|
|
Data mining and prediction of ship shock spectral velocity based on RBF neural network |
FENG Linhan1, YANG Junjie2, JIAO Liqi1 |
1. Naval Research Institute, Beijing 100161, China;
2. Dalian Shipbuilding Industry Co., Ltd., Dalian 116000, China |
|
|
Abstract The impulsive environment calculation of ship subjected to underwater explosion is the key of shock resistance design of ship equipment. The approach to improve the accuracy of calculation about impulsive environment was concerned with the researchers. In this research, ten FEM ships with varied dimensions and types were established for prediction. On varied decks of ships, 400 groups were uniformly distributed when the ship subjected to underwater explosions. More than 120 million impulsive environment data was produced to build the impulsive environment data base. In this paper the impulsive environment prediction model was constructed base on radial basis function network. The input parameters were main dimension parameters, underwater explosion cases and measuring point locations, and the only output parameter was velocity shock spectrum. The model network parameters were optimized by clustering algorithm. Then the prediction results about the impulsive environment of an unknown ship subjected to specified underwater explosion case expresses the high precision, the better generalization ability and optimal robust performance. The method present a new choice for rapidly prediction of ship impulsive environment in design stage.
Key words: shock response spectrum of ship; prediction; RBF neural network; optimization algorithms
|
Received: 09 March 2021
Published: 15 July 2022
|
|
|
|
[1] 马焱. 基于机器学习的水下非接触爆炸作用下船体总体毁伤快速评估方法研究[D].中北大学,2018.
MA Yan. The A rapid assessment method for the overall damage of ship subjected to non-contact underwater explosion based on machine learning[D]. 2018. North University of China, 2018.
[2] Guo Jun, Yong Yang. (2019): The Spherical Shock Factor Theory of a FSP with an UnderwaterAdded Structure. Mathematical Problems in Engineering, vol. 2019.
[3] Xiong-liang Yao, Jun Guo.(2009): Comparability research on impulsive response of double stiffened cylindricalshells subjected to underwater explosion. International Journal of Impact Engineering, vol. 36, pp. 754-762.
[4] 冯麟涵. 船舶系统抗冲击性能全局优化方法研究[D].哈尔滨工程大学,2009.
FENG Linhan, Research on the global optimization method of ship system impact resistance[D]. Harbin Engineering University, 2009
[5] Jun Guo. (2019): Prediction of Ship Cabin Noise Based on RBF Neural Network. Mathematical Problems in Engineering, vol. 2019, pp. 21.
[6] 古滨,郎天奇,刘翠丹.基于样本库方法的船舶冲击环境预报[J].船舶科学技术,2013,35(08):11-17.
GU Bin, LANG Tianqi, LIU Cuidan. Prediction method for ship impulsive environment based on Sample Library[J]. Ship Science and Technology, 2013,35(08):11-17.
[7] Dehghan M, Mohammadi V. A numerical scheme based on radial basis function finite difference (RBF-FD) technique for solving the high-dimensional nonlinear Schrödinger equations using an explicit time discretization: Runge–Kutta method[J]. Computer Physics Communications, 2017.
[8] 朱卫云, 付东翔, 葛懂林,等. 基于RBF神经网络的永磁同步伺服电机控制系统[J]. 电子科技, 2016, 29(1):161-164.
ZHU Weiyun, FU Dongxiang, GE Donglin, etc. Permanent magnetic synchronous servo motor control system based on RBF neural network[J]. Electronic technology, 2016, 29(1):161-164.
[9] 张杨杨,隋天雨,裴俊.人工神经网络技术及其在岩土工程领域的应用[J].应用技术,2021,(03):62-64+69.
ZHAGN Yang-yang, SUI Tian-yu, PEI Jun, CUI Min-rui. Artificial Neural Network Technology and Its Application in Geotechnical Engineering[J].Applied Technology. 2021,(03):62-64+69.
[10] 秦立新,张凯,王玉宝,陈宁.基于优化PSO-RBF的柴油机故障诊断方法[J].柴油机,2020,42(06):23-28.
Qin Lixin, Zhang Kai, Wang Yubao, ChenNing. A Diesel Engine Fault Diagnosis Method Based on Optimized PSO-RBF[J].Diesel Engine, 2020,42(06):23-28.
[11] Huang Z, Yuan H. Ionospheric single‐station TEC short‐term forecast using RBF neural network[J]. Radio Science, 2014, 49(4): 283-292.
[12] Poggio T, Girosi F. Networks for approximation and learning[J]. Proceedings of the IEEE, 1990, 78(9): 1481-1497.
[13] 陶砾,杨朔,杨威.深度学习的模型搭建及过拟合问题的研究[J].计算机时代,2018(02):14-17+21.
TAO Li, YANG Shuo, YANG Wei. Research on model construction method and overfitting of deep learning[J].Computer Era,2018(02):14-17+21.
[14] 郭际. 船舶冲击环境频域与时域特性研究[D].哈尔滨工程大学,2010.
GUO Ji. Characteristics of time domain and frequency domain of ship impulsive environment[D]. Harbin Engineering University, 2010.
[15] Wang, Ruo-Jiang et al. A dimensionless study on thermal control of positive temperature coefficient (PTC) materials[J]. International Communications in Heat and Mass Transfer (2020): 104987.
[16] Jun Guo, Chen-xu Gu, Jun-jie Yang, Yin Zhang, Heng Yang. Data mining and application of ship impact spectrum acceleration based on PNN neural network[J]. Ocean Engineering,2020,203.
[17] 李志辉,刘辉,李其修,吴向君.水下非接触爆炸作用下船舶结构损伤评估[J].船舶科学技术,2012,34(07):40-44.
LI Zhihui, LIU Hui, LI Qixiu, WU Xiangjun. Research on damage evaluation of ship structure in underwater non-contact explosion[J]. Ship Science and Technology, 2012,34(07):40-44.
[18] 梁霄,陈江涛,王瑞利,胡星志.非接触水下爆炸下舰船冲击环境的不确定度量化[J].中国舰船研究2020,15(06):128-136
LIANG Xiao, CHEN Jiangtao, WANG Ruili, HU Xingzhi. The uncertainty quantification of ship shock environment subjected to non-contact underwater explosion[J].Chinese Journal of Ship Research. 2020,15(06):128-136
[19] 姜忠涛. 大型水面船舶抗爆冲击能力分析研究[D].哈尔滨工程大学,2017.
JIANG Zhongtao. Research on shock resistance of large ship hull subjected to underwater explosion[D]. Harbin Engineering University. 2017
[20] 张义. 径向基函数神经网络的优化研究[D].山东理工大学,2016.
ZHANG Yi. The optimization study of radial base function neural network[D]. Shangdong University of Technology, 2016
[21] 魏海坤. 神经网络结构设计的理论与方法[M]. 国防工业出版社, 2005.
WEI Haikun. Theory and Method of Neural Network Construction[M]. National Defense Industry Press. 2005 |
|
|
|