Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neural Networks for Chemical Engineers
Neural Networks for Chemical Engineers
Information Theory, Inference & Learning Algorithms
Information Theory, Inference & Learning Algorithms
Mining students' behavior in web-based learning programs
Expert Systems with Applications: An International Journal
Mining learners' behavior in accessing web-based interface
Edutainment'07 Proceedings of the 2nd international conference on Technologies for e-learning and digital entertainment
| Hi-index | 0.00 |
Artificial neural network (ANN) approach was used to design an optimum Ni/Al"2O"3 catalyst for the production of hydrogen by the catalytic reforming of crude ethanol based on determining the inter-relationships between catalyst-preparation methods, nickel loading, catalyst characteristics and catalyst performance. ANN could predict hydrogen production performance of various Ni/Al"2O"3 catalysts of various elemental compositions and methods of preparation in the production of hydrogen by the catalytic reforming of crude ethanol in terms of crude-ethanol conversion, hydrogen selectivity and hydrogen yield. Specifically on catalyst design, ANN was used to determine the optimum catalyst conditions for obtaining maximum hydrogen production performance of a Ni/Al"2O"3 catalyst for the production of hydrogen by the catalytic reforming of crude ethanol. The optimal hydrogen yield was 4.4mol%, and the associated crude-ethanol conversion and H"2 selectivity for the optimal hydrogen yield were 79.6 and 91.4mol%, respectively. The optimal catalyst was the one prepared by the coprecipitation method with the optimal nickel loading of 12.4wt% and an optimal aluminum composition of 42.5wt%.