基于灰色理论的烧结矿质量预测智能优化研究

针对铁矿石烧结过程工艺流程长、影响因素多、机理复杂的特点,提出一种基于灰色理论的烧结矿质量预测智能优化方法,为生产提供准确的烧结矿质量信息.本模型根据灰色理论模型的原理确定出参考序列和比较序列,利用灰色关联分析方法评价参考序列与比较序列的合理性,从而指导实际生产操作.研究结果表明,本模型能在贫信息、小样本的情况下准确预测出烧结矿质量信息,其优点是能在样本数据较少的状态下通过简单的EXCEL程序计算,预测出精度较高、满意度较好的结果.和传统的预测模型相比,灰色关联理论在烧结矿质量预测方面值得大力应用和推广.     

基于LS-SVM的烧结矿碱度预报研究

开发了最小二乘支持向量机(LS-SVM)模型,并用于对烧结矿碱度进行预测.仿真结果证明,本模型能在小样本贫信息的条件下对烧结矿碱度做出比较准确的预测.此种模型具有预测精度高、所需样本少、计算简便等优点.和BP神经网络算法相比,最小二乘支持向量机算法有很好的应用前景和推广价值.     

基于改进BP神经网络的烧结矿FeO含量预测

影响烧结矿FeO含量的因素较多且FeO含量与各因素间呈现非线性关系，预测难度较大。针对烧结矿FeO含量难以直接预测的问题，提出一种Dropout算法与Adam算法和四层BP神经网络相融合的烧结矿FeO含量预测模型。为提高烧结矿FeO含量的预测准确率，结合烧结工艺，选取与烧结矿FeO含量强相关性的烧结机尾断面热成像关键帧的温度特征作为模型的参数输入。利用Dropout算法改善四层BP神经网络结构，Adam算法优化四层BP神经网络的训练过程，进而提高模型的预测精度和泛化能力。试验表明，改进的模型预测烧结矿FeO含量误差值在±0.5、±0.8和±1.0时，命中率分别达到77.42%、88.71%和96.77%。与三层BP神经网络预测模型和支持向量机回归(support vector regression, SVR)模型相比，该模型的误差更小，同时预测精度也得到显著提升。     

基于烧结大数据预测小于10 mm烧结矿含量模型

为了给高炉提供合格的烧结矿，提出基于烧结生产线各个环节的大量数据，将XGBoost算法、因子相关分析与深度学习算法相结合的大数据技术对烧结矿小于10 mm粒级含量进行预测。首先，对烧结厂数据库的数据进行搜集、整合和预处理；其次，进行因子分析，筛选出适合建模的14个相关变量并进行变量之间的相关性分析；最后，建立深度神经网络算法模型。通过测试并与传统算法模型进行性能比较，结果表明，模型预测效果很好，达到了精确预测烧结矿小于10 mm粒级含量的目的，对烧结实际生产具有很好的指导意义。     

基于BP神经网络钒钛烧结矿低温还原粉化性能预测

为了改善钒钛烧结矿的低温还原粉化性能,将BP神经网络算法应用于钒钛烧结矿低温还原粉化性能预测中,指标数据的样本分为输入样本和输出样本,其中:输入样本为配碳量、碱度、w(Mg O)以及FMG粉配比,输出样本为钒钛烧结矿RDI+3.15,运用BP神经网络算法探索输入样本与输出样本间的关系。结果表明:BP神经网络模型适用于烧结矿还原粉化性能的研究,可以根据输入样本有效的预测输出样本,且平均相对误差为5.7%,满足工程实践中预测精度的要求,为钒钛烧结矿生产提供了指导。     

组合模型在农业用水量预测中的应用

在分析灰色模型与人工神经网络模型特点的基础上提出了灰色神经网络组合预测模型,并以最小二乘法确定了2个单一模型权重系数的分配.结果显示,灰色神经网络组合预测模型的最大、最小及平均误差均明显优于2个单一模型,有效提高了预测的精度.     

基于灰色神经网络的金属疲劳寿命预测研究

为了对金属轴类零件的低周扭转疲劳寿命进行评估预测,搭建了灰色模型和灰色LSTM神经网络组合模型,并根据大量试验研究,对比分析了金属轴类零件低周扭转疲劳的实际循环寿命与用模型预测的循环寿命之间的误差.试验结果表明,提出的灰色神经网络组合模型相对于传统单一模型,能对金属轴类零件的扭转循环寿命进行有效预测,降低了预测寿命与实际寿命间的相对误差,提高了预测精度,为金属轴类零件的低周扭转疲劳寿命预测提供参考依据,具有一定的实用价值.     

烧结矿质量预测中神经网络的结构优化

利用BP神经网络，建立了烧结矿质量预测模型，预测烧结矿FeO含量和碱度及指标。并采取遗传算法、网络隐含层节点自构性学习等办法优化网络构造。仿真结果表明，模型能取得良好的预测结果。     

基于自适应遗传神经网络的烧结矿化学成分超前预报模型

提出了自适应遗传神经网络模型预测烧结矿化学成分的方法，用实际烧结生产数据对模型进行训练，并用该模型对烧结矿化学成分进行预报，仿真结果表明。该模型取得了很好的预测效果。     

基于BP神经网络的烧结矿性能预报模型

 为解决烧结矿预报模型中未考虑铁矿粉高温基础特性的情况,在预报模型中添加了反应铁矿粉高温性能的同化反应特征数,即流动性特征数。采用BP神经网络建立烧结矿性能预报模型。选择影响高炉生产的烧结矿指标作为输出,分析影响这些指标的烧结操作制度,铁矿粉的高温、物化特性作为输入;通过BP神经网络建立预测模型,并对BP神经网络的算法进行优化。预报模型采用8-17-4的BP神经网络结构,经过训练后,预测精度达到85%以上,具有很好的准确性和自适应性。     

Simulation and prediction of the alkalinity in sintering process based on grey least support vector machine

 Prediction of the alkalinity is a difficult problem during the process of sintering .Whether the level of he alkalinity of it is successful or not direct relates to the quality of sinter.By now,there isn’t a very good method due to the high complexity ,high non-linear, strong coupling, high delay-time and etc.A grey support vector machine model was proposed on the basis of the models.The fluctuation of data sequence is weakened by the grey theory and the support vector machine is capable of processing non-linear adaptable information, and the grey support vector machine is a combination of those advantages. The results reveal, the alkalinity of sinter can be accurately predicted through this model by reference to small sample and information. It was concluded that the grey support vector machine model is effective with the advantages of high precision, less samples required and simple calculation.     

Simulation and Prediction of Alkalinity in Sintering Process Based on Grey Least Squares Support Vector Machine

The prediction of the alkalinity is difficult during the sintering process. Whether or not the level of the alkalinity of sintering process is successful is directly related to the quality of sinter. There is no very good method for predicting the alkalinity by now owing to the high complexity, high nonlinearity, strong coupling, high time delay, and etc. Therefore, a new technique, the grey squares support machine, was introduced. The grey support vector machine model of the alkalinity enabled the development of new equation and algorithm to predict the alkalinity. During modelling, the fluctuation of data sequence was weakened by the grey theory and the support vector machine was capable of processing nonlinear adaptable information, and the grey support vector machine has a combination of those advantages. The results revealed that the alkalinity of sinter could be accurately predicted using this model by reference to small sample and information. The experimental results showed that the grey support vector machine model was effective and practical owing to the advantages of high precision, less samples required, and simple calculation.     

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。     

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.     

基于综合神经网络的优化配矿系统模拟模型及应用

针对烧结配矿的复杂性，建立了综合神经网络模拟模型，用以仿真烧结配矿与烧结矿产质量指标问的关系，并利用生产数据对模型进行了检验。综合神经网络的应用能大大提高预报的命中率。同时，对在其他领域的应用，也有很好的参考价值。