1. Key Lab 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, Qinhuangdao 066004, Hebei, China
Abstract:In the light of the problems existed in flatness pattern recognition models which had low generation ability and slow training speed, a new model was proposed. The model took linear, quadratic, cubic and biquadrate Legendre orthogonal polynomials as flatness basic patterns and was constituted by support vector regression (SVR). In order to improve the precision of the model, gravitational search algorithm (GSA) was brought in. So the GSA-SVR model was completed. The simulation experiments indicate that the model’s (GSA-SVR) recognition result is more precise than PSO-BP model, and it has strong generalization ability and fast training speed. The result of GSA-SVR model can provide reliable basis for the formulation of flatness control strategy.
牛培峰,,李鹏飞,,李国强,马云飞,. 基于万有引力优化的支持向量机模型在板形识别中的应用[J]. 钢铁, 2012, 47(12): 45-49.
NIU Pei-feng1,2,LI Peng-fei1,2,LI Guo-qiang1,2,MA Yun-fei1,2. Application of GSA-SVR Model in Flatness Pattern Recognition. Iron and Steel, 2012, 47(12): 45-49.