Predictions for start-up processes of reactive distillation column via artificial neural network

The time consumed in starting up the unit with appropriate holdups can form an important part of the total distillation time, particularly for reactive distillation systems with large holdups. Also, the products formed during the start-up time are off specification, and are not easily recycled as for traditional distillation, but must be carefully disposed of, which can be very costly. A back-propagation algorithm artificial neural network model is presented as a tool to assess the start-up process for a given reactive distillation system. All the data required for training and testing the artificial neural network have been generated using the CHEMCAD simulator, version 5.2-0. The values for the learning rate, momentum term, and gain term of the artificial neural network have been taken as 0.01, 0.6, and 1.0, respectively. From the case studied in this work, it can be seen that a good start-up policy can reduce both the energy and time requirements in the start-up phase of reactive distillation processes. Results from predictions show the time consumed in the start-up period has an average error of 2.833%, and a maximum error of 7.600%, for the case studied here. The accuracy of the model will depend upon the data available and the type of model being approximated.