汽车后围板拉深成形过程中的回弹预测
|
摘要
以汽车后围板为对象,运用BP神经网络对其拉深过程中的回弹量进行预测。通过CATIA建立CAD模型,运用Dynaform软件对板料冲压过程进行仿真分析,借助正交试验获取不同参数组合下的回弹数据,并通过试验验证了关键数据的可靠性,建立了4-9-6的3层BP神经网络回弹预测模型。通过对数据样本进行训练学习,控制其预测的精度为0.01,将预测结果与实际测量结果进行对比,显示预测误差最大为5.62%。说明运用BP神经网络可以实现对复杂拉深件成形的回弹预测,可以大量节省仿真预测的时间,对模具的设计具有很好的指导作用。
For automobile back panel,the springback in deep drawing was predicted by BP neural network. Then,a CAD model was established by CATIA,and the sheet metal stamping process was simulated by Dynaform. Based on springback data of different parameters obtained by orthogonal experiment,reliability of the key data was verified by actual experiment,and three-layer BP neural network of 4-9-6 was established. Through training and testing the data samples,the accuracy of the prediction was up to 0. 01. Furthermore,comparing with the prediction results and the actual measurement results,its maximum error is 5. 62%. Therefore,it indicates that the BP neural network can predict the springback of the complex drawing parts with higher precision,and less time,which provides a good guide for drawing part die design.
For automobile back panel,the springback in deep drawing was predicted by BP neural network. Then,a CAD model was established by CATIA,and the sheet metal stamping process was simulated by Dynaform. Based on springback data of different parameters obtained by orthogonal experiment,reliability of the key data was verified by actual experiment,and three-layer BP neural network of 4-9-6 was established. Through training and testing the data samples,the accuracy of the prediction was up to 0. 01. Furthermore,comparing with the prediction results and the actual measurement results,its maximum error is 5. 62%. Therefore,it indicates that the BP neural network can predict the springback of the complex drawing parts with higher precision,and less time,which provides a good guide for drawing part die design.
引文
[1]戴欣平,倪昀.基于BP神经网络的汽车车身覆盖件回弹预测[J].热加工工艺,2012,41(9):100-103.Dai X P,Ni Y.Prediction of springback of automobile body covering based on BP neural network[J].Hot Working Technology,2012,41(9):100-103.
[2]王晓莉,穆瑞,张咏琴.基于BP神经网络的薄板成形回弹仿真预测[J].锻压技术,2016,41(6):146-149.Wang X L,Mu R,Zhang Y Q.Numerical prediction of springback in sheet metal forming based on BP neural network[J].Forging&Stamping Technology,2016,41(6):146-149.
[3]刘海燕,金霞.板料成形的回弹预测方法研究[J].机械制造与自动化,2008,37(6):40-44.Liu H Y,Jin X.Springback prediction method research of sheet metal forming[J].Machine Building&Automation,2008,37(6):40-44.
[4]Hatem Mrad,Mohamed Bouazara,Gholamreza Aryanpour.A reliability study of springback on the sheet metal forming process under probabilistic variation of prestrain and blank holder force[J].Acta Mechanica Sinica,2013,29(4):557-566.
[5]Teng F,Zhang W,Liang J,et al.Springback prediction and optimization of variable stretch force trajectory in three-dimensional stretch bending process[J].Chinese Journal of Mechanical Engineering,2015,28(6):1132-1140.
[6]马国英,黄彬兵,苏春建,等.汽车翼子板拉深成形模拟及工艺参数优化[J].锻压技术,2015,40(3):21-24.Ma G Y,Huang B B,Su C J,et al.Simulation and parameters optimization of deep drawing for automobile fender[J].Forging&Stamping Technology,2015,40(3):21-24.
[7]吴超,严勇,胡志力.基于BP神经网络的管材数控弯曲多参数优化方法研究[J].锻压技术,2015,40(6):131-137.Wu C,Yan Y,Hu Z L.Research on optimization method of multiparameter in NC tube bending based on BP neural network[J].Forging&Stamping Technology,2015,40(6):131-137.
[8]陈靖芯,蔡兰,陆国民.基于BP神经网络的车身钣金件冲压成形回弹预测[J].农业机械学报,2005,36(7):135-139.Chen J X,Cai L,Lu G M.Springback prediction in the autobody panel stamping process based on the BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2005,36(7):135-139.
[9]倪昀,黄亚玲,章跃洪.基于DYNAFORM汽车覆盖件冲压仿真分析[J].热加工工艺,2011,40(11):108-111.Ni Y,Huang Y L,Zhang Y H.Stamping simulation analysis of auto-body panels based on DYNAFORM[J].Hot Working Technology,2011,40(11):108-111.
[10]姜志宏,黄信建,熊洋,等.基于正交试验和BP神经网络的板材多点渐进成形工艺优化[J].锻压技术,2015,40(5):33-37.Jiang H Z,Huang X J,Xiong Y,et al.Optimization of process parameters for multi-point incremental forming of sheet metal based on orthogonal examination and BP neural network[J].Forging&Stamping Technology,2015,40(5):33-37.
[11]张德丰.MATLAB神经网络应用设计[M].北京:机械工业出版社,2009.Zhang D F.Application Design of MATLAB Neural Network[M].Beijing:China Machine Press,2009.
[12]张德丰.MATLAB神经网络仿真与应用[M].北京:电子工业出版社,2009.Zhang D F.Simulation and Application of MATLAB Neural Network[M].Beijing:Publishing House of Electronics Industry,2009.
[2]王晓莉,穆瑞,张咏琴.基于BP神经网络的薄板成形回弹仿真预测[J].锻压技术,2016,41(6):146-149.Wang X L,Mu R,Zhang Y Q.Numerical prediction of springback in sheet metal forming based on BP neural network[J].Forging&Stamping Technology,2016,41(6):146-149.
[3]刘海燕,金霞.板料成形的回弹预测方法研究[J].机械制造与自动化,2008,37(6):40-44.Liu H Y,Jin X.Springback prediction method research of sheet metal forming[J].Machine Building&Automation,2008,37(6):40-44.
[4]Hatem Mrad,Mohamed Bouazara,Gholamreza Aryanpour.A reliability study of springback on the sheet metal forming process under probabilistic variation of prestrain and blank holder force[J].Acta Mechanica Sinica,2013,29(4):557-566.
[5]Teng F,Zhang W,Liang J,et al.Springback prediction and optimization of variable stretch force trajectory in three-dimensional stretch bending process[J].Chinese Journal of Mechanical Engineering,2015,28(6):1132-1140.
[6]马国英,黄彬兵,苏春建,等.汽车翼子板拉深成形模拟及工艺参数优化[J].锻压技术,2015,40(3):21-24.Ma G Y,Huang B B,Su C J,et al.Simulation and parameters optimization of deep drawing for automobile fender[J].Forging&Stamping Technology,2015,40(3):21-24.
[7]吴超,严勇,胡志力.基于BP神经网络的管材数控弯曲多参数优化方法研究[J].锻压技术,2015,40(6):131-137.Wu C,Yan Y,Hu Z L.Research on optimization method of multiparameter in NC tube bending based on BP neural network[J].Forging&Stamping Technology,2015,40(6):131-137.
[8]陈靖芯,蔡兰,陆国民.基于BP神经网络的车身钣金件冲压成形回弹预测[J].农业机械学报,2005,36(7):135-139.Chen J X,Cai L,Lu G M.Springback prediction in the autobody panel stamping process based on the BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2005,36(7):135-139.
[9]倪昀,黄亚玲,章跃洪.基于DYNAFORM汽车覆盖件冲压仿真分析[J].热加工工艺,2011,40(11):108-111.Ni Y,Huang Y L,Zhang Y H.Stamping simulation analysis of auto-body panels based on DYNAFORM[J].Hot Working Technology,2011,40(11):108-111.
[10]姜志宏,黄信建,熊洋,等.基于正交试验和BP神经网络的板材多点渐进成形工艺优化[J].锻压技术,2015,40(5):33-37.Jiang H Z,Huang X J,Xiong Y,et al.Optimization of process parameters for multi-point incremental forming of sheet metal based on orthogonal examination and BP neural network[J].Forging&Stamping Technology,2015,40(5):33-37.
[11]张德丰.MATLAB神经网络应用设计[M].北京:机械工业出版社,2009.Zhang D F.Application Design of MATLAB Neural Network[M].Beijing:China Machine Press,2009.
[12]张德丰.MATLAB神经网络仿真与应用[M].北京:电子工业出版社,2009.Zhang D F.Simulation and Application of MATLAB Neural Network[M].Beijing:Publishing House of Electronics Industry,2009.