三维针刺C/C-SiC复合材料预制体工艺参数优化

doi:10.11868/j.issn.1001-4381.2019.000041

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(2138 KB)

HTML ( 10 )
输出: BibTeX | EndNote (RIS) 背景资料

文章导读

摘要

基于误差反向传播（BP）神经网络与改进的遗传算法建立三维针刺C/C-SiC复合材料预制体工艺优化的代理模型，获得针刺工艺参数与复合材料刚度性能之间的关系。利用BP网络实现复合材料刚度性能预测，BP网络的预测值与有限元计算结果吻合程度较好，模型训练误差最大为0.526%，测试数据误差最大为0.454%，BP网络预测精度高。对传统遗传算法的遗传策略和优化策略进行改进，利用两种改进的遗传算法对针刺工艺参数进行优化。优化后的工艺参数显著提高了材料的刚度性能，其中面内拉伸模量分别提高了11.07%和11.48%，面外拉伸模量分别提高了49.64%和48.13%，复合材料的综合刚度性能分别提高18.17%和18.21%。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	戚云超
	方国东
	梁军
	谢军波

关键词 ：针刺复合材料, BP神经网络, 刚度性能预测, 遗传算法, 工艺优化

Abstract：

A surrogate model was established to optimize needling process parameters of three dimensional needled C/C-SiC composites by using back propagation (BP) neural network and improved genetic algorithm. The relationship between needling process parameters and composites stiffness was obtained. The stiffness prediction obtained by BP neural network is in good agreement with the finite element calculated results. The maximum error of training data is 0.526%, and the maximum error of test data is 0.454%. Thus, the BP neural network model exhibits the high prediction accuracy. The genetic and optimization strategies of genetic algorithm were improved to optimize the needling process parameters. The calculated needling process parameters by the model can significantly improve the stiffness of the C/C-SiC composites. The in-plane tensile modulus increase by 11.07% and 11.48%, and the out-of-plane tensile modulus increase by 49.64% and 48.13%, respectively. The comprehensive stiffness performance of composite material increase by 18.17% and 18.21%, respectively.

Key words： needling composites BP neural network stiffness prediction genetic algorithm process optimization

收稿日期: 2019-01-30 出版日期: 2020-01-09

中图分类号:

TB332

基金资助:国家自然科学基金资助项目(11732002);国家自然科学基金资助项目(11672089)

通讯作者: 方国东,梁军 E-mail: fanggd@hit.edu.cn;liangjun@bit.edu.cn

作者简介: 梁军(1969—), 男, 教授, 博士, 主要研究方向:先进复合材料力学, 联系地址:北京海淀区中关村南大街5号北京理工大学宇航学院(100081), E-mail:liangjun@bit.edu.cn
方国东(1983—), 男, 副教授, 博士主要研究方向:复合材料力学性能表征及评价, 联系地址:黑龙江省哈尔滨市南岗区一匡街2号哈尔滨工业大学复合材料与结构研究所, E-mail:fanggd@hit.edu.cn

引用本文:

戚云超, 方国东, 梁军, 谢军波. 三维针刺C/C-SiC复合材料预制体工艺参数优化[J]. 材料工程, 2020, 48(1): 27-33.
Yun-chao QI, Guo-dong FANG, Jun LIANG, Jun-bo XIE. Optimization of process parameters of three-dimensional needled preforms for C/C-SiC composites. Journal of Materials Engineering, 2020, 48(1): 27-33.

链接本文:

http://jme.biam.ac.cn/CN/10.11868/j.issn.1001-4381.2019.000041 或 http://jme.biam.ac.cn/CN/Y2020/V48/I1/27

Fig.1 针刺复合材料单胞模型^[14]
(a)有限元模型；(b)针刺区域

Table 1 20组针刺工艺参数及有限元模拟的刚度值

Fig.2 BP神经网络示意图

Fig.3 BP网络输出值与有限元计算值比较

Fig.4 网络输出值与有限元计算值的相对误差

Table 2 遗传算法输入参数

Fig.5 最优个体保存策略遗传算法流程图

Table 3 4种遗传算法的优化效果

Fig.6 两种不同遗传算法所出现的适应度随遗传代数变化情况
(a)正弦型算子; (b) S型算子

Table 4 优化前后的材料刚度性能

Table 5 优化后的针刺工艺参数

1	李飞, 刘建军, 程文, 等. 工艺参数对炭/炭复合材料针刺预制体力学性能的影响[J]. 炭素, 2004, (1): 25- 28. doi: 10.3969/j.issn.1001-8948.2004.01.007
1	LI F , LIU J J , CHENG W , et al. Effect of technology parameters on mechanics performances of C/C composite needling perfabricat[J]. Carbon, 2004, (1): 25- 28. doi: 10.3969/j.issn.1001-8948.2004.01.007
2	张晓虎, 李贺军, 郝志彪, 等. 针刺工艺参数对炭布网胎增强C/C材料力学性能的影响[J]. 无机材料学报, 2007, 22 (5): 963- 967. doi: 10.3321/j.issn:1000-324x.2007.05.037
2	ZHANG X H , LI H J , HAO Z B , et al. Influence of needle-punching processing parameters on mechanical properties of C/C composites reinforced by carbon cloth and carbon fiber net[J]. Journal of Inorganic Materials, 2007, 22 (5): 963- 967. doi: 10.3321/j.issn:1000-324x.2007.05.037
3	张盼.三维针刺C/C复合材料的微结构建模及力学性能预测[D].西安: 西北工业大学, 2016.
3	ZHANG P. Microstructure modeling and prediction of effective properties of 3D needled C/C composites[D]. Xi'an: Northwestern Polytechnical University, 2016.
4	宋磊磊.高性能纤维针刺毡三维重构及其复合材料性能表征[D].天津: 天津工业大学, 2016.
4	SONG L L. Three-dimensional reconstruction of high-performance fiber needle felt and characterization of composite material[D].Tianjin: Tianjin Polytechnic University, 2016.
5	KRUCINSKA I . The influence of technological parameters on the filtration efficiency of electret needled non-woven fabrics[J]. Journal of Electrostatics, 2002, 56 (2): 143- 153. doi: 10.1016/S0304-3886(02)00060-8
6	白光辉.基于遗传算法与神经网络的碳/碳材料使用性能表征与优化[D].哈尔滨: 哈尔滨工业大学, 2007.
6	BAI G H. Performance characterization and optimization of C/C composites based on GA and ANN[D]. Harbin: Harbin Institute of Technology, 2007.
7	VATANKHAH E , SEMNANI D , PRABHAKARAN M P , et al. Artificial neural network for modeling the elastic modulus of electro spun polycaprolactone/gelatin scaffolds[J]. Acta Biomaterialia, 2014, 10 (2): 709- 721. doi: 10.1016/j.actbio.2013.09.015
8	YAN F , LIN Z B , WANG X Y , et al. Evaluation and prediction of bond strength of GFRP-bar reinforced concrete using artificial neural network optimized with genetic algorithm[J]. Composite Structures, 2017, 161, 441- 452. doi: 10.1016/j.compstruct.2016.11.068
9	LIU G X , JIA L N , KONG B , et al. Artificial neural network application to study quantitative relationship between silicide and fracture toughness of Nb-Si alloys[J]. Materials & Design, 2017, 129, 210- 218.
10	LIN Y , ZHENG Z Q , ZHANG H F , et al. Effect of heat treatment process on tensile properties of 2A97 Al-Li alloy:experiment and BP neural network simulation[J]. Trans Nonferrous Met Soc China, 2013, 23 (6): 1728- 1736. doi: 10.1016/S1003-6326(13)62655-2
11	WANG Z , MAK M C . Optimization of geometrical parameters for periodical structures applied to floating raft systems by genetic algorithms[J]. Applied Acoustics, 2018, 129, 108- 115. doi: 10.1016/j.apacoust.2017.07.018
12	PAPPU S M J , GUMMADI S N . Artificial neural network and regression coupled genetic algorithm to optimize parameters for enhanced xylitol production by Debaryomyces nepalensis in bioreactor[J]. Biochemical Engineering Journal, 2017, 120, 136- 145. doi: 10.1016/j.bej.2017.01.010
13	D'ADDONA D M , TETI R . Genetic algorithm-based optimization of cutting parameters in turning processes[J]. Procedia CIRP, 2013, 7, 323- 328. doi: 10.1016/j.procir.2013.05.055
14	XIE J B , LIANG J , FANG G D , et al. Effect of needling parameters on the effective properties of 3D needled C/C-SiC composites[J]. Composites Science and Technology, 2015, 117, 69- 77. doi: 10.1016/j.compscitech.2015.06.003
15	谢军波.针刺预制体工艺参数建模及复合材料本构关系研究[D].哈尔滨: 哈尔滨工业大学, 2012.
15	XIE J B. Parametric modeling of needling process and constitutive relationship of needled composite[D]. Harbin: Harbin Institute of Technology, 2016.
16	XU Y J , YOU T , DU C L . An integrated micromechanical model and BP neural network for predicting elastic modulus of 3-D multi-phase and multi-layer braided composite[J]. Composite Structures, 2015, 122, 308- 315. doi: 10.1016/j.compstruct.2014.11.052
17	朱凯, 王正林. 精通MATLAB神经网络[M]. 北京: 电子工业出版社, 2010.
17	ZHU K , WANG Z L . Proficient in MATLAB neural network[M]. Beijing: Publishing House of Electronics Industry, 2010.
18	周明, 孙树栋. 遗传算法原理及应用[M]. 北京: 国防工业出版社, 1999.
18	ZHOU M , SUN S D . Principle and application of genetic algorithm[M]. Beijing: National Defense Industry Press, 1999.
19	SRINVAS M , PATNAIK L M . Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Trans on Systems, Man and Cybernetics:Part A, 1994, 24 (4): 656- 667. doi: 10.1109/21.286385
20	王小平, 曹立明. 遗传算法:理论、应用与软件实现[M]. 西安: 西安交通大学出版社, 2002.
20	WANG X P , CAO L M . Genetic algorithm:theory, application and software implementation[M]. Xi'an: Xi'an Jiaotong University Press, 2002.

[1]	汪雅婷, 黎俊良, 袁楷峰, 陈广义. 基于GA改进BP神经网络预测热变形流变应力模型的建立[J]. 材料工程, 2022, 50(6): 170-177.
[2]	周峰, 王克鲁, 鲁世强, 万鹏, 陈虚怀. Ti-22Al-24Nb-0.5Y合金流变行为及BP神经网络高温本构模型[J]. 材料工程, 2019, 47(8): 141-146.
[3]	万鹏, 王克鲁, 鲁世强, 陈虚怀, 周峰. 基于应变补偿和PSO-BP神经网络的Ti-2.7Cu合金本构关系[J]. 材料工程, 2019, 47(4): 113-119.
[4]	卢玉章, 熊英, 彭建强, 申健, 郑伟, 张功, 谢光. 重型燃机定向结晶空心叶片凝固过程的实验与模拟[J]. 材料工程, 2018, 46(1): 8-15.
[5]	李伟东, 张金栋, 李韶亮, 刘刚, 钟翔屿, 包建文. 耐高温双马来酰亚胺树脂的固化反应动力学和TTT图[J]. 材料工程, 2016, 44(9): 44-51.
[6]	卢玉章, 申健, 郑伟, 徐正国, 张功, 谢光. 单晶铸件凝固过程工艺优化的数值模拟[J]. 材料工程, 2016, 44(11): 1-8.
[7]	任维彬, 董世运, 徐滨士, 王玉江, 闫世兴, 方金祥. FV520(B)钢叶片模拟件激光再制造工艺优化及成形修复[J]. 材料工程, 2015, 43(1): 6-12.
[8]	曹宁, 李木森, 李和胜. 等离子喷涂HA涂层的制备工艺优化与表征研究进展[J]. 材料工程, 2009, 0(2): 79-84.
[9]	邓文斌, 陈慧琴, 李臻熙. TC11钛合金盘模锻过程微观组织的数值模拟[J]. 材料工程, 2009, 0(12): 30-33.
[10]	翟言强, 李克智, 李贺军, 刘皓, 王闯. 超声电沉积碳/碳复合材料磷灰石涂层的工艺优化[J]. 材料工程, 2007, 0(4): 27-31.
[11]	袁杰, 肖刚, 曹茂盛. 用遗传算法计算设计多薄层雷达吸波材料的程序实现技术[J]. 材料工程, 2005, 0(6): 13-16,40.
[12]	姜开宇, 李贺军, 王敏杰. 遗传算法在C/C复合材料等温CVI工艺参数优化中的应用[J]. 材料工程, 2002, 0(10): 33-35,47.

Viewed

Full text

Abstract

Cited

Shared

Discussed