QQ客服 官方微博 反馈留言

	基于RBF神经网络的QA110-5-5铝青铜时效处理硬度的预测; Forecasting the hardness of QAl10-5-5 aluminum bronze aged based on RBF neural network
	由伟 ; 赖惠先 ; 赵玮玮 ; 白秉哲
	2013-05-25
关键词	RBF神经网络 铝青铜 时效参数 硬度 RBF neural network aluminum bronze aging parameters hardness
英文摘要	用人工神经网络模型分析了时效参数对铝青铜硬度的影响。用“舍一法“训练了模型。模型对训练样本的计算值与实测值在散点图中沿着45°角平分线分布,统计学指标为:均方误差(MSE)为2.1388,相对均方误差(MSrE)为6.59%,拟合分值(VOf)为1.8301。用训练后的网络模型进行预测,得到的散点大致分布于45°角平分线附近,统计学指标为:均方误差为1.9512;相对均方误差为5.62%;拟合分值为1.7783。对时效参数的影响分析表明:时效温度和时效时间对硬度的影响,都存在一个最佳值,在时效温度和时效时间分别为450℃和30 MIn时,铝青铜的硬度达到最大值。; Artificial neural network model was used to analyze the influence of aging parameters on aluminum bronze hardness."Leave-one-out method" was used to train ANN model.The predicted and measured values of training samples distribute along the 45°diagonal in the scatter-plot diagram,statistical indicators are 2.1388(MSE),6.59%(MSRE),and 1.8301(Vof).Then the trained network model was used to forecast,the scatters are broadly distributed in the 45°diagonal nearby,statistical indicators are 1.9512(MSE),5.62%(MSRE),and 1.7783(Vof).Analysis results show that the influence of aging temperature and aging time on the aluminum bronze hardness exists an optimal value,respectively,and aluminum bronze hardness will reach maximum value when aging temperature is 450 ℃ and aging time is 30 min.
语种	zh_CN
内容类型	期刊论文
源URL	[http://dspace.xmu.edu.cn/handle/2288/98420]
专题	材料学院－已发表论文
推荐引用方式 GB/T 7714	由伟,赖惠先,赵玮玮,等. 基于RBF神经网络的QA110-5-5铝青铜时效处理硬度的预测, Forecasting the hardness of QAl10-5-5 aluminum bronze aged based on RBF neural network[J],2013.
APA	由伟,赖惠先,赵玮玮,&白秉哲.(2013).基于RBF神经网络的QA110-5-5铝青铜时效处理硬度的预测..
MLA	由伟,et al."基于RBF神经网络的QA110-5-5铝青铜时效处理硬度的预测".(2013).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。