摘要
从全面考虑机床的加工能力、加工中心偏移等各种加工因素的角度出发 ,提出一种由机械加工能力反求公差的新方法 ,能较正确地反映零件加工的真实过程。给出了其数学分析模型 ,并运用神经网络和遗传算法相结合的方法实现之。
The purpose of tolerance design is to find the best combination of the individual component tolerances in the given assembly under the condition that the assembly requirements are satisfied so that the production cost is minimum. Based on neural networks and genetic algorithm, this paper presents a new reverse approach for the tolerance design considering machine capabilities and mean shifts, which can present the real condition of the component production. A mathematical model has been given, and it is realized by using neural network and genetic algorithm. At last, an example is given and the results are analyzed.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2000年第5期535-537,共3页
China Mechanical Engineering
基金
国家自然科学基金资助项目 !(5970 50 2 2 )
关键词
加工能力
公差反求
神经网络
遗传算法
机械加工
machining capability tolerance reversing neural network genetic algorithm