High gravity and high productivity ethanol fermentation with self-flocculating yeast cells (original) (raw)
Related papers
Renewable and Sustainable Energy Reviews , 2020
An anaerobic fermentation process for biogas production integrated with wastewater purification in a modern wastewater treatment plant (WWTP) of designed nominal capacity 27,000 m 3 /day was modelled using artificial neural networks (ANNs). Neural models were trained, validated, and tested based on real-scale industrial data (covering three years of continuous plant operation), considering both technological aspects of the process and treated wastewater quality. An innovative approach addressing the simultaneous effect of seven adjustable main plant operation parameters together with wastewater characteristics (five parameters) on biogas production is reported for the first time in the literature. A parameter sensitivity analysis indicated clearly the higher importance of the operation process parameters on the biogas yield compared to the wastewater quality (COD, BOD 5 , TSS, P g , N g). The operation process parameters were the subject of modelling and analysis in respect to new, innovative possibilities, and technological strategies for biogas yield enhancement. The ANN model presented can be used as a predictive tool, an important element in such complex processes as steering/control strategies or for their optimisation procedures, as well as in the testing of other promising process intensification and optimisation scenarios.
Recently, process control in wastewater treatment plants (WWTPs) is, mostly accomplished through examining the quality of the water effluent and adjusting the processes through the operator's experience. This practice is inefficient, costly and slow in control response. A better control of WTPs can be achieved by developing a robust mathematical tool for performance prediction. Due to their high accuracy and quite promising application in the field of engineering, Artificial Neural Networks (ANNs) are attracting attention in the domain of WWTP predictive performance modeling. This work focuses on applying ANN with a feed-forward, back propagation learning paradigm to predict the effluent water quality of the Habesha brewery WTP. Data of influent and effluent water quality covering approximately an 11-month period (May 2016 to March 2017) were used to develop, calibrate and validate the models. The study proves that ANN can predict the effluent water quality parameters with a correlation coefficient (R) between the observed and predicted output values reaching up to 0.969. Model architecture of 3-21-3 for pH and TN, and 1-76-1 for COD were selected as optimum topologies for predicting the Habesha Brewery WTP performance. The linear correlation between predicted and target outputs for the optimal model architectures described above were 0.9201 and 0.9692, respectively.
Wastewater treatment methods are dynamic and have high non-linear behaviour. The significance of the influent disturbances and the bioreactor performances are generally predicted off-line in a laboratory, since there is no consistent on-line sensor available for the prediction. This work suggests the development of a neural network model for prediction of the values of the influent disturbances using Z-score as a normalization technique followed by Genetic Algorithm (GA) as a feature selection process to improve the speed and quality of the prediction accuracy. A Back Propagation Network (BPN) trained using Modified Levenberg–Marquardt (MLM) algorithm was efficiently utilized to develop a BPN for an Up-flow Anaerobic filter (UAF) for predicting the chemical oxygen demand (COD) level in the effluent. In this paper, MLM algorithm has been applied to train the BPN based on the normalized influent parameters of the cheese-dairy wastewater treatment using UAF. COD is an essential test fo...