Research on first-ply failure prediction of fiberglass reinforced plastic pipes based on PSO-BP neural network

doi:10.19936/j.cnki.2096-8000.20230928.009

Abstract

Abstract: Predicting the first-ply failure of fiberglass reinforced plastic (FRP) pipe is essential to ensure service safety in water conveyance projects. In this research, a particle swarm algorithm optimized backpropagation neural network (PSO-BP) is used to predict the first-ply failure of FRP pipe under biaxial stress. Experimental data verify the prediction results of the PSO-BP model as well. The results illustrated that the average prediction accuracy of the PSO-BP neural network model for the first-ply failure of the FRP pipe could reach more than 85%, which has advantages over the control backpropagation neural network model regarding convergence and accuracy. The plotted biaxial failure envelopes of axial and hoop stresses showed that the failure envelopes predicted by the PSO-BP model are very close to the failure envelopes measured in the test. The predicted failure envelopes are primarily located in the test failure envelopes. Most of the predicted failure envelope is located inside the test failure one. Therefore, the model is a rational safety prediction model, which can be used as an effective approach to identify FRP pipes before they are qualified according to the specification.

Key words: fiberglass reinforced plastic pipe, particle swarm optimization backpropagation neural network, glass fiber, composite pipes, pipe failure

CLC Number:

TB332

LI Yuanhao, HU Shaowei, SHAN Changxi, MU Zhao, PAN Fuqu, LI Jiang. Research on first-ply failure prediction of fiberglass reinforced plastic pipes based on PSO-BP neural network[J]. COMPOSITES SCIENCE AND ENGINEERING, 2023, 0(9): 61-66.

References

[1] 付成华, 周洪波. 玻璃钢管在水电站压力管道中的应用复核分析[J]. 西华大学学报(自然科学版), 2015, 34(4): 80-82, 92.
[2] FITRIAH S N, MAJID M A, RIDZUAN M, et al. Influence of hydrothermal ageing on the compressive behaviour of glass fibre/epoxy composite pipes[J]. Composite Structures, 2017, 159(1): 350-360.
[3] 倪爱清, 朱以文, 王继辉. 缠绕角对复合材料内压管强度的影响[J]. 武汉理工大学学报, 2006, 28(3): 4-7.
[4] FARSHAD M, NECOLA A. Effect of aqueous environment on the long-term behavior of glass fiber-reinforced plastic pipes[J]. Polymer Testing, 2004, 23(2): 163-167.
[5] FROST S R, CERVENKA A. Glass fibre-reinforced epoxy matrix filament-wound pipes for use in the oil industry[J]. Composites Manufacturing, 1994, 5(2): 73-81.
[6] 喻西崇, 赵金洲, 吴应湘, 等. 利用改进的神经网络预测腐蚀管道的剩余强度[J]. 压力容器, 2003(10): 22-27.
[7] 徐鲁帅, 凌晓, 马娟娟, 等. 基于DE-BPNN模型的含腐蚀缺陷管道失效压力预测[J]. 中国安全生产科学技术, 2021, 17(3): 91-96.
[8] 宋春山, 林立邦, 韩红卫, 等. 基于BP神经网络的黑龙江漠河段冰坝预测[J]. 水利水运工程学报, 2021(2): 57-63.
[9] EBERHART R, KENNEDY J. A new optimizer using particle swarm theory[C]//MHS95 Sixth International Symposium on Micro Machine & Human Science. IEEE, 2002.
[10] KENNEDY J, EBERHART R. Particle swarm optimization[C]//ICNN95-International Conference on Neural Networks. IEEE, 2002.
[11] 徐鹍鹏, 惠虎. 基于Tsai-Hill理论环氧玻璃钢管的强度分析[J]. 化工进展, 2016, 35(12): 3799-3806.
[12] 耿沛, 邢静忠, 陈晓霞. 纤维螺旋缠绕管的缠绕角优化[J]. 纺织学报, 2017, 38(1): 61-66.
[13] RAFIEE R, AMINI A. Modeling and experimental evaluation of functional failure pressures in glass fiber reinforced polyester pipes[J]. Computational Materials Science, 2014, 96(partB): 579-588.
[14] SODEN P D, KITCHING R, TSE P C. Experimental failure stresses for ±55° filament wound glass fibre reinforced plastic tubes under biaxial loads[J]. Composites, 1989, 20(2): 125-135.
[15] ANG J Y, MAJID M, NOR A M, et al. First-ply failure prediction of glass/epoxy composite pipes using an artificial neural network model[J]. Composite Structures, 2018, 200(9): 579-588.
[16] MAJID M, ASSALEH T A, GIBSON A G, et al. Ultimate elastic wall stress (UEWS) test of glass fibre reinforced epoxy (GRE) pipe[J]. Composites Part A: Applied Science and Manufacturing, 2011, 42(10): 1500-1508.
[17] SODEN P D, KITCHING R, TSE P C, et al. Influence of winding angle on the strength and deformation of filament-wound composite tubes subjected to uniaxial and biaxial loads[J]. Composites Science and Technology, 1993, 46(4): 363-378.
[18] 叶鸥, 张璟, 李军怀. 中文数据清洗研究综述[J]. 计算机工程与应用, 2012, 48(14): 121-129.
[19] KRISHNAN P, MAJID M, AFENDI M, ET AL. Effects of winding angle on the behaviour of glass/epoxy pipes under multiaxial cyclic loading[J]. Materials & Design, 2015, 88(25): 196-206.