上海交通大学学报

上海交通大学学报 >

2025 , Vol. 59 >Issue 8: 1092 - 1102

DOI: https://doi.org/10.16183/j.cnki.jsjtu.2023.576

船舶海洋与建筑工程

面向船舶大型曲面薄板的装配形变TSM-TLHS预测方法

  • 金轩铖 ,
  • 洪舸 ,
  • 高硕 ,
  • 夏唐斌 ,
  • 胡小锋 ,
  • 奚立峰
展开
  • 1.上海交通大学 机械与动力工程学院, 上海 200240
    2.上海交通大学-弗劳恩霍夫协会智能制造创新中心, 上海 201306
金轩铖(1999—),硕士生,从事船舶分段装配的质量控制研究.
夏唐斌,副教授,博士生导师,电话(Tel.):021-34208589;E-mail:xtbxtb@sjtu.edu.cn.

收稿日期: 2023-11-14

  修回日期: 2023-12-29

  录用日期: 2024-01-12

  网络出版日期: 2024-02-09

基金资助

国家重点研发计划重点项目(2022YFF0605700);上海交通大学深蓝计划基金(SL2021MS008);中船-交大海洋装备前瞻创新联合基金面上项目(22B010432)

收起

TSM-TLHS Prediction Method for Assembly Deformation of Large Curved Thin Plates in Shipbuilding

  • JIN Xuancheng ,
  • HONG Ge ,
  • GAO Shuo ,
  • XIA Tangbin ,
  • HU Xiaofeng ,
  • XI Lifeng
Expand
  • 1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    2. Fraunhofer Project Center for Smart Manufacturing at Shanghai Jiao Tong University, Shanghai 201306, China

Received date: 2023-11-14

  Revised date: 2023-12-29

  Accepted date: 2024-01-12

  Online published: 2024-02-09

Fold

摘要

船舶分段装配过程中,大型曲面薄板(如外板)放置在胎架上时,会受重力作用发生形变,将影响装配精度进而影响分段建造质量.为预测给定胎架布局下大型曲面薄板的形变,建立了一种基于两阶段拉丁超立方采样和Transformer神经网络结构的代理模型(TSM-TLHS).首先,设计了两阶段拉丁超立方采样,相较传统方法,能直接适用于形状不规则薄板的采样.同时,建立了包含多头注意力模块和位置编码的Transformer代理模型,综合考虑了胎架位置与胎架布置点位移对薄板形变的影响.实际案例结果显示,提出的TSM-TLHS方法的预测误差仅为61 μm,且满足现场装配对薄板形变的预测精度需求,便于船厂及时对分段进行反变形补偿,从而确保装配质量.

关键词： 分段装配; 曲面薄板; 形变预测; 代理模型; 拉丁超立方采样

本文引用格式

金轩铖 , 洪舸 , 高硕 , 夏唐斌 , 胡小锋 , 奚立峰 . 面向船舶大型曲面薄板的装配形变TSM-TLHS预测方法[J]. 上海交通大学学报, 2025 , 59(8) : 1092 -1102 . DOI: 10.16183/j.cnki.jsjtu.2023.576

Abstract

During the block assembly, large curved thin plates (such as outer plates) undergo deformation due to the force of gravity when they are placed on the jigs, which affects the accuracy and quality of the block assembly in shipbuilding. In order to predict the deformation of these large curved thin plates within a given jig layout, this paper introduces a Transformer-based surrogate model with two-stage Latin hypercube sampling (TSM-TLHS). Primarily, compared to traditional approaches, the two-stage Latin hypercube sampling (TLHS) method enables direct sampling of irregularly shaped thin plates. Simultaneously, this paper uses a Transformer-based surrogate model (TSM) incorporating multi-head attention modules and positional encoding to comprehensively consider the impact of jig positions and corresponding node displacements on thin plate deformation. Real case results demonstrate that the prediction error of this TSM-TLHS method is only 61 μm, meeting the on-site assembly precision requirements for predicting plate deformation. This facilitates timely anti-deformation compensation by block in shipyards, ensuring assembly quality.

Key words： block assembly; curved thin plates; deformation prediction; surrogate model; Latin hypercube sampling

参考文献

[1] 应长春. 船舶工艺技术[M]. 上海: 上海交通大学出版社, 2013: 359.
  YING Changchun. Shipbuilding technology[M]. Shanghai: Shanghai Jiao Tong University Press, 2013: 359.
[2] CAI W, HU S, YUAN J. Deformable sheet metal fixturing: Principles, algorithms, and simulations[J]. Journal of Manufacturing Science and Engineering, 1996, 118(3): 318-324.
[3] 王威, 王珉, 胡俊聪, 等. 面向汽车覆盖件的有限元仿真虚拟匹配方法[J]. 上海交通大学学报, 2020, 54(5): 532-543.
  WANG Wei, WANG Min, HU Juncong, et al. Virtual matching method based on finite element simulation in automotive panel[J]. Journal of Shanghai Jiao Tong University, 2020, 54(5): 532-543.
[4] VINOSH M, RAJ T, PRASATH M. Optimization of sheet metal resistance spot welding process fixture design[J]. Materials Today: Proceedings, 2021, 45: 1696-1700.
[5] JU K, DUAN C, KONG J, et al. Prediction of clamping deformation in vacuum fixture-workpiece system for low-rigidity thin-walled precision parts using finite element method[J]. The International Journal of Advanced Manufacturing Technology, 2020, 109(7): 1895-1916.
[6] SLON C, PANDEY V. An optimization framework for fixture layout design for nonrigid parts[J]. SAE International Journal of Materials and Manufacturing, 2020, 13(1): 5-18.
[7] LOOSE J, CHEN N, ZHOU S. Surrogate modeling of dimensional variation propagation in multistage assembly processes[J]. IIE Transactions, 2009, 41(10): 893-904.
[8] 杨国林, 孙学先, 锁旭宏, 等. 桥梁形变监测中LSTM预测方法研究[J]. 兰州交通大学学报, 2022, 41(5): 1-5.
  YANG Guolin, SUN Xuexian, SUO Xuhong, et al. The application of LSTM method to bridge deformation prediction[J]. Journal of Lanzhou Jiaotong University, 2022, 41(5): 1-5.
[9] ZHANG Y, MA N, GU X, et al. Surrogate model based on an MLP neural network and Bayesian hyperparameter tuning for ship hull form optimization[J]. International Journal of Offshore and Polar Engineering, 2023, 33(2): 184-195.
[10] 胡新明, 王德禹. 基于迭代均值组合近似模型和序贯优化与可靠性评估法的船舶结构优化设计[J]. 上海交通大学学报, 2017, 51(2): 150-156.
  HU Xinming, WANG Deyu. Optimization of ship structures using ensemble of surrogates with recursive arithmetic average and sequential optimization and reliability assessment[J]. Journal of Shanghai Jiao Tong University, 2017, 51(2): 150-156.
[11] QIU W, LIU K, ZONG S, et al. An optimization method for anti-blast performance of corrugated sandwich plate structure based on neural network and sparrow search algorithm[J]. Ships and Offshore Structures, 2024, 19(8): 1028-1043.
[12] 何维, 孙宏磊, 陶袁钦, 等. 开挖引起的隧道位移动态多目标优化反演预测[J]. 上海交通大学学报, 2022, 56(12): 1688-1699.
  HE Wei, SUN Honglei, TAO Yuanqin, et al. Dynamic multi-objective optimization inverse prediction of excavation-induced tunnel displacement[J]. Journal of Shanghai Jiao Tong University, 2022, 56(12): 1688-1699.
[13] DU J, LIU C, LIU J, et al. Optimal design of fixture layout for compliant part with application in ship curved panel assembly[J]. Journal of Manufacturing Science and Engineering, 2021, 143(6): 061007.
[14] TANG B. Orthogonal array-based Latin hypercubes[J]. Journal of the American Statistical Association, 1993, 88(424): 1392-1397.
[15] JOSEPH V, HUNG Y. Orthogonal-maximin Latin hypercube designs[J]. Statistica Sinica, 2008, 18: 171-186.
[16] 夏立, 邹早建, 袁帅, 等. 基于非侵入式混沌多项式法的随机阻曳流CFD模拟不确定度量化[J]. 上海交通大学学报, 2020, 54(6): 584-591.
  XIA Li, ZOU Zaojian, YUAN Shuai, et al. Uncertainty quantification for CFD simulation of stochastic drag flow based on non-intrusive polynomial chaos method[J]. Journal of Shanghai Jiao Tong University, 2020, 54(6): 584-591.
[17] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Advances in Neural Information Processing Systems 30. La Jolla, USA: NIPS, 2017: 6000-6010.
[18] YUE X, SHI J. Surrogate model-based optimal feed-forward control for dimensional-variation reduction in composite parts’ assembly processes[J]. Journal of Quality Technology, 2018, 50(3): 279-289.
Options
文章导航

/

〈 〉