scholarly journals Performance improvement of wastewater treatment processes by application of machine learning

2020 ◽  
Vol 82 (12) ◽  
pp. 2671-2680
Author(s):  
O. Icke ◽  
D. M. van Es ◽  
M. F. de Koning ◽  
J. J. G. Wuister ◽  
J. Ng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Wastewater Treatment ◽  
Predictive Control ◽  
Stable Operation ◽  
Load Prediction ◽  
Network Modelling ◽  
Quality Requirements ◽  
Effluent Quality ◽  
Treatment Processes ◽  
Advanced Analytics

Abstract Improving wastewater treatment processes is becoming increasingly important, due to more stringent effluent quality requirements, the need to reduce energy consumption and chemical dosing. This can be achieved by applying artificial intelligence. Machine learning is implemented in two domains: (1) predictive control and (2) advanced analytics. This is currently being piloted at the integrated validation plant of PUB, Singapore's National Water Agency. (1) Primarily, predictive control is applied for optimised nutrient removal. This is obtained by application of a self-learning feedforward algorithm, which uses load prediction and machine learning, fine–tuned with feedback on ammonium effluent. Operational results with predictive control show that the load prediction has an accuracy of ≈88%. It is also shown that an up to ≈15% reduction of aeration amount is achieved compared to conventional control. It is proven that this load prediction-based control leads to stable operation and meeting effluent quality requirements as an autopilot system. (2) Additionally, advanced analytics are being developed for operational support. This is obtained by application of quantile regression neural network modelling for anomaly detection. Preliminary results illustrate the ability to autodetect process and instrument anomalies. These can be used as early warnings to deliver data-driven operational support to process operators.

Performance evaluation of different wastewater treatment technologies operating in a developing country

2011 ◽  
Vol 1 (1) ◽  
pp. 37-56 ◽  
Author(s):  
Sílvia C. Oliveira ◽  
Marcos von Sperling
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plants ◽  
Septic Tank ◽  
Operational Parameters ◽  
Technical Literature ◽  
Effluent Quality ◽  
Loading Rates ◽  
Treatment Processes ◽  
Treatment Technologies ◽  
Uasb Reactors

This article analyses the performance of 166 wastewater treatment plants operating in Brazil, comprising six different treatment processes: septic tank + anaerobic filter, facultative pond, anaerobic pond + facultative pond, activated sludge, UASB reactors alone, UASB reactors followed by post-treatment. The study evaluates and compares the observed effluent quality and the removal efficiencies in terms of BOD, COD, TSS, TN, TP and FC with typical values reported in the technical literature. In view of the large performance variability observed, the existence of a relationship between design/operational parameters and treatment performance was investigated. From the results obtained, no consistent relationship between loading rates and effluent quality was found. The influence of loading rates differed from plant to plant, and the effluent quality was dictated by several combined factors related to design and operation.

scholarly journals Effluent Quality Prediction of Papermaking Wastewater Treatment Processes Using Stacking Ensemble Learning

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 180844-180854
Author(s):  
Hongbin Liu ◽  
Chen Xin ◽  
Hao Zhang ◽  
Fengshan Zhang ◽  
Mingzhi Huang
Keyword(s):  
Wastewater Treatment ◽  
Ensemble Learning ◽  
Quality Prediction ◽  
Effluent Quality ◽  
Treatment Processes ◽  
Papermaking Wastewater

Impact of the volume of rain water on the operating constraints for a treatment plant

1999 ◽  
Vol 39 (2) ◽  
pp. 145-150
Author(s):  
T. Dormoy ◽  
B. Tisserand ◽  
L. Herremans
Keyword(s):  
Wastewater Treatment ◽  
Activated Sludge ◽  
Wastewater Treatment Plant ◽  
Wastewater Treatment Plants ◽  
Treatment Plant ◽  
Simulation Software ◽  
Quality Requirements ◽  
Effluent Quality ◽  
Operating Constraints ◽  
Pollution Loads

The new regulations require an increased amount of treatment of stormwater and a reduction of pollution loads discharged into the natural surroundings to be considered. Drainage systems therefore and particularly wastewater treatment plants should be sized correctly to cope with these peaks. Using a simulation software of wastewater treatment plant with activated sludge, such as SIMBAD, enables us to check that planned structures are appropriate in relation to the effluent quality requirements laid down, and to fix the most appropriate operating procedures. Operating constraints on a plant for treating stormwater are not negligible. It is advisable to allow for increased sludge production, O2 requirements and also sludge quality (fermentability).

Energy consumption model for wastewater treatment process control

2013 ◽  
Vol 67 (3) ◽  
pp. 667-674 ◽  
Author(s):  
Xiaoqi Huang ◽  
Honggui Han ◽  
Junfei Qiao
Keyword(s):  
Wastewater Treatment ◽  
Energy Consumption ◽  
Treatment Process ◽  
Wastewater Treatment Process ◽  
Elman Neural Network ◽  
Effluent Quality ◽  
Treatment Processes ◽  
Energy Consumption Model ◽  
Consumption Model ◽  
The Relationship

Wastewater treatment must satisfy discharge requirements under specified constraints and have minimal operating costs (OC). The operating results of wastewater treatment processes (WWTPs) have significantly focused on both the energy consumption (EC) and effluent quality (EQ). To reflect the relationship between the EC and EQ of WWTPs directly, an extended Elman neural network-based energy consumption model (EENN-ECM) was studied for WWTP control in this paper. The proposed EENN-ECM was capable of predicting EC values in the treatment process. Moreover, the self-adaptive characteristic of the EENN ensured the modeling accuracy. A performance demonstration was carried out through a comparison of the EC between the benchmark simulation model No.1 (BSM1) and the EENN-ECM. The experimental results demonstrate that this EENN-ECM is more effective to model the EC of WWTPs.

Sign in / Sign up

Export Citation Format

Share Document