郭稚弧
,
金名惠
,
桂修文
,
孟厦兰
,
邢政良
,
罗逸
腐蚀学报（英文）
利用人工神经网络从已有的土壤腐蚀试验数据中通过训练求得土壤的理化性能与碳钢在土壤中的腐蚀速度之间的非线性关系,从而预测碳钢在土壤中的腐蚀速度采用的神经网络结构为5—8—1的形式,学习算法采用BP算法.结果表明,含水量和Cl-离子是影响碳钢土壤腐蚀的主要因素.
关键词:
土壤腐蚀
,
neural network
,
corrosion rate
$ D.L*
,
D.N.He
,
X.J.Bao
,
Y. Q.Zhang
,
X. Y.Ruan
,
J.L. Cheng and J. Y. Jiang 1) National Die & Mold CAD Engineering Research Center
,
Shanghai Jiaotong University
,
Shanghai 200030
,
China 2) Shanghai Volkswagen Automotive Company Limited
,
Shanghai 201805
,
China
金属学报(英文版)
With the combination of a new theoretical formula, physical simulation experiments, the technology of artificial neural network and database, an intelligent system for the prediction of sheet metal drawing capability is constructed for the first time. A modified criterion for sheet metal drawing capability is proposed in this paper, namely, the Technological Limiting Drawing Ratio, TLDR = f(R, n, s, t, F, μ,r_d,r_p…). Based on the studies of other scholars, a new formula is derived to predict the TLDR in this paper. Then a series of orthogonal physical simulation experiments are designed to investigate the effect of technological parameters on the TLDR, and the results are analyzed in the paper. Then the predicting system is constructed with the combination of the theoretical formula, orthogonal experiments, the technology of artifocial neural network and database. The predicted results show good agreements with experimental data, so it can be used to avoid the blindness in the selection of sheet metal before stamping. The system operates under the Windows operating system, and it supports the mechanism of Client/Server as well as Intranet, so the system has high engineering value.
关键词:
TLDR
,
null
,
null
,
null
,
null
,
null
,
null
岳远旺
,
温彤
,
刘澜涛
,
刘磊
,
陈世
,
吴颖
稀有金属
doi:10.13373/j.cnki.cjrm.2014.04.005
在Gleeble-1500热模拟实验机上对多组TC4钛合金试样进行热压缩实验,获得了变形温度在1053～1273 K、应变速率在0.01～ 10.00s-1情况下的真应力-应变曲线.通过BP神经网络对实验数据进行训练,建立了流变应力与应变、应变速率和温度相对应的预测模型,并对该模型的预测性能进行评估验证,采用预测数据构造了预测加工图,最后结合微观组织对预测加工图的可行性进行验证.结果表明,预测数据和实验数据的相关系数R为0.99886,平均相对误差为-0.21％,相对误差标准偏差为2.48 MPa,此模型具有良好的预测性能.预测加工图与实验加工图能够很好的吻合,通过预测加工图对材料的可加工性能进行预测,在一定程度上可以解决实验数据不足的缺陷.真应变为0.916的预测加工图大致分为A,B,C3个区域.失稳A区η值出现极小值(-0.16),应变速率较高时,材料局部发生动态再结晶,出现局部变形失稳的现象;应变速率较低时,组织很不均匀,易失稳.稳定B区具有较大的η值,并出现极大值(0.45),其α相球化效果显著、组织均匀,在相界处出现一定数量的细小等轴组织和较大比例的片状组织,确定此区为最优加工区.稳定C区α相球化效果比较明显,可作为加工区.
关键词:
TC4钛合金
,
流变应力
,
神经网络
,
加工图
,
微观组织
田欣利
,
王龙
,
王望龙
,
李浩
,
唐修检
,
吴志远
人工晶体学报
基于边缘效应驱动裂纹推挤加工技术是一项对工程陶瓷的非传统的接触式加工.基于灰度共生矩阵(GLCM)对采集的Si3N4陶瓷加工表面形貌图像提取了纹理特征参数,充分研究了步长、灰度量化级、方向三个构造参数对灰度共生矩阵的对比度、熵、相关性、能量的影响.结果表明:采用步长4,灰度量化级128时能更好获得较稳定的加工表面纹理特征参数,在采集图像的45°、135°两条对角线上的纹理特征变化更为明显.通过径向基层网络和竞争层网络两类神经网络(NN)的分工协作,针对不同加工参数的纹理特征的预测和分类,并探讨了各加工参数对纹理特征的影响规律.
关键词:
工程陶瓷
,
灰度共生矩阵
,
纹理特征
,
神经网络
B. GUO
,
S. X. Wu
,
H. M. Dai and R. H. Luo School of Materials Science and Engineering
,
Harbin Institute of Technology
,
Harbin 150001
,
China
金属学报(英文版)
Regarding heat forming process of 1Cr18Ni9Ti as typical forming process, this paper presents the study of the effect of various parameters on flow stress, grain size and hardness of formed specimen by means of Gleeble-1500 Thermo-simulation machine and metalloscope. On the basis of technical experi- ment this paper, data are proceeded by applying multilayer feedforward back-propagation neural network, a prediction model of technological parameters together with microstructure and property in the heat forming process is established, thus forging property prediction in the heat forming process is realized.
关键词:
heat forming
,
null
,
null
,
null
J. T.Niu
,
L.J.Sun and P.Karjalainen 1) Harbin Institute of Technology
,
Harbin 150001
,
China 2) University of Oulu
,
FIN-90571
,
Oulu
,
Finland
金属学报(英文版)
For the great significance of the prediction of control parameters selected for hot-rolling and the evaluation of hot-rolling quality for the analysis of prod uction problems and production management, the selection of hot-rolling control parameters was studied for microalloy steel by following the neural network principle. An experimental scheme was first worked out for acquisition of sample data, in which a gleeble-1500 thermal simolator was used to obtain rolling temperature, strain, stain rate, and stress-strain curves. And consequently the aust enite grain sizes was obtained through microscopic observation. The experimental data was then processed through regression. By using the training network of BP algorithm, the mapping relationship between the hotrooling control parameters (rolling temperature, stain, and strain rate) and the microstructural paramete rs (austenite grain in size and flow stress) of microalloy steel was function appro ached for the establishment of a neural network-based model of the austeuite grain size and flow stress of microalloy steel. From the results of estimation made with the neural network based model, the hot-rolling control parameters can be effectively predicted.
关键词:
microalloy steel
,
null
,
null
,
null
,
null
,
null
