中文摘要：

无缝钢管穿孔生产是利用穿孔机将实心管坯斜轧穿孔成空心毛管的生产过程。斜轧穿孔中毛管质量与许多工艺参数,如辊型、送进角、顶头前伸量及温度,以及设备性能参数如穿孔机刚度、加工精度和顶杆振动等有关。由于其具有复杂的金属流动状态,传统的轧制理论难以解决其质量预报问题。本文通过对斜轧穿孔过程的分析,提出了步进子时段MICR（multiway independent component regression）算法,利用现场采集的多根毛管生产数据建立了预测毛管质量的数学模型。经仿真证明该模型具有较高的可靠性和精度,可以用于毛管质量的在线预报和优化。

英文摘要：

Cross piercing manufacture of seamless tubes is the process that pierces solid pierced billet into tube hollow. The quality of tube hollow in cross piercing process relates to complicated factors and technical parameters, such as roller shape, feed angle, plug advance and temperature, and the piercing mill properties including stiffness and manufacture precision of the mill, vibration of the plug and driving system. It is difficult to solve quality prediction problem using traditional rolling theory For cross piercing process, a step-by-step staged MICR scheme is developed, the mathematic model for quality prediction of tube hollow is established using the on-site production data. The simulation shows that the method has preferable accuracy and reliability; and can be used for on-line prediction and optimization of tube hollow quality.