Prediction of blast loads on bridge girders based on PCA-BPNN

DU Xiaoqing; HE Yiping; QIU Tao; CHENG Shuai; ZHANG Dezhi

doi:10.11883/bzycj-2023-0343

Volume 45 Issue 3

Mar. 2025

Turn off MathJax

Article Contents

Abstract

References

Article Navigation > Explosion And Shock Waves > 2025 > 45(3): 033201

DU Xiaoqing, HE Yiping, QIU Tao, CHENG Shuai, ZHANG Dezhi. Prediction of blast loads on bridge girders based on PCA-BPNN[J]. Explosion And Shock Waves, 2025, 45(3): 033201. doi: 10.11883/bzycj-2023-0343

Citation:

DU Xiaoqing, HE Yiping, QIU Tao, CHENG Shuai, ZHANG Dezhi. Prediction of blast loads on bridge girders based on PCA-BPNN[J]. Explosion And Shock Waves, 2025, 45(3): 033201. doi: 10.11883/bzycj-2023-0343

Citation:

PDF( 4250 KB)

Prediction of blast loads on bridge girders based on PCA-BPNN

doi: 10.11883/bzycj-2023-0343

1.
School of Mechanics and Engineering Science, Shanghai University, Shanghai 200444, China
2.
Northwest Institute of Nuclear Technology, Xi’an 710024, Shaanxi, China

Received Date: 2023-09-26
Rev Recd Date: 2024-04-19

Available Online: 2024-04-19

Publish Date: 2025-03-05

Abstract

Abstract

Facing the challenges on the accurate and effective prediction under extreme loads, machine learning has gradually demonstrated its potential to replace traditional methods. Existing approaches primarily focus on predicting the peak overpressure or impulse of explosive shock waves, with limited research on predicting the reflected overpressure time history. Load-time history prediction encompasses not only the peak overpressure but also embraces various multi-dimensional information including duration, waveform, and impulse, thereby offering a more comprehensive depiction of the dynamic temporal and spatial characteristics of shock waves. To address this issue, a prediction model for bridge surface reflected overpressure time history is proposed, targeting a planar shock wave diffracting around a bridge section. This model is based on principal component analysis (PCA) and back propagation neural network (BPNN) algorithm with multi-task learning. A loss function considering the impact of peak overpressure and maximum impulse is introduced to fully consider the potential correlations between different modes after PCA dimension reduction. This enables the model to effectively predict bridge shock wave load time histories under varying incident overpressure. Through the analysis of three types of BPNN models, multi-task learning model, multi-input single-output model, and multi-input multi-output model. It was found that the multitask learning model has the highest prediction accuracy, while the multi-input multi-output model struggles to effectively adapt to the current predictive task requirements. The multitask learning model, used for predicting, achieves high precision in forecasting the time history of reflected overpressure at various measurement points on the bridge surface and the peak overpressure values, with R² values of 0.792 and 0.987. It also closely matches the simulation values in predicting the time history of combined forces and torque acting on the box girder. Additionally, this model performs better in interpolative value prediction than in extrapolative value prediction, but it also demonstrates a certain capability in predicting extrapolative values.
- explosion load prediction,
- reflected overpressure time history,
- back propagation neural network,
- principal components analysis,
- multi-task learning

FullText(HTML)

References(27)

References

[1]	CLUBLEY S K. Non-linear long duration blast loading of cylindrical shell structures [J]. Engineering Structures, 2014, 59: 113–126. DOI: 10.1016/j.engstruct.2013.10.030.
[2]	DENNY J W, CLUBLEY S K. Long-duration blast loading & response of steel column sections at different angles of incidence [J]. Engineering Structures, 2019, 178: 331–342. DOI: 10.1016/j.engstruct.2018.10.019.
[3]	JIANG Y X, ZHANG B Y, WANG L, et al. Dynamic response of polyurea coated thin steel storage tank to long duration blast loadings [J]. Thin-Walled Structures, 2021, 163: 107747. DOI: 10.1016/j.tws.2021.107747.
[4]	SAKURAI A. Blast wave theory [M]. Mathematics Research Center, United States Army, University of Wisconsin, 1964.
[5]	RIGBY S E, AKINTARO O I, FULLER B J, et al. Predicting the response of plates subjected to near-field explosions using an energy equivalent impulse [J]. International Journal of Impact Engineering, 2019, 128(1): 24–36. DOI: 10.1016/j.ijimpeng.2019.01.014.
[6]	KINGERY C N, BULMASH G. Airblast parameters from TNT spherical air burst and hemispherical surface burst [R]. US Army Armament and Development Center, Ballistic Research Laboratory, 1984.
[7]	RIGBY S E, TYAS A, FAY S D, et al. Validation of semiempirical blast pressure predictions for far field explosions: is there inherent variability in blast wave parameters? [C]//Proceedings of the 6th International Conference on Protection of Structures Against Hazards. Sheffield, 2014.
[8]	LARCHER M, CASADEI F. Explosions in complex geometries: a comparison of several approaches [J]. International Journal of Protective Structures, 2010, 1(2): 169–195. DOI: 10.1260/2041-4196.1.2.169.
[9]	DENNIS A A, PANNELL J J, SMYL D J, et al. Prediction of blast loading in an internal environment using artificial neural networks [J]. International Journal of Protective Structures, 2021, 12(3): 287–314. DOI: 10.1177/2041419620970570.
[10]	HANSEN O R, HINZE P, ENGEL D, et al. Using computational fluid dynamics (CFD) for blast wave predictions [J]. Journal of Loss Prevention in the Process Industries, 2010, 23(6): 885–906. DOI: 10.1016/j.jlp.2010.07.005.
[11]	REMENNIKOV A M, ROSE T A. Modelling blast loads on buildings in complex city geometries [J]. Computers & Structures, 2005, 83(27): 2197–2205. DOI: 10.1016/j.compstruc.2005.04.003.
[12]	SOHAIMI A S M, RISBY M S. Using computational fluid dynamics (CFD) for blast wave propagation under structure [J]. Procedia Computer Science, 2016, 80: 1202–1211. DOI: 10.1016/j.procs.2016.05.463.
[13]	HASTIE T, TIBSHIRANI R, FRIEDMAN J H, et al. The elements of statistical learning: data mining, inference, and prediction [M]. New York: Springer, 2009.
[14]	FLOOD I, BEWICK B T, DINAN R J, et al. Modeling blast wave propagation using artificial neural network methods [J]. Advanced Engineering Informatics, 2009, 23(4): 418–423. DOI: 10.1016/j.aei.2009.06.005.
[15]	REMENNIKOV A M, ROSE T A. Predicting the effectiveness of blast wall barriers using neural networks [J]. International Journal of Impact Engineering, 2007, 34(12): 1907–1923. DOI: 10.1016/j.ijimpeng.2006.11.003.
[16]	BEWICK B, FLOOD I, CHEN Z. A neural-network model-based engineering tool for blast wall protection of structures [J]. International Journal of Protective Structures, 2011, 2(2): 159–176. DOI: 10.1260/2041-4196.2.2.159.
[17]	ALSHAMMARI O G, ISAAC O S, CLARKE S D, et al. Mitigation of blast loading through blast-obstacle interaction [J]. International Journal of Protective Structures, 2023, 14(3): 357–389. DOI: 10.1177/20414196221115869.
[18]	PANNELL J J, RIGBY S E, PANOUTSOS G. Physics-informed regularisation procedure in neural networks: an application in blast protection engineering [J]. International Journal of Protective Structures, 2022, 13(3): 555–578. DOI: 10.1177/20414196211073501.
[19]	PANNELL J J, RIGBY S E, PANOUTSOS G. Application of transfer learning for the prediction of blast impulse [J]. International Journal of Protective Structures, 2023, 14(2): 242–262. DOI: 10.177/20414196221096699.
[20]	LI Q L, WANG Y, SHAO Y D, et al. A comparative study on the most effective machine learning model for blast loading prediction: from GBDT to transformer [J]. Engineering Structures, 2023, 276: 115310. DOI: 10.1016/j.engstruct.2022.115310.
[21]	LI Q L, WANG Y, LI L, et al. Prediction of BLEVE loads on structures using machine learning and CFD [J]. Process Safety and Environmental Protection, 2023, 171: 914–925. DOI: 10.1016/j.psep.2023.02.008.
[22]	HUANG Y, ZHU S J, CHEN S W. Deep learning-driven super-resolution reconstruction of two-dimensional explosion pressure fields [J]. Journal of Building Engineering, 2023, 78: 107620. DOI: 10.1016/j.jobe.2023.107620.
[23]	孙传猛, 裴东兴, 陈嘉欣, 等. 基于深度学习的爆炸冲击波信号重构模型 [J]. 计测技术, 2022, 42(2): 57–67. DOI: 10.11823/j.issn.1674-5795.2022.02.07. SUN C M, PEI D X, CHEN J X, et al. Model for reconstruction of explosion shock wave signals based on deep learning [J]. Measurement Technology, 2022, 42(2): 57–67. DOI: 10.11823/j.issn.1674-5795.2022.02.07.
[24]	QIU T, CHENG S, DU X Q, et al. Spacing effects on blast loading characteristics of two tandem square columns under planar shock waves [J]. Physics of Fluids, 2023, 35(12): 127116. DOI: 10.1063/5.0177869.
[25]	KARLOS V, LARCHER M, SOLOMOS G. Analysis of the blast wave decay coefficient in the Friedlander equation using the Kingery-Bulmash data [R]. Joint Research Center, European Commission, 2015.
[26]	ZHOU Z H. Machine learning [M]. Springer Nature, 2021. DOI: 10.1007/978-981-15-1967-3.
[27]	MISRA D. Mish: a self-regularized non-monotonic activation function[R]. British Machine Vision Conference, 2019. DOI: 10.48550/arXiv.1908.08681.

Relative Articles

[1]	CHEN Ziwei, WANG Zhongqi, ZENG Linghui. A method for predicting peak pressure in an explosion shock tube based on BP neural network[J]. Explosion And Shock Waves, 2024, 44(5): 054101. doi: 10.11883/bzycj-2023-0187
[2]	LI Yanchao, LIANG Bo, JIANG Yuting. Prediction of natural gas explosion overpressure considering external turbulence[J]. Explosion And Shock Waves, 2023, 43(11): 115402. doi: 10.11883/bzycj-2023-0098
[3]	LIU Bowen, LONG Renrong, ZHANG Qingming, JU Yuanyuan, ZHONG Xianzhe, WANG Haiyang, LIU Wenjin. Study on the corner overpressure characteristics of concentrated reflected shock wave due to internal blast in cabin[J]. Explosion And Shock Waves, 2023, 43(1): 012201. doi: 10.11883/bzycj-2022-0232
[4]	LI Qinchao, YAO Chengbao, CHENG Shuai, ZHANG Dezhi, LIU Wenxiang. Application of the neural network equation of state in numerical simulation of intense blast wave[J]. Explosion And Shock Waves, 2023, 43(4): 044202. doi: 10.11883/bzycj-2022-0222
[5]	LUO Haoshun, NIU Huanhuan, WANG Mufei, CHEN Jiajun, LI Zhiqiang. Impact response of transparent ceramic sandwich structures and its prediction by BP neural network[J]. Explosion And Shock Waves, 2023, 43(10): 103103. doi: 10.11883/bzycj-2022-0199
[6]	LI Jingye, JIANG Xinsheng, YU Binbin, WANG Chunhui, WANG Zituo. Visualization experimental research of oil gas vapor cloud deflagration in large-scale unconfined space[J]. Explosion And Shock Waves, 2022, 42(3): 035401. doi: 10.11883/bzycj-2021-0176
[7]	LI Yanchao, BI Mingshu, GAO Wei. Theoretical prediction of hydrogen cloud explosion overpressure considering self-accelerating flame propagation[J]. Explosion And Shock Waves, 2021, 41(7): 072101. doi: 10.11883/bzycj-2020-0140
[8]	HE Li, ZHONG Dongwang, LI Peng, SONG Kun, SI Jianfeng. Vibration prediction and energy analysis of slope under blasting load in underpass tunnel[J]. Explosion And Shock Waves, 2020, 40(7): 075201. doi: 10.11883/bzycj-2019-0255
[9]	LI Yanchao, BI Mingshu, GAO Wei. Explosion pressure prediction considering the flame instabilities[J]. Explosion And Shock Waves, 2020, 40(1): 012101. doi: 10.11883/bzycj-2019-0004
[10]	QIN Yi, CHEN Xiaowei, HUANG Wei. Overpressure prediction of combustible gas explosion in confined space[J]. Explosion And Shock Waves, 2020, 40(3): 032202. doi: 10.11883/bzycj-2019-0175
[11]	YI Wenhua, LIU Liansheng, YAN Lei, DONG Binbin. Vibration signal de-noising based on improved EMD algorithm[J]. Explosion And Shock Waves, 2020, 40(9): 095201. doi: 10.11883/bzycj-2019-0471
[12]	Shi Jianjun, Li Qingya, Zhang Qi, Wei Xing, Wang Hui. Forecast system for blasting vibration velocity peak based on Matlab and BP neural network[J]. Explosion And Shock Waves, 2017, 37(6): 1087-1092. doi: 10.11883/1001-1455(2017)06-1087-06
[13]	Zhu Xiuyun, Lin Gao, Pan Rong, Lu Yu. Sensitivity analysis for impact resistance of steel plate concrete walls based on force vs. time-history analysis[J]. Explosion And Shock Waves, 2016, 36(5): 670-679. doi: 10.11883/1001-1455(2016)05-0670-10
[14]	SHI Xiu-zhi, LIN Da-neng, CHEN Shou-ru. Blasting-vibration-induced damage prediction by rough set-based fuzzy-neural network[J]. Explosion And Shock Waves, 2009, 29(4): 401-407. doi: 10.11883/1001-1455(2009)04-0401-07