锻压技术

利用RBF神经网络预测反挤压连杆衬套过程中的挤压力

英文标题：Prediction of extrusion force in backward extruding connecting rod  bushing process by RBF neural network

单位：1.中北大学机械工程学院山西太原 030051 2.装甲军代局驻太原地区军代室山西太原 030006

分类号：TG391

出版年,卷(期):页码：2019,44(5):180-184

摘要：

采用单因素试验法，利用模拟软件Simufact进行了锡青铜连杆衬套反挤压试验，试验选取了挤压温度、凹模圆角半径和挤压比为试验因素，挤压力为评价指标。基于MATLAB软件，建立了挤压因素与挤压力之间的RBF神经网络模型，得到挤压温度、凹模圆角半径、挤压比和挤压力之间的非线性关系。通过试验数据进行RBF神经网络模型训练，然后再用训练好的RBF神经网络模型预测挤压力，并将预测的挤压力值与模拟的挤压力值做对比。结果表明：该神经网络模型能高精度地预测反挤压连杆衬套过程中的挤压力。

By using the singlefactor test method,the extrusion test of tin bronze connecting rod bushing was simulated by the simulation software Simufact, then the extrusion temperature, die radius and extrusion ratio were selected as the test factors, and the extrusion force was selected as the evaluation index. [JP3]Based on software MATLAB, the RBF neural network model of the relationship between extrusion factors and extrusion force was established，and the nonlinear relationships between extrusion temperature, die radius, extrusion ratio and extrusion force were obtained. The RBF neural network model was trained by the experiment data, and then the extrusion force was predicted by the trained RBF neural network model. In the end, the predicted extrusion force value was compared with the simulated extrusion force value. The results show that the neural network model can predict the extrusion force in the process of backward extruding connecting rod bushing with high precision.

基金项目：

山西省自然科学基金资助项目(2012011023-2)；山西省高校高新技术产业化项目(20120021)

作者简介：樊文欣（1964-），男，博士，教授 Email：fanwx@nuc.edu.cn

参考文献：

［1］杨华龙. 连杆衬套温挤压预成形技术及数值模拟研究
［D］. 太原：中北大学, 2017.

Yang H L. Study on Warm Extrusion Preforming Technology and Numerical Simulation of Connecting Rod Bushing
［D］．Taiyuan: North University of China，2017.〖ZK)〗

［2］苏娟华, 陈钢, 吴朋越,等. 基于BP神经网络的Cu0.75Cr挤压过程中的挤压力预测
［J］. 有色金属工程, 2005, 57(1):35-38.

Su J H，Chen G，Wu P Y，et al. Prediction of extrusion force in Cu0.75Cr extrusion process based on BP neural network
［J］. Nonferrous Metals Engineering, 2005, 57(1):35-38.[ZK)]

［3］牟洪波. 基于BP和RBF神经网络的木材缺陷检测研究
［D］. 哈尔滨：东北林业大学, 2010.

Mu H B.Study on Wood Defects Testing Based on BP and RBF Neural Networks
［D］.Harbin：Northeast Forestry University，2010.[ZK)]〖JP〗

［4］张永志, 董俊慧. 基于模糊C均值聚类的模糊RBF神经网络预测焊接接头力学性能建模
［J］. 机械工程学报, 2014, 50(12):58-64.

Zhang Y Z，Dong J H. Modeling fuzzy RBF neural network to predict of mechanical properties of welding joints based on fuzzy Cmeans cluster
［J］.Journal of Mechanical Engineering, 2014, 50(12):58-64.[ZK)]

［5］杨锋,樊文欣,李志伟，等.基于灰色神经网络模型的强力旋压连杆衬套屈服强度预测
［J］.塑性工程学报,2018,25(4):212-216.

Yang F，Fan W X，Li Z W，et al. Prediction of yield strength of power spinning connecting rod bushing based on grey neural network model
［J］.Journal of Plasticity Engineering, 2018,25(4):212-216.[ZK)]

［6］吉梦雯,樊文欣,尹馨妍，等.基于RBF神经网络的连杆衬套强力旋压轴线直线度预测
［J］.锻压技术,2018,43(3):67-71.

Ji M W，Fan W X，Yin X Y，et al. Prediction on axial straightness of connecting rod bushing in the power spinning based on RBF neural network
［J］.Forging ＆ Stamping Technology, 2018,43(3):67-71.[ZK)]

［7］张俊明, 刘军, 俞小峰,等. 一种RBF神经网络在某冷连轧机组轧制力计算中的组合应用
［J］. 塑性工程学报, 2008, 15(1):133-137.

Zhang J M，Liu J，Yu X F，et al. Application of the combination of a sort of RBF neural network in roll force calculation of certain tandem cold mill
［J］.Journal of Plasticity Engineering, 2008, 15(1):133-137.[ZK)]

［8］佘勇,樊文欣,陈东宝,等.基于RBF神经网络的强力旋压连杆衬套力学性能预测研究
［J］.锻压技术,2017,41(6):128-132.

She Y，Fan W X，Chen D B，et al. Prediction of mechanical properties of strong spinning connecting rod bushing based on RBF neural network
［J］.Forging ＆ Stamping Technology, 2017,41(6):128-132.[ZK)]

［9］周平.MATLAB神经网络设计与应用
［M］.北京：清华大学出版社，2013.

Zhou P．Design and Application of MATLAB Neural Network
［M］．Beijing: Tsinghua University Press，2013．[ZK)]

［10］樊振宇. BP神经网络模型与学习算法
［J］. 软件导刊, 2011, 10(7):66-68.

Fan Z Y. BP neural network neural network model and learning algorithm
［J］. Software Guide，2011，10(7)：66-68.

［11］王小川. MATLAB神经网络43个案例分析
［M］.北京：北京航空航天大学出版社, 2013.

Wang X C. 43 Case Studies of MATLAB Neural Network
［M］. Beijing:Beijing University of Aeronautics and Astronautics Press,2013.

［12］苏志坚，林明华. RBF神经网络在高程异常拟合中的应用
［J］. 城市勘测, 2011, (3):65-67.

Su Z J，Lin M H. RBF neural network in height anomaly fitting
［J］. Urban Geotechnical Investigation ＆ Surveying，2011, (3):65-67.

服务与反馈：

【文章下载】【加入收藏】