Accurate prediction of wastewater treatment plants(WWTPs) influent quality can provide valuable decision-making support to facilitate operations and management.However,since existing methods overlook the data noise ge...Accurate prediction of wastewater treatment plants(WWTPs) influent quality can provide valuable decision-making support to facilitate operations and management.However,since existing methods overlook the data noise generated from harsh operations and instruments,while the local feature pattern and long-term dependency in the wastewater quality time series,the prediction performance can be degraded.In this paper,a discrete wavelet transform and convolutional enhanced Transformer(DWT-Ce Transformer) method is developed to predict the influent quality in WWTPs.Specifically,we perform multi-scale analysis on time series of wastewater quality using discrete wavelet transform,effectively removing noise while preserving key data characteristics.Further,a tightly coupled convolutional-enhanced Transformer model is devised where convolutional neural network is used to extract local features,and then these local features are combined with Transformer's self-attention mechanism,so that the model can not only capture long-term dependencies,but also retain the sensitivity to local context.In this study,we conduct comprehensive experiments based on the actual data from a WWTP in Shaanxi Province and the simulated data generated by BSM2.The experimental results show that,compared to baseline models,DWT-Ce Transformer can significantly improve the prediction performance of influent COD and NH_(3)-N.Specifically,MSE,MAE,and RMSE improve by 78.7%,79.5%,and 53.8% for COD,and 79.4%,70.2%,and 54.5% for NH_(3)-N.On simulated data,our method shows strong improvements under various weather conditions,especially in dry weather,with MSE,MAE,and RMSE for COD improving by 68.9%,48.0%,and 44.3%,and for NH_(3)-N by 78.4%,54.8%,and 53.2%.展开更多
Two sequencing batch reactors（SBRs） were operated for 100 days under aerobic conditions,with one being fed with unsterilized municipal wastewater（USBR）, and the other fed with sterilized municipal wastewater（SSBR...Two sequencing batch reactors（SBRs） were operated for 100 days under aerobic conditions,with one being fed with unsterilized municipal wastewater（USBR）, and the other fed with sterilized municipal wastewater（SSBR）. Respirometric assays and fluorescence in situ hybridization（FISH） results show that active nitrifiers were present in the unsterilized influent municipal wastewater. The maximum ammonia utilization rate（AUR） and nitrite utilization rate（NUR） of the unsterilized influent were 0.32 ± 0.12 mg NH4＋-N/（L·hr） and0.71 ± 0.18 mg NO2--N/（L·hr）. Based on the maximum utilization rates, the estimated seeding intensity for the ammonia oxidizing bacteria（AOB） and nitrite oxidizing bacteria（NOB） of the USBR was 0.08 g AOB/（g AOB·day） and 0.20 g NOB/（g NOB·day） respectively. The fraction of nitrifiers/total bacteria in the influent was 5.35% ± 2.1%, the dominant AOB was Nitrosomonas spp., Nitrosococcus mobilis hybridizated with Nsm156, and the dominant NOB was Nitrospira hybridizated with Ntspa662. The influent nitrifiers potentially seeded the activated sludge of the bioreactor and hence demonstrated a mitigation of the acclimatization times and instability during start-up and early operation. The AUR and NUR in the USBR was 15% and 13% higher than the SSBR respectively during the stable stage, FISH results showed that nitrifiers population especially the Nitrospira in the USBR was higher than that in the SSBR. These results indicate that the natural continuous immigration of nitrifiers from municipal influent streams may have some repercussions on the modeling and design of bioreactors.展开更多
With the development of activated sludge model, the simulation software for the design and operation of wastewater treatment plant （WWTP） was produced and has been widely used. The dynamic change of the quality and ...With the development of activated sludge model, the simulation software for the design and operation of wastewater treatment plant （WWTP） was produced and has been widely used. The dynamic change of the quality and flow of influent are major factors causing the unstable operation of wastewater treatment process. As a basic model, ASMI model was used for the simulation of activated sludge process, and double exponential model was selected for the simulation of secondary sedimentation tank. The influences of influent change to the aeration tank and secondary sedimentation tank were investigated, and the relationship among influent change, the quality of effluent and the level of sludge blanket in secondary sedimentation tank was established. On the basis of the simulation results, the operation of the WWTP could be adjusted under the dynamic change of the influent. Furthermore, the controlling strategy combined the feed-forward on the influent flow and the feedback on the level of sludge blanket in the secondary sedimentation tank was studied.展开更多
In order to investigate the effect of influent condition heterogeneity on diversity of the bacterial community,the degree of microbial resolution and effluent quality,biological treatment of micro-polluted source wate...In order to investigate the effect of influent condition heterogeneity on diversity of the bacterial community,the degree of microbial resolution and effluent quality,biological treatment of micro-polluted source water is proposed. Scanning Electron Microscopy( SEM) analysis reflects that influent conditions change the morphologies of biofilm. Denaturing Gradient Gel Electrophoresis( DGGE) analysis shows differences of H values are due to succession of functional bacterial communities. Microbial resolution values and species identifications reveal organic carbon is the main cause of community differentiation and bacterial migration.展开更多
Daily influent quantity forecasting plays an important role in sewage treatment plant design and operation. Its uncertain factors are classified into three categories including day types, weather conditions and specia...Daily influent quantity forecasting plays an important role in sewage treatment plant design and operation. Its uncertain factors are classified into three categories including day types, weather conditions and special events, of which the latter two are considered with a BP (Back Propagation) model. On this basis, the daily period feature is taken into account in the presented model. The data from a practical sewage treatment plant utility is employed to show the effectiveness of the method.展开更多
The application of the Genetic Algorithm （GA） for the influent flow optimized distribution in the four stage pilot plant of Step-Feed Biological Nutrient Removal （BNR） System was discussed. Under decided process p...The application of the Genetic Algorithm （GA） for the influent flow optimized distribution in the four stage pilot plant of Step-Feed Biological Nutrient Removal （BNR） System was discussed. Under decided process parameter and influent water conditions, the objective function of optimization was designed to minimize the difference between estimated and required effluent concentrations at the four stage pilot plant of Step-Feed BNR System, the optimized parameter for influent distribution ratios of the four stages is 37.2%, 27.4%, 23.2% and 12.2% respectively. According to the optimizations results and raw wastewater pilot-scale experiment, the average removal efficiencies for pollutants are higher.展开更多
基金funded by the Natural Science Basic Research Program of Shaanxi (2024JCYBMS576)the National Natural Science Foundation of China (62366053)。
文摘Accurate prediction of wastewater treatment plants(WWTPs) influent quality can provide valuable decision-making support to facilitate operations and management.However,since existing methods overlook the data noise generated from harsh operations and instruments,while the local feature pattern and long-term dependency in the wastewater quality time series,the prediction performance can be degraded.In this paper,a discrete wavelet transform and convolutional enhanced Transformer(DWT-Ce Transformer) method is developed to predict the influent quality in WWTPs.Specifically,we perform multi-scale analysis on time series of wastewater quality using discrete wavelet transform,effectively removing noise while preserving key data characteristics.Further,a tightly coupled convolutional-enhanced Transformer model is devised where convolutional neural network is used to extract local features,and then these local features are combined with Transformer's self-attention mechanism,so that the model can not only capture long-term dependencies,but also retain the sensitivity to local context.In this study,we conduct comprehensive experiments based on the actual data from a WWTP in Shaanxi Province and the simulated data generated by BSM2.The experimental results show that,compared to baseline models,DWT-Ce Transformer can significantly improve the prediction performance of influent COD and NH_(3)-N.Specifically,MSE,MAE,and RMSE improve by 78.7%,79.5%,and 53.8% for COD,and 79.4%,70.2%,and 54.5% for NH_(3)-N.On simulated data,our method shows strong improvements under various weather conditions,especially in dry weather,with MSE,MAE,and RMSE for COD improving by 68.9%,48.0%,and 44.3%,and for NH_(3)-N by 78.4%,54.8%,and 53.2%.
基金supported by the National Natural Science Foundation for Young Scholars of China(No.51208414)the Education Department of Shaanxi Province Special Scientific Research(No.12JK0650)
文摘Two sequencing batch reactors（SBRs） were operated for 100 days under aerobic conditions,with one being fed with unsterilized municipal wastewater（USBR）, and the other fed with sterilized municipal wastewater（SSBR）. Respirometric assays and fluorescence in situ hybridization（FISH） results show that active nitrifiers were present in the unsterilized influent municipal wastewater. The maximum ammonia utilization rate（AUR） and nitrite utilization rate（NUR） of the unsterilized influent were 0.32 ± 0.12 mg NH4＋-N/（L·hr） and0.71 ± 0.18 mg NO2--N/（L·hr）. Based on the maximum utilization rates, the estimated seeding intensity for the ammonia oxidizing bacteria（AOB） and nitrite oxidizing bacteria（NOB） of the USBR was 0.08 g AOB/（g AOB·day） and 0.20 g NOB/（g NOB·day） respectively. The fraction of nitrifiers/total bacteria in the influent was 5.35% ± 2.1%, the dominant AOB was Nitrosomonas spp., Nitrosococcus mobilis hybridizated with Nsm156, and the dominant NOB was Nitrospira hybridizated with Ntspa662. The influent nitrifiers potentially seeded the activated sludge of the bioreactor and hence demonstrated a mitigation of the acclimatization times and instability during start-up and early operation. The AUR and NUR in the USBR was 15% and 13% higher than the SSBR respectively during the stable stage, FISH results showed that nitrifiers population especially the Nitrospira in the USBR was higher than that in the SSBR. These results indicate that the natural continuous immigration of nitrifiers from municipal influent streams may have some repercussions on the modeling and design of bioreactors.
文摘With the development of activated sludge model, the simulation software for the design and operation of wastewater treatment plant （WWTP） was produced and has been widely used. The dynamic change of the quality and flow of influent are major factors causing the unstable operation of wastewater treatment process. As a basic model, ASMI model was used for the simulation of activated sludge process, and double exponential model was selected for the simulation of secondary sedimentation tank. The influences of influent change to the aeration tank and secondary sedimentation tank were investigated, and the relationship among influent change, the quality of effluent and the level of sludge blanket in secondary sedimentation tank was established. On the basis of the simulation results, the operation of the WWTP could be adjusted under the dynamic change of the influent. Furthermore, the controlling strategy combined the feed-forward on the influent flow and the feedback on the level of sludge blanket in the secondary sedimentation tank was studied.
基金Sponsored by Major Science and Technology Program for Water Pollution Control and Treatment(Grant No.2012ZX07408001)State Key Laboratory of Urban Water Resource and Environment in China,Fundamental Research Funds for the Central Universities,China(Grant No.5710006113,HIT.BRETIII.201417)Postdoctoral Science Foundation of China(Grant No.2014T70324,LBH-Z12090)
文摘In order to investigate the effect of influent condition heterogeneity on diversity of the bacterial community,the degree of microbial resolution and effluent quality,biological treatment of micro-polluted source water is proposed. Scanning Electron Microscopy( SEM) analysis reflects that influent conditions change the morphologies of biofilm. Denaturing Gradient Gel Electrophoresis( DGGE) analysis shows differences of H values are due to succession of functional bacterial communities. Microbial resolution values and species identifications reveal organic carbon is the main cause of community differentiation and bacterial migration.
基金Funded by the National Natural Science Foundation of China (No.59838300)
文摘Daily influent quantity forecasting plays an important role in sewage treatment plant design and operation. Its uncertain factors are classified into three categories including day types, weather conditions and special events, of which the latter two are considered with a BP (Back Propagation) model. On this basis, the daily period feature is taken into account in the presented model. The data from a practical sewage treatment plant utility is employed to show the effectiveness of the method.
文摘The application of the Genetic Algorithm （GA） for the influent flow optimized distribution in the four stage pilot plant of Step-Feed Biological Nutrient Removal （BNR） System was discussed. Under decided process parameter and influent water conditions, the objective function of optimization was designed to minimize the difference between estimated and required effluent concentrations at the four stage pilot plant of Step-Feed BNR System, the optimized parameter for influent distribution ratios of the four stages is 37.2%, 27.4%, 23.2% and 12.2% respectively. According to the optimizations results and raw wastewater pilot-scale experiment, the average removal efficiencies for pollutants are higher.
