Neural network prediction of thermophilic (65 degrees C) sulfidogenic fluidized-red reactor performance for the treatment of metal-containing wastewater

Sahinkaya E., Ozkaya B., Kaksonen A. H., Puhakka J. A.

BIOTECHNOLOGY AND BIOENGINEERING, vol.97, no.4, pp.780-787, 2007 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 97 Issue: 4
  • Publication Date: 2007
  • Doi Number: 10.1002/bit.21282
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.780-787
  • Middle East Technical University Affiliated: No


The performance of a fluidized-bed reactor (FBR) based sulfate reducing bioprocess was predicted using artificial neural network (ANN). The FBR was operated at high (65 degrees C) temperature and it was fed with iron (40-90 mg/ L) and sulfate (1,000-1,500 mg/L) containing acidic (pH = 3.5-6) synthetic wastewater. Ethanol was supplemented as carbon and electron source for sulfate reducing bacteria (SRB). The wastewater pH of 4.3-4.4 was neutralized by the alkalinity produced in acetate oxidation and the average effluent pH was 7.8 +/- 0.8. The oxidation of acetate is the rate-limiting step in the sulfidogenic ethanol oxidation by thermophilic SRB, which resulted in acetate accumulation. Sulfate reduction and acetate oxidation rates showed variation depending on the operational conditions with the maximum rates of 1 g/L/d (0.2 g/g volatile solids (VS)/d) and 0.3 g/L/d (0:06 g/g VS/d), respectively. This study presents an ANN model predicting the performance of the reactor and determining the optimal architecture of this model; such as best back-propagation (BP) algorithm and neuron numbers. The Levenberg-Marquardt algorithm was selected as the best of 12 BP algorithms and optimal neuron number was determined as 20. The developed ANN model predicted acetate (R=0.91), sulfate (R=0.95), sulfide (R=0.97), and alkalinity (R=0.94) in the FBR effluent. Hence, the ANN based model can be used to predict the FBR performance, to control the operational conditions for improved process performance.