针刺C/C复合材料拉伸强度预测的深度学习模型  

Deep learning prediction model for tensile strength of needle-punched C/C composites

作　　者：成博 弓站朋 邓俊楷 白侠[2] 李艳[2] 张承双[2,3] CHENG Bo;GONG Zhanpeng;DENG Junkai;BAI Xia;LI Yan;ZHANG Chengshuang(State Key Laboratory for Mechanical Behavior of Materials,Xi’an Jiaotong University,Xi’an 710049,China;Xi’an Aerospace Composites Research Institute,Xi’an 710025,China;Shaanxi Key Laboratory of Aerospace Composites,Xi’an 710025,China)

机构地区：[1]西安交通大学金属材料强度国家重点实验室,西安710049 [2]西安航天复合材料研究所,西安710025 [3]陕西省航天复合材料重点实验室,西安710025

出　　处：《固体火箭技术》2022年第6期851-859,共9页Journal of Solid Rocket Technology

摘　　要：针刺C/C复合材料利用针刺工艺,将炭布和网胎中的面内纤维引入到铺层厚度方向,在增强层间强度的同时,针刺工艺导致针刺C/C复合材料成品中针刺位置的分布具有显著的随机性,即使在针刺密度和针刺深度相同的条件下,针刺C/C复合材料中不同针刺位置的分布,也会对其拉伸强度等力学性能造成很大的影响。利用有限元(FEM)数值模拟的方法,基于一种针刺C/C复合材料的实验数据,通过高通量计算,获得了100000个相同针刺密度、针刺深度和不同针刺位置分布的有限元模型及其对应的拉伸强度,揭示了针刺C/C复合材料中不同针刺位置分布对其拉伸强度影响的细观机理。随后,利用深度学习算法训练了预测模型,可以对任意针刺位置分布所对应的复合材料的拉伸强度进行预测,从而为优化针刺C/C复合材料中针刺位置的分布提供理论工具。Through needle-punched process,in-plane fibers in carbon-cloth and feltwere introduced into C/C composite materials along the thickness direction of layup.While enhancing the interlayer strength,the needle-punched process leads to a significant randomness of needling position distribution for the finished needle-punched C/C composites.Even under the same conditions of needle-punched density and depth,the distribution of different needling positions in needle-punched C/C composites can have a great impact on mechanical properties such as tensile strength.By means of finite element numerical simulation method(FEM)and high-throughput calculations,100000 finite element models with the same needling density,needling depth,different needling position distribution and corresponding tensile strength were obtained based on experimental data of a needle-punched C/C composite material.The microscopic correlation mechanism of different needling position distribution on the tensile strength of needle-punched C/C composites was revealed.Subsequently,the model was trained using a deep learning algorithm to predict the tensile strength of composites for any needling position distribution,which can provide theoretical reference for optimizing the needling position distribution of needle-punched C/C composites.

关 键 词：C/C复合材料 针刺预制体 力学性能 有限元方法 深度学习 

分 类 号：V258[一般工业技术—材料科学与工程]