论文部分内容阅读
连续退火是改善带钢的力学性能的关键过程。但在实际生产过程中,连续退火过程机理复杂,并且对带钢质量的检测有很大的时间滞后,这给提高带钢质量带来了很大的障碍。文章利用正交信号校正提取与带钢质量密切相关的过程信息,选用偏最小二乘方法构建更为精准的带钢质量预测模型,具有良好的预测性能,可以及时准确地在线估计带钢质量。通过对现场实际数据的仿真分析证明了所提出方法的可行性和有效性。
Continuous annealing is the key process to improve the mechanical properties of the strip. However, in the actual production process, the mechanism of continuous annealing process is complex, and there is a great time lag in the quality inspection of the steel strip, which brings great obstacles to improving the quality of the steel strip. In this paper, orthogonal signal calibration is used to extract the process information closely related to strip quality. Partial least squares method is used to build a more accurate strip quality prediction model with good predictive performance. The quality of strip steel can be estimated timely and accurately. The feasibility and validity of the proposed method are proved through the simulation analysis of the actual field data.