锻压技术

基于DPSO-BP神经网络的V形自由折弯成形角度和回弹预测

英文标题：Prediction on V-shaped free bending angle and springback based on DPSO-BP neural network

分类号：TG386

出版年,卷(期):页码：2023,48(8):151-157

摘要：

采用基于DPSO算法优化BP神经网络(DPSO-BP)的机器学习算法建模，提出一种考虑材料参数和几何参数的V形自由折弯成形角度和回弹的预测方法。该方法主要引入非线性惯性权重改进粒子群(PSO)算法，进一步优化神经网络的初始权值和阈值，构建神经网络预测模型。以不同批号的SUS304不锈钢板料为研究对象，通过设计正交试验得到45个训练样本数据，验证所建立的预测模型的准确性。结果表明：采用DPSO-BP神经网络模型预测的成形角和回弹角的平均误差分别为0.150°和0.120°，与未优化的PSO-BP神经网络模型相比，预测的成形角和回弹角的平均误差明显减小，且计算耗时由14.0 min 大幅缩短至0.8 min，同时实现了高预测精度和高计算效率。

A prediction method about V-shaped free bending angle and springback considering material parameters and geometric parameters was proposed, according to the machine learning algorithm modelling based on the BP neural network optimized by the DPSO algorithm (DPSO-BP).The method mainly introduced the nonlinear inertia weight to improve particle swarm (PSO) algorithm, further optimized the initial weight and threshold of the neural network, and constructed the neural network prediction model. Then, the different batches of SUS304 stainless steel sheets was taken as the research object, 45 training sample data were obtained by designing orthogonal experiment, and the accuracy of the constructed prediction model was verified. The results show that the average errors of the forming angle and the springback angle predicted by the DPSO-BP neural network model are 0.150° and 0.120°, respectively. Compared with the PSO-BP neural network model before optimization, the average errors of the forming angle and the springback angle are significantly reduced, and the calculation time is greatly shortened from 14.0 min to 0.8 min, achieving high prediction accuracy and high calculation efficiency at the same time.

基金项目：

江苏省自然科学基金青年基金项目（BK20190869）

作者简介：占少伟（1999-），男，硕士研究生,E-mail：zhansw0506@163.com;通信作者：龚俊杰（1969-），男，博士，教授,E-mail：gjunj@126.com

参考文献：

[1]Leu D K, Zhuang Z W. Springback prediction of the vee bending process for high-strength steel sheets[J]. Journal of Mechanical Science and Technology, 2016, 30(3): 1077-1084.

[2]Li H Z, Dong X H, Shen Y, et al. Size effect on springback behavior due to plastic strain gradient hardening in microbending process of pure aluminum foils[J]. Materials Science and Engineering: A, 2010, 527(16-17): 4497-4504.

[3]Jiang Z Q, Yang H, Zhan M, et al. Coupling effects of material properties and the bending angle on the springback angle of a titanium alloy tube during numerically controlled bending[J]. Materials & Design, 2010, 31(4): 2001-2010.

[4]王飞, 游有鹏. 钣金 V 形折弯回弹影响因素的有限元分析[J]. 沈阳工业大学学报, 2012, 34(5): 526-529，535.

Wang F, You Y P. Finite element analysis on influencing factors of springback in sheet metal V-bending [J]. Journal of Shenyang University of Technology, 2012, 34(5): 526-529，535.

[5]Trzepieciński T, Lemu H G. Prediction of springback in V-die air bending process by using finite element method[A]. Proceedings of Matec Web of Conferences[C].Shanghai,2017.

[6]高云亮,缪卫东,冯昭伟,等.M型Ti-Ni合金血管支架的结构设计对性能的影响[J].稀有金属,2017,41(8):936-942.

Gao Y L，Miao W D，Feng Z W，et al. Influence of structural design of M type Ti-Ni alloy vascular stents on performance[J]. Chinese Journal of Rare Metals,2017,41(8):936-942.

[7]Teimouri R, Baseri H, Rahmani B, et al. Modeling and optimization of spring-back in bending process using multiple regression analysis and neural computation[J]. International Journal of Material Forming, 2014, 7(2): 167-178.

[8]刘晓宇,陆小龙,黄茜,等.基于BP神经网络的W形微弯曲回弹预测[J].机械设计,2019,36(10):14-17.

Liu X Y, Lu X L, Huang X, et al. Prediction of the micro W-bending′s springback based on the BP neural network[J]. Journal of Machine Design, 2019,36(10):14-17.

[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.

Chen 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]GB/T 228.1—2021，金属材料拉伸试验第1部分:室温试验方法 [S].

GB/T 228.1—2021，Metallic materials—Tensile testing—Part 1: Method of test at room temperature[S].

[11]管志平,李金钊,韦钦洋,等.基于BPNN神经网络的板材V型折弯回弹预测模型[J].塑性工程学报,2022,29(8):1-10.

Guan Z P，Li J Z，Wei Q Y，et al. Prediction model of V-shaped bending springback of sheet metal based on BPNN neural network[J]. Journal of Plasticity Engineering, 2022,29(8):1-10.

[12]Fu Z M, Mo J H. Springback prediction of high-strength sheet metal under air bending forming and tool design based on GA-BPNN[J]. The International Journal of Advanced Manufacturing Technology, 2011, 53(5): 473-483.

[13]闻新, 周露, 李翔, 等. MATLAB 神经网络仿真与应用[M]. 北京:科学出版社，2003.

Wen X,Zhou L,Li X,et al. MATLAB Neural Network Simulation and Application[M].Beijing: Science Press,2003.

[14]Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5): 359-366.

[15]Shi Y H, Eberhart R C. A modified particle swarm optimizer[A]. Proceedings of the IEEE International Conference on Evolutionary Computation[C]. Anchorage, 1998.

[16]张炎亮,齐聪,程燕培.基于DPSO-BP的机械转子故障诊断[J].机床与液压,2022,50(19):194-199.

Zhang Y L，Qi C，Cheng Y P. Fault diagnosis of mechanical rotor based on DPSO-BP[J]. Machine Tool & Hydraulics, 2022,50(19):194-199.

[17]Bansal J C, Singh P K, Saraswat M, et al. Inertia weight strategies in particle swarm optimization[A].Proceedings of the Third World Congress on Nature and Biologically Inspired Computing[C]. Salamanca,2011.

服务与反馈：

【文章下载】【加入收藏】