基于RBF神经网络的连杆衬套强力旋压轴线直线度预测
|
摘要
为了实现对连杆衬套强力旋压轴线直线度误差的预测,从而改善连杆衬套的性能,基于MATLAB平台,建立了减薄率、进给比、首轮压下比与轴线直线度误差之间的RBF神经网络模型。用仿真数据对其进行训练,然后预测内、外轴线的直线度误差。并将预测值与仿真值比较,得出RBF神经网络预测误差百分比,与实测值进行比较,验证RBF神经网络在实际生产中的预测性能。再与同样条件下所建立的BP神经网络预测误差百分比对比。发现RBF神经网络可以用来预测连杆衬套强力旋压轴线的直线度误差,并且比BP神经网络收敛速度及学习速率更高,训练过程更稳定,预测精度更高。
In order to realize the prediction of axial straightness error of the connecting rod bushing during the power spinning and improve the performance of connecting rod bushing,RBF neural network model was established based on the MATLAB platform among the thinning ratio,feeding ratio,the first pressure ratio and axis straightness error. Then,it is trained by the simulation data,and straightness error of the inside and outside axis was predicted. Next,comparing the prediction value with simulation value,the prediction error percentage of RBF neural network was obtained,and the prediction performance of the RBF neural network model in the actual production was verified by comparing with the measured values. Furthermore,the prediction error percentage was compared with that of the BP neural network built under the same conditions,and RBF neural network can predict the axial straightness error of the connecting rod bushing during power spinning. Thus,compared with BP neural network,RBF neural network can obtain higher convergence rate,better learning rate,more stable training process and higher prediction accuracy.
In order to realize the prediction of axial straightness error of the connecting rod bushing during the power spinning and improve the performance of connecting rod bushing,RBF neural network model was established based on the MATLAB platform among the thinning ratio,feeding ratio,the first pressure ratio and axis straightness error. Then,it is trained by the simulation data,and straightness error of the inside and outside axis was predicted. Next,comparing the prediction value with simulation value,the prediction error percentage of RBF neural network was obtained,and the prediction performance of the RBF neural network model in the actual production was verified by comparing with the measured values. Furthermore,the prediction error percentage was compared with that of the BP neural network built under the same conditions,and RBF neural network can predict the axial straightness error of the connecting rod bushing during power spinning. Thus,compared with BP neural network,RBF neural network can obtain higher convergence rate,better learning rate,more stable training process and higher prediction accuracy.
引文
[1]原霞,王铁,樊文欣,等.基于Simufact的连杆衬套旋压工艺参数的模拟研究[J].热加工工艺,2013,42(1):63-66.Yuan X,Wang T,Fan W X,et al.Simulation research on spinning parameters of connecting rod bushing based on Simufact[J].Hot Working Technology,2013,42(1):63-66.
[2]吕伟,樊文欣,王跃,等.连杆衬套旋压尺寸精度分析[J].塑性工程学报,2016,23(3):29-33.Lyu W,Fan W X,Wang Y,et al.Analysis of dimensional accuracy of connecting rod bushing spinning.[J].Journal of Plasticity Engineering,2016,23(3):29-33.
[3]樊文欣,张涛,宋河金,等.强力旋压加工的铜合金连杆衬套[J].车用发动机,1997,(2):32-35.Fan W X,Zhang T,Song H J,et al.The engine with copper alloy rod bushing[J].Vehicle Engine,1997,(2):32-35.
[4]罗亚军,何丹农,张永清,等.人工神经网络在塑性成形领域中的应用研究[J].锻压技术,2001,26(5):46-49.Luo Y J,He D N,Zhang Y Q,et al.Application of artificial neural networks in the field of plastic forming[J].Forging&Stamping Technology,2001,26(5):46-49.
[5]盛仲飙.BP神经网络原理及MATLAB仿真[J].渭南师范学院学报,2008,23(5):65-67.Sheng Z B.BP neural network theory and MATLAB simulation[J].Journal of Weinan Normal University,2008,23(5):65-67.
[6]梁大珍,樊文欣,冯志刚,等.强力旋压连杆衬套的工艺参数优化[J].中国农机化学报,2015,36(3):229-232.Liang D Z,Fan W X,Feng Z G,et al.Optimization of process parameters for power spinning connecting rod[J].Journal of Chinese Agricultural Mechanization,2015,36(3):229-232.
[7]吕创能,樊文欣,舒成龙.基于BP神经网络的锡青铜连杆衬套磨损量预测[J].河北农机,2016,(1):52-54.Lyu C N,Fan W X,Shu C L.Prediction of wear capacity of tin bronze connecting rod bushing based on BP neural network[J].Hebei Agricultural Machinery,2016,(1):52-54.
[8]周品.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.
[9]高立,樊文欣,马学军,等.基于RBF神经网络的强力旋压连杆衬套成形质量预测研究[J].锻压技术,2015,40(9):134-138.Gao L,Fan W X,Ma X J,et al.Study on forming quality prediction of power spinning connecting rod bushing based on RBF neural network[J].Forging&Stamping Technology,2015,40(9):134-138.
[10]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,2016,41(6):128-132,145.She Y,Fan W X,Chen D B,et al.Study on forging technology forecasting spinning rod bushing mechanical properties based on RBF neural network[J].Forging&Stamping Technology,2016,41(6):128-132,145.
[11]GB/T 11336—2004,直线度误差检测[S].GB/T 11336—2004,Measurement of departures from straightness[S].
[12]樊振宇.BP神经网络模型与学习算法[J].软件导刊,2011,(7):66-68.Fan Z Y.BP neural network model and learning algorithm[J].Software Guide,2011,(7):66-68.
[13]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.
[2]吕伟,樊文欣,王跃,等.连杆衬套旋压尺寸精度分析[J].塑性工程学报,2016,23(3):29-33.Lyu W,Fan W X,Wang Y,et al.Analysis of dimensional accuracy of connecting rod bushing spinning.[J].Journal of Plasticity Engineering,2016,23(3):29-33.
[3]樊文欣,张涛,宋河金,等.强力旋压加工的铜合金连杆衬套[J].车用发动机,1997,(2):32-35.Fan W X,Zhang T,Song H J,et al.The engine with copper alloy rod bushing[J].Vehicle Engine,1997,(2):32-35.
[4]罗亚军,何丹农,张永清,等.人工神经网络在塑性成形领域中的应用研究[J].锻压技术,2001,26(5):46-49.Luo Y J,He D N,Zhang Y Q,et al.Application of artificial neural networks in the field of plastic forming[J].Forging&Stamping Technology,2001,26(5):46-49.
[5]盛仲飙.BP神经网络原理及MATLAB仿真[J].渭南师范学院学报,2008,23(5):65-67.Sheng Z B.BP neural network theory and MATLAB simulation[J].Journal of Weinan Normal University,2008,23(5):65-67.
[6]梁大珍,樊文欣,冯志刚,等.强力旋压连杆衬套的工艺参数优化[J].中国农机化学报,2015,36(3):229-232.Liang D Z,Fan W X,Feng Z G,et al.Optimization of process parameters for power spinning connecting rod[J].Journal of Chinese Agricultural Mechanization,2015,36(3):229-232.
[7]吕创能,樊文欣,舒成龙.基于BP神经网络的锡青铜连杆衬套磨损量预测[J].河北农机,2016,(1):52-54.Lyu C N,Fan W X,Shu C L.Prediction of wear capacity of tin bronze connecting rod bushing based on BP neural network[J].Hebei Agricultural Machinery,2016,(1):52-54.
[8]周品.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.
[9]高立,樊文欣,马学军,等.基于RBF神经网络的强力旋压连杆衬套成形质量预测研究[J].锻压技术,2015,40(9):134-138.Gao L,Fan W X,Ma X J,et al.Study on forming quality prediction of power spinning connecting rod bushing based on RBF neural network[J].Forging&Stamping Technology,2015,40(9):134-138.
[10]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,2016,41(6):128-132,145.She Y,Fan W X,Chen D B,et al.Study on forging technology forecasting spinning rod bushing mechanical properties based on RBF neural network[J].Forging&Stamping Technology,2016,41(6):128-132,145.
[11]GB/T 11336—2004,直线度误差检测[S].GB/T 11336—2004,Measurement of departures from straightness[S].
[12]樊振宇.BP神经网络模型与学习算法[J].软件导刊,2011,(7):66-68.Fan Z Y.BP neural network model and learning algorithm[J].Software Guide,2011,(7):66-68.
[13]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.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |