Application Of Artificial Neural Network In Modeling Anisole Distillation Column

The background of this paper is using chemical exchange reaction and distillation to separate boron isotopes. In the process of separation of boron isotopes, anisole as the complexing agent need to be recycled and high purity of the complexing agent during the process is required, so the purity of the complexing agent is very important to the start working and running. In this paper, purifying experiment on anisole was carried out .Established mathematical model of anisole rectifying tower and made the process design according to the separating requirement.In this thesis, artificial neural network( ANN)models are presented to simulate distillation. More data are produced by software of ASPEN to make up the shortage of experimental data when setting up the ANN models. By comparing the different predictive results of different ANNs to the training set and testing set, the transfer function and nodes of hidden layer are ascertained, thus the optimal structure of ANN is established and the optimal structure is 6×11×2. The comparison of simulated and experiment result is that the average absolute relative error of the composition of top product is 0.3283%. It shows that the rectifying process can be achieved by using ANN models with high accuracy. Artificial neural network models are presented to simulate distillation with no consideration of the specific process and mechanism in the columns and the results show that good effects can be achieved by using ANN models with high simplicity.