Abstract
For the characteristics of the dynamic response real test data of underwater explosive vessels with few feature dimensions, unclear feature relationships and small effective data amount, to improve the prediction precision of the dynamic response of the container, a dynamic response prediction model based on the LOO-XGBoost algorithm is proposed. The model uses a CART tree as the base learner, inputs the preprocessed data, and trains the target model layer by building multiple weak learners. Compared with the prediction models based on LOO-SVR, 10FLOD-XGBoost and BPNN, the simulation performance is better, the prediction accuracy is higher, and it has the significant advantage of avoiding the standardization of data features and not caring about whether the features are inter-dependent. It provides certain feasibility for the statistical prediction of the small sample capacity of similar projects.
Similar content being viewed by others
Data availability statement
Data are available on request from the authors.
References
Linna L, Tian L, Dongwang Z et al (2018) Dynamic response prediction of underwater explosive vessel based on GRNN. Blasting 35(4):141–146. https://doi.org/10.3963/j.issn.1001-487X.2018.04.025
Linna L, Dongwang Z, Xiaowu H et al (2021) reliability analysis of deepwater explosion test vessel based on dynamic prediction. Explos Impact. https://doi.org/10.11883/bzycj-2020-0078
Dongwang Z, Linna L (2014) Experimental investigation on dynamic response of chamber to simulate deepwater explosive. Chin Eng Sci 11:78–81. https://doi.org/10.3969/j.issn.1009-1742.2014.11.012
Li L (2013) Dynamic responses analysis and experimental study on the water medium explosion vessels. Wuhan University of Science and Technology, Hubei
Erwei L, Xiuzhi S, Jiayao C (2016) Research on peak velocity prediction of blasting vibration based on LS-SVR small sample size. World Sci Technol Res Dev 38(06):1258–1261. https://doi.org/10.16507/j.issn.1006-6055.2016.06.026
Miao S, Li W, Qing Y, Yuchun Z, Chenyang M (2017) Prediction of blasting vibration of underground gas storage reservoir cavity group based on PSO-LSSVM algorithm. Blasting 34(03):145–150. https://doi.org/10.3963/j.issn.1001-487X.2017.03.026
Pu C, Guo W, Qin X, Xu J, He G, Xiao D (2018) Prediction of pile foundation blasting vibration speed based on BP neural network. Blasting 35(02):177–181. https://doi.org/10.3963/j.issn.1001-487X.2018.02.030
Bi M, Xuguang W, Renshu Y (2019) Research on explosion vibration intensity prediction based on AdaBoost-SVM combined algorithm. J Vib Shock 38(18):231–235. https://doi.org/10.13465/j.cnki.jvs.2019.18.032
Haiwang Y, Junjie H, Tao L et al (2022) LOO-XGboost model predicts rock blasting blockiness. Blasting 39(1):16–21. https://doi.org/10.3963/j.issn.1001-487X.2022.01.003
Haiwang T, Qiliang Y, Jianchun X, Kefeng H, Shuo Z, Haoyu H (2022) Photovoltaic output prediction based on XGBoost-LSTM combination model. J Solar Energy, 1–6
Xu R, Su H, Yang L (2021) Dam deformation prediction model based on GP-XGBoost. Prog Water Resour Hydropower Sci Technol 41(05):41–46. https://doi.org/10.3880/j.issn.1006-7647.2021.05.007
Xingyu Y, Hanming G, Yifei X, Hao R, Jun N (2019) Application of XGBoost algorithm in well logging interpretation of tight sandstone gas reservoir. Pet Geophys Explor 54(02):447–455. https://doi.org/10.13810/j.cnki.issn.1000-7210.2019.02.024
Guotian W, Junyi D, Shaojun X, Tao J (2019) Research on laboratory security risk prediction model based on XGBoost algorithm. Exp Technol Manage 36(12):245–251. https://doi.org/10.16791/j.cnki.sjg.2019.12.058
Yezi L, Zhenyou W, Yilu Z et al (2018) Improvement and application of Xgboost algorithm based on bayesian optimization. J Guangdong Univ Technol 35(1):23–28. https://doi.org/10.12052/gdutxb.170124
Chenyang L, Xiongfei C, Yong Z et al (2021) Spectral classification and identification method of LIBS of aluminum alloy based on XGBoost. Spectrosc Spect Anal 41(2):624–628. https://doi.org/10.3964/j.issn.1000-0593(2021)02-0624-0
Feng X, Yanjun F (2019) Error prediction of field calibrator based on bayesian optimization XGBoost. Electr Meas Instrum 56(18):120–125. https://doi.org/10.19753/j.issn1001-1390.2019.018.017
Xin Z (2012) Research on evaluation theory and method based on small sample size. Anhui University of Science and Technology, Hefei, pp 15–37
Xiaohui W, Liang Z, Junqing L et al (2020) Research on XGBoost improvement method based on genetic algorithm and random forest. Comput Sci 47(z2):454–458. https://doi.org/10.11896/jsjkx.200600002
Junbo Z, Chuan H, Jian Y, Fangyin W, Wei M (2020) Discussion on the applicability of XGBoost algorithm based on cross-validation in rock burst intensity classification prediction. Tunnel Construct 40(S1):247–253. https://doi.org/10.3973/j.issn.2096-4498.2020.S1.031
Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system. Association for Computing Machinery. pp 775–784
Acknowledgements
This work was supported by Hubei Key Laboratory of Blasting Engineering Foundation under Grant No. HKLBEF202009.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors disclosed no relevant relationships.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, L., Gu, J., Huang, X. et al. Dynamic response prediction of underwater explosive vessel based on LOO-XGBoost model. Neural Comput & Applic 35, 25057–25067 (2023). https://doi.org/10.1007/s00521-023-08613-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08613-x