Hybrid Mechanistic and Data-driven Modeling Method of Compliant Assembly Variation Prediction for Train Body

doi:10.3901/JME.2024.06.177

Abstract

Abstract: As a typical welded thin-wall assembly structure, the train body has characteristics of low stiffness, easy deformation, and significant influence by welding process, which makes it difficult to control manufacturing accuracy, and affects the assembly quality and takt time. Assembly variation prediction for train body requires a comprehensive consideration of random geometric deviation, component’s global deformation and local welding deformation. Combined with compliant variation analysis theory and data - based welding deformation prediction method, a physical-data hybrid modeling method is proposed to predict the welding assembly dimensions of train body. First, the stiffness matrixes of components are extracted and reduced by using substructure method to construct the physical relation between loads and deformation. Then, a dataset of local welding shrinkage and angular distortion is obtained for typical welding form by using finite element analysis, which is used to construct the mapping relation between match gaps and local deformations with a data model by using BP neural network. Finally, a physical-data hybrid compliant variation analysis model is established for the welding structures with consideration of the effects of global gravity, local gap and welding distortion. The proposed method is validated by comparing predicted the height and profile variation with the actual measurement data. Simulation results show that the physical-data hybrid modeling method avoids the welding simulation process with random input deviations, and can greatly improve the computational efficiency of statistical deviation simulation by combining substructure method.

Key words: train body, assembly variation prediction, substructure method, BP neural network, physical-data hybrid model

CLC Number:

TH161

WANG Junjiu, LIU Jinyu, HOU Xiujuan, QI Zhenguo, LI Zhimin, LIU Tao. Hybrid Mechanistic and Data-driven Modeling Method of Compliant Assembly Variation Prediction for Train Body[J]. Journal of Mechanical Engineering, 2024, 60(6): 177-186.

References

[1] LIU S C，HU S J. Variation simulation for deformable sheet metal assemblies using finite element methods[J]. Journal of Manufacturing Science and Engineering，1997，119(3)：368-374.
[2] CAMELIO J A，HU S J，CEGLAREK D. Impact of fixture design on sheet metal assembly variation[J]. Journal of Manufacturing Systems，2004，23(3)：182-193.
[3] LIN Jia，JIN Sun，ZHENG Cheng，et al. Compliant assembly variation analysis of aeronautical panels using unified substructures with consideration of identical parts[J]. Computer-Aided Design，2014，57：29-40.
[4] 王健. 高速列车侧墙装配偏差建模及夹具稳健设计方法研究[D]. 上海：上海交通大学，2012. WANG Jian. The research on modeling and robust fixture design of high-speed train sidewall [D]. Shanghai：Shanghai Jiao Tong University，2012.
[5] CAI Na，QIAO Lihong. Rigid-compliant hybrid variation modeling of sheet metal assembly with 3D generic free surface[J]. Journal of Manufacturing Systems，2016，41：45-64.
[6] 梁伟，郑颖，邓德安. 外拘束对铝合金薄板结构焊接变形的影响[J]. 机械工程学报，2021，57(6)：70-77. LIANG Wei，ZHENG Ying，DENG Dean. Influence of external restraint on welding distortion of aluminum alloy thin-plate structures[J]. Journal of Mechanical Engineering，2021，57(6)：70-77.
[7] 吴桃生，李志敏，王华，等. 基于工装预变形的高速列车侧墙尺寸偏差控制方法[J]. 铁道机车车辆，2012，32(1)：1-5. WU Taosheng，LI Zhimin，WANG Hua，et al. Variation control method for the sidewall of high-speed train based on fixture’s pre-variation[J]. Railway Locomotive & Car，2012，32(1)：1-5.
[8] 张风东，刘胜龙. 高速动车组铝合金车体底架焊接变形控制[J]. 机车车辆工艺，2012(6)：22-23. ZHANG Fengdong，LIU Shenglong. Welding deformation control of aluminum alloy underframe of high-speed EMU[J]. Locomotive & Rolling Stock Technology，2012(6)：22-23.
[9] LI Zhimin，YAO Limin，LI Baowang. Variation simulation considering welding distortion applied in high-speed trains [C]// American Society of Mechanical Engineers International Mechanical Engineering Congress and Exposition，November 3-9，2017，Tampa，Florida，USA. New York：ASME，2017：1-7.
[10] PAHKAMAA A，WÄRMEFJORD K，KARLSSON L，et al. Combining variation simulation with welding simulation for prediction of deformation and variation of a final assembly[J]. Journal of Computing & Information Science in Engineering，2016，12(12)：021002-021007.
[11] 姚利民，张道刘，侯秀娟，等. 考虑焊接变形的装配偏差分析在动力集中型动车组中的应用[J]. 上海交通大学学报，2019，53(3)：260-268. YAO Limin，ZHANG Daoliu，HOU Xiujuan，et al. Assembly deviation simulation considering welding deformation applied on electric multiple unit[J]. Journal of Shanghai Jiaotong University，2019，53(3)：260-268.
[12] 刘阳，姜斌，王卉子，等. 焊接顺序对横向止挡焊接残余应力及变形的影响[J]. 机械工程学报，2019，55(24)：57-65. LIU Yang，JIANG Bin，WANG Huizi，et al. Influence of welding sequence on welding residual stress and deformation of lateral stop[J]. Journal of Mechanical Engineering，2019，55(24)：57-65.
[13] LIU Tao，LI Yongjun，LI Baowang，et al. Compliant variation analysis for high-speed train with consideration of welding distortion [C]// American Society of Mechanical Engineers International Mechanical Engineering Congress and Exposition，November 9-15，2018，Pittsburgh，Pennsylvania，USA. New York：ASME，2018：1-8.
[14] LEE D，KWON K E，LEE J，et al. Tolerance analysis considering weld distortion by use of pregenerated database[J]. Journal of Manufacturing Science & Engineering，2009，131(4)：583-590.
[15] LIU Jinyu，LI Zhimin，LIU Tao，et al. A novel compliant assembly variation analysis with consideration of initial deviation and welding shrinkage[J]. Ocean Engineering，2021，237：109636.
[16] 王建勋，初冠南，于昌利，等. 船舶与海洋工程中的焊接变形预测方法研究[J]. 船舶工程，2011，33(S2)：1-5. WANG Jianxun，CHU Guannan，YU Changli. General study on prediction of welding distortion of construction in naval architecture[J]. Ship Engineering，2011，33(S2)：1-5.
[17] TIAN Liang，LUO Yu，WANG Yang，et al. Prediction of transverse and angular distortions of gas tungsten arc bead-on-plate welding using artificial neural network[J]. Materials and Design，2014，54：458-472.
[18] 罗留祥，邢彦锋. 基于BP神经网络遗传算法的薄板CMT点焊变形[J]. 焊接学报，2019，40(4)：79-83，164. LUO Liuxiang，XING Yanfeng. Deformation of CMT spot welding of thin plate based on BP neural network genetic algorithm[J]. Transactions of the China Welding Institution，2019，40(4)：79-83，164.
[19] 马思群，刘选，金辉，等. BP及RBF神经网络铝合金车体焊接残余应力预测[J]. 大连交通大学学报，2018，39(6)：30-34. MA Siqun，LIU Xuan，JIN Hui，et al. BP and RBF neural network welding residual stress prediction of aluminum alloy train body[J]. Journal of Dalian Jiaotong University，2018，39(6)：30-34.
[20] WU Chunbiao，WANG Chao，KIM J W. Bending deformation prediction in a welded square thin-walled aluminum alloy tube structure using an artificial neural network[J]. The International Journal of Advanced Manufacturing Technology，2021，117：2791-2805.
[21] WÄRMEFJORD K，SÖDERBERG R，ERICSSON M，et al. Welding of non-nominal geometries-physical tests[J]. Procedia CIRP，2016，43：136-141.
[22] DENG Dean，MURAKAWA H，LIANG Wei. Numerical simulation of welding distortion in large structures[J]. Computer Methods in Applied Mechanics & Engineering，2007，196(45-48)：4613-4627.
[23] DENG Dean，MURAKAWA H. Numerical simulation of temperature field and residual stress in multi-pass welds in stainless steel pipe and comparison with experimental measurements[J]. Computational Materials Science，2006，37(3)：269-277.
[24] PERIĆ M，TONKOVIĆ Z，RODIĆ A，et al. Numerical analysis and experimental investigation of welding residual stresses and distortions in a T-joint fillet weld[J]. Materials & Design，2014，53(1)：1052-1063.
[25] 王元良，陈辉. 高速列车铝合金车体的焊接技术[M]. 成都：西南交通大学出版社，2012. WANG Yuanliang，CHEN Hui. Welding technology of aluminum alloy body of high-speed train [M]. Chengdu：Southwest Jiaotong Univerisity Press，2012.