二辊矫直过程导板间距工艺参数分析

针对某钢厂棒材矫直过程中二辊矫直机导板间距没有明确规定并且导板磨损严重的情况,用大型非线性有限元软件建立了棒材二辊矫直过程的三维弹塑性有限元模型。基于此模型研究了不同导板间距下矫直力、导板支撑力、塑性变形程度、矫后残余应力及最大挠度的变化规律,综合分析提出了合理的导板间距取值范围。新的导板间距比之前实际应用的值有所增大,应用后导板更换频率降低。

Experimental study of low-temperature electrical radiant floor heating system

To evaluate the thermal performance of a low-temperature electrical radiant floor heating system,an experimental facility equipped with a constant temperature chamber and different specimen floors is designed and built.The heating cable is installed in the floor slab with a unit-rated power of 30 W/m.Twenty-four different schemes are worked out and tested,which include three kinds of composite floor structures and eight kinds of cable distances.The cable distances are 30,40,50,60,80,100,130,150 mm.The main affective factors of the thermal performance and their influencing regularity are discussed.The experimental results show that the system has good stability and reliability,and the ratio of the radiation heat-transfer rate to the gross heat-transfer rate is greater than 50%.When the floor structure and the cable distance are fixed,the gross heat-transfer rate of the upper floor surface has a maximum value at an optimal cable distance.Under the experimental conditions in this paper,the optimal cable distance is 50 mm.

中小棒材两辊矫直技术探索与实践

本文对中小棒材两辊矫直机发生的入口导板容易磨损、材料矫不直问题进行了技术探索和多次实验,从实践中分析原材料弯曲度、材料屈服强度、导板间距、矫直速度对导板磨损的影响,解决了入口导板容易磨损的问题,使生产效率大幅提升。通过实验,发现工作辊距、矫直速度、原材料弯曲度、加工硬化以、工作辊斜角对材料矫直效果的影响特征,解决了材料矫不直问题,使矫直质量稳步提升。

基于深度神经网络的斜轧穿孔机调整参数预测

针对无缝钢管二辊斜轧穿孔生产工艺中轧机调整参数对钢管质量影响较大,且传统机理公式计算的设定值精度不高的问题,提出了基于深度神经网络的斜轧穿孔机调整参数预测模型。首先,综合分析了传统的调整参数的数学模型,并在此基础上确定了调整参数的主要影响因素。依据现场收集的数据集,训练了二辊斜轧穿孔时轧机参数的深度神经网络预测模型。在训练深度神经网络时,运用小批量梯度下降法和Adam算法相结合的方法进行了梯度估计修正,优化了训练速度。仿真结果表明:经深度神经网络模型预测的轧机调整参数与实测数据比较,预测模型的R-squared值控制在0.98左右,调整参数的相对误差均可控制在5%以内。相比于传统数学模型,该预测模型具有更高的预测精度,能够实现轧机调整参数高精度预测并用于指导生产。