The potential of utilizing an artificial neural network (ANN) model approach to simulate and predict hydrogen yield in a batch model using Clostridium saccharoperbutylacetonicum N1-4 (ATCC 13564) was investigated. A unique architecture has been introduced in this research to mimic the inter-relationship between three input parameters: initial substrate, initial medium pH, and reaction temperature (37°C, 6.0±0.2, 10) to predict hydrogen yield. Sixty data records from the experiment were utilized to develop the ANN model. The results showed that the proposed ANN model provided a significant level of accuracy for prediction with a maximum error of 10%. Furthermore, a comparative analysis with the traditional Box-Wilson Design (BWD) approach proved that the ANN model output significantly outperformed the BWD. The ANN model overcomes the limitation of the BWD approach concerning the number of records, which considers merely a limited length of stochastic pattern for hydrogen yield (15 records).

Login to Download PDF

Please login with your Paper ID and password to access the full PDF.

🔑 Login to Download