Principal component analysis method of parameters for network prediction of ship impact environment

被引：0
|
作者：
Zhao, Xiaojun [1 ]
Guo, Jun [1 ]
Yang, Junjie [2 ]
Zhao, Huaxun [1 ]
机构：
[1] College of Shipbuilding Engineering, Harbin Engineering University, Harbin
[2] Dalian Shipbuilding Industry Co., Ltd., Dalian
来源：
Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University | / 45卷 / 09期
关键词：
dimension reduction; factor analysis; matrix transformation; neural network; principal component; quick forecast; shock environment; underwater explosion;
D O I：
10.11990/jheu.202206084
中图分类号：
学科分类号：
摘要：
Aiming at the problem of low accuracy in shock environment prediction using neural networks because of the strong nonlinear characteristics of ship underwater explosion shock, a method based on principal component analysis is used to improve accuracy by downscaling the input parameters of the network model. Using mathematical matrix eigenvalue extraction and matrix transformation, original data samples are subjected to dimensionality reduction by principal component analysis and factor analysis. Then, the adapted network is selected for the fast forecasting of shock spectral values. The experimental results show that the selection of principal components mainly considers the size and decreasing trend of the eigenvalues, retains the eigenvalues of the steeply decreasing section, and analyzes the trade-offs of the eigenvalues of the transition section. Meanwhile, the implementation of the decor-relation and dimensionality reduction processing on the parameters can significantly improve the forecasting accuracy of the neural network. © 2024 Editorial Board of Journal of Harbin Engineering. All rights reserved.
引用
收藏
页码：1655 / 1661
页数：6
相关论文
共 21 条
  • [1] LIANG Xiao, CHEN Jiangtao, WANG Ruili, Et al., The uncertainty quantification of ship shock environment subjected to non-contact underwater explosion, Chinese journal of ship research, 15, 6, pp. 128-136, (2020)
  • [2] ZHANG A M, WANG S P, HUANG C, Et al., Influences of initial and boundary conditions on underwater explosion bubble dynamics [ J], European journal of mechanics-b / fluids, 42, pp. 69-91, (2013)
  • [3] GAO M, SHI G Y., Ship-handling behavior pattern recognition using AIS sub-trajectory clustering analysis based on the T-SNE and spectral clustering algorithms [ J ], Ocean engineering, 205, (2020)
  • [4] GUO J, WANG M, KANG Y, Et al., Prediction of ship cabin noise based on RBF neural network[J], Mathematical problems in engineering, 1, (2019)
  • [5] DU J, ZHANG Y, TAO X U., Airport noise prediction model based on BP neural network[J], Computer engineering & applications, 49, 9, pp. 236-239, (2013)
  • [6] GUO Jun, GU Chenxu, YANG Junjie, Et al., Data mining and application of ship impact spectrum acceleration based on PNN neural network [ J], Ocean engineering, 203, (2020)
  • [7] GUO Jun, Research on characteristics of impact environment of stiffened double cylindrical shell, (2005)
  • [8] HOLT S, LUTZ A, SAGA B, Et al., Developing an approach for a three-dimensional hydrogeologic framework to find water in northern Ghana, Open journal of modern hydrology, 5, 4, pp. 105-120, (2015)
  • [9] MUKHERJEE I, RAY P K., A systematic solution methodology for inferential multivariate modelling of industrial grinding process, Journal of materials processing technology, 196, 1, pp. 379-392, (2008)
  • [10] ZHANG L, DONG W, ZHANG D, Et al., Two-stage image denoising by principal component analysis with local pixel grouping, Pattern recognition, 43, 4, pp. 1531-1549, (2010)
123