摘要
针对无缝钢管斜轧穿孔生产中衡量毛管质量好坏的毛管横向和纵向壁厚不均检验滞后和难以建立其机理模型的问题,提出了基于均值子时段MPLS方法的毛管质量预报模型。介绍了均值子时段MPLS方法中过程数据时段分解、均值求取、回归模型建立和模型在线预报等关键内容。将建立的预报模型用于毛管质量预报中,为斜轧穿孔生产的无缝钢管质量提高奠定了良好的基础,并且其维护费用低、实时性好、可靠性及精度高,可以用于毛管质量的在线预报和优化。
Tube hollow was produced by cross piercing, whose shall longitudinal and transversal wall thickness unevenness was often lagged to check. The quality prediction of tube hollow model was proposed based on mean value staged MPLS method to overcome the disadvantage. The staged decomposition of the productive data, the calculation of the mean value in the mean value MPLS method, modeling, on-lined prediction were introduced. The model used in tube hollow quality prediction can improve seamless tubes quality effectively. Its obvious benefits are low maintenance cost, good real time function, high reliability precision, and can be used on-line for the prediction and optimization on quality of tube hollow.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2008年第7期1677-1680,共4页
Journal of System Simulation
基金
国家自然科学基金(60374003)
辽宁省自然科学基金(20062024)
关键词
无缝钢管
斜轧穿孔
毛管质量预报
均值子时段MPLS
seamless tubes
cross piercing
quality prediction of tube hollow
mean value staged MPLS
