupled with hardening law and chemical composition of steel pipelines.
Graphic Abstract
中文翻译：
基于神经网络的钢X70管道Gurson损伤模型参数预测与硬化规律识别
摘要
Gurson-Tvergaard-Needleman 损伤模型 (GTN) 描述了钢的韧性撕裂的三个阶段：微孔的形核、生长和聚结。这项工作分为两个主要部分。第一部分，基于逆向分析和实验数据与数值数据的对比，结合硬化规律确定了GTN损伤模型的参数。鉴定范围扩大到包括从我们以前的工作和在 ALFAPIPE Ghardaia 实验室完成的其他工作中提取的大量实验测试。在第二部分中，开发了人工神经网络模型来预测 (GTN) 模型的参数，并结合硬化规律，根据其化学成分预测 API X70 钢管的牵引和冲击性能。以百分比表示的化学元素的权重被视为输入，GTN 参数被视为输出。为了验证获得的 ANNGTN 参数，模拟了牵引力和冲击力测试。将数值结果与实验结果进行比较，表明所开发的模型非常精确，有可能捕获 GTN 参数与钢管道的硬化规律和化学成分之间的相互作用。
京公网安备 11010802027423号