普碳热轧带钢力学性能回归方程及其应用

确定了厚度为2.75mm普碳热轧带钢σ_b与碳、硅、锰含量的定量关系,得到3σ_b与碳、硅、锰含量的定量关系,得到了σ_b与碳、硅、锰含量呈显著的线性回归方程。     

热轧带钢层流冷却过程中温度与相变耦合预测模型

建立了温度与相变耦合有限元模型,对带钢轧后冷却过程中带钢厚度和宽度方向的温度场进行了模拟计算.建模过程中,考虑带钢的各金相组织的密度、导热系数、比热容等物性参数为温度的函数,取各相的线性平均值用于计算.根据连续等温转变实验曲线,采用Avrami方程和Scheil可加性法则计算带钢相变潜热,实现温度和相变耦合求解.计算结果表明,带钢经过层流冷却后,沿厚度方向存在着一定的温差,带钢温度沿宽度方向分布不均匀,和现场实测结果吻合.     

热轧带钢温度场计算模型及其计算偏差分析

热轧带钢温度场可根据热传导偏微分方程与边界条件和初始条件计算,也可采用忽略厚度方向温度梯度的集总参数法计算.在假设前者计算结果准确的基础上,将集总参数法所获得的温度计算模型与前者进行偏差计算,得到了相对偏差计算公式并采用Matlab求得不等式的解,由此得到了集总参数法的应用范围:当相对偏差在5%以内时,带钢心部、1/4和表面的毕渥数范围分别为0~0.100 8,0~0.136 1和0~0.959 3;相对偏差在10%以内时,带钢心部、1/4和表面的毕渥数范围分别为0~0.203 3,0~0.278 2和0~1.497 4.     

Ti对高强耐候钢力学性能的影响

通过光学显微镜、透射电镜(TEM)以及力学性能测试等手段分析了薄板坯连铸连轧(TSCR)工艺生产Ti微合金化高强耐候钢的成分及工艺对显微组织和力学性能的影响.研究结果表明:钢中加入Ti,屈服强度有明显的提高;钛质量分数为0.05%～0.08%时,高强耐候钢的晶粒尺寸随着钛含量的增加基本不变;高强耐候钢强度的提高主要取决于钢中有效钛的含量,有效钛不仅与钛的含量有关,而且还与S, N的含量有关;在有效钛含量一定的条件下,析出强化的大小主要取决于轧后的卷取温度.     

无取向硅钢热轧工作辊磨损预报模型

根据1700mm热连轧机采集的现场数据分析了硅钢轧制工作辊磨损的规律和其磨损轮廓曲线.采用中部磨损和边部磨损分别建立磨损计算函数的方式,建立了无取向硅钢轧制的工作辊磨损预报模型.采用遗传算法优化计算了模型参数.现场实测数据验证表明,模型预报精度可靠实用,可用于指导生产实践.     

基于卷积神经网络的热轧带钢力学性能预报

为解决热轧带钢力学性能预报精度的问题,本文提出了一种将一维数值型数据转换为二维图像型数据的建模方法,基于LeNet-5和GoogLeNet卷积神经网络,构建了一种新型的热轧带钢力学性能预报模型,并利用实际生产数据对模型的适用性进行了测试。结果表明,所建模型的抗拉强度预报误差为2.49%,均方根误差为19.15 MPa,预测精度高于BP神经网络和单独的LeNet-5和GoogleNet卷积神经网络模型,所建模型的有效性和准确性均得到了验证。     

Effect of hot stamping parameters on the mechanical properties and microstructure of cold-rolled 22MnB5 steel strips

Thermomechanical experiments were carried out to reproduce the hot stamping process and to investigate the effects of process parameters on the microstructure and mechanical properties of stamped parts. The process parameters, such as austenitizing temperature, soaking time, initial deformation temperature and cooling rate, are studied. The resulting microstructures of specimens were observed and analyzed. To evaluate the mechanical properties of specimens, tensile and hardness tests were also performed at room temperature. The optimum parameters to achieve the highest tensile strength and the desired microstructure were acquired by comparing and analyzing the results. It is indicated that hot deformation changes the transformation characteristics of 22MnB5 steel. Austenite deformation promotes the austenite-to-ferrite transformation and elevates the critical cooling rate to induce a fully martensitic transformation.     

热镀锌钢卷力学性能GBDT预报模型

针对热镀锌钢卷力学性能预报建模条件属性选取难、预报精度不足的问题,研究了热镀锌钢卷力学性能梯度提升树(gradient boosting decision tree,GBDT)预报模型。利用互信息差算法综合评估工艺参数、化学成分和钢卷尺寸参数等条件属性的相对重要性以及属性之间冗余性,进行模型条件属性筛选;采用同分布原理进行样本划分,结合网格搜索法和交叉验证法优化模型参数,建立力学性能GBDT预报模型。将GBDT模型预报结果与随机森林(random forest,RF)、AdaBoost算法和BP神经网络的预报结果进行比较,比较表明GBDT模型优于其他模型,90%的数据样本预测的绝对误差小于14.24 MPa,94.6%的数据样本相对误差在6%范围内,具有更高的预测精度。     

运用BP人工神经网络方法构建碳钢区域土壤腐蚀预测模型

通过测量大庆地区区域土壤的理化性质以及碳钢的短期腐蚀数据,分析土壤传质过程的逻辑关系,构建了碳钢短期土壤腐蚀预测模型. 通过用该模型在BP人工神经网络中进行学习、训练及模拟,并与现场碳钢埋片腐蚀实验结果对比,进一步验证了腐蚀模型的合理性. 结果表明:含水量、空气容量、pH、Cl~-含量、SO_4~(2-)含量和可溶盐总量六种土壤环境参数为影响区域土壤中碳钢腐蚀的主要因素;运用基于Matlab平台的人工神经网络,通过不断地积累土壤腐蚀信息,多次训练后可以建立起稳定性好、泛化能力强的土壤腐蚀预测模型,能较好地预测了大庆地区碳钢在土壤中的腐蚀速率.     

Artificial neural network prediction of mechanical properties of hot rolled low carbon steel strip

Conventionally, direct tensile tests are employed to measure mechanical properties of industrially pro- duced products. In mass production, the cost of sampling and labor is high, which leads to an increase of total pro- duction cost and a decrease of production efficiency. The main purpose of this paper is to develop an intelligent pro- gram based on artificial neural network （ANN） to predict the mechanical properties of a commercial grade hot rolled low carbon steel strip, SPHC. A neural network model was developed by using 7 x 5 x 1 back-propagation （BP） neural network structure to determine the multiple relationships among chemical composition, product pro- cess and mechanical properties. Industrial on-line application of the model indicated that prediction results were in good agreement with measured values. It showed that 99.2 % of the products＇ tensile strength was accurately pre- dicted within an error margin of ~ 10 %, compared to measured values. Based on the model, the effects of chemical composition and hot rolling process on mechanical properties were derived and the relative importance of each in- put parameter was evaluated by sensitivity analysis. All the results demonstrate that the developed ANN models are capable of accurate predictions under real-time industrial conditions. The developed model can be used to sub- stitute mechanical property measurement and therefore reduce cost of production. It can also be used to control and optimize mechanical properties of the investigated steel.     

焊接热影响区性能的神经网络预测模型

针对四类２４种钢材，将其化学成分和ｔ８／５性能的数据作为样本，构造学习空间，建立了一种新的预测方法ＢＰ网络预测模型，并讨论了网络参数对网络收敛速度及误差函数的影响     

Mechanical properties and characteristics of nanometer-sized precipitates in hot-rolled low-carbon ferritic steel

The microstructures and properties of hot-rolled low-carbon ferritic steel have been investigated by optical microscopy, field-emission scanning electron microscopy, transmission electron microscopy, and tensile tests after isothermal transformation from 600℃ to 700℃ for 60 min. It is found that the strength of the steel decreases with the increment of isothermal temperature, whereas the hole expansion ratio and the fraction of high-angle grain boundaries increase. A large amount of nanometer-sized carbides were homogeneously distributed throughout the material, and fine (Ti, Mo)C precipitates have a significant precipitation strengthening effect on the ferrite phase because of their high density. The nanometer-sized carbides have a lattice parameter of 0.411–0.431 nm. After isothermal transformation at 650℃ for 60 min, the ferrite phase can be strengthened above 300 MPa by precipitation strengthening according to the Ashby-Orowan mechanism.     

高铝TRIP钢的高温力学性能

利用Gleeble3500试验机研究汽车用C-Mn-Al系TRIP钢的高温力学性能,测定了零塑性温度和零强度温度,应用差示扫描量热法测定其相变区间,采用扫描电镜和光学显微镜分析了不同拉伸温度对应的断口宏观形貌及断口附近组织组成.该钢种零塑性温度和零强度温度分别为1425℃和1430℃,第Ⅰ脆性区间为1400℃~熔点,第Ⅲ脆性区间为800~925℃.第Ⅲ脆性区脆化的原因是α铁素体从γ晶界析出,试样从975℃冷却至700℃过程中,随着α铁素体析出比例的增大,断面收缩率先减小后增大.基体α铁素体比例为8.1%时(850℃),断面收缩率降至28.9%;而拉伸温度在800℃以下时,基体α铁素体比例超过16.7%,断面收缩率回升至38.5%以上.该钢种在1275.6℃时开始析出少量粗大的AlN颗粒,但对钢的热塑性没有影响.     

基于GA-BP神经网络与敏感性分析的带钢厚度预测

为提高带钢厚度预测精度,构建了融合GA-BP神经网络和敏感性分析的T-GA-BP预测模型。首先通过循环迭代方式确定较优的BP神经网络隐含层的层数与节点数,再采用遗传算法对BP网络的权阈值进行优化。在此基础上,利用Tchaban算法进行敏感性分析,研究输入层中各工艺参数对带钢厚度的影响程度,筛选出重要参数作为新的输入样本来训练T-GA-BP神经网络模型,以降低网络复杂度。采用实际生产数据进行测试,结果表明,T-GA-BP模型的带钢厚度预测精度要高于BP、GA-BP、RBF、Elman神经网络等其他优化模型。同时,工艺参数敏感性分析结果可为轧制工艺调控方案的制定提供参考。     

Influence of oxide scales on the corrosion behaviors of B510L hot-rolled steel strips

The influence of oxide scales on the corrosion behaviors of B510L hot-rolled steel strips was investigated in this study. Focused ion beams and scanning electron microscopy were used to observe the morphologies of oxide scales on the surface and cross sections of the hot-rolled steel. Raman spectroscopy and X-ray diffraction were used for the phase analysis of the oxide scales and corrosion products. The corrosion potential and impedance were measured by anodic polarization and electrochemical impedance spectroscopy. According to the results, oxide scales on the hot-rolled strips mainly comprise iron and iron oxides. The correlation between mass gain and test time follows a power exponential rule in the damp-heat test. The corrosion products are found to be mainly composed of γ-FeOOH, Fe₃O₄, α-FeOOH, and γ-Fe₂O₃. The contents of the corrosion products are different on the surfaces of the steels with and without oxide scales. The steel with oxide scales is found to show a higher corrosion resistance and lower corrosion rate.