Hybrid Modelling and Optimisation in CBD

In Mujtaba and Hussain (1998), the detailed dynamic model was assumed to be the exact representation of the process while the difference in predictions of the process behaviour using a simple model and the detailed model was assumed to be the dynamic process-model mismatches. Theses dynamic mismatches were modelled using neural network techniques and were coupled with the simple model 

In Greaves et al. (2001), a hybrid model for an actual pilot plant batch distillation column is developed. However, taking advantage of some of the inherent properties of batch distillation processes a simpler version (new algorithm) of the general optimisation framework is developed to find optimal reflux ratio policies which minimises the batch time for a given separation task. 

Discrete reflux ratio used in most pilot plant batch distillation columns, including those used in industrial R D Departments (Jenkins, 2000 Greaves, 2003), does not allow a direct implementation of the optimum reflux ratio (treated as a continuous variable) obtained using a model based technique (as presented in earlier chapters of this book). In Greaves et al. (2001), a relationship between the continuous and the discrete reflux ratio is developed. This allows easy communication between the model and the process and comparison on a common basis. 

---