基于数据驱动的纤维增强复合材料自动铺放速度预测与规划

doi:10.7527/S1000-6893.2023.29313

Abstract

Abstract:

During the Automated Fiber Placement （AFP） process of composite materials， sudden changes in laying speed can easily cause defects such as tows folding， wrinkles， and slippage， thereby reducing laying quality and efficiency. Optimizing and adjusting laying speed based on predictive results is an important approach to improve laying speed stability and ensure laying quality. Therefore， this paper proposes a data-driven method for predicting and planning the laying speed of fiber placement machines. Firstly， based on the random forest method， a laying speed prediction model with the motion axis of the laying machine as the subtree is established. A method for defining feature parameters of the random forest model is proposed， with joint nominal speed， acceleration， and joint trajectory angle as input features， and actual joint speed as output features. Furthermore， based on the analysis of speed prediction results， a segmented uniform command speed planning method is proposed. Finally， a method for estimating the manufacturing cycle based on command speed is given. The above methods are verified through laying experiments on a six-degree-of-freedom horizontal machine tool. The results show that the accuracy of predicting laying speed for layers laid at the same training angle reaches 91%， and with the increase of learning data， the prediction accuracy of laying paths at various angles is improved. The segmented planning method for command speed based on speed prediction results can significantly reduce speed fluctuations and effectively improve laying quality. In terms of computational cost， compared with neural network methods， the random forest method demonstrates efficient laying speed prediction capabilities.

Key words: composite materials, automated fiber placement, layup speed, speed prediction, data driven model

CLC Number:

V261.97

Qian YANG, Yanzhe WANG, Di YANG, Zezhong LI, Weiwei QU. Prediction and planning of automatic laying speed for fiber reinforced composite materials based on data⁃driven model[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(10): 429313.

Figures/Tables 31

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Table 1

Goodness of fit of training data set obtained using OOB samples

随机森林模型	$R R F_O O B 2$
$M o d e l_J X$	0.992 7
$M o d e l_J Y$	0.983 8
$M o d e l_J Z$	0.983 0
$M o d e l_J B$	0.996 7
$M o d e l_J C$	0.994 3
$M o d e l_J D$	0.974 8

Table 1

Table 2

Predicted results of same angular path feed speed

铺层	MAE			RMSE			$R 2$
铺层	1号路径	2号路径	3号路径	1号路径	2号路径	3号路径	1号路径	2号路径	3号路径
Ply1_45°	0.86	1.21	1.89	1.78	2.12	1.68	0.98	0.98	0.98
Ply5_45°	2.21	1.63	1.94	3.58	2.82	3.86	0.95	0.97	0.91
Ply9_45°	1.29	2.18	2.21	2.05	3.60	3.95	0.97	0.94	0.92

Table 2

Fig.12

Table 3

Non⁃training angular path prediction error

铺层	MAE	RMSE	$R 2$
Ply2_-45°	9.521	14.029	0.20
Ply3_0°	6.187	10.602	0.29
Ply4_90°	4.659	7.443	0.84

Table 3

Fig.13

Table 4

Predicted results of four⁃angle path laying speed

铺层	MAE			RMSE			$R 2$
铺层	1号路径	2号路径	3号路径	1号路径	2号路径	3号路径	1号路径	2号路径	3号路径
Ply3_0°	5.23	5.56	5.53	9.24	9.63	8.89	0.46	0.45	0.47
Ply4_90°	3.81	3.95	4.56	6.83	6.89	8.81	0.86	0.84	0.77
Ply5_45°	2.11	1.60	1.67	3.45	2.54	3.28	0.95	0.97	0.93
Ply6_-45°	2.17	2.30	1.60	3.70	3.92	3.04	0.94	0.94	0.94

Table 4

Fig.14

Fig.15

Fig.16

Fig.17

Fig.18

Fig.19

Fig.20

Fig.21

Table 5

Fig.22

Fig.23

Table 6

Table 7

Prediction results of neural network model and random forest regression model

方法	MAE	RMSE	$R 2$	时间误差/s	训练时间/s
ANNs#1 （9特征）	55.434 9	83.152 3	0.302 3	10.672	126.866
ANNs#1 （42特征）	55.434 4	83.151 6	0.302 5	10.672	129.301
ANNs#2 （9特征）	7.492 1	11.238 1	0.765	3.557	170.167
ANNs#2 （42特征）	5.062 9	7.594 4	0.884	1.678	123.185
随机森林回归模型	2.212	3.583	0.955	0.238	6.977

Table 7

Fig.24

References 34

1	牛春匀. 实用飞机复合材料结构设计与制造［M］. 程小全，张纪奎，译. 北京：航空工业出版社， 2010： 20-25.
	NIU C Y. Design and manufacturing of practical aircraft composite structure［M］. CHENG X Q， ZHANG J K， translated. Beijing： Aviation Industry Press， 2010： 20-25 （in Chinese）.
2	古托夫斯基 T G. 先进复合材料制造技术［M］. 李宏运，译. 北京：化工工业出版社， 2004： 30-36.
	GUTOWSKI T G. Advanced composite material manufacturing technology［M］. LI H Y， translated. Beijing： Chemical Industry Press， 2004： 30-36 （in Chinese）.
3	杜善义. 先进复合材料与航空航天［J］. 复合材料学报， 2007， 24（1）： 1-12.
	DU S Y. Advanced composite materials and aerospace engineering［J］. Acta Materiae Compositae Sinica， 2007， 24（1）： 1-12 （in Chinese）.
4	FREEMAN W T. The use of composites in aircraft primary structure［J］. Composites Engineering， 1993， 3（7-8）： 767-775.
5	贾振元，肖军，湛利华，等. 大型航空复合材料承力构件制造关键技术［J］. 中国基础科学， 2019， 21（2）： 20-27.
	JIA Z Y， XIAO J， ZHAN L H， et al. Research of large aviation and loading-bearing composite components manufacturing［J］. China Basic Science， 2019， 21（2）： 20-27 （in Chinese）.
6	杜善义，关志东. 我国大型客机先进复合材料技术应对策略思考［J］. 复合材料学报， 2008， 25（1）： 1-10.
	DU S Y， GUAN Z D. Strategic considerations for development of advanced composite technology for large commercial aircraft in China［J］. Acta Materiae Compositae Sinica， 2008， 25（1）： 1-10 （in Chinese）.
7	DHINAKARAN V， SURENDAR K V， HASUNFUR RIYAZ M S， et al. Review on study of thermosetting and thermoplastic materials in the automated fiber placement process［J］. Materials Today： Proceedings， 2020， 27： 812-815.
8	肖军，李勇，文立伟，等. 树脂基复合材料自动铺放技术进展［J］. 中国材料进展， 2009， 28（6）： 28-32.
	XIAO J， LI Y， WEN L W， et al. Progress of automated placement technology for polymer composites［J］. Materials China， 2009， 28（6）： 28-32 （in Chinese）.
9	FRKETIC J， DICKENS T， RAMAKRISHNAN S. Automated manufacturing and processing of fiber-reinforced polymer （FRP） composites： An additive review of contemporary and modern techniques for advanced materials manufacturing［J］. Additive Manufacturing， 2017， 14： 69-86.
10	KOZACZUK K. Automated fiber placement systems overview［J］. Transactionsofthe Institute of Aviation， 2016， 245（4）： 52-59.
11	方宜武. 基于测地线算法的复合材料翼梁自动铺丝技术研究［D］. 南京：南京航空航天大学， 2014： 15-20.
	FANG Y W. Research on automated fiber placement technology of composite wing spar based on geodesic algorithm［D］. Nanjing： Nanjing University of Aeronautics and Astronautics， 2014： 15-20 （in Chinese）.
12	文立伟，肖军，王显峰，等. 中国复合材料自动铺放技术研究进展［J］. 南京航空航天大学学报， 2015， 47（5）： 637-649.
	WEN L W， XIAO J， WANG X F， et al. Progress of automated placement technology for composites in China［J］. Journal of Nanjing University of Aeronautics & Astronautics， 2015， 47（5）： 637-649 （in Chinese）.
13	张建宝，赵文宇，王俊锋，等. 复合材料自动铺放工艺技术研究现状［J］. 航空制造技术， 2014， 57（16）： 80-83， 94.
	ZHANG J B， ZHAO W Y， WANG J F， et al. Research status of automated placement processing technology of composites［J］. Aeronautical Manufacturing Technology， 2014， 57（16）： 80-83， 94 （in Chinese）.
14	DENKENA B， SCHMIDT C， WEBER P. Automated fiber placement head for manufacturing of innovative aerospace stiffening structures［J］. Procedia Manufacturing， 2016， 6： 96-104.
15	肖海涛. 面向五轴数控加工的刀具位姿优化及线性插补算法研究［D］. 杭州：浙江大学， 2019： 83-117.
	XIAO H T. Research on optimization and linear interpolation of CL data for five-axis CNC machining［D］. Hangzhou： Zhejiang University， 2019： 83-117 （in Chinese）.
16	ERKORKMAZ K， YEUNG C H， ALTINTAS Y. Virtual CNC system. Part II. High speed contouring application［J］. International Journal of Machine Tools and Manufacture， 2006， 46（10）： 1124-1138.
17	TULSYAN S. Prediction and reduction of cycle time for five-axis CNC machine tools［D］. Vancouver： University of British Columbia， 2014： 63-110.
18	LIN M T， TSAI M S， YAU H T. Development of a dynamics-based NURBS interpolator with real-time look-ahead algorithm［J］. International Journal of Machine Tools and Manufacture， 2007， 47（15）： 2246-2262.
19	BEUDAERT X， LAVERNHE S， TOURNIER C. Feedrate interpolation with axis jerk constraints on 5-axis NURBS and G1 tool path［J］. International Journal of Machine Tools and Manufacture， 2012， 57： 73-82.
20	张盼盼，吴凤彪，张子英. 高精度数控机床非均匀有理B样条曲线插补控制研究［J］. 机械制造， 2020， 58（3）： 59-61， 70.
	ZHANG P P， WU F B， ZHANG Z Y. Research on interpolation control of non-uniform rational B-spline curve of high precision CNC machine tool［J］. Machinery， 2020， 58（3）： 59-61， 70 （in Chinese）.
21	何文杰. 五轴双NURBS刀具路径拟合及其插补算法研究［D］. 合肥：合肥工业大学， 2018： 23-104.
	HE W J. Study on five-axis dual NURBS tool path fitting and its interpolation algorithm［D］. Hefei： Hefei University of Technology， 2018： 23-104 （in Chinese）.
22	宁志豪，周璐雨，陈豪文. 浅谈机器学习与深度学习的概要及应用［J］. 科技风， 2019（15）： 19.
	NING Z H， ZHOU L Y， CHEN H W. Brief introduction and application of machine learning and deep learning［J］. Technology Wind， 2019（15）： 19 （in Chinese）.
23	HORNIK K. Approximation capabilities of multilayer feedforward networks［J］. Neural Networks， 1991， 4（2）： 251-257.
24	CHEN S， BILLINGS S A. Neural networks for nonlinear dynamic system modelling and identification［J］. International Journal of Control， 1992， 56（2）： 319-346.
25	SUN C， DOMINGUEZ-CABALLERO J， WARD R， et al. Machining cycle time prediction： Data-driven modelling of machine tool feedrate behavior with neural networks［J］. Robotics and Computer-Integrated Manufacturing， 2022， 75： 102293.
26	张煜东，吴乐南，吴含前. 工程优化问题中神经网络与进化算法的比较［J］. 计算机工程与应用， 2009， 45（3）： 1-6.
	ZHANG Y D， WU L N， WU H Q. Comparison of neural network and evolutionary algorithm on engineering optimization［J］. Computer Engineering and Applications， 2009， 45（3）： 1-6 （in Chinese）.
27	LOH W Y. Classification and regression trees［J］. WIREs Data Mining and Knowledge Discovery， 2011， 1（1）： 14-23.
28	ALPAYDIN E. Introduction to machine learning［M］. 3rd ed. Boston： MIT Press， 2014： 21-63.
29	BREIMAN L. Bagging predictors［J］. Machine Learning， 1996， 24（2）： 123-140.
30	LIAW A， WIENER M. Classification and regression by randomForest［J］. R news， 2002， 2（3）： 18-22.
31	PETERS J， DE BAETS B， VERHOEST N E C， et al. Random forests as a tool for ecohydrological distribution modelling［J］. Ecological Modelling， 2007， 207（2-4）： 304-318.
32	李艳，李英浩，高峰，等. 基于互信息法和改进模糊聚类的温度测点优化［J］. 仪器仪表学报， 2015， 36（11）： 2466-2472.
	LI Y， LI Y H， GAO F， et al. Investigation on optimization of temperature measurement key points based on mutual information and improved fuzzy clustering analysis［J］. Chinese Journal of Scientific Instrument， 2015， 36（11）： 2466-2472 （in Chinese）.
33	CRAIG J J. 机器人学导论［M］. 贠超，译. 北京：机械工业出版社， 2018： 55-120
	CRAIG J J. Introduction to robotics［M］. YUN C， translated.Beijing： China Machine Press， 2018： 55-120 （in Chinese）.
34	LI L N， WANG X G， XU D， et al. A placement path planning algorithm based on meshed triangles for carbon fiber reinforce composite component with revolved shape［J］. International Journal on Control Systems and Applications， 2014， 1（1）： 23-32.

状态	褶皱数量	褶皱平均长度/mm	褶皱平均高度/mm	位置偏差均值/mm
优化前	22	5.71	0.94	1.87
优化后	4	2.12	0.33	0.24

状态	褶皱数量	褶皱平均长度/mm	褶皱平均高度/mm	位置偏差均值/mm
优化前	27	8.75	0.88	1.85
优化后	9	2.26	0.31	0.40

[1]	Miaojiao PENG, Jinwen HUANG, Dianyin HU, Rongqiao WANG, Junjie YANG, Zhigang JIA, Qinglin CHEN, Yifeng SUN, Yingqiang CAI, Kuan FAN, Zhaoyi ZHU, Xiaowen LI. Research progress on interfacial mechanical properties, damage mechanisms, and reinforcement strategies of CFRP composites for aero-engines [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(16): 231600-231600.
[2]	Chen LIU, Chen HE, Wenming GAO, Xianfeng WANG, Lin JIANG, Shuo CHENG, Yong LI, Jun XIAO. Dual scale ply design of composite aircraft auxiliary fuel tank [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(1): 230541-230541.
[3]	Zhiting GAO, Zhuang MA, Yanbo LIU. Effect of CVD-SiC array structure on ablation resistance of ZrB₂/SiC coatings [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(3): 428842-428842.
[4]	Jiqiang GAN, Xiaoping WANG. Surface defect detection of fiber placement based on virtual sample generation [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(1): 428624-428624.
[5]	Jian HAN, Shiyong SUN, Bin NIU, Rui YANG, Dongjiang WU. Progress in manufacturing technologies of resin⁃based composite lattice structures [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(9): 628255-628255.
[6]	Liping LIU, Yuyang QI, Yueguo LIN, Rui BAO, Jianxin XU, Zhenyu FENG, Guanghui QING. Tensile failure of carbon fiber composite material bonded-rivet hybrid repaired structure [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(24): 428676-428676.
[7]	WAN Aoshuang. Probabilistic assessment on damage tolerance of composite helicopter horizontal tail structure [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 525557-525557.
[8]	ZHANG Junrui, ZHENG Xitao, YUAN Lin, ZHONG Guiyong, LI Guochen. Fatigue life prediction method for hybrid multi-bolted joints based on damage weight [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(5): 524306-524306.
[9]	WANG Binwen, AI Sen, ZHANG Guofan, NIE Xiaohua, WU Cunli. Validation method for post-buckling analysis model of stiffened composite panels considering uncertainties [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(8): 223987-223987.
[10]	XIE Linshan, CHEN Haoran, WANG Haoyu. Placement suitability of T700 carbon fiber/bismaleimide resin prepreg for complex rotary bodies in AFP [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(4): 423279-423279.
[11]	DONG Anqi, ZHAO Xinqing, ZHAO Yan. Tension-tension fatigue performance of unidirectional out-of-autoclave composite manufactured by automated fiber placement [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(2): 421422-421422.
[12]	LIU Yongjiao, WANG Xianfeng, XIAO Jun. Trajectory planning method for constant geodesic curvature curve of cone [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2017, 38(7): 420904-420904.
[13]	WANG Xiaoming, ZHOU Wenya, WU Zhigang. Dynamic shape control of wings using piezoelectric fiber composite materials [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2017, 38(1): 220313-220313.
[14]	ZHAO Cong, XIAO Jun, WANG Xianfeng, LI Junfei, HUANG Wei. Effects of tows tension on automated fiber placement process [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2016, 37(4): 1384-1392.
[15]	LIU Jianming, WAN Xiaopeng, ZHAO Meiying. Fatigue life prediction of laminated bolted joint structures [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2015, 36(6): 1867-1875.

Prediction and planning of automatic laying speed for fiber reinforced composite materials based on data⁃driven model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 31

References 34

Related Articles 15

Recommended Articles

Metrics

Comments