BP神经网络算法用于专业机械快速设计
|
摘要
现阶段对起重机金属结构的优化设计,都是利用智能算法通过筛选最优目标值的方式来获得结果。为开发专业机械CAD软件探索新思路,并探寻一种快速获得非标产品参数的可行方法,引入BP神经网络算法,采用映射的方式来获得设计方案。把入粒子群结合惩罚函数算法,作为金属结构设计问题的方案发生器,产生大量针对不同设计要求的设计方案数据样本。再利用所得的数据样本训练BP神经网络,得到相应的权值和阈值。利用训练好的神经网络强大的非线性映射能力实现快速设计的功能。基于Visual C++6.0进行了软件开发及算法功能实现。
At present,the optimal design of crane metal structure is obtained by using intelligent algorithm to select the optimal target value.The method of mapping is used to obtain design scheme by the BP neural network algorithm to explore a new idea for developing professional mechanical CAD software and a feasible method for obtaining nonstandard product parameters rapidly. It is a generator that aprogramforthe metal structure design of overhead crane by particle swarm optimization with penalty function. The generator can generate a large number of sample for the differentrequirements of design.TheBP neural network algorithmis trained by these samples to obtain theavailable weights and thresholds. The function of rapid design is achieved by using the strongcapability of nonlinear mappingof trained neural networkalgorithm. The realization of the algorithm of software is developed based on Visual C++6.0.
At present,the optimal design of crane metal structure is obtained by using intelligent algorithm to select the optimal target value.The method of mapping is used to obtain design scheme by the BP neural network algorithm to explore a new idea for developing professional mechanical CAD software and a feasible method for obtaining nonstandard product parameters rapidly. It is a generator that aprogramforthe metal structure design of overhead crane by particle swarm optimization with penalty function. The generator can generate a large number of sample for the differentrequirements of design.TheBP neural network algorithmis trained by these samples to obtain theavailable weights and thresholds. The function of rapid design is achieved by using the strongcapability of nonlinear mappingof trained neural networkalgorithm. The realization of the algorithm of software is developed based on Visual C++6.0.
引文
[1]徐格宁.机械装备金属结构设计[M].北京:机械工业出版社,2009.(Xu Ge-ning.The Metal Structure Design of Mechanical Equipment[M].Beijing:China Machine Press,2009.)
[2]孙靖民,梁迎春.机械优化设计[M].北京:机械工业出版社,2006.(SunJin-min,Liang Yin-chun.Optimial Design of Machine[M].Beijing:China Machine Press,2006.)
[3]Kennedy J.Particle swarm:Social Adaptation of Knowledge[C].Proceedings of the IEEE Conference on Evolutionary Computation,Indianapolis,1997:303-308.
[4]Eberhart R.C.Fuzzy Adaptive Particle Swarm Optizimation[C].Proceedings of the Congress on Evolutionary Computation 2001,2001:101-106.
[5]黄丽.BP神经网络算法改进及应用研究[D].重庆:重庆师范大学,2008:8-15.(Huang Li.The research of improvement and application of BP neural network algorithm[D].Chongqing:Chongqing Normal University,2008:8-15.)
[6]陶元芳,石小飞.基于改进微粒群算法的起重机主梁优化设计[J]中国工程机械学报,2012,1(10):50-53.(Tao Yuan-fang,Shi Xiao-fei.Optimization design for crane girders based on improved particle swarm algorithm[J].Chinese Journal of Construction Machinery,2012,1(10):50-53.)
[7]叶志萍,屈福政,董炜.桥式起重机桥架结构参数优化[J].机械设计与制造,2003(5):78-80.(Ye Zhi-ping,Qu Fu-zheng,Dong Wei.The parameter optimization of ouverhead traveting crane briage strueture[J].Machinery Design and Manufacture,2003(5):78-80.)
[8]叶青林,陶元芳,邵南曦.粒子群算法结合惩罚函数用于桥式起重机主梁优化[J]起重运输机械,2015,(4):46-49.(Ye Qing-ling,Tao Yuan-fang,Shao Nan-xi.Optimization design for crane girders by particle swarm optimization combing with penalty function[J].Hoisting and Conveying Machinery,2015(4):46-49.)
[9]王吉权,王福林,邱立春.基于BP神经网络的农机总动力预测[J].农业机械学报,2011,42(12).(Wang Ji-quan,Wang Fu-lin,Qiu Li-chun.Prediction of total power in agriculture machinery based on BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2011,42(12).)
[10]刘希玉,刘弘.人工神经网络与微粒群优化[M].北京:北京邮电大学出版社,2008:84-94.(Liu Xi-yu,Liu Hong.Artificial Neural Networks and Particle swarm Algorithm Optimization[M].Beijing:Beijing University of Posts and Telecommunications Press,2008:84-94.)
[11]朱跃峰,朱敬超.基于Solid Works的机械产品参数化设计研究[J].机械设计与制造,2008(6):50-51.(Zhu Yue-feng,Zhu Jing-chao.Parameterized design for mechanical product based on Solid Works[J].Machinery Design and Manufacture,2008(6):50-51.)
[2]孙靖民,梁迎春.机械优化设计[M].北京:机械工业出版社,2006.(SunJin-min,Liang Yin-chun.Optimial Design of Machine[M].Beijing:China Machine Press,2006.)
[3]Kennedy J.Particle swarm:Social Adaptation of Knowledge[C].Proceedings of the IEEE Conference on Evolutionary Computation,Indianapolis,1997:303-308.
[4]Eberhart R.C.Fuzzy Adaptive Particle Swarm Optizimation[C].Proceedings of the Congress on Evolutionary Computation 2001,2001:101-106.
[5]黄丽.BP神经网络算法改进及应用研究[D].重庆:重庆师范大学,2008:8-15.(Huang Li.The research of improvement and application of BP neural network algorithm[D].Chongqing:Chongqing Normal University,2008:8-15.)
[6]陶元芳,石小飞.基于改进微粒群算法的起重机主梁优化设计[J]中国工程机械学报,2012,1(10):50-53.(Tao Yuan-fang,Shi Xiao-fei.Optimization design for crane girders based on improved particle swarm algorithm[J].Chinese Journal of Construction Machinery,2012,1(10):50-53.)
[7]叶志萍,屈福政,董炜.桥式起重机桥架结构参数优化[J].机械设计与制造,2003(5):78-80.(Ye Zhi-ping,Qu Fu-zheng,Dong Wei.The parameter optimization of ouverhead traveting crane briage strueture[J].Machinery Design and Manufacture,2003(5):78-80.)
[8]叶青林,陶元芳,邵南曦.粒子群算法结合惩罚函数用于桥式起重机主梁优化[J]起重运输机械,2015,(4):46-49.(Ye Qing-ling,Tao Yuan-fang,Shao Nan-xi.Optimization design for crane girders by particle swarm optimization combing with penalty function[J].Hoisting and Conveying Machinery,2015(4):46-49.)
[9]王吉权,王福林,邱立春.基于BP神经网络的农机总动力预测[J].农业机械学报,2011,42(12).(Wang Ji-quan,Wang Fu-lin,Qiu Li-chun.Prediction of total power in agriculture machinery based on BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2011,42(12).)
[10]刘希玉,刘弘.人工神经网络与微粒群优化[M].北京:北京邮电大学出版社,2008:84-94.(Liu Xi-yu,Liu Hong.Artificial Neural Networks and Particle swarm Algorithm Optimization[M].Beijing:Beijing University of Posts and Telecommunications Press,2008:84-94.)
[11]朱跃峰,朱敬超.基于Solid Works的机械产品参数化设计研究[J].机械设计与制造,2008(6):50-51.(Zhu Yue-feng,Zhu Jing-chao.Parameterized design for mechanical product based on Solid Works[J].Machinery Design and Manufacture,2008(6):50-51.)