Axial Compressive Capacity Prediction of CFRST Columns Based on PSO-BP Neural Network

ZHANG Yunlong; HE Yuzhou; DU Guofeng; ZHANG Juan

doi:10.3724/j.gyjzG23121108

Volume 54 Issue 9

Sep. 2024

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2024 > 54(9): 141-148

ZHANG Yunlong, HE Yuzhou, DU Guofeng, ZHANG Juan. Axial Compressive Capacity Prediction of CFRST Columns Based on PSO-BP Neural Network[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(9): 141-148. doi: 10.3724/j.gyjzG23121108

Citation:

ZHANG Yunlong, HE Yuzhou, DU Guofeng, ZHANG Juan. Axial Compressive Capacity Prediction of CFRST Columns Based on PSO-BP Neural Network[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(9): 141-148. doi: 10.3724/j.gyjzG23121108

Citation:

PDF( 4837 KB)

Axial Compressive Capacity Prediction of CFRST Columns Based on PSO-BP Neural Network

doi: 10.3724/j.gyjzG23121108

School of Urban Construction, Yangtze University, Jingzhou 434000, China

Received Date: 2023-12-11
Available Online: 2024-10-18

Abstract

Abstract

The traditional back propagation (BP) neural network has some defects in predicting the axial compressive capacity of concrete-filled rectangular steel tube (CFRST), such as system instability, slow convergence speed and difficult selection of hyperparameters, which will affect the stability of the prediction model and the accuracy of the prediction results. In order to improve the traditional BP model to achieve better prediction effect, particle swarm optimization algorithm (PSO) was applied to BP prediction model, and a CFRST axial compressive capacity prediction model PB7-7-1 based on PSO-BP neural network was proposed. The results showed that the fluctuation range of the predicted values of the PB7-7-1 model was substantially reduced compared with that of the traditional BP model, in which the absolute relative error (ARE) of the predicted values of 45% of the components was within 5%, and the ARE of 80% of the components was within 10%; prediction accuracy of the PB7-7-1 model had been improved by 30.79%, and the average ARE of its predictive values was only 6%. This showed that the PB7-7-1 model based on PSO-BP neural network had a significant improvement in the stability and accuracy of prediction results of CFRST axial compressive capacity compared with traditional BP network. In addition, according to the weight and bias of the hidden layer and output layer of PB7-7-1 model, the prediction formula of CFRST axial compressive capacity was constructed. Finally, SHAP machine learning interpretation algorithm was used to analyze the importance and contribution of each input parameter to the axial compressive capacity.

FullText(HTML)

References(33)

References

[1]	韩林海, 陶忠, 刘威. 钢管混凝土结构:理论与实践[J]. 福州大学学报(自然科学版), 2001(6): 24-34.
[2]	马骐, 曾希, 雷震, 等. 轴向冲击荷载下L形截面钢管混凝土短柱受力性能[J]. 科学技术与工程, 2020, 20(8): 3170-3178.
[3]	刘子丹, 焦文帅, 程展, 等. 钢骨不锈钢管超高性能混凝土柱轴压性能研究[J]. 工业建筑, 2023, 53(5): 17-27.
[4]	刘坚, 招渝, 王飞程, 等. 钢管约束型钢混凝土圆柱承载力的神经网络分析模型研究[J]. 工业建筑, 2022, 52(9): 147-152 ,120.
[5]	朱美春, 王清湘, 冯秀峰. 方钢管混凝土短柱轴心受压承载力的神经网络模拟[J]. 计算力学学报, 2006(3): 353-356.
[6]	陆征然, 赵婉东, 郭超. 基于BP神经网络的缺陷CFST短柱承载力预测[J]. 沈阳建筑大学学报(自然科学版), 2021, 37(4): 702-708.
[7]	赵明. 基于神经网络的矩形钢管混凝土柱承载性能研究[D]. 天津: 天津大学, 2014.
[8]	PANDA S, PANDA G. Fast and improved back propagation learning of multi-layer artificial neural network using adaptive activation function[J]. Expert Systems, 2020, 37(5), e12555.
[9]	尚宇, 杨妮. 改进粒子群优化BP神经网络的心理压力识别算法[J]. 科学技术与工程, 2020,20(4): 1467-1472.
[10]	刘伟吉, 冯嘉豪, 祝效华, 等. 基于动量自适应学习率PSO-BP神经网络的钻速预测模型研究[J]. 科学技术与工程, 2023, 23(24): 10264-10272.
[11]	SOUSA-FERREIRA I, SOUSA D. A review of velocity-type PSO variants[J]. Journal of Algorithms & Computational Technology, 2017, 11(1):23-30.
[12]	THANGARAJ R, PANT M, ABRAHAM A, et al. Par-ticle swarm optimization: hybridization persp-ectives and experimental illustrations[J]. Applied Mathematics and Computation, 2011, 217(12): 5208-5226.
[13]	高峰, 冯民权, 滕素芬. 基于PSO优化BP神经网络的水质预测研究[J]. 安全与环境学报, 2015, 15(4): 338-341.
[14]	叶再利. 方形、矩形钢管高强混凝土轴压短柱基本力学性能研究[D] 哈尔滨: 哈尔滨工业大学, 2003.
[15]	Đ-DORDEVIĆ F, KOSTIĆ S M. Practical ANN prediction models for the axial capacity of square CFST columns[J]. Journal of Big Data, 2023, 10(1): 1-22.
[16]	韩林海, 陶忠. 方钢管混凝土轴压力学性能的理论分析与试验研究[J]. 土木工程学报, 2001(2): 17-25.
[17]	韩林海, 杨有福. 矩形钢管混凝土轴心受压构件强度承载力的试验研究[J]. 土木工程学报, 2001(4): 22-31.
[18]	周凯凯. 方钢管超高性能混凝土短柱轴心受压性能研究[D]. 武汉: 武汉大学, 2018.
[19]	杜颜胜.高强钢矩形钢管混凝土柱理论分析及试验研究[D]. 天津: 天津大学, 2017.
[20]	高金良, 姚民乐. 轴心受压矩形钢管混凝土短柱承载力研究[J]. 建筑材料学报, 2006 (6): 716-719.
[21]	曲秀姝, 刘琦. 矩形钢管混凝土柱轴压性能研究[J]. 建筑科学, 2018, 34(3): 37-42.
[22]	杨有福, 韩林海.混凝土密实度对矩形钢管混凝土短柱力学性能影响研究[J]. 工业建筑, 2004,34(8): 62-65.
[23]	张忠杰. 矩形薄壁钢管混凝土短柱轴心受压性能试验研究[D]. 烟台: 烟台大学, 2020.
[24]	史义博. 矩形钢管混凝土轴压短柱研究[J]. 山西建筑, 2012, 38(33): 63-65.
[25]	郝艳娥, 刘雅君, 杨红霞. 矩形钢管混凝土轴压短柱极限承载力多元线性回归分析[J]. 科学技术与工程, 2010, 10(24): 6066-6070.
[26]	张素梅, 郭兰慧, 叶再利, 等. 方钢管高强混凝土轴压短柱的试验研究[J]. 哈尔滨工业大学学报, 2004(12): 1610-1614.
[27]	陶忠, 韦灼彬, 韩林海.方钢管混凝土轴心受压稳定承载力的研究[J]. 工业建筑, 1998,29(10):10-14.
[28]	LIU D, GHO W M. Axial load behaviour of high-strength rectangular concrete-filled steel tubular stub columns[J]. Thin-Walled Structures,2005, 43(8): 1131-1142.
[29]	SAKINO K, NAKAHARA H, MORINO S, et al. Behavior of centrally loaded concrete-filled steel-tube short columns[J]. Journal of Structural Engineering, 2004, 130(2): 180-188.
[30]	徐迪. 方钢管混凝土短柱轴压性能分析[D]. 武汉: 武汉理工大学, 2007.
[31]	沈花玉, 王兆霞, 高成耀, 等. BP神经网络隐含层单元数的确定[J]. 天津理工大学学报, 2008, 91(5): 13-15.
[32]	陈铮衍, 林逸珊, 谢佳晖, 等. 传统村落旅游地景观品质对空间活力影响作用研究:基于多源数据与机器学习的平潭县北港村实证[J/OL]. 工业建筑,2023,53[2023-12-04 ].https://link.cnki.net/urlid/11.2068.TU.20231204.1037.002.
[33]	LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[J]. Advances in Neural Information Processing Systems, 2017, 30:4766-4775.