Modeling the Direct Synthesis of Dimethyl Ether using Artificial Neural Networks

Artificial neural networks (ANNs) are designed and implemented to model the direct synthesis of dimethyl ether (DME) from syngas over a commercial catalyst system. The predictive power ANNs is assessed by comparison with predictions lumped parameterized fit same data used for ANN training. training converges much faster than parameter estimation model, show higher degree accuracy under all conditions. Furthermore, simulations that also accurate even at some conditions beyond validity range.