收藏切换
Shock environment prediction and feature importance analysis of shipborne cabinet-type equipment based on deep neural network
收藏切换
Zhong-you YOU1, Hai-kun WANG1, 2, Teng XIE1, 2, Wei-di WU1
Journal of Ship Mechanics | 2026, 30(8) : 1321 - 1331
Less
收藏切换
Journal of Ship Mechanics | 2026, 30(8): 1321-1331
• Structural Mechanics •
Shock environment prediction and feature importance analysis of shipborne cabinet-type equipment based on deep neural network
Full
Zhong-you YOU1, Hai-kun WANG1, 2, Teng XIE1, 2, Wei-di WU1
Affiliations
  • 1China Ship Scientific Research Center, Wuxi 214082, China
  • 2National Key Laboratory of Ship Structure Safety, Wuxi 214082, China
Published: 2026-08-15 doi: 10.3969/j.issn.1007-7294.2026.08.009
Outline
收藏切换

To establish an intelligent prediction method for internal shock environments of shipboard cabinet-type equipment, this study conducted shock tests on typical shipboard electrical cabinets to verify the reliability of numerical calculation methods. Based on industry survey data, a parametric simplified model of cabinet-type equipment was established. Using Abaqus secondary development, a batch finite element analysis platform was constructed, successfully obtaining 1000 complete datasets containing structural parameters, shock loads, and dynamic responses. To address the limitations of traditional regression models, an innovative deep neural network (DNN) shock response prediction model was developed, creating dedicated prediction networks for spectral acceleration, spectral velocity and spectral displacement. Through grid search algorithm optimization of network topology, a coefficient of determination R2 > 0.9 was achieved, with the mean absolute error of spectral acceleration prediction being 0.14, while spectral velocity and spectral displacement prediction errors were both below 0.1. The SHAP (SHapley Additive exPlanations) interpretability analysis method was introduced, revealing that installation frequency, spectral velocity of foundation shock environment and plate thickness are dominant factors in shock responses, clarifying the coupling mechanism between structural parameters and shock loads. The research results provide efficient analysis tools and theoretical support for shock-resistant design of shipboard equipment.

shipborne equipment  /  DNN  /  shock environment  /  SHAP analysis
游忠友, 王海坤, 谢腾, 武炜迪. 基于深度神经网络的舰载柜型设备冲击环境预报及特征重要性分析. 船舶力学, 2026 , 30 (8) : 1321 -1331 . DOI: 10.3969/j.issn.1007-7294.2026.08.009
Zhong-you YOU, Hai-kun WANG, Teng XIE, Wei-di WU. Shock environment prediction and feature importance analysis of shipborne cabinet-type equipment based on deep neural network[J]. Journal of Ship Mechanics, 2026 , 30 (8) : 1321 -1331 . DOI: 10.3969/j.issn.1007-7294.2026.08.009
Year 2026 volume 30 Issue 8
0
0
Cite this Article
BibTeX
Article Info
doi: 10.3969/j.issn.1007-7294.2026.08.009
  • Receive Date:2026-03-16
  • Online Date:2026-11-03
  • Published:2026-08-15
Article Data
Affiliations
History
  • Received:2026-03-16
Affiliations
    1China Ship Scientific Research Center, Wuxi 214082, China
    2National Key Laboratory of Ship Structure Safety, Wuxi 214082, China
References
Share
https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2026.08.009
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT