Research on Prediction of Outlet Moisture of Thin Plate Dryer Based on Model Merging
In this paper,outlet moisture of thin plate dryer is taken as the research object.Three kinds of machine learn-ing models are used to model,analyze and predict the outlet moisture of the tobacco drying machine.The weighted average model merging strategy is adopted,the model mean square error of the verification set is used as the weight calculation ba-sis for model merging.The test results show that compared with the three separate machine learning models,the fusion model has certain improvement in each goodness of fit index.Among them,the mean square error of XGBoost model im-proved the most,reducing by 30.26%.The prediction model makes full use of the advantages of the three models.
NETL
NSTL
万方数据
