scholarly journals Real-time model predictive control of a wastewater treatment plant based on machine learning

Author(s):  
A. Bernardelli ◽  
S. Marsili-Libelli ◽  
A. Manzini ◽  
S. Stancari ◽  
G. Tardini ◽  
...  

Abstract Two separate goals should be jointly pursued in wastewater treatment: nutrient removal and energy conservation. An efficient controller performance should cope with process uncertainties, seasonal variations and process nonlinearities. This paper describes the design and testing of a model predictive controller (MPC) based on neuro-fuzzy techniques that is capable of estimating the main process variables and providing the right amount of aeration to achieve an efficient and economical operation. This algorithm has been field tested on a large-scale municipal wastewater treatment plant of about 500,000 PE, with encouraging results in terms of better effluent quality and energy savings.

2012 ◽  
Vol 518-523 ◽  
pp. 2324-2327
Author(s):  
Jun Feng Wu ◽  
Hua Shu Ouyang ◽  
Xian Li Wang

To alleviate the water pollution, the original wastewater treatment process was transformed based on the existing structures. Anaerobic-anoxic-aerobic process (A2/O process) was used as the main process, instead of the original two-stage aeration process (AB process). Pretreatment process and advanced treatment process were strengthened. After transformation, the effluent quality could meet the first class of A standard of the "municipal wastewater treatment plant emission standards" (GB18918-2002) and all the quality indexes of the treated water met the requirements of discharge standard of sewage treatment. The original structures were fully used in this transformation, saving investment, which provided a practical reference for the transformation of the wastewater treatment plants.


Water ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1339
Author(s):  
Javier Bayo ◽  
Sonia Olmos ◽  
Joaquín López-Castellanos

This study investigates the removal of microplastics from wastewater in an urban wastewater treatment plant located in Southeast Spain, including an oxidation ditch, rapid sand filtration, and ultraviolet disinfection. A total of 146.73 L of wastewater samples from influent and effluent were processed, following a density separation methodology, visual classification under a stereomicroscope, and FTIR analysis for polymer identification. Microplastics proved to be 72.41% of total microparticles collected, with a global removal rate of 64.26% after the tertiary treatment and within the average retention for European WWTPs. Three different shapes were identified: i.e., microfiber (79.65%), film (11.26%), and fragment (9.09%), without the identification of microbeads despite the proximity to a plastic compounding factory. Fibers were less efficiently removed (56.16%) than particulate microplastics (90.03%), suggesting that tertiary treatments clearly discriminate between forms, and reporting a daily emission of 1.6 × 107 microplastics to the environment. Year variability in microplastic burden was cushioned at the effluent, reporting a stable performance of the sewage plant. Eight different polymer families were identified, LDPE film being the most abundant form, with 10 different colors and sizes mainly between 1–2 mm. Future efforts should be dedicated to source control, plastic waste management, improvement of legislation, and specific microplastic-targeted treatment units, especially for microfiber removal.


Proceedings ◽  
2021 ◽  
Vol 52 (1) ◽  
pp. 3
Author(s):  
Luis F. Carmo-Calado ◽  
Roberta Mota-Panizio ◽  
Gonçalo Lourinho ◽  
Octávio Alves ◽  
I. Gato ◽  
...  

The technical-economic analysis was carried out for the production of sludge-derived fuel from a municipal wastewater treatment plant (WWTP). The baseline for the analysis consists of a sludge drying plant, processing 6 m3 of sludge per day and producing a total of about 1 m3 of combustible material with 8% of moisture and a higher calorific power of 18.702 MJ/kg. The transformation of biofuel into energy translates into an electricity production of about 108 kW per 100 kg of sludge. The project in the baseline scenario demonstrated feasibility with a payback time of about six years.


2000 ◽  
Vol 41 (7) ◽  
pp. 31-37 ◽  
Author(s):  
E. Carraro ◽  
E. Fea ◽  
S. Salva ◽  
G. Gilli

The aim of this study was to assess the impact of a municipal wastewater treatment plant (MWTP) on the occurrence of Cryptosporidium oocysts and Giardia cysts in the receiving water. All MWTP effluent samples were Giardia and Cryptosporidium contaminated, although low mean values were found for both parasites (0.21±0.06 oocysts/L; 1.39±0.51 cysts/L). Otherwise, in the raw sewage a greater concentration was detected (4.5±0.3 oocysts/L; 53.6±6.8 cysts/L). The major occurrence of Giardia over Cryptosporidium, both in the influent and in the effluent of the MWTP, is probably related to the human sewage contribution to the wastewater. Data on protozoa contamination of the receiving water body demonstrated similar concentrations in the samples collected before (0.21±0.07 oocysts/L; 1.31±0.38 cysts/L) and after (0.17±0.09 oocysts/L and 1.01±1.05 cysts/L) the plant effluent discharge. The results of this study suggest that the MWTP has no impact related to Giardia and Cryptosporidium river water contamination, and underline the need for investigation into the effectiveness of these protozoa removal by less technologically advanced MWTPs which are the most widespread and could probably show a lower ability to reduce protozoa.


2001 ◽  
Vol 43 (11) ◽  
pp. 189-196 ◽  
Author(s):  
M. Bongards

One of the main problems in operating a wastewater treatment plant is the purification of the excess water from dewatering and pressing of sludge. Because of a high load of organic material and of nitrogen it has to be buffered and treated together with the inflowing wastewater. Different control strategies are discussed. A combination of neural network for predicting outflow values one hour in advance and fuzzy controller for dosing the sludge water are presented. This design allows the construction of a highly non-linear predictive controller adapted to the behaviour of the controlled system with a relatively simple and easy to optimise fuzzy controller. Measurement results of its operation on a municipal wastewater treatment plant of 60,000 inhabitant equivalents are presented and discussed. In several months of operation the system has proved very reliable and robust tool for improving the system's efficiency.


Sign in / Sign up

Export Citation Format

Share Document