Reducing wear on a side dam can prolong the casting operation life of a twin-roll strip casting process,thus reducing production cost and improving casting stability.To lengthen the service life of the side dam,it is ...Reducing wear on a side dam can prolong the casting operation life of a twin-roll strip casting process,thus reducing production cost and improving casting stability.To lengthen the service life of the side dam,it is necessary to understand the wear performance of the side dam material.To investigate the wear behavior mechanism of the side dam,in this study,the UMT-2 friction and wear tester was used to determine the relationship between the wear rate of the side-dam material and various parameters.Based on the roughness of the contact area between the side dam and the end of the casting rolls as well as on the amount of deformation of the side dam,which was derived using a thermal-deformation simulation model,the reasons for the uneven wear of the side dam were obtained.展开更多
文摘Reducing wear on a side dam can prolong the casting operation life of a twin-roll strip casting process,thus reducing production cost and improving casting stability.To lengthen the service life of the side dam,it is necessary to understand the wear performance of the side dam material.To investigate the wear behavior mechanism of the side dam,in this study,the UMT-2 friction and wear tester was used to determine the relationship between the wear rate of the side-dam material and various parameters.Based on the roughness of the contact area between the side dam and the end of the casting rolls as well as on the amount of deformation of the side dam,which was derived using a thermal-deformation simulation model,the reasons for the uneven wear of the side dam were obtained.
文摘随着电子信息技术的快速发展,极薄带综合性能面临更高要求,尤其是不锈钢极薄带的表面形貌控制成为关键技术难点。针对这一问题,基于12辊精密极薄带轧机,采用磨削、喷砂和抛光3种典型表面处理的轧辊,对厚度为0.08 mm的304不锈钢极薄带开展单道次轧制试验,构建了适用于极薄带的表面粗糙度转印机理模型(roughness transfer mechanism model,RTM)。通过遗传算法对机理模型中的关键参数进行优化,系统揭示了压下率、张力、轧辊粗糙度以及原始带材粗糙度对轧制过程中表面粗糙度的影响规律。进一步将机理模型与机器学习方法深度融合,提出轧制转印机理约束的表面粗糙度预测模型,通过提取机理模型预测值与实际值的偏差作为机器学习输入,利用其非线性拟合能力捕捉传统机理模型未能解释的复杂非线性特征,最终通过偏差修正实现表面粗糙度的精准预测。试验结果表明,该融合模型充分发挥了2类模型优势,以算数平均粗糙度Ra为例,最优模型的预测准确率达到95.08%,相关系数达到0.9347,并最终在工业现场采集数据进行验证,预测精度依旧可以保持在90%以上。该模型兼具机器学习的高效预测性能与轧制转印机理的物理可解释性,为极薄带表面质量控制提供了新的方向,对深入探究表面粗糙度形成机理与极薄带的工艺参数优化具有重要工程意义。
