Prediction of roll force in skin pass rolling using numerical and artificial neural network methods

A combination of finite element method and neural network methods was used for rapid prediction of the roll force during skin pass rolling of 980DP and 1180CP high strength steels. The FE based commercial package DEFOEM-2D was used to develop a mathematical model of the skin pass rolling operation. Numerical experiments were designed with different process parameters to produce training data for a neural network algorithm. The friction coefficient was considered as an input parameter in the neural network but it was optimised using an iterative method employing an equation that relates the friction coefficient to the rolling force. The load prediction method described in this paper is sufficiently rapid that it can be used in real-time as an adjustment tool for skin pass rolling mills with error within 10% (based on plant data from POSCO).     

基于PCA-BP神经网络模型的充填体强度预测

充填体强度预测对矿山充填设计具有重要意义。选取胶砂比、水泥、石灰、石膏及矿渣含量作为充填体强度影响因素,借助主成分分析（PCA）消除自变量间相关性,降低数据维数,再结合BP神经网络具有较好预测性的特点,建立了PCA-BP模型以预测充填体强度。对18组充填体试验数据进行主成分分析,5个影响因子降维为3个主成分,将其作为BP神经网络的输入因子,进而探讨了隐含层神经元个数对充填体强度训练和预测精度的影响,并比较了PCA-BP神经网络、标准BP神经网络和二次线性回归效果。结果表明：PCA-BP模型最佳预测结构为3-7-1;PCA-BP神经网络结果优于BP神经网络和二次线性回归;PCA-BP神经网络训练和预测的最大相对误差仅为3.65%,实现了充填体强度的准确预测。PCA-BP模型为充填体强度预测提供了一种高精度的分析方法。     

Modeling Pile Capacity Using Support Vector Machines and Generalized Regression Neural Network

This note investigates the potential of support vector machines based regression approach to model the static pile capacity from dynamic stress-wave data. A data set of 105 prestressed precast high strength concrete spun pipe piles is used. Radial basis function and polynomial kernel based support vector machines were used to model the total pile capacity and results were compared with a generalized regression neural network approach. A total of 81 data set were used to train, whereas the remaining 24 data sets were used to test the created model. A correlation coefficient value of 0.977 was achieved by generalized regression neural network in comparison to values of 0.967 and 0.964 achieved by radial basis function and polynomial kernel based support vector machines, respectively. Results suggest an improved performance by generalized regression neural network based approach in comparison to support vector machines but polynomial kernel based support vector machines provide a linear relationship to predict total pile capacity using stress-wave data.     

基于T-S模糊神经网络模型的高炉铁水温度预测建模

 针对高炉炉温与铁水硅含量呈正相关而非严格的线性关系和机制建模的主观性以及其难以建立各变量之间隐含的数学关系等的不足,在数据挖掘理论的基础上,对海量的样本数据进行预处理和特征提取,然后以高炉铁水温度为研究对象,建立了基于T-S模糊神经网络的高炉铁水温度预测模型。最后,应用某高炉数据进行模型验证,并将该模型与T-S模糊多元回归模型以及BP神经网络模型进行比较研究,仿真结果表明T-S模糊神经网络模型的有效性和优越性。     

Adverse effects of tribromoethanol as used in the production of transgenic mice

The authors developed and cross-validated prediction models for newly diagnosed cases of liver disorders by using logistic regression and neural networks. Computerized files of health care encounters from the Fallon Community Health Plan were used to identify 1,674 subjects who had had liver-related health services between July 1, 1992, and June 30, 1993. A total of 219 subjects were confirmed by review of medical records as incident cases. The 1,674 subjects were randomly and evenly divided into training and test sets. The training set was used to derive prediction algorithms based solely on the automated data; the test set was used for cross-validation. The area under the Receiver Operating Characteristic curve for a neural network model was significantly larger than that for logistic regression in the training set (p = 0.04). However, the performance was statistically equivalent in the test set (p = 0.45). Despite its superior performance in the training set, the generalizability of the neural network model is limited. Logistic regression may therefore be preferred over neural network on the basis of its established advantages. More generalizable modeling techniques for neural networks may be necessary before they are practical for medical research.     

金矿浮选回收率预测模型

浮选回收率是金矿选矿过程重要的生产指标,目前主要是通过人工化验的方法检测获得,人工检测周期较长,造成金矿厂不能及时把握浮选工艺水平.在大量现场生产数据的基础上,分别采用多元线性回归和BP神经网络的方法,建立了金矿厂浮选回收率的预测模型.预测误差分析表明,BP神经网络预测模型能较好地预测金矿厂的浮选回收率,当预测相对误差在±3%范围内时,模型的预测精度达到91%,对于实际生产具有良好的参考作用.      

基于极限学习机(ELM)的连铸坯质量预测

针对传统基于BP神经网络建立的连铸坯质量预测模型训练速度慢、适应能力弱、预测精度低等问题,本文提出一种基于极限学习机的连铸坯质量预测方法,对方大特钢60Si2Mn连铸坯中心疏松和中心偏析缺陷进行预测,并与BP和遗传算法优化BP神经网络预测模型的预测结果进行分析对比.结果表明:BP及GA-BP神经网络预测模型对连铸坯中心疏松和中心偏析缺陷的预测准确率分别为50%、57.5%、70%和72.5%;而基于极限学习机的连铸坯预测模型预测准确率更高,对连铸坯中心疏松和中心偏析缺陷的预测准确率分别为85%和82.5%,且该模型具有极快的运算时间,仅需0.1 s.该模型可对连铸坯质量进行迅速准确地分析,为连铸坯质量预测的在线应用提供了一种新的方法.      

Establishment of Neural Network Prediction Model for Terminative Temperature Based on Grey Theory in Hot Metal Pretreatment

 In order to improve the accuracy of model for terminative temperature in steelmaking, it is necessary to predict and control before decarburization. Thus, an optimization neural network model of terminative temperature in the process of dephosphorization by laying correlative degree weights to all input factors related was used. Then simulation experiment of model newly established is conducted utilizing 210 data from a domestic steel plant. The results show that hit rate arrives at 5645% when error is within plus or minus 5%, and the value is 100% when within ±10%. Comparing to the traditional neural network prediction model, the accuracy almost increases by 6839%.Thus, the simulation prediction fits the real perfectly, which accounts for that neural network model for terminative temperature based on grey theory can reflect accurately the practice in dephosphorization. Naturally, this method is effective and practicable.     

基于IPSO-BP神经网络的富氧底吹铜熔炼炉喷枪寿命预测模型

富氧底吹铜熔炼炉喷枪是整个熔炼炉中最重要的部件,并且造价高,易损坏,工作环境恶劣复杂,对其进行准确的寿命预测比较困难。提出了一种基于IPSO-BP神经网络的寿命预测模型,粒子群优化算法解决了BP神经网络容易陷入局部极小值和训练速度慢的问题,优化的粒子群算法优化了惯性权重和学习因子,进一步加快了训练速度和搜索速度,提高了BP神经网络跳出局部极小值的能力。以工作环境中容易对喷枪寿命造成影响的因素作为输入,喷枪寿命作为输出,通过实际生产采集的数据做验证,并与BP神经网络和PSO-BP神经网络预测模型作对比。结果表明,本文构建的寿命预测模型预测效果比BP神经网络和PSO-BP神经网络的预测更加准确,精度更高,该预测模型为富氧底吹铜熔炼的喷枪寿命预测提供了一种方法借鉴。     

Neural network modelling of flow stress and mechanical properties for hot strip rolling of TRIP steel using efficient learning algorithm

Abstract

Transformation 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.     

BP神经网络和弹跳方程在铝热连轧厚度预报中的综合应用

采用BP神经网络方法建立了铝热连轧精轧机组出口厚度预测模型,采用试错法解决了中间隐层最佳隐层单元数的问题,采用回归法确定了轧机的相关弹性系数,建立了轧机的弹跳方程数学模型。通过比较有、无传统弹跳方程数学模型输入的神经网络厚度预测模型,确定了弹跳方程对神经网络在热连轧厚度预报应用中的重要性,提出了BP神经网络与数学模型相结合的综合网络方法。相比全部使用整体神经网络,中间隐层最佳隐层单元数减小,网络结构得以简化,网络负担减小,网络的泛化能力也得到加强,同时也进一步提高了预报精度。预测结果与实测数据对比表明,相对误差在1％以内,实现了高精度预报,为铝热连轧出口厚度预报提供了一条准确高效的新途径。     

中厚板轧制过程智能化温度预报模型

 采用有限元(FEM)程序模拟计算了中厚板轧制过程中的温度变化,得到与实测温度符合甚好的模拟结果。以模拟计算结果为基础,建立了BP神经网络和回归温度预报模型。采用两种模型对中厚板热轧过程中轧件表面温度变化情况进行了预报。结果表明,神经元网络模型的预报值较回归模型更接近FEM模拟计算值和实测值,可将神经元网络模型应用于中厚板轧制过程中轧件表面温度变化的在线预报。     

极限学习机在中厚板轧制力预报中的应用

摘要：轧制力是影响中厚板厚度精度和板型的关键因素。兴澄特钢中厚板轧机二级模型采用传统Sims公式计算轧制力，精度较低。为提高轧制力预报精度，首先基于大量历史生产数据，通过主成分分析法对影响轧制力的因素进行处理和分析，选出权重较大的影响因子；其次选取现场代表钢种进行热模拟压缩实验，在此基础上提出基于极限学习机(ELM)的综合神经网络轧制力预报模型，即先通过化学成分计算出基准变形抗力，再将其作为轧制力神经网络输入变量进行轧制力预报。建模采用10折10次交叉验证确定最佳网络隐层节点数，并用现场实际生产过程数据对网络进行训练与测试。综合神经网络模型投入现场生产，轧制力预报相对误差±10%以内占比提高15.61%，钢板头部厚度命中率提高1.9%。     

Hybrid Model of Molten Steel Temperature Prediction Based on Ladle Heat Status and Artificial Neural Network简

Aiming at the characteristics of the practical steelmaking process, a hybrid model based on ladle heat sta- tus and artificial neural network has been proposed to predict molten steel temperature. The hybrid model could over- come the difficulty of accurate prediction using a single mathematical model, and solve the problem of lacking the consideration of the influence of ladle heat status on the steel temperature in an intelligent model. By using the hybrid model method, forward and backward prediction models for molten steel temperature in steelmaking process are es- tablished and are used in a steelmaking plant. The forward model, starting from the end-point of BOF, predicts the temperature in argon-blowing station, starting temperature in LF, end temperature in LF and tundish temperature forwards, with the production process evolving. The backward model, starting from the required tundish tempera- ture, calculates target end temperature in LF, target starting temperature in LF, target temperature in argon-blo- wiag station and target BOF end-point temperature backwards. Actual application results show that the models have better prediction accuracy and are satisfying for the process of practical production.     

基于GRNN神经网络的4200轧机宽展模型

 轧制过程中,针对4200轧机在轧件宽展变化自动预测和控制,分析了轧制过程中宽展变化的影响因素。在神经网络技术和现场实测数据的基础上,利用Matlab人工神经网络工具箱,应用GRNN广义回归神经网络建立宽展变化预测模型来提高轧制宽展变化预测的精度。结果表明,该方法建立的模型可以实现对宽展变化的预测,其预测精度有较大提高。     

基于灰色理论的铁水预处理终点磷含量神经网络预测模型

 在传统BP神经网络预测模型的基础上,依据灰色理论中的灰色关联度,提出了输出变量各个影响因素的灰色关联度权值,首次建立基于灰色理论的神经网络预测模型,并依据国内某钢厂300组实际生产数据进行仿真试验。试验结果表明：误差绝对值小于5%的炉数有39炉,占总炉数的65.00%;误差绝对值小于10%的炉数共有58炉,占到96.67%。与传统BP神经网络相比,基于灰色理论的神经网络模型的预测精度提高近12.5%,说明基于灰色理论的铁水预处理终点磷含量神经网络预测模型能更精确地反映现场实际水平。     

BOF→LF→CC流程钢水温度预报

针对炼钢连铸流程的工艺特点和生产数据,建立了基于BP神经网络的"BOF→LF→CC"流程钢水温度预报模型。通过相关性分析筛选模型变量,利用五数概括法筛选数据,采用LM优化算法改进BP神经网络,利用生产数据对模型进行了训练和测试。并用Java语言开发了钢水温度预报模型的程序,在某钢厂进行了应用。结果表明,各区段钢水温度预报模型的预报命中率基本可以满足生产的要求。     

基于FA-PSO-RBF神经网络的富氧底吹铜锍品位预测模型

铜锍品位是富氧底吹铜熔炼过程中的一个关键工艺参数,针对铜锍品位实时检测困难、检测结果滞后时间长、指导生产工艺参数优化滞后等问题,基于生产数据深入挖掘及处理,提出了一种基于FA-PSO-RBF神经网络的铜锍品位预测模型。首先为了降低模型的预测误差,利用FA分析方法对原始生产数据进行降维处理,确定主要因子数量为6个,并计算因子得分,然后针对RBF神经网络模型对关键参数依赖性较大的不足,利用改进PSO算法对网络结构中的关键参数进行寻优,最后,以因子得分为输入,铜锍品位值为输出,通过实际生产数据验证模型的准确性,并与RBF、标准PSO-RBF预测模型进行对比,结果表明,本文构建的铜锍品位预测模型预测精度更高,与标准PSO-RBF预测模型相比,RMSE和MAE的值分别降低了17.2%和21.2%,该预测模型对富氧底吹铜熔炼生产过程参数优化控制提供了一种方法借鉴。     

Modeling and Predicting Biological Performance of Contact Stabilization Process Using Artificial Neural Networks

In this paper, the microfauna distribution data of a contact stabilization process were used in a neural network system to model and predict the biological activity of the effluent. Five uncorrelated components of the microfauna were used as the artificial neural network model input to predict the dehydrogenase activity of the effluent (DAE) using back-propagation and general regression algorithms. The models’ optimum architectures were determined for the back-propagation neural network (BPNN) model by varying the number of hidden layers, hidden transfer functions, test set size percentages, and initial weights. Comparison of the two model prediction results showed that the genetic general regression neural network model demonstrated the ability to calibrate the multicomponent microfauna, and yielded reliable DAE close to that resulting from direct experimentation, and thus was judged superior to BPNN models.