Search

Developing monitoring system for paper industrial wastewater treatment system is an important route for wastewater reuse and recycling from wastewater, which are regarded as effective way for cleaner production. A novel hybrid deep leaning CLSTMA model, which based on sequential fusion convolutional neural network (CNN), long short term memory (LSTM) and attention mechanism (AM), was developed to monitor the water quality in a full-scale paper industrial wastewater treatment system for energy conservation and emissions reduction. The hybrid CLSTMA model for predicting water quality of paper industrial wastewater treatment system was divided into three steps: spatial information fusion by using CNN module, temporal information fusion by using LSTM module and variable weighted calculation by using AM module. Compare with other models (CNN, LSTM and CLSTM models), RMSE of CLSTMA model for the effluent chemical oxygen demand (COD eff) reduced by 23.3–31.55%, MAE of CLSTMA model reduced by 38.89–74.50%, R of CLSTMA model increased by 8.29–11.86%. For the effluent suspended solids (SS eff), compared with CNN and LSTM models, RMSE of CLSTMA model reduced by 10.26% and 9.92%, MAE of CLSTMA model reduced by 5.37% and 3.44%, R of CLSTMA model increased by 15.13% and 37.21%, respectively. While, R of CLSTMA was consistent with CLSTM model, but RMSE and MAE of CLSTMA model reduced by 16.07% and 7.49% than the CLSTM model. Simulation results demonstrate that the proposed CLSTMA model has a great potential in monitoring paper industrial wastewater treatment system for cleaner production. [Display omitted] • A new deep learning model was proposed for real-time estimation of water quality. • The new model was based on convolutional neural network, long-term short-term memory and attention mechanism. • The new model can guarantee wastewater reuse and reduce the wastewater treatment cost. [ABSTRACT FROM AUTHOR]

Coupling of methanogenesis and denitrification with elevated nitrate under the methanogenic condition shows potential advantages for (N-) heterocyclic compounds removal and methane recovery simultaneously. However, methane production, sludge characteristics and microbial evolution response to elevated nitrate were seldom reported. Here, an experiment lasing about 300 days under the methanogenic condition with sequential influent nitrate addition as COD/NO 3 −-N ratio from 486.03 to 8.00 was carried out. More than 50% decline of removal rate of COD was observed when the COD/NO 3 −-N ratio varied from 19.97 to 8.00 (232 d). At last, the removal rate of COD recovered to around 94% at the COD/NO 3 −-N ratio of 8.00. About 90% of nitrate was removed through denitrification, and a lower content of methane (40–45%) and effluent acetate and propionate (<10 mg/L) were observed with elevated nitrate. Damage of the granule-shaped and multi-layer structure of the sludge with the lift of nitrate addition was studied. Results of high-throughput sequencing hinted that bacteria accounted for about 70% of total microbes and Proteobacteria , Bacteroidetes , Firmicute and Chloroflexi were the dominant phyla shared with sludge at different COD/NO 3 −-N ratio. Pseudomonas genus and Enterobacteriaceae family (Gammaproteobacteria class, Proteobacteria phylum), Brachymonas genus and Rhodocyclaceae family (Betaproteobacteria class, Proteobacteria phylum) might be vital for the denitrification process under the methanogenic condition. An increase of Smithella and Syntrophobacterale genus with elevated nitrate could be partly contributed to denitrification from the transformation of intermediates as propionate and butyrate. Methanosaeta and Methanobacterium genus were two major methanogens, and Methanosaeta seemed to be less adaptable for elevated nitrate than Methanobacterium. A suitable nitrate addition as influent COD/NO 3 −-N ratio ranged from 121.43 to 15.18 was recommended for the coupling of methanogenesis and denitrification. The results of this work would enhance the understanding of the effects and adaptation with elevated nitrate under the methanogenic condition and instruct engineering practice for low COD/NO 3 −-N wastewater treatment and methane recovery. Image 1 • Structure and architecture of methanogenic sludge with elevated nitrate was studied. • Conversion of different nitrogen form and biomethane with elevated nitrate was explored. • The Archaeal and bacterial community were significantly influenced by elevated nitrate. • A sharp increase of Smithella and Syntrophobacterale with nitrate addition was observed. • Methanobacterium and Methanosaeta genera were two major methanogenic archaea. [ABSTRACT FROM AUTHOR]