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BP神经网络的钢水温度预定模型

针对目前钢水温度预定方法存在不足,在分析钢水温度预定原理的基础上,在邯钢邯宝炼钢厂建立了基于BP神经网络的精炼终点目标温度和转炉终点目标温度的动态预定模型。利用邯宝炼钢厂的历史生产数据对模型进行了训练和测试,并进行了现场应用试验。结果表明,预定模型对转炉和精炼终点目标温度进行了优化,应用预定模型后,LF开始温度命中率提高到75%,中间包温度命中率提高到96.7%。     

基于Kmeans–BP神经网络的KR工序终点铁水硫含量预测模型

针对KR工序终点铁水硫含量预测问题,提出一种基于Kmeans聚类分析和BP神经网络（BPNN）相结合的建模方法。首先,通过Kmeans聚类对KR工序生产数据进行模式识别和分类,构建不同工况特征的数据集;然后,基于BP神经网络,针对不同数据集训练预测模型;最后,将不同数据集的预测模型进行集成,形成最终的终点铁水硫含量预测模型,实现对不同铁水条件和工况条件的预测。利用某钢铁企业实际生产数据,分别用基于脱硫反应动力学、BP神经网络和Kmeans–BPNN方法建立的预测模型,对KR工序终点铁水硫含量进行预测。结果表明,Kmeans–BPNN的KR工序终点硫含量预测模型的精度显著高于脱硫反应动力学和BP神经网络的预测模型。      

智能LF控制系统的研究

提出一种基于人工神经网络的智能LF控制系统模型,该系统的核心是LF精炼过程钢水温度和成分的实时预测,并确定了一种部分反馈的人工神经网络进行钢水温度和成分的实时预测。     

Hybrid Modeling for Soft Sensing of Molten Steel Temperature in LF

 Aiming at the limitations of traditional thermal model and intelligent model, a new hybrid model is established for soft sensing of the molten steel temperature in LF. Firstly, a thermal model based on energy conservation is described; and then, an improved intelligent model based on process data is presented by ensemble ELM (extreme learning machine) for predicting the molten steel temperature in LF. Secondly, the self adaptive data fusion is proposed as a hybrid modeling method to combine the thermal model with the intelligent model. The new hybrid model could complement mutual advantage of two models by combination. It can overcome the shortcoming of parameters obtained on line hardly in a thermal model and the disadvantage of lacking the analysis of ladle furnace metallurgical process in an intelligent model. The new hybrid model is applied to a 300 t LF in Baoshan Iron and Steel Co Ltd for predicting the molten steel temperature. The experiments demonstrate that the hybrid model has good generalization performance and high accuracy.     

基于AdaBoost.RS算法的LF炉钢水温度预报分析

LF炉钢水温度的精准控制有利于缩短钢的冶炼时间,从而节约其生产成本。而获得准确的LF炉钢水温度预报是钢水温度控制的先决条件。通过分析LF炉冶炼过程对钢水温度的影响因素,提出一种适用于LF炉钢水温度预报同时具有增量学习功能的AdaBoost.RS集成建模算法。该算法引入松弛变量和遗忘因子2个参数,在提高预测精度的同时,可以克服大噪声数据带来的干扰,同时增量学习可以降低早期生产数据对模型的影响。以福建三钢有限责任公司100tLF炉为研究对象,采用5个测试函数验证算法的抗噪性能,分别用静态数据和动态数据对钢水出站的终点温度进行预报。实验结果表明,预测的绝对误差小于10℃的样本数量超过了样本总数的90%,算法精度较高,有利于实际生产应用。     

LF炉钢水温度的预估

考察了影响LF炉钢水温度的因素.从能量平衡的角度出发,将整个钢包体系作为1个系统,确定加热功率、钢水质量、钢包温度、包龄、渣厚、氩气吹入量、时段7个主要因素作为网络的输入量,应用BP神经元网络进行初步预报,再根据专家工艺知识对一些特殊情况进行修正.使用本方法可减少点测次数,获得连续的钢水温度信息,降低炼钢成本,提高质量...     

LF精炼终点钢水温度灰箱预报模型

LF精炼工序在炼钢过程起着调节温度的关键作用,准确预报LF精炼终点钢水温度对实际生产有重要意义.传统的LF精炼预报模型包括机理模型与黑箱模型.机理预报模型能够体现各工艺因素对终点钢水温度的影响,但由于LF精炼传热机理研究尚不完善,依靠机理模型预报终点钢水温度,难以达到预期效果;黑箱预报模型能够准确预报终点钢水温度,但不能反映精炼过程各工艺因素对钢水温度的影响,尤其当生产工艺条件发生改变时,黑箱模型在应用上会受到限制.本文以方大特钢LF精炼炉为研究对象,建立一种机理预报模型与黑箱预报模型(BP神经网络预报模型)相结合的LF精炼终点钢水温度灰箱预报模型.该模型既能反映各工艺因素对终点钢水温度的影响,又能准确预测终点钢水温度,其终点钢水温度预测误差在±5℃以内的命中率可以达到95%以上.      

新型纳米级微孔隔热材料在炼钢生产中的应用

唐山中厚板材有限公司针对炼钢生产中钢水热量损失过大问题,在转炉、钢包和中间包上,系统采用了新型WDS纳米级微孔隔热材料,提高了耐火衬的蓄热量,在不影响耐火材料使用寿命的情况下,转炉的终点温度提高了7℃,从转炉、钢包到LF炉过程温降速度减小了0.3℃/min,采取降低LF炉出站温度5℃的方式,中间包后期钢水温度仍然能够满足连铸工艺需要,达到了节能降耗的目的,可以产生综合经济效益1480万元/a。     

Thermodynamic analysis of steel deoxidization processes during tapping and refining operations

A thermodynamic model based on the interaction parameter approach for molten metal solutions and a quasi‐chemical model for molten slags and non‐metallic inclusions was employed to analyze steel deoxidization during tapping and refining operations in a ladle furnace. This model is able to predict the mineralogical nature of non‐metallic inclusions and their amount through thermodynamics and mass balances. It was found that the addition sequence of deoxidizers during a tapping procedure influences the nature and amount of the different inclusions. Besides, the metal‐slag equilibrium is readily reached after tapping and at the end of steel treatment in the ladle furnace. The model proved to be useful for steel cleanliness assessments and the design of steel deoxidization practices.     

超低温LNG储罐用钢的炼钢生产实践

介绍了超低温LNG储罐用钢的炼钢生产实践。采用转炉双渣、双联低温冶炼脱磷技术实现了转炉终点磷含量≤0.002 0%;钢水扒渣与LF脱硫实现了硫含量≤0.001 0%;RH真空度≤200 Pa,循环时间30 min,使钢中氮、氢含量分别控制在0.003 0%和0.000 1%以下;采用连铸全程保护浇铸工艺、铸坯高温矫直工艺以及铸坯缓冷工艺,抑制了铸坯表面和皮下裂纹的产生。     

Technical Study on Ultra-Low Sulfur Steel Production in Ansteel

Based on the fact of long period deep desulfurization treatment in LF,the relationships among top slag constituent in LF,molten steel constituent,stirring ability of blowing argon,molten steel temperature and desulphurization rate were analyzed.Through the experiments,the parameters about treatment technology of top slag in LF,the [Als] content in molten steel,slag charge match,molten steel temperature and the argon flow for stirring have been optimized.The desulphurization treatment period in LF can be shortened by 5～8 minutes.The target sulfur content in molten steel can be controlled below 30 ppm within one LF treatment period which is only 36 minutes.The LF treatment period of ultra-low sulfur steel can primarily match with the continuous casting period,multi-heat continuous casting can be ensured.     

55CrMnA弹簧扁钢的研制

采用氧气顶吹转炉、LF炉精炼、小方坯连铸机、型材轧机等工序开发生产了55CrMnA弹簧扁钢。通过采取拉碳法、稳定的终点控制、复合钢水脱氧及LF炉精炼工艺、优化的连铸控制技术、合理的轧制温度和冷却制度等措施,生产出的55CrMnA弹簧扁钢各项性能指标均符合GB/T1222—2007要求。     

LF精炼成分预报模型的开发

采用经验计算、统计回归以及基于自学习的参考炉次法,建立了LF精炼成分的预报模型,对精炼过程中及精炼终点的钢水成分进行预报。结果表明,采用经验计算结合统计回归的方法可以预报铌、钛、碳、锰等收得率稳定的合金元素含量,采用基于自学习的参考炉次法可以预报硅、铝等收得率不稳定的合金元素含量,该模型基本满足了现场生产的要求。     

钢包精炼过程中钢水成分微调及温度预报

开发了钢包精炼（ＬＦ）过程钢水成分微调模型并应用于现场。计算了不同合金加入钢包后引起钢水温度的变化,为ＬＦ钢水温度的精确控制提供了依据。     

基于数据驱动的转炉二吹阶段钢水温度动态预测模型

转炉钢水温度是转炉终点控制的工艺参数之一,精确的钢水温度预测对转炉终点控制具有重要的指导意义。然而,以往的大多数转炉终点预测模型属于静态模型,只能够实现对转炉吹炼终点钢水温度的预测,无法实现动态预测,导致模型的作用有限。针对该问题,提出了一种基于数据驱动的转炉二吹阶段钢水温度动态预测模型。模型先通过新案例主吹阶段的工艺参数,基于案例推理算法找到历史案例库中相似案例。再利用相似案例的二吹阶段工艺参数并基于长短期记忆网络（Long short-term memory,LSTM）算法训练工艺参数与钢水温度的变化关系。然后利用训练好的LSTM模型,计算新案例二吹阶段的钢水温度变化。最后,利用某钢厂实际生产数据,研究了不同重用案例个数及神经元个数对模型预测精度的影响,实验结果表明:模型在重用案例个数为4,神经元个数为10时模型的预测精度最高,此时模型对钢水温度的预测误差在[?5 ℃, 5 ℃]、[?10 ℃,10 ℃]和[?15 ℃,15 ℃]的命中率分别达到40.33%、68.92%和88.33%,模型的性能高于传统二次方模型和三次方模型。      

Hybrid Neural Network Model for RH Vacuum Refining Process Control

A hybrid neural network model, in which RH process (theoretical) model is combined organically with neural network (NN) and case-base reasoning (CBR), was established.The CBR method was used to select the operation mode and the RH operational guide parameters for different steel grades according to the initial conditions of molten steel, and a three-layer BP neural network was adopted to deal with nonlinear factors for improving and compensating the limitations of technological model for RH process control and end-point prediction. It was verified that the hybrid neural network is effective for improving the precision and calculation efficiency of the model.     

LF炉钢水成分预报模型的建立及应用

宣钢LF炉钢水成分预报模型,通过机理模型算法,准确、快速地提供了精炼过程中钢水成分的实时预报,减少了精炼通电时间和测温次数,提高了精炼生产效率;充分发挥了LF炉优质、低耗、低成本的优势,保证了连铸生产的顺行.     

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。     

唐钢150tLF供中薄板连铸钢液温度改进实践

针对唐钢150t LF供中薄板连铸中间包钢液温度过高或过低的情况,通过对影响LF和中间包钢液温降的因素分析,经过优化相关工艺制度,提高了LF供钢离站温度的灵活性及中间包温降的稳定性,实现了中间包温度较高的可控性,在提高中间包温度合格率、降低生产事故及减少铸坯质量缺陷方面取得了显著成效。