12 / 2021-03-22 09:14:37

基于渐近分析-机器学习耦合方法之材料性能跨尺度分析

微结构设计,位错,晶界,渐近,机器学习

报告人将讨论传统渐近均匀化方法与新兴机器学习工具在数学结构层面的天然互补性，以期总结基于材料细观演化机制高效保真预测其宏观性能的一般方法。报告从点缺陷-晶界相互作用机制跨尺度建模开始讨论，分析如何建立晶界细观结构与其晶体点缺陷长时等效汇强度的预测公式，进而给出辐照条件下多晶材料对点缺陷吸收效率的预测公式^[1]。随后报告人将讨论如何将孔洞等各类点缺陷汇之汇强度以神经网络的形式进行刻画^[2]。最后报告人将渐近分析-机器学习耦合分析方法应用于点阵分析渐变结构力学性能分析中^[3-6]，从而论证该方法的通用性。



参考文献：

[1] Y. C. Zhu, J. Luo, X. Guo*, Y. Xiang, S. J. Chapman. “Role of grain boundaries under long-time radiation”, Phys. Rev. Lett., 120, 222501-5, 2018.

[2] J. Luo, Y. Xin, Z. C. Zhou, Y. C. Zhu*, X. Guo*. “Attempts on representing sink strengths with machine learning formulations and the long-term role of crystalline interfaces in the development of irradiation-induced bubbles”, Journal of Nuclear Materials., 544, 152676, 2021.

[3] Y. C. Zhu, S. S. Li, Z. L. Du, C. Liu, X. Guo*, W. S. Zhang*. “A novel asymptotic-analysis-based homogenisation approach towards fast design of infill graded microstructures”, J. Mech. Phys. Solids, 124, 612-633, 2019.

[4] D. C. Xue, Y. C. Zhu*, X. Guo*. “Generation of smoothly-varying infill configurations from a continuous menu of cell patterns and the asymptotic analysis of its mechanical behaviour”, Comput. Methods Appl. Mech. Engrg., 366, 113037, 2020.

[5] D. C. Xue, Y. C. Zhu*, S. S. Li, C. Liu, W. S. Zhang, X. Guo*. “On speeding up an asymptotic-analysis-based homogenisation scheme for designing gradient porous structured materials using a zoning strategy”, Struct. Multidiscip. Optim., 62, 457-473, 2020.

[6] Z. C. Zhou, Y. C. Zhu*, J. Luo, Y. Xiang, X. Guo*. “Characterisation of dislocation patterning behaviour with a continuum dislocation dynamics model on two parallel slip planes equipped with a deep neural network resolving local microstructures”, Int. J. Solids Struct., 198, 57-71, 2020.