Data-based flatness prediction and optimization in tandem cold rolling
- PDF / 3,777,519 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 251 Views
(0123456789().,-volV)(0123456789().,-volV)
ORIGINAL PAPER
Data-based flatness prediction and optimization in tandem cold rolling Jie Sun1
•
Peng-fei Shan1 • Zhen Wei1 • Yao-hui Hu1 • Qing-long Wang2 • Wen Peng1 • Dian-hua Zhang1
Received: 9 March 2020 / Revised: 12 August 2020 / Accepted: 18 August 2020 China Iron and Steel Research Institute Group 2020
Abstract In cold rolling process, the flatness actuator efficiency is the basis of the flatness control system. The precision of flatness is determined by the setpoints of flatness actuators. In the presence of modeling uncertainties and unmodeled nonlinearities in rolling process, it is difficult to obtain efficiency factors and setpoints of flatness actuators accurately. Based on the production data, a method to obtain the flatness actuator efficiency by using partial least square (PLS) combined with orthogonal signal correction (OSC) was adopted. Compared with the experiential method and principal component analysis method, the OSC–PLS method shows superior performance in obtaining the flatness actuator efficiency factors at the last stand. Furthermore, kernel partial least square combined with artificial neural network (KPLS–ANN) was proposed to predict the flatness values and optimize the setpoints of flatness actuators. Compared with KPLS or ANN, KPLS–ANN shows the best predictive ability. The root mean square error, mean absolute error and mean absolute percentage error are 0.51 IU, 0.34 IU and 0.09, respectively. After the setpoints of flatness actuators are optimized, KPLS–ANN shows better optimization ability. The result in an average flatness standard deviation is 2.22 IU, while the unoptimized value is 4.10 IU. Keywords Cold rolling Flatness actuator efficiency Data-driven prediction Partial least square Flatness control optimization
1 Introduction Flatness is an important geometrical feature of cold-rolled strips. Many severe defects and quality problems can appear [1, 2]. Strips with poor flatness are more likely to be broken with quality issues during later manufacturing phases. In the flatness control system, the flatness effect of force applied by any actuators can be quantified to be the efficiency factors of flatness actuators. Based on the efficiency factors of flatness actuators, the adjustment values can be calculated, and the flatness deviation can be eliminated. Therefore, the flatness actuator efficiency is the basis of the flatness closed-loop control. There are two methods used to & Jie Sun [email protected] 1
State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, Liaoning, China
2
Department of Mechanical Engineering, North China Electric Power University, Baoding 071003, Hebei, China
obtain the flatness actuator efficiency at present. One is from rolling experiments, and the other one is by finite element simulation [3]. It should be emphasized that the rolling experiments have suffered from some limits, since they can only test a few rolling conditions and the cost is high. The
Data Loading...
