【摘要】 针对精炼炉(LF)钢水脱硫过程的非线性、强动态和多工况问题,提出了基于局部模型迁移方法的钢水硫含量终点预报模型.首先建立简化的机理模型捕捉主要的过程特性,然后采用模型迁移方法补偿机理简化和工况变化引起的预报误差.针对传统模型迁移方法不能处理过程非线性问题,提出局部模型迁移方法,在输入空间内建立多个局部迁移模型,通过融合算法组合成全局迁移模型来自适应校正机理模型的偏差.由于充分利用了机理模型的优势,相比现有的智能预报模型,该方法具有良好的预报精度.最后,通过现场实际数据验证了所提方法的有效性.更多还原

【Abstract】 Because of the modeling problems of the ladle furnace( LF) desulfurization process that are nonlinear,intensive dynamic and characterized of multiple conditions,end point sulphur content prediction model w as proposed based on local model migration algorithm,w here a simplified principle model w as first established to capture the main process behavior and fine corrected by local model migration method to compensate the remain prediction error caused by mechanism simplification process and condition changes. A new local model migration algorithm w as developed to automatically rectify the process nonlinearity deviation. The new method w orks by integrating several local migration models that are established in several local regions of the input space. The presented predictor show s better performance w ith respect to existing intelligent predictors due to the full exploitation of first principles,w hich is validated by the practical data.更多还原