Back propagation neural network (BPNN) prediction model and control strategies of methanogen phase reactor treating traditional Chinese medicine wastewater (TCMW).

Based on the prototype experiment of treating herb wastewater by Up flow Anaerobic Sludge Bed and Anaerobic Filter reactor (UASBAF), an artificial neural network (ANN) model which adopts a back propagation algorithm with momentum and adaptive learning rate was established. And the effect of each parameter to the performance of the reactor was compared, using the method of partitioning connection weights (PCW). The result is pH values>influent of chemical oxygen demand (COD)>hydraulic retention time (HRT)>alkalinity. In addition, many strategies were proposed to optimize the working condition of the system. Adding some alkali to increase pH value when raising influent COD, was an effective way to avoid negative effect to system; low influent COD had a negative impact on the performance of the reactor; pH was suggested to be controlled more than 7.5 when the influent COD was increased over 6000mgL(-1). The best influent COD concentration was 6000-8000mgL(-1) when the conditions were that pH was 7.5, alkalinity was 2000mgL(-1) and HRT was 35-50h; HRT was suggested to be controlled more than 50h to maintain good performance of the reactor with high influent COD (8000-10,000mgL(-1)). These strategies provided an effective way of controlling UASBAF simply.

Hydrogen bio-production through anaerobic microorganism fermentation using kitchen wastes as substrate.

In order to treat the kitchen wastes and produce hydrogen, anaerobic fermentation technology was used in this experiment. The results showed that the fermentation type changed from mixed acid fermentation to ethanol fermentation in a continuous stirred tank reactor (CSTR) 22 days after start-up. The maximum efficiency of hydrogen bio-production in the CSTR was 4.77 LH(2)/(L reactor d) under the following conditions: organic loading rate (OLR) of 32-50 kg COD/(m(3) d), oxidation reduction potential (ORP) of -450 to -400 mV, influent pH value of 5.0-6.0, effluent pH value of 4.0-4.5, influent alkalinity of 300-600 mg/l, temperature of 35 +/- 1 degrees C and hydraulic retention time (HRT) of 7 h. An artificial neural network (ANN) model was established, and each parameter influencing the performance of the reactor was compared using the method of partitioning connection weights (PCW). The results showed that OLR, pH, ORP and alkalinity could influence the fermentation characteristics and hydrogen yield of the anaerobic activated sludge; with an influence hierarchy: OLR > pH values > ORP > alkalinity. An economic analysis showed that the cost of producing hydrogen in this experiment was less than the cost of electrolysis of water.