共查询到18条相似文献,搜索用时 281 毫秒
1.
2.
利用人工神经网络模型预测SS400热轧板带力学性能 总被引:10,自引:1,他引:9
针对传统的回归方法的某些不足 ,采用了人工神经网络的方法预测力学性能。从宝钢 2 0 5 0热轧管理机中随机抽取数据 ,用人工神经网络中的BP网络建立原始化学成分和热轧生产的主要工艺参数与产品力学性能之间的关系。离线仿真表明 ,产品力学性能的预报值与实际值拟合良好 ,预报结果的相对误差很小 ,屈服强度相对误差 88%在± 4 %以内 ,抗拉强度的相对误差 86 %在± 2 %以内 ,伸长率的相对误差 78%在± 6%以内。 相似文献
3.
以现场收集的四钢轧SS400热轧板的原始化学成分、终轧厚度、实测的力学性能数据为基础,通过回归模型和人工神经网络BP算法建模,确定其相互关系,并最终通过其化学成分和终轧厚度来预测产品力学性能。现场使用证明,在现有的条件下,回归模型比人工神经网络更适用。经测试,其抗拉强度预报值与实测值的相对误差有80%7g超过5%,屈服强度预报值与实测值的相对误差有76%不超过10%,延伸率预报值与实测值的相对误差有77%不超过10%。 相似文献
4.
5.
应用人工神经网络对高炉下部热量水平与风量、风温、湿度、煤气利用率及负荷的关系进行拟合和预报,并通过训练好的神经网络进行工艺参数离线模拟调整,为炉稳定生产提供一种有效途径。 相似文献
6.
传统的产品力学性能检测是一种建立在统计学随机抽样理论基础上的检验方法,即在实验室中对取样板卷的头尾部切割样品进行检测,检测结果代表整批产品的力学性能。由于钢材生产流程长,生产过程控制参数存在一定的波动,传统力学性能检测方法不能反应每一卷带钢的力学性能,所检测样品的代表性不够充分。随着工业互联网、大数据和人工智能技术的飞速发展,特别是工业大数据相关技术的发展和应用,为这一问题的解决提供了新的途径。以实现山东钢铁集团日照有限公司热连轧产品力学性能在线预报为试验对象,以热连轧产品生产全流程关键控制工艺参数为基础,采用神经元网络、随机森林等算法建立碳素结构钢、低合金高强度结构钢的力学性能预报模型,构建了一种基于工业大数据为基础的热轧产品力学性能预报系统,包括数据采集、数据清洗、模型训练、结果分析、再现性试验和在线应用。力学性能在线预报系统已成功运行2年多时间,系统的预测精度高、稳定可靠。预测结果精度在±6%以内的比例达到90%以上,MAPE(平均绝对百分误差)不大于4%,均低于再现性检测水平,预测结果完全可以取代检测试验;提高了生产效率,缩短了产品的检测周期,轧后即可掌握产品的力学性能,降低了生产成本,已成为生产运行过程不可缺少的环节。 相似文献
7.
用人工神经网络模型预测高碳钢高速线材力学性能 总被引:4,自引:1,他引:3
以现场正交试验数据为基础,采用人工神经网络方法预测高碳钢高碳钢高速线材产品力学性能,将预报结果与试验结果相比较可知,该模型具有较高的精度。 相似文献
8.
基于人工神经网络软件Matlab,采用改进的BP(Back Propagation)网络Levenberg-Marquardt训练规则,根据中板轧件入口厚度、出口厚度和宽度、轧辊直径、轧制速度和温度、轧件主要成分等输入参数,优化计算2350中板轧机的轧制压力和力矩。通过该网络的μ参数的自适应调整,提高收敛速度,使2350中板轧机轧制力和力矩的预报精度显著提高。轧制压力的BP网络预报值相对误差小于3%,轧制力矩的BP网络预报值相对误差小于4%。 相似文献
9.
10.
11.
12.
13.
Nowadays it is known that the thermomechanical schedules applied during hot rolling of flat products provide the steel with improved mechanical properties.In this work an optimisation tool,OptiLam (OptiLam v.1),based on a predictive software and capable of generating optimised rolling schedules to obtain the desired mechanical properties in the final product is described.OptiLam includes some well-known metallurgical models which predict microstructural evolution during hot rolling and the transformation austenite/ferrite during the cooling.Furthermore,an optimisation algorithm,which is based on the gradient method,has been added,in order to design thermomechanical sequences when a specific final grain size is desired.OptiLam has been used to optimise rolling parameters,such as strain and temperature.Here,some of the results of the software validation performed by means of hot torsion tests are presented,showing also the functionality of the tool.Finally,the application of classical optimisation models,based on the gradient method,to hot rolling operations,is also discussed. 相似文献
14.
15.
《钢铁冶炼》2013,40(4):298-304
AbstractTransformation induced plasticity (TRIP) steels exhibit excellent strength and ductility and can be engineered to provide excellent formability for manufacturing complex parts. In this study, a data driven multi-input multi-output multilayer perceptron based neural network model has been developed to predict the flow stress, yield strength, ultimate tensile strength and elongation as a function of composition and thermomechanical processing parameters for strip rolling of TRIP steels. The input parameters in this generalised regression artificial neural network (ANN) model are steel chemistry, cooling rate and finish roll temperature. The network training architecture has been optimised using the Broyden–Fletcher–Goldfarb–Shanno algorithm to minimise the network training error within few training cycles. The algorithm facilitates a faster convergence of network training and testing errors. There has been an excellent agreement between the ANN model predictions and the target (measured) values for flow stress and mechanical properties depicted by the respective regression fit between these values. 相似文献
16.
Radko Kaspar 《国际钢铁研究》2003,74(5):318-326
By using a thin slab casting simulator combined with the hot deformation simulator WUMSI, laboratory tests were performed to investigate the microstructure processes and mechanical properties in the process of thin slab direct rolling (TSDR). The paper shows the possibilities to improve the initial as‐cast state of microstructure prior to hot rolling (microvoids, dendritic structure, austenite grain size, state of precipitation). The main part of the study is dedicated to the role of microalloying and sulphur for the austenite grain control and for the precipitation hardening in the final structure. On examples of selected low carbon steel grades the effect of the variation of the process parameters of hot rolling and cooling on the microstructure and mechanical properties is presented. 相似文献
17.
利用MATLAB软件建立了反映材料热变形本构关系的神经网络模型,该模型中采用遗传算法优化其权值和阈值提高了网络收敛的稳定性。并采用Themecmastor-Z型热加工模拟试验机上进行的TC11钛合金等温恒应变速率压缩试验获得的试验数据进行训练,建立了TC11钛合金热变形本构关系的BP神经网络模型,并进行了预测,预测误差小于10%。 相似文献
18.