摘要
研究可修复零部件精度参数的分配是关系到再制造机床性能和再制造成本的重要问题。本文提出了用BP+GA的混合算法优化分配可修复零部件精度参数的方法。首先利用BP神经网络建立零部件精度参数与再制造机床空间几何误差之间的正向映射模型,然后用正交设计法得到训练样本数据并训练网络,最后再用BP+GA的混合算法逆向确定零部件的精度参数。仿真结果表明了混合算法是解决复杂精度分配问题的一种理想方法,优化结果可用于指导零部件精度的修复。
Precision distribution among restorable parts and components is an important problem for the performance of remanufactured machine tools and the cost of remanufacturing. A hybrid algorithm of back-propagation（BP） neural network and genetic algorithm （GA） for distributing the precision parameters among restorable parts and components is presented in this paper. Firstly, a BP neural network positive model was constructed to represent the relationship between the precision parameters of parts and the volumetric error of remanufaetured machine tools. Then, the training sample data was obtained with orthogonal design. Finally, the precision parameters of parts and components were determined conversely by the hybrid algorithm of BP and GA. Simulation results show that the hybrid algorithm is an effective approach to solving the complex problem of precision distribution, and the optimizing results can be used to guide the restoring of precision of parts and components.
出处
《机械科学与技术》
CSCD
北大核心
2007年第11期1466-1470,共5页
Mechanical Science and Technology for Aerospace Engineering
基金
科技部中小型企业创新基金项目(05C26213400546)
江苏高校高新技术产业化发展项目(JHB05-19)资助
关键词
再制造机床
BP神经网络
遗传算法
精度分配
最优化
remanufactured machine tools
BP neural network
genetic algorithm
precision distribution
