Transactions of Materials and Heat Treatment

Title：Springback prediction of aluminum alloy profile based on deep learning neural network

Authors：

Unit：

KeyWords：

ClassificationCode：TG386

year,vol(issue):pagenumber：2024,49(7):105-111

Abstract：

Aluminum alloy profiles are widely used in various fields, in order to solve the springback problem in the production and processing of 6061 aluminum alloy square tubes, an artificial neural network (ANN) algorithm was established by using Python as the development environment and Keras as the deep learning framework, and the data training was conducted by using a four-layer fully connected neural network model with two hidden layers. Then, the backend database content for the algorithm was derived by bending springback tests, and the 198 bending springback data records obtained from these tests were stored and managed by using a structured MySQL relational database system. Finally, through sufficient model training and actual prediction, the average value of a mean squared error (MSE) of angle springback prediction for this algorithm was 0.044, and the average of a mean absolute percentage error (MAPE) of curvature springback prediction for this algorithm was 4.255. The results of algorithm training and comparative validation show that this springback prediction system achieves the requisite accuracy of error requirement, which provides an effective reference for the bending springback and compensation of aluminum alloy profiles.

Funds：

高精度型材成型加工工艺技术（P114401222）

作者简介：王鹏鹏（2001-），男，硕士研究生 E-mail：2276449687@qq.com 通信作者：王春举（1978-），男，博士，教授 E-mail：cjwang@suda.edu.cn

Reference：

［1］姜银方, 王飞, 李新城,等. 基于正交试验和神经网络的激光拼焊板回弹预测
［J］. 塑性工程学报, 2009，16(3): 40-44.

Jiang Y F, Wang F, Li X C, et al. Study on springback prediction in laser TWBs forming based orthogonal experiment and neural network
［J］. Journal of Plasticity Engineering, 2009, 16(3): 40-44.

［2］王吉权. BP神经网络的理论及其在农业机械化中的应用研究
［D］. 沈阳：沈阳农业大学, 2011.

Wang J Q. Research on BP Neural Network Theory and Its Application in Agricultural Mechanization
［D］. Shenyang: Shenyang Agricultural University, 2011.

［3］詹梅, 杨合, 栗振斌. 管材数控弯曲回弹规律的有限元分析
［J］. 材料科学与工艺, 2004(4): 349-352.

Zhan M, Yang H, Li Z B. FEM numerical analysis of springback law of NC tube bending
［J］. Materials Science and Technology, 2004(4): 349-352.

［4］巩伦庆, 吉晓民. 汽车翼子板的曲率对冲压回弹的影响研究
［J］. 机械设计, 2018, 35(12): 41-45.

Gong L Q, Ji X M. Study on the influence of curvature of automobile fender upon springback
［J］. Journal of Machine Design, 2018, 35(12): 41-45.

［5］Akrichi S, Abbassi A, Abid S, et al. Roundness and positioning deviation prediction in single point incremental forming using deep learning approaches
［J］. Adv. Mech. Eng., 2019, 11: 1-15.

［6］Jenab A, Sarraf I S, Green D E, et al. The use of genetic algorithm and neural network to predict rate-dependent tensile flow behaviour of AA5182-O sheets
［J］. Mater. Des., 2016, 94: 262-273.

［7］王建华. 基于GPU的显式有限元快速计算方法及在车身设计制造中的应用
［D］.长沙：湖南大学,2011.

Wang J H. Fast Calculation Method Based GPU of Explicit Finite Element and Application of Design and Manufacturing for Vehicle Body
［D］. Changsha: Hunan University, 2011.

［8］滕菲, 梁继才, 张万喜, 等. 矩形截面型材三维拉弯成形的回弹预测
［J］. 华南理工大学学报(自然科学版), 2015(2): 107-113.

Teng F, Liang J C, Zhang W X, et al. Springback Prediction of Rectangular Profiles During Three-dimension Stretch Bending Forming
［J］. Journal of South China University of Technology (Natural Science Edition), 2015(2): 107-113.

［9］陈光耀, 李恒, 贺子芮, 等. 基于机器学习的管材弯曲回弹有效预测与补偿
［J］. 中国机械工程, 2020, 31(22): 2745-2752.

Li G Y, Li H, He Z R, et al. Effective prediction and compensation of springbacks for tube bending using machine learning approach
［J］. China Mechanical Engineering, 2020, 31(22): 2745-2752.

［10］占少伟, 龚俊杰, 韦源源, 等. 基于DPSO-BP神经网络的V形自由折弯成形角度和回弹预测
［J］.锻压技术, 2023, 48(8): 151-157.

Zhan S W, Gong J J, Wei Y Y, et al. Prediction on V-shaped free bending angle and springback based on DPSO-BP neural network
［J］. Forging & Stamping Technology, 2023,48(8):151-157.

［11］Prete D A, Primo T, Vitis D A A. Non deterministic approach in metal forming springback simulation
［J］. Key Engineering Materials,2007, 67(344):399-410.

［12］Jamli M, Ariffin A, Wahab D. Integration of feedforward neural network and finite element in the draw-bend springback prediction
［J］. Expert Systems with Applications, 2014, 41(8):3662-3670.

［13］Oliveira M C, Alves J L, Chaparro B M, et al. Study on the influence of work-hardening modeling in springback simulation accuracy of V-free bending
［J］. International Journal of Plasticity, 2007, 23: 426-439.

［14］Welo T, Ringen G, Wang J. Smart control of springback in stretch bending of a rectangular tube by an artificial neural network
［J］. Journal of Manufacturing Science and Engineering, 2024, 146: 040905.

［15］鄂大辛, 宁汝新, 唐承统, 等. 管材的回转牵引弯曲试验及回弹分析
［J］. 北京理工大学学报, 2006(5): 410-412, 432.

E D X, Ning R X, Tang C T, et al. Experiments and analysis on the spring-back in rotary-drawing tube bending
［J］. Transactions of Beijing Institute of Technology, 2006(5):410-412, 432.

［16］张驰, 郭媛, 黎明. 人工神经网络模型发展及应用综述
［J］.计算机工程与应用, 2021, 57(11):57-69.

Zhang C, Guo Y, Li M. Review of development and application of artificial neural network models
［J］. Computer Engineering and Applications, 2021,57(11):57-69.

［17］张慧. 深度学习中优化算法的研究与改进
［D］. 北京：北京邮电大学,2018.

Zhang H. Research and Improvement of Optimization Algorithms in Deep Learning
［D］. Beijing: Beijing University of Posts and Telecommunications, 2018.

Service：

【This site has not yet opened Download Service】【Add Favorite】