【作者】 陈晓波； 赵忠雷； 秦树凯；

【Author】 CHEN Xiao-bo ZHAO Zhong-lei QIN Shu-kai College of Information Science and Engineering,Northeastern University,Shenyang 110004,China.

【机构】 东北大学 信息科学与工程学院；

【摘要】 针对机理建模的复杂性和辨识建模实验数据获得的困难性,提出基于 GA 和 BP 网络相结合的方法建立的钢坯表面温度预报模型．使用 GA 来初始化 BP 网络,避免了 BP 算法易陷入局部最优的缺点．在模型建立的基础上．再利用 BP 算法进行在线补偿,从而使模型更加精确．仿真结果表明钢温预报模型建立简单、精度高、适应性强．更多还原

【Abstract】 Considering the complex nature of mathematic model with physical mechanaism means and difficulties to get experimental data,a billet surface temperature prediction model is presented based on GA and BP neural network. The BP network initialization on the basis of GA can avoid the shortcomings of BP algorithm that easy to fall into a local optimal.Based on this model,online compensation is used to make the model more accurate.Simulation results show that this prediction model is simple and has high accuracy and adaptability.更多还原