人工神经网络在层流冷却卷取温度预报中的应用

针对宝山钢铁（集团）公司2050热连轧层流冷却系统，采用神经网络与数学模型相结合的方法，给出优化的层流冷却对流换热系数，以实现准确地预报卷取温度的目的。结果表明，采用神经网络计算出的对流换热系数后，卷取温度的计算值与实测值的标准差降低了22．84％，效果显著。     

基于BP神经网络的热轧带钢卷取温度预报

 为了提高卷取温度的精度,采用BP神经网络方法并结合大量的现场数据,对热轧带钢层流冷却水冷数学模型中的综合换热系数因子进行预报,将预报结果应用于计算卷取温度的数学模型中,可将卷取温度的计算值控制在目标值的±15 ℃之间,大大提高了卷取温度的精度,具有在线应用的前景。     

热轧带钢卷取温度高精度预报的人工神经网络方法

针对传统卷取温度模型的固有缺陷，为了满足扩展钢种，规格及卷取温度高精度的要求，提出热轧带钢卷取温度预报的人工神经网络方法，运用实际生产数据对BP神经网络进行了训练和仿真。结果表明，它能准确地预报钢卷取温度，实现卷取温度高精度的实时预报，有在线实际应用的前景。     

基于神经网络的热带层流基本热流密度的计算

利用现场的数据，采用BP神经元网络预报热连轧层流水冷区集管组内的基本热流密度，将预报的结果用于上、下集管组的热流密度的数学模型计算，进而优化层冷集管组的水冷温降计算数学模型的精度。将结果与采用多元回归方法所得到的结果作比较，表明采用BP神经元网络计算基本热流密度的精度要高于多元回归方法的计算精度，卷取温度的计算值与实测值的标准差比解析回归方法减少了近20％，说明该方法具有良好的在线应用前景。     

层流冷却中带钢温度分布模型的开发

在热轧带钢层冷却控制数学模型中，由于忽略带钢内部的热传导而使卷取温度控制不良，本文采用离线二维数模计算带钢沿厚度方向上的温度分布，在线控制中给予补偿，取得较好的效果。     

Numerical determination of heat transfer coefficient for boiling phenomenon at runout table of hot strip mill

Abstract

The heat transfer coefficient during film boiling at the runout table of the hot strip mill is usually determined by experimental methods. Described in the present paper is a finite difference based model for analysis of the thermal behaviour of the strip during cooling at the runout table of the hot strip mill at Tata Steel, India. The model, developed for the prediction of strip temperature, is used to determine the heat transfer coefficient at the water/strip interface while water cooling occurs. A simple form of polynomial as a function of the strip surface temperature is proposed to describe the heat transfer coefficient at the water/strip interface. Good correlation has been found between model predicted temperatures considering the polynomial type heat transfer coefficient and the actual coiling temperature.     

带钢层流冷却过程中冲击穿透深度的数值模拟

带钢在层流冷却过程中距表面较近的区域温度存在反复升降的现象,造成厚度方向上组织和性能的差异。结合酒钢CSP热轧带钢生产数据,建立一维热轧带钢有限元模型,计算层流冷却过程中带钢的温度场。提出了冷却过程中带钢冲击穿透深度的概念,并初步探究其影响因素。厚度为3和4mm的带钢计算得出的卷取温度比实测温度分别高3和8℃,相对误差分别为0.44%和1.16%,验证了模型和假设的合理性。结果表明,冷却过程中冲击穿透深度受带钢的导热系数、平流区的对流换热系数、带钢表面温度和喷嘴分布的影响;带钢上表面喷嘴分布较少,冲击穿透深度随对流换热系数的增大而增加,下表面喷嘴分布密集起主导作用,增加对流换热系数,冲击穿透深度几乎不受影响。     

水流量对热轧钢板层流冷却过程对流换热系数的影响

提高带钢层流冷却控制模型的精度,关键是建立精确的对流换热系数与冷却工艺之间的关系.采用有限差分法和反向热传导法,获得了实验条件下钢板表面的对流换热系数及表面温度.研究了不同水流量(0.9~2.1 m³·h^-1)对换热系数与表面温度变化规律的影响.在层流冷却过程中,对流换热系数与表面温度呈非线性关系;在距离驻点70 mm内,水流量对换热系数随表面温度变化规律没影响;远离驻点70 mm外,对流换热系数比随远离冲击区驻点距离的增加而减小.采用所确定的换热系数计算得到的温降曲线与实测曲线吻合较好.     

层流冷却的前馈控制

为提高热轧带钢层流冷却卷取目标温度的控制精度,根据冷却过程的传热机理,分析了带钢层流冷却的传热过程.在此基础上,给出了冷却控制的空冷和水冷预测数学模型,分析并阐述了层流冷却控制系统的前馈控制算法及其在实际控制中的应用.本前馈控制的使用效果良好,具有较高的目标卷取温度控制精度,能满足生产的需要.     

安钢1780mm带钢热连轧卷取温度控制系统的分析

系统地对安钢1780mm带钢热轧卷取温度控制系统进行了分析，卷取温度控制完成的好坏直接关系到整个系统的正常运行及所产带钢的组织性能和力学性能的好坏。通过对系统分析，提出了提高卷取温度控制质量的根本在于提高预设定模型的精度。     

机架间冷却数学模型计算带钢温度分布

为提高带钢终轧温度的控制精度 ,对精轧过程中导致带钢温度变化的热交换过程进行了分析 ,以此作为机架间冷却控制的传热模型和自学习模型的理论依据 ,给出了带钢厂热轧机组机架间冷却在线控制的传热和自学习模型的算法 ,通过程序开发对精轧机组内带钢的温度分布进行了离线模拟 ,终轧温度计算值与实际生产数据符合较好 ,并对所用数学模型的实际计算结果进行了分析     

带钢超快速冷却条件下的换热过程

 分析了轧后加速冷却过程中带钢表面的局部换热机理，认为冷却系统实现超快速冷却的关键在于扩大带钢表面射流冲击换热区的面积。确定了薄带钢实现超快速冷却所需的对流换热系数，并采用有限元分析工具ANSYS模拟得到了超快速冷却条件下不同厚度带钢的温度场。温度场的分布表明薄带钢在超快速冷却过程中具有较好的温度一致性。同时还表明随着带钢厚度增加，超快速冷却条件下厚度方向的温度梯度显著增大，对于带钢内部组织的均匀性将产生不利的影响。带钢厚度范围应是超快速冷却技术实际应用过程中的重要考虑因素。     

带高压水除鳞换热的带钢粗轧过程温度场数值模拟

热带钢在轧制前通常需用高压水去除氧化铁皮。随着高压水对带钢表面冲击强度的增加,除鳞效果明显增强,带钢的温度也显著降低。影响带钢温度变化的因素复杂多变,其中尤以高压水的影响较显著,因此研究带钢在高压水除鳞过程中的温度场分布,对于了解带钢粗轧过程中的温度变化、合理制定后续精轧工艺非常必要。笔者将有限元数值解法与实验结果相结合,研究了高压水冲击强度与带钢换热系数之间的对应关系,得出了换热系数计算模型。将该模型应用于宝山钢铁集团公司2050mm热带钢粗轧机组进行模拟计算。结果表明模拟值与现场实测值吻合良好。     

Development of New Generation Cooling Control System After Rolling in Hot Rolled Strip Based on UFC

 Ultra-fast cooling (UFC) is an advanced technology in hot rolling field. Through this technology, great changes on the run-out table are produced in the strip cooling process. In order to adapt to these changes, a new generation of hot strip cooling control system after rolling was developed based on the UFC basic principle. The system can not only accomplish temperature of UFC delivery side, coiling temperature, cooling rate, etc, and multi-objective accuracy control, but also offer more flexibility and new attractive possibilities in terms of cooling pattern on the run-out table, which could be of prime importance for the production of some difficult steels. In addition, through the time-velocity-distance (TVD) profile prediction combined with speed feed-forward control and coiling temperature feedback control, the coiling temperature control precision can be effectively improved during accelerative rolling in the system. At present, the system has been successfully used in the conventional strip production line and CSP short process production line, and its application effect is perfect.     

Algorithm Design and Application of Laminar Cooling Feedback Control in Hot Strip Mill

 Abstract： Feedback control is one of the most important ways to improve coiling temperature control precision during laminar cooling process. Laminar cooling equipments of a hot strip mill and structure of the control system were introduced. Feedback control algorithm based on PI controller and that based on Smith predictor were designed and tested in a hot strip mill respectively. Practical application shows that the feedback control system based on PI controller plays a limited role in improving coiling temperature control precision. The feedback control system based on Smith predictor runs stable and reliable. When the measured coiling temperature deviates from the target value, it can be adjusted to the required range quickly and steadily by Smith predictor feedback control, which improves the coiling temperature control precision greatly, and qualities of hot rolled strips are improved significantly.     

厚规格热轧带钢高精度卷取温度控制模型

卷取温度是影响带钢组织性能的重要工艺参数.在生产实践中,如何提高厚规格带钢卷取温度的控制精度是一个难点.针对厚规格带钢在层流冷却过程中的工况特点,提出了温度场计算模型和对流换热系数模型的改进方法,并开发了一种全新的基于相似策略的自适应模型,以改善卷取温度前馈控制效果.经现场应用证明,本文提出的方案能有效提高厚规格带钢的卷取温度控制精度,其中厚度大于12 mm的带钢平均命中率可达到94.9%.     

Modelling the Temperature Distribution along the Length of Strip during Hot Rolling Process

Hot strip rolling process includes four main stages, which are reheating process, roughing and finishing process, laminar‐cooling process, and coiling process respectively. Temperature is the most sensitive parameter and has direct effect on the microstructural evolution and further the mechanical properties, and the accurate control of temperature guarantees the quality of products and homogeneity of properties along the strip length. However, for the conventional hot strip rolling process, thermal history along the strip length is very complex, the related temperature variation concerns air cooling, water cooling, heat transmission by roll contact, heat generation by deformation and friction. Based on the actual hot strip mill, the thermal models are established in this paper to simulate the temperature distribution along the whole strip length from the reheating furnace exit to the down coiler. Different interface heat transmission coefficients are selected for the scale breaking and spray water‐cooling process, and a self‐learning algorithm is thus employed to improve the calculation accuracy. This model is characterized as simple and fast, and convenient for on‐line/off‐line prediction of temperature. Finally the simulated results are verified by the on‐line temperature detection at typical points such as roughing exit (RT2), finishing exit (FT7) and coiling position (CT).     

Modeling of Strip Heating Process in Vertical Continuous Annealing Furnace

 The mechanism for heat transfer of radiation is usually adopted to heat strip in vertical continuous annealing furnace. The rate of heat transfer among strip and other objects can be hugely affected by the parameters of strip speed, geometry factors and radiating characteristic of surfaces of strip, radiating tubes and walls of furnace. A model including all parameters is proposed for calculating the heat transfer coefficient, predicting the strip temperature and boundary temperature of strip through analyzing these parameters. The boundary temperature is a important datum and different from average arithmetic value of temperature of strip and temperature in furnace. Also, the model can be used to analyze the relation for temperature of strip and heat transfer coefficient, total heat transfer quantity and heating time. The model is built by using the radiating heat transfer rate, the Newton′s law of cooling, and lumped system analysis. The results of calculation are compared to the data from production line. The comparisons indicate that the model can well predict the heating process. The model is already applied for process control in production line. Also, this research will provide a new method for analyzing the radiation heat transfer.     

基于面向对象技术的热轧卷取温度模型开发

以面向对象的视角审视热轧带钢轧后冷却过程涉及的轧件、辊道、集管、冷却介质与仪表5要素,对轧件在辊道的传热过程、冷却水量和温度的控制过程进行分析、分解并抽象成类。利用面向对象的方法对卷取温度控制(coiling trmperature control,简称CTC)模型的体系结构进行设计,结合模型的触发逻辑进行对象设计,利用C++语言开发面向对象的卷取温度模型。基于有限差分计算方法的模型设定时间满足在线快速计算的要求,模型具有良好的可移植性和可扩展性。现场应用表明,冷却控制系统运行稳定,模型设定准确,卷取温度控制效果良好。     

热轧带钢轧后冷却控制及其智能反馈控制方法

热轧带钢轧后冷却过程中卷取温度的控制精度是保证带钢组织性能、表面质量和板形良好的1个关键因素。温度控制的核心是冷却过程控制模型的建立及其自适应反馈功能。建立了具有非线性结构特征的热轧带钢冷却过程控制的数学模型,并对新模型的智能反馈控制方法进行了研究,增强了控制模型的自适应性。现场实际应用表明：实测卷取温度与目标温度相差...