scholarly journals Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6315
Author(s):  
Ivan Pisa ◽  
Antoni Morell ◽  
Ramón Vilanova ◽  
Jose Lopez Vicario
Keyword(s):  
Wastewater Treatment ◽  
Transfer Learning ◽  
Wastewater Treatment Plant ◽  
Short Term Memory ◽  
Control Strategies ◽  
Treatment Plant ◽  
Absolute Error ◽  
Control Structures ◽  
Control Loops ◽  
Long Short Term Memory

In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be directly obtained from input and output measurements without requiring a huge knowledge of the processes under control. However, ANNs have to be designed, implemented, and trained, which can become complex and time-demanding processes. This can be alleviated by means of Transfer Learning (TL) methodologies, where the knowledge obtained from a unique ANN is transferred to the remaining nets reducing the ANN design time. From the control viewpoint, the first ANN can be easily obtained and then transferred to the remaining control loops. In this manuscript, the application of TL methodologies to design and implement the control loops of a Wastewater Treatment Plant (WWTP) is analysed. Results show that the adoption of this TL-based methodology allows the development of new control loops without requiring a huge knowledge of the processes under control. Besides, a wide improvement in terms of the control performance with respect to conventional control structures is also obtained. For instance, results have shown that less oscillations in the tracking of desired set-points are produced by achieving improvements in the Integrated Absolute Error and Integrated Square Error which go from 40.17% to 94.29% and from 34.27% to 99.71%, respectively.

scholarly journals Forecasting Energy Consumption of Wastewater Treatment Plants with a Transfer Learning Approach for Sustainable Cities

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1149
Author(s):  
Pedro Oliveira ◽  
Bruno Fernandes ◽  
Cesar Analide ◽  
Paulo Novais
Keyword(s):  
Wastewater Treatment ◽  
Energy Consumption ◽  
Transfer Learning ◽  
Short Term Memory ◽  
Wastewater Treatment Plants ◽  
Learning Approach ◽  
Sustainable Cities ◽  
Short Term ◽  
Long Short Term Memory ◽  
Gated Recurrent Units

A major challenge of today’s society is to make large urban centres more sustainable. Improving the energy efficiency of the various infrastructures that make up cities is one aspect being considered when improving their sustainability, with Wastewater Treatment Plants (WWTPs) being one of them. Consequently, this study aims to conceive, tune, and evaluate a set of candidate deep learning models with the goal being to forecast the energy consumption of a WWTP, following a recursive multi-step approach. Three distinct types of models were experimented, in particular, Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRUs), and uni-dimensional Convolutional Neural Networks (CNNs). Uni- and multi-variate settings were evaluated, as well as different methods for handling outliers. Promising forecasting results were obtained by CNN-based models, being this difference statistically significant when compared to LSTMs and GRUs, with the best model presenting an approximate overall error of 630 kWh when on a multi-variate setting. Finally, to overcome the problem of data scarcity in WWTPs, transfer learning processes were implemented, with promising results being achieved when using a pre-trained uni-variate CNN model, with the overall error reducing to 325 kWh.

Improving the efficiency of a wastewater treatment plant by fuzzy control and neural networks

2001 ◽  
Vol 43 (11) ◽  
pp. 189-196 ◽  
Author(s):  
M. Bongards
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Municipal Wastewater ◽  
Fuzzy Controller ◽  
Control Strategies ◽  
Treatment Plant ◽  
Municipal Wastewater Treatment ◽  
Controlled System ◽  
Measurement Results ◽  
Predictive Controller

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.

Multi-criteria evaluation of wastewater treatment plant control strategies under uncertainty

2008 ◽  
Vol 42 (17) ◽  
pp. 4485-4497 ◽  
Author(s):  
Xavier Flores-Alsina ◽  
Ignasi Rodríguez-Roda ◽  
Gürkan Sin ◽  
Krist V. Gernaey
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Control Strategies ◽  
Treatment Plant ◽  
Multi Criteria Evaluation ◽  
Plant Control

An evaluation of the efficiency of the combined sewer – wastewater treatment system under transient conditions

1996 ◽  
Vol 33 (2) ◽  
pp. 199-208 ◽  
Author(s):  
W. Bauwens ◽  
P. Vanrolleghem ◽  
M. Smeets
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Control Strategies ◽  
Treatment Plant ◽  
Problem Area ◽  
Control Measures ◽  
Plant Management ◽  
Potential Control ◽  
Combined Sewer ◽  
Management Schemes

The paper considers the efficiency of alternative sewer and wastewater treatment plant management schemes with respect to the effluents to the receiving waters. The input time series for the flows and concentrations at the CSO structures and at the treatment plant intake are obtained through a continuous sewer simulation model. The wastewater treatment plant model is based on a structured dynamic model describing COD removal and final settling. Special emphasis is put on the sludge inventory of the plant since this is considered to be the main problem area under storm conditions. The methodology is illustrated on the combined sewer network of Brussels. Scenarios without and with CSO control measures in the sewer are considered. At the treatment plant, the simulation study evaluates the effect of potential control strategies such as ratio control of the RAS, step feed and retention of first flush in a storm tank.

Adaptive predictive expert control of dissolved oxygen concentration in a wastewater treatment plant

2011 ◽  
Vol 64 (5) ◽  
pp. 1130-1136 ◽  
Author(s):  
G. Kandare ◽  
A. Nevado Reviriego
Keyword(s):  
Wastewater Treatment ◽  
Dissolved Oxygen ◽  
Wastewater Treatment Plant ◽  
Treatment Plant ◽  
Operating Conditions ◽  
Expert Control ◽  
Control Loops ◽  
Process Dynamics ◽  
The Common ◽  
Do Control

In this paper we present the application of adaptive predictive expert controllers to dissolved oxygen (DO) control in the aerobic reactors of a wastewater treatment plant. The control system described in this paper consists of adaptive predictive expert control loops complemented by optimisation logic. The controllers successfully cope with nonlinearity and changing operating conditions of the process by predicting the evolution of the controlled variable and adapting to changes in the process dynamics. This results in more precise and stable DO control, offering many benefits. The complementary optimisation logic maintains the air pressure in the common collector at the lowest possible level, enabling adequate DO control and thus considerably reducing energy consumption.

Validation and implementation of model based control strategies at an industrial wastewater treatment plant

2001 ◽  
Vol 44 (2-3) ◽  
pp. 145-154 ◽  
Author(s):  
D. Demey ◽  
B. Vanderhaegen ◽  
H. Vanhooren ◽  
J. Liessens ◽  
L. Van Eyck ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Industrial Wastewater ◽  
Dynamic Models ◽  
Control Strategies ◽  
Treatment Plant ◽  
Practical Implementation ◽  
Industrial Wastewater Treatment ◽  
Model Based ◽  
On Line

In this paper, the practical implementation and validation of advanced control strategies, designed using model based techniques, at an industrial wastewater treatment plant is demonstrated. The plant under study is treating the wastewater of a large pharmaceutical production facility. The process characteristics of the wastewater treatment were quantified by means of tracer tests, intensive measurement campaigns and the use of on-line sensors. In parallel, a dynamical model of the complete wastewater plant was developed according to the specific kinetic characteristics of the sludge and the highly varying composition of the industrial wastewater. Based on real-time data and dynamic models, control strategies for the equalisation system, the polymer dosing and phosphorus addition were established. The control strategies are being integrated in the existing SCADA system combining traditional PLC technology with robust PC based control calculations. The use of intelligent control in wastewater treatment offers a wide spectrum of possibilities to upgrade existing plants, to increase the capacity of the plant and to eliminate peaks. This can result in a more stable and secure overall performance and, finally, in cost savings. The use of on-line sensors has a potential not only for monitoring concentrations, but also for manipulating flows and concentrations. This way the performance of the plant can be secured.

scholarly journals Control Strategies of a Wastewater Treatment Plant

2019 ◽  
Vol 52 (1) ◽  
pp. 257-262
Author(s):  
Laurentiu Luca ◽  
Ramon Vilanova ◽  
George Adrian Ifrim ◽  
Emil Ceanga ◽  
Sergiu Caraman ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Control Strategies ◽  
Treatment Plant

Odour emission estimates and control strategies using models and sampling for East Bay Municipal Utility District's collection sewage system and wastewater treatment plant

2000 ◽  
Vol 41 (6) ◽  
pp. 65-71
Author(s):  
J. R. Witherspoon ◽  
A. Sidhu ◽  
J. Castleberry ◽  
L. Coleman ◽  
K. Reynolds ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Model Comparison ◽  
Control Strategies ◽  
Treatment Plant ◽  
Sewage System ◽  
Control Options ◽  
East Bay ◽  
Odour Control ◽  
Odour Emissions

For several years, public complaints regarding odours generated by East Bay Municipal Utility District's (EBMUD's) wastewater treatment plant and sewage collection system (SCS) have been increasing. In response, an Odor Control Master Plan was completed to develop near- and long-term odour abatement strategies for their wastewater system. The plan's strategies include using an advisory committee to assist in setting odour threshold levels, prioritizingodour sources, issuing an odour-status newsletter, and reviewing odour control options. The objective is to provide an odour-free community environment at least 99 percent of the year. This paper provides innovative approaches to estimate odour emissions and identify viable odour control options for SCSs through complete wastewater treatment. This paper also presents a CH2M HILL SCS odour model comparison to a comprehensive EBMUD sewage system corrosion study, illustrating that areas having high predicted odours also have high corrosion rates.

scholarly journals Design of Feedback Control Strategies in a Plant-Wide Wastewater Treatment Plant for Simultaneous Evaluation of Economics, Energy Usage, and Removal of Nutrients

Energies ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 6386
Author(s):  
Abdul Gaffar Sheik ◽  
Eagalapati Tejaswini ◽  
Murali Mohan Seepana ◽  
Seshagiri Rao Ambati ◽  
Montse Meneses ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Wastewater Treatment Plant ◽  
Removal Rate ◽  
Control Strategies ◽  
Treatment Plant ◽  
Feedback Signal ◽  
Operational Cost ◽  
Effluent Quality ◽  
Control Framework ◽  
Pi Controllers

Simultaneous removal of nitrogen and phosphorous is a recommended practice while treating wastewater. In the present study, control strategies based on proportional-integral (PI), model predictive control (MPC), and fuzzy logic are developed and implemented on a plant-wide wastewater treatment plant. Four combinations of control frameworks are developed in order to reduce the operational cost and improve the effluent quality. As a working platform, a Benchmark simulation model (BSM2-P) is used. A default control framework with PI controllers is used to control nitrate and dissolved oxygen (DO) by manipulating the internal recycle and oxygen mass transfer coefficient (KLa). Hierarchical control topology is proposed in which a lower-level control framework with PI controllers is implemented to DO in the sixth reactor by regulating the KLa of the fifth, sixth, and seventh reactors, and fuzzy and MPC are used at the supervisory level. This supervisory level considers the ammonia in the last aerobic reactor as a feedback signal to alter the DO set-points. PI-fuzzy showed improved effluent quality by 21.1%, total phosphorus removal rate by 33.3% with an increase of operational cost, and a slight increase in the production rates of greenhouse gases. In all the control design frameworks, a trade-off is observed between operational cost and effluent quality.

Sign in / Sign up

Export Citation Format

Share Document