Optimization and Predictive Modeling of Variable Temperature Drying Process on the Basis of Glass Transition Maize
In order to study the drying effect of variable temperature drying process based on glass transition on maize,the optimal parameters of variable temperature drying process were explored under different initial drying temperatures,precipitation amplitudes,and heating amplitudes,and a mathematical model was established to compare with the prediction model established by neural networks.The results showed that the optimal process parameter combination based on crack rate as the response index was 46.11 ℃,4.99％,and 9.63 ℃,with a crack rate of 12.02％.Using Particle swarm optimization-Back propagation(PSO-BP)neural network to construct a prediction model for maize temperature dependent drying crack rate with 3 inputs and 1 output,the network topology is 3-9-1,and the R2 of the model is 0.9834.Compared with the quadratic regression model fitted by response surface methodology(RSM)(R2=0.9248),the prediction accuracy of the model constructed by PSO-BP neural network is better than that of RSM.Therefore,the PSO-BP model has higher modeling efficiency than RSM,and can accurately predict the crack rate of maize after drying.It provides a better solution and theoretical reference for the intelligent drying process of maize at variable temperature and the quality after drying.
maizevariable temperature dryingglass transitionprocess optimizationpredictive modeling
NETL
NSTL
万方数据
