1. Key Laboratory of Industrial Computer Control Engineering of Hebei Province， Yanshan University， Qinhuangdao 066004， Hebei， China 2. National Engineering Research Center for Equipment and Technology of Cold Strip Rolling， Yanshan University， Qinhuangdao 066004， Hebei， China 3. Grid Plate Department of Xinxing Ductile Iron Pipes Co.，Ltd.， Handan 056000， Hebei， China
Abstract：The working rolls in cold rolling temper mill are in direct contact with the strips. Therefore，the surface roughness of working rolls will affect the flatness and surface quality of strip. So it’s necessary to predict the attenuation of working roll’s surface roughness accurately by analyzing roll wear mechanisms. Firstly，the factors which influence the working roll’s surface roughness are analyzed by the means of grey relational analysis. A system for evaluating the working roll’s surface roughness is determined. Then optimized OS-LSSVR model is used for on-line prediction of the surface roughness. The new key nodes are added recursively by using prediction error criterion，and the redundant key nodes are deleted following FLOO. Moreover，the gradient descent method is adopted to optimize the two hyper-parameters online. The results of simulation show that the average absolute error of the model is 0.014 9，much smaller than other models. In addition，the model has on-line adaptive ability，and is able to evolve over time.
魏立新，高江曼，麻 诚，车海军，杨景明，. 冷轧平整机工作辊表面粗糙度衰减模型[J]. 钢铁, 2015, 50(6): 51-56.
WEI Li-xin，，GAO Jiang-man，，MA Cheng，CHE Hai-jun，，YANG Jing-ming，. Attenuation model for working roll’s surface roughness in cold rolling temper mill. Iron and Steel, 2015, 50(6): 51-56.
KHALIL Hossam, Mohammad, El-BARDINI Mohammad.Implementation of speed controller for rotary hydraulic motor based on LS-SVM[J].Expert Systems with Applications, 2011, 38(11):14249-14256
[6]
KHALIL Hossam, Mohammad, El-BARDINI Mohammad.Implementation of speed controller for rotary hydraulic motor based on LS-SVM[J].Expert Systems with Applications, 2011, 38(11):14249-14256
[7]
LIU Yi, HU Naiping, WANG Haiqing, et al.Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size[J].Industrial and Engineering Chemistry Research, 2009, 48(12):5731-5741
[7]
LIU Yi, HU Naiping, WANG Haiqing, et al.Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size[J].Industrial and Engineering Chemistry Research, 2009, 48(12):5731-5741
[8]
TANG Hesheng, XUE Song-tao, CHEN Rong et al.Online weighted LS-SVM for hysteretic structural system identification[J].Engineering Structure, 2006, 28(12):1728-1735
[8]
TANG Hesheng, XUE Song-tao, CHEN Rong et al.Online weighted LS-SVM for hysteretic structural system identification[J].Engineering Structure, 2006, 28(12):1728-1735
DENG S, YEH Tsung-Han.Applying least squares support vector machines to the airframe wing-box structural design cost estimation[J].Expert Systems with Applications, 2010, 37(12):8417-8423
[13]
DENG S, YEH Tsung-Han.Applying least squares support vector machines to the airframe wing-box structural design cost estimation[J].Expert Systems with Applications, 2010, 37(12):8417-8423
CAWLEY G, TALBOT N.Fast exact leave-one-out cross-validation of sparse least-squares support vector maehines[J].Neural Networks, 2004, 17(10):1467-1475
[16]
CAWLEY G, TALBOT N.Fast exact leave-one-out cross-validation of sparse least-squares support vector maehines[J].Neural Networks, 2004, 17(10):1467-1475
[17]
SUYKENS J A K, BRABANTER J D, LUKAS L, et al.Weighted least squares support vector machines: Robustness and sparse approximation[J].Neurocomputing, 2002, 48(1-4):85-105
[17]
SUYKENS J A K, BRABANTER J D, LUKAS L, et al.Weighted least squares support vector machines: Robustness and sparse approximation[J].Neurocomputing, 2002, 48(1-4):85-105
ZHAO Ying, KWOH Chee Keong.Fast leave-one-out evaluation and improvement on inference for LS-SVMs[J].17th International Conference on Pattern Recognition. Cambridge, UK: IEEEComputer Society, 2004, 4(08): 494-497
[19]
ZHAO Ying, KWOH Chee Keong.Fast leave-one-out evaluation and improvement on inference for LS-SVMs[J].17th International Conference on Pattern Recognition. Cambridge, UK: IEEEComputer Society, 2004, 4(08): 494-497
2015, Vol. 50 
