Prediction of membrane fouling using artificial neural networks for wastewater treated by membrane bioreactor technologies: bottlenecks and possibilities

Artificial-intelligence-model to optimize biocide dosing in seawater-cooled industrial process applications considering environmental, technical, energetic, and economic aspects

This research introduces an Artificial Intelligence (AI) based model designed to concurrently optimize energy supply management, biocide dosing, and maintenance scheduling for heat exchangers. This optimization considers energetic, technical, economic, and environmental considerations. The impact of biofilm on heat exchangers is assessed, revealing a 41% reduction in thermal efficiency and a 113% increase in flow frictional resistance of the fluid compared to the initial state. Consequently, the pump's power consumption, required to maintain hydraulic conditions, rises by 9%. The newly developed AI model detects the point at which the heat exchanger's performance begins to decline due to accumulating dirt, marking day 44 of experimentation as the threshold to commence the antifouling biocide dosing. Leveraging this AI model to monitor heat exchanger efficiency represents an innovative approach to optimizing antifouling biocide dosing and reduce the environmental impact stemming from industrial plants.

Modelling and optimization of membrane process for removal of biologics (pathogens) from water and wastewater: Current perspectives and challenges

As one of the 17 sustainable development goals, the United Nations (UN) has prioritized "clean water and sanitation" (Goal 6) to reduce the discharge of emerging pollutants and disease-causing agents into the environment. Contamination of water by pathogenic microorganisms and their existence in treated water is a global public health concern. Under natural conditions, water is frequently prone to contamination by invasive microorganisms, such as bacteria, viruses, and protozoa. This circumstance has therefore highlighted the critical need for research techniques to prevent, treat, and get rid of pathogens in wastewater. Membrane systems have emerged as one of the effective ways of removing contaminants from water and wastewater However, few research studies have examined the synergistic or conflicting effects of operating conditions on newly developing contaminants found in wastewater. Therefore, the efficient, dependable, and expeditious examination of the pathogens in the intricate wastewater matrix remains a significant obstacle. As far as it can be ascertained, much attention has not recently been given to optimizing membrane processes to develop optimal operation design as related to pathogen removal from water and wastewater. Therefore, this state-of-the-art review aims to discuss the current trends in removing pathogens from wastewater by membrane techniques. In addition, conventional techniques of treating pathogenic-containing water and wastewater and their shortcomings were briefly discussed. Furthermore, derived mathematical models suitable for modelling, simulation, and control of membrane technologies for pathogens removal are highlighted. In conclusion, the challenges facing membrane technologies for removing pathogens were extensively discussed, and future outlooks/perspectives on optimizing and modelling membrane processes are recommended.

Machine learning methods for the modelling and optimisation of biogas production from anaerobic digestion: a review

Biogas plant operators often face huge challenges in the monitoring, controlling and optimisation of the anaerobic digestion (AD) process, as it is very sensitive to surrounding changes, which often leads to process failure and adversely affects biogas production. Conventional implemented methods and mechanistic models are impractical and find it difficult to model the nonlinear and intricate interactions of the AD process. Thus, the development of machine learning (ML) algorithms has attracted considerable interest in the areas of process optimization, real-time monitoring, perturbation detection and parameter prediction. This paper provides a comprehensive and up-to-date overview of different machine learning algorithms, including artificial neural network (ANN), fuzzy logic (FL), adaptive network-based fuzzy inference system (ANFIS), support vector machine (SVM), genetic algorithm (GA) and particle swarm optimization (PSO) in terms of working mechanism, structure, advantages and disadvantages, as well as their prediction performances in modelling the biogas production. A few recent case studies of their applications and limitations are also critically reviewed and compared, providing useful information and recommendation in the selection and application of different ML algorithms. This review shows that the prediction efficiency of different ML algorithms is greatly impacted by variations in the reactor configurations, operating conditions, influent characteristics, selection of input parameters and network architectures. It is recommended to incorporate mixed liquor volatile suspended solids (MLVSS) concentration of the anaerobic digester (ranging from 16,500 to 46,700 mg/L) as one of the input parameters to improve the prediction efficiency of ML modelling. This review also shows that the combination of different ML algorithms (i.e. hybrid GA-ANN model) could yield better accuracy with higher R2 (0.9986) than conventional algorithms and could improve the optimization model of AD. Besides, future works could be focused on the incorporation of an integrated digital twin system coupled with ML techniques into the existing Supervisory Control and Data Acquisition (SCADA) system of any biogas plant to detect any operational abnormalities and prevent digester upsets.

Predictive modeling based on artificial neural networks for membrane fouling in a large pilot-scale anaerobic membrane bioreactor for treating real municipal wastewater

Membrane fouling is the primary obstacle to applying anaerobic membrane bioreactors (AnMBRs) in municipal wastewater treatment. This issue holds critical significance as efficient wastewater treatment serves as a cornerstone for achieving environmental sustainability. This study uses machine learning to predict membrane fouling, taking advantage of rapid computational and algorithmic advances. Based on the 525-day operation data of a large pilot-scale AnMBR for treating real municipal wastewater, regression prediction was realized using multilayer perceptron (MLP) and long short-term memory (LSTM) artificial neural networks under substantial variations in operating conditions. The models involved employing the organic loading rate, suspended solids concentration, protein concentration in extracellular polymeric substance (EPSp), polysaccharide concentration in EPS (EPSc), reactor temperature, and flux as input features, and transmembrane pressure as the prediction target output. Hyperparameter optimization enhanced the regression prediction accuracies, and the rationality and utility of the MLP model for predicting large-scale AnMBR membrane fouling were confirmed at global and local levels of interpretability analysis. This work not only provides a methodological advance but also underscores the importance of merging environmental engineering with computational advancements to address pressing environmental challenges.

Effects of CO2 concentration and time on algal biomass film, NO3-N concentration, and pH in the membrane bioreactor: Simulation-based ANN, RSM and NSGA-II

The practice of aquaculture is associated with the generation of a substantial quantity of effluent. Microalgae must effectively assimilate nitrogen and phosphorus from their surrounding environment for growth. This study modeled the algal biomass film, NO3-N concentration, and pH in the membrane bioreactor using the response surface methodology (RSM) and an artificial neural network (ANN). Furthermore, it was suggested that the optimal condition for each parameter be determined. The results of ANN modeling showed that ANN with a structure of 5-3 and employing the transfer functions tansig-logsig demonstrated the highest level of accuracy. This was evidenced by the obtained values of coefficient (R2) = 0.998, R = 0.999, mean squared error (MAE) = 0.0856, and mean square error (MSE) = 0.143. The ANN model, characterized by a 5-5 structure and employing the tansig-logsig transfer function, demonstrates superior accuracy when predicting the concentration of NO3-N and pH. This is evidenced by the high values of R2 (0.996), R (0.998), MAE (0.00162), and MSE (0.0262). The RSM was afterward employed to maximize the performance of algal film biomass, pH levels, and NO3-N concentrations. The optimal conditions for the algal biomass film were a concentration of 2.884 mg/L and a duration of 6.589 days. Similarly, the most favorable conditions for the NO3-N concentration and pH were 2.984 mg/L and 6.787 days, respectively. Therefore, this research uses non-dominated sorting genetic algorithm II (NSGA II) to find the optimal NO3-N concentration, algal biomass film, and pH for product or process quality. The region has the greatest alkaline pH and lowest NO3-N content.

A Comprehensive Analysis of the Impact of Inorganic Matter on Membrane Organic Fouling: A Mini Review

Membrane fouling is a non-negligible issue affecting the performance of membrane systems. Particularly, organic fouling is the most persistent and severe form of fouling. The complexation between inorganic and organic matter may exacerbate membrane organic fouling. This mini review systematically analyzes the role of inorganic matter in membrane organic fouling. Inorganic substances, such as metal ions and silica, can interact with organic foulants like humic acids, polysaccharides, and proteins through ionic bonding, hydrogen bonding, coordination, and van der Waals interactions. These interactions facilitate the formation of larger aggregates that exacerbate fouling, especially for reverse osmosis membranes. Molecular simulations using molecular dynamics (MD) and density functional theory (DFT) provide valuable mechanistic insights complementing fouling experiments. Polysaccharide fouling is mainly governed by transparent exopolymer particle (TEP) formations induced by inorganic ion bridging. Inorganic coagulants like aluminum and iron salts mitigate fouling for ultrafiltration but not reverse osmosis membranes. This review summarizes the effects of critical inorganic constituents on fouling by major organic foulants, providing an important reference for membrane fouling modeling and fouling control strategies.

Artificial intelligence-incorporated membrane fouling prediction for membrane-based processes in the past 20 years: A critical review

Membrane fouling is one of major obstacles in the application of membrane technologies. Accurately predicting or simulating membrane fouling behaviours is of great significance to elucidate the fouling mechanisms and develop effective measures to control fouling. Although mechanistic/mathematical models have been widely used for predicting membrane fouling, they still suffer from low accuracy and poor sensitivity. To overcome the limitations of conventional mathematical models, artificial intelligence (AI)-based techniques have been proposed as powerful approaches to predict membrane filtration performance and fouling behaviour. This work aims to present a state-of-the-art review on the advances in AI algorithms (e.g., artificial neural networks, fuzzy logic, genetic programming, support vector machines and search algorithms) for prediction of membrane fouling. The working principles of different AI techniques and their applications for prediction of membrane fouling in different membrane-based processes are discussed in detail. Furthermore, comparisons of the inputs, outputs, and accuracy of different AI approaches for membrane fouling prediction have been conducted based on the literature database. Future research efforts are further highlighted for AI-based techniques aiming for a more accurate prediction of membrane fouling and the optimization of the operation in membrane-based processes.

Deep learning model for simulating influence of natural organic matter in nanofiltration

Controlling membrane fouling in a membrane filtration system is critical to ensure high filtration performance. A forecast of membrane fouling could enable preliminary actions to relieve the development of membrane fouling. Therefore, we established a long short-term memory (LSTM) model to investigate the variations in filtration performance and fouling growth. For data acquisition, we first conducted lab-scale membrane fouling experiments to identify the diverse fouling mechanisms of natural organic matter (NOM) in nanofiltration (NF) systems. Four types of NOMs were considered as model foulants: humic acid, bovine-serum-albumin, sodium alginate, and tannic acid. In addition, real-time 2D images were acquired via optical coherence tomography (OCT) to quantify the cake layer formed on the membrane. Subsequently, experimental data were used to train the LSTM model to predict permeate flux and fouling layer thickness as output variables. The model performance exhibited root mean square errors of <1 L/m²/h for permeate flux and <10 µm for fouling layer thickness in both the training and validation steps. In this study, we demonstrated that deep learning can be used to simulate the influence of NOMs on the NF system and also be applied to simulate other membrane processes.

Permeate Flux Control in SMBR System by Using Neural Network Internal Model Control

This paper presents a design of a data-driven-based neural network internal model control for a submerged membrane bioreactor (SMBR) with hollow fiber for microfiltration. The experiment design is performed for measurement of physical parameters from an actuator input (permeate pump voltage), which gives the information (outputs) of permeate flux and trans-membrane pressure (TMP). The palm oil mill effluent is used as an influent preparation to depict fouling phenomenon in the membrane filtration process. From the experiment, membrane fouling potential is observed from flux decline pattern, with a rapid increment of TMP (above 200 mbar). Membrane fouling is a complex process and the available models in literature are not designed for control system (filtration performance). Therefore, this work proposes an aeration fouling control strategy to measure the filtration performance. The artificial neural networks (Feed-Forward Neural Network—FFNN, Radial Basis Function Neural Network—RBFNN and Nonlinear Autoregressive Exogenous Neural Network—NARXNN) are used to model dynamic behaviour of flux and TMP. In this case, only flux is used in closed loop control application, whereby the TMP effect is used for monitoring. The simulation results show that reliable prediction of membrane fouling potential is obtained. It can be observed that almost all the artificial neural network (ANN) models have similar shape with the actual data set, with the highest accuracy of more than 90% for both RBFNN and NARXN. The RBFNN is preferable due to simple structure of the network. In the control system, the RBFNN IMC depicts the highest closed loop performance with only 3.75 s (settling time) for setpoint changes when compared with other controllers. In addition, it showed fast performance in disturbance rejection with less overshoot. In conclusion, among the different neural network tested configurations the one based on radial basis function provides the best performance with respect to prediction as well as control performance.

Position paper - progress towards standards in integrated (aerobic) MBR modelling

Membrane bioreactor (MBR) models are useful tools for both design and management. The system complexity is high due to the involved number of processes which can be clustered in biological and physical ones. Literature studies are present and need to be harmonized in order to gain insights from the different studies and allow system optimization by applying a control. This position paper aims at defining the current state of the art of the main integrated MBR models reported in the literature. On the basis of a modelling review, a standardized terminology is proposed to facilitate the further development and comparison of integrated membrane fouling models for aerobic MBRs.

Modeling and multi-objective optimization for ANAMMOX process under COD disturbance using hybrid intelligent algorithm

Anaerobic ammonium oxidation (ANAMMOX) has been regarded as an efficient process to treat nitrogen-containing wastewater. However, the treatment process is not fully understood in terms of reaction mechanisms, process simulation, and control. In this paper, a multi-objective control strategy mixed soft-sensing model (MCSSM) is developed to systematically design the operating variations for multi-objective control by integrating the developed model, a least square support vector machine optimized with principal component analysis (PCA-LSSVM) and non-dominated sorting genetic algorithm-II (NSGA-II). The results revealed that the PCA-LSSVM model is a feasible and efficient tool for predicting the effluent ammonia nitrogen concentration ([Formula: see text]) and the total nitrogen removal concentration (C_{TN, rem}) with determination coefficients (R²) were 0.997 for [Formula: see text] and 0.989 for C_{TN, rem}, and gives us the reasonable solutions in influent by using NSGA-II. To achieve a better removal effect, the influent pH should be kept between 7.50 and 7.52, the COD/TN ratio is suggested to maintain at 0.15 and the NH₄⁺-N/NO₂^--N ratio is suggested to maintain at 0.61. The developed MCSSM approach and its general modeling framework have a high potential of applicability and guidance to bioprocess in wastewater treatment, and numerical models can be structured for predicting and optimization and experiments can be conducted for data acquisition and model establishment.