王惠琳,胡树根,王 耘.基于模拟退火遗传算法优化的BP网络在质量预测中的应用[J].轻工机械,2011,29(4):0 |
基于模拟退火遗传算法优化的BP网络在质量预测中的应用 |
Application of BP Networks Based on Genetic Simulated Annealing Algorithm for the Quality Prediction |
|
DOI: |
中文关键词: 注塑工艺参数 翘曲量 神经网络 遗传模拟退火算法 预测精度 |
英文关键词:molding injection wrap neural networks genetic simulated annealing algorithm prediction accuracy |
基金项目: |
王惠琳 胡树根 王 耘 |
浙江大学能源工程学系 |
摘要点击次数: 2322 |
全文下载次数: 1007 |
中文摘要: |
翘曲量预测精度是注塑成形优化的难点。文章以某零件翘曲量为对象,选取注射温度、模具温度、保压压力、保压时间、注射速度等参数,进行数值模拟实验,建立BP神经网络的翘曲量预测模型。针对BP神经网络易陷入局部最优解的缺陷,设计一种基于模拟退火遗传算法优化的BP网络模型,与BP网络的预测精度对比。结果表明,基于模拟退火遗传算法优化的BP网络模型预测精度高于BP网络模型,同时加快收敛速度,增强全局搜索能力。 |
英文摘要: |
The accuracy of warpage prediction is the difficulty in injection molding optimization.Taking wrap of plastic part as the study object, the paper set up the numerical simulation experiment with selecting injection temperature, mold temperature, packing pressure, packing time, injection speed as the experimental parameters, based on the simulation experiment, created the BP neural network prediction model for warpage. Due to the trap in local defects, a BP network optimized by genetic simulated annealing algorithm to improve the accuracy of warpage prediction was designed, comparing the prediction accuracy. The results show that the optimized BP network can not only speed up convergence rate,but also enhance the global searching ability, the accuracy of the optimized BP network is higher than that of BP network. |
查看全文 查看/发表评论 下载PDF阅读器 |
关闭 |
|
|
|