Control and soft sensing strategies for a wastewater treatment plant using a neuro-genetic approach

Abstract

During the last years, machine learning-based control and optimization systems are playing an important role in the operation of wastewater treatment plants in terms of reduced operational costs and improved effluent quality. In this paper, a machine learning-based control strategy is proposed for optimizing both the consumption and the number of regulation violations of a biological wastewater treatment plant. The methodology proposed in this study uses neural networks as a soft-sensor for on-line prediction of the effluent quality and as an identification model of the plant dynamics, all under a neuro-genetic optimum model-based control approach. The complete scheme was tested on a simulation model of the activated sludge process of a large-scale municipal wastewater treatment plant running under the GPS-X simulation frame and validated with operational gathered data, showing optimal control performance by minimizing operational costs while satisfying the effluent requirements, thus reducing the investment in expensive sensor devices.

An Algorithm for Soft Sensor Development for a Class of Processes with Distinct Operating Conditions

“…There are different approaches to soft sensor development, but the complexity of the production process and uncertainties in determining the connection between laboratory values and signals that are measured in the process are reasons why soft sensors in the process industry are mainly based on black box or gray box models. The black box approach is successfully applied to different processes, from the cement industry [ 1 , 2 , 3 , 4 ] and chemical processes [ 5 , 6 , 7 ] to water treatment [ 8 , 9 , 10 ], energy production [ 11 ] and the oil industry [ 12 , 13 , 14 ]. Since it proved appropriate for the development of soft sensors for a variety of industrial processes, the black box approach has the potential to be used as a basis for a wide industrial implementation of soft sensors.…”

“…Different model types have been used for the development of black box models for soft sensors in industrial processes, from models based on different types of Neural Networks [ 1 , 3 , 6 , 8 , 9 , 10 , 11 , 14 ], which represent the most common class of models, to Support Vector Regression [ 2 , 9 ], Neuro Fuzzy [ 13 ], Fuzzy Modeling [ 15 ], Linear Regression [ 16 ], and various other types of models. Determining the model type that is suitable for developing soft sensors for all industrial processes is, of course, not possible.…”

Data-Based Modelling of Chemical Oxygen Demand for Industrial Wastewater Treatment

“…Therefore, these sensors require constant maintenance, recalibration or replacement to keep them accurate, which is why soft sensors could prove to be a good alternative. A soft sensor can be utilised to indicate the malfunction of a hardware sensor or used instead of a hardware sensor for monitoring a process variable [3][4][5]. With a real-time estimator, process operators could match the process conditions to the incoming COD more accurately.…”

Developing accurate data-driven soft-sensors through integrating dynamic kernel slow feature analysis with neural networks

“…The selection of nonlinear modelling techniques is vast and, with the era of machine learning and artificial intelligence rapidly growing alongside hardware improvements, the selection keeps increasing. Neural networks have always been one of the most used techniques for softsensing (Corrigan & Zhang, 2020;Fernandez de Canete et al, 2021) ever since they were first used for inferential estimation by Willis et al (1991). In more recent times, neural networks have evolved and extensions such as deep learning (Shang et al, 2014;Yuan et al, 2020b), ensembles (Li et al, 2015;Yi et al, 2020;Zhang et al, 1997) and echo state networks (Bo et al, 2020;He et al, 2020; have been widely used for soft-sensing applications.…”