一种基于混合建模技术的MIMO软测量建模方法

针对复合肥产品中几种养分含量需要同时预报的一类多输入/多输出(MIMO)软测量建模问题,提出一种基于混合建模方法的复合肥养分含量MIMO软测量模型。该混合模型首先对几个不能实时测量的关键辅助变量采用基于限定记忆部分最小二乘算法的数据驱动建模方法建立自适应软测量模型,然后采用简化机理模型实时计算三种养分含量。基于实际工业过程数据的仿真结果表明,所建模型运算速度快、预测精度高,可以满足复合肥养分含量在线预报的要求。

A MIMO Soft-sensor Modeling Method Based on Hybrid Modeling Technique

In compound fertilizer production,several quality variables need to be monitored and controlled simultaneously.It is very difficult to measure these variables on-line by existing instruments and sensors.So,soft-sensor technique becomes an indispensable method to implement real-time quality control.A new model of multi-inputs multi-outputs（MIMO） soft-sensor,which was constructed based on hybrid modeling technique,was proposed for these interactional variables.Data-driven modeling method and simplified first principle modeling method were combined in this model.Data-driven modeling method based on limited memory partial least squares（LM-PLS） algorithm was used to build soft-senor models for some secondary variables;then,the simplified first principle model was used to compute three primary variables on-line.Simulation results indicate that the proposed model is precise and efficient,and it is possible to realize on-line quality control for compound fertilizer process.