홈 › Papers

Dynamic optimization of volatile fatty acids to enrich biohydrogen production using a deep learning neural network

A new strategy was developed to investigate the effect of volatile fatty acids (VFAs) on the efficiency of biogas production with a focus on improving bio-H$_2$. The inoculum used, anaerobic granular sludge obtained from a UASB reactor treating poultry slaughterhouse wastewater, was pretreated with five different pretreatments. The relationship between VFAs and biogas compounds was studied as time-dependent components. In time-dependent processes with small sample size data, regression models may not be good enough at estimating responses. Therefore, a deep learning neural network (DNN) model was developed to estimate the biogas compounds based on the VFAs. The accuracy of this model to predict the biogas compounds was higher than that of multivariate regression models. Further, it could predict the effect of time changes on biogas compounds. Analysis showed that all the pretreatments were able to increase the ratio of butyric acid / acetic acid successfully, decrease propionic acid drastically, and increase the efficiency of bio-H$_2$ production. As discovered, butyric acid had the greatest effect on bio-H$_2$, and propionic acid had the greatest effect on CH$_4$ production. The best amounts of the VFAs were determined using an optimization method, integrated DNN and desirability analysis, dynamically retrained based on digestion time. Accordingly, optimal ranges of acetic, propionic, and butyric acids were 823.2 - 1534.3, 36.3 - 47.4, and 1522 - 1822 mg/L, respectively, determined for digestion time of 25.23 - 123.63 h. These values resulted in the production of bio-H$_2$, N$_2$, CO$_2$, and CH$_4$ in ranges of 6.4 - 26.2, 12.2 - 43.2, 5 - 25.3, and 0 - 1.4 mmol/L, respectively. The optimum ranges of VFAs are relatively wide ranges and practically can be used in biogas plants.

Code (0)

등록된 구현이 없습니다.

Tasks

Similar Papers 제목 키워드 기반