Figure - available from: Research on Chemical Intermediates
This content is subject to copyright. Terms and conditions apply.
Source publication
In present study, a new method based on the support vector machine (SVM) approach was employed to calculate the oil–water permeation flux and grafting yield of maleic anhydride and hyperbranched polyethylene glycol (PEG) on the polyethersulfone (PES) membrane surface. A set of 7 input/output experimental data was applied for training and testing th...
Citations
... In the last 2 decades, AI has been demonstrated to offer an alternate approach for accurately simulating these membrane processes. The commonly used AI-ML techniques include artificial neural network (ANN), fuzzy logic, adaptive neuro-fuzzy inference system (ANFIS), genetic programming, and support vector machine (Dornier et al., 1995;Kim et al., 2009;Cho et al., 2010;Madaeni and Kurdian, 2011;Rahmanian et al., 2011;Rahmanian et al., 2012;Salehi and Razavi, 2012;Shokrkar et al., 2012;Shokrkar et al., 2012;Fazeli et al., 2013;Khayet and Cojocaru, 2013;Barello et al., 2014;Rahimzadeh, Ashtiani, and Okhovat, 2016;Salehi and Razavi, 2016;Adib, Raisi, and Salari, 2019;Nejad et al., 2019). ANN is the most often utilized for modelling membrane separation (Jawad, Hawari, and Javaid Zaidi, 2021). ...
Single-pass tangential flow filtration (SPTFF) is a crucial technology enabling the continuous manufacturing of monoclonal antibodies (mAbs). By significantly increasing the membrane area utilized in the process, SPTFF allows the mAb process stream to be concentrated up to the desired final target in a single pass across the membrane surface without the need for recirculation. However, a key challenge in SPTFF is compensating for flux decline across the membrane due to concentration polarization and surface fouling phenomena. In continuous downstream processing, flux decline immediately impacts the continuous process flowrates. It reduces the concentration factor achievable in a single pass, thereby reducing the final concentration attained at the outlet of the SPTFF module. In this work, we develop a deep neural network model to predict the NWP in real-time without the need to conduct actual NWP measurements. The developed model incorporates process parameters such as pressure and feed concentrations through inline sensors and a spectroscopy-coupled data model (NIR-PLS model). The model determines the optimal timing for membrane cleaning steps when the normalized water permeability (NWP) falls below 60%. Using SCADA and PLC, a distributed control system was developed to integrate the monitoring sensors and control elements, such as the NIRS sensor for concentration monitoring, the DNN model for NWP prediction, weighing balances, pressure sensors, pumps, and valves. The model was tested in real-time, and the NWP was predicted within <5% error in three independent test cases, successfully enabling control of the SPTFF step in line with the Quality by Design paradigm.
... In the last two decades and a half, artificial intelligence has stepped in to provide an alternative way of modeling these membrane processes with accuracy, among several other advantages. These AI techniques include ANN [7][8][9][10], fuzzy logic [11][12][13][14][15], Adaptive Neuro-Fuzzy Inference System (ANFIS) [16][17][18][19], genetic programming [20][21][22][23] and support vector machine [24][25][26]. ANN is one of the most popular machine learning techniques, which is a subset of AI. Neural networks are from a class of 'black box' models as the information about the physical parameters of the process is not required [27]. ...
The freshwater scarcity is causing a major challenge due to the growing global population. The brackish water and seawater are the biggest sources of water on the planet. Therefore, using desalination and water treatment techniques, household and industrial demands can be met. Microfiltration (MF), ultrafiltration (UF), nanofiltration (NF), reverse osmosis (RO), membrane bioreactor (MBR), and membrane distillation (MD) are some of the membrane processes used in water and wastewater treatment. Artificial intelligence models, such as artificial neural networks (ANN), have recently become a popular alternative to modeling these processes due to several advantages over the conventional model. Therefore, this paper presents a review of ANN models from the last two and a half decades developed for the membrane processes used in wastewater treatment and desalination. Moreover, a complete procedure for the development of two types of ANN models is provided in the paper. The study also discusses the development strategies and comparison of different sorts of ANN models. These models have been applied to several lab-scale, pilot and commercial plants for simulation, optimization, and process control. This work may aid in the development of new ANN models for membrane processes by considering the recent improvements in the field.
... Support vector machines also represent a good alternative for many industries in the way it support managers in the decision-making process to improve yield. For example: in feed additive industry to promote animal growth [Niu et al., 2013]; in culture of cocoa [Gamboa et al., 2019]; in the separation process of oily wastewaters produced by domestic sewages [Adib et al., 2019]; in the polyhydrobutyrate production [Fang et al., 2010]; in water quality parameters [Najafzadeh e Ghaemi, 2019]; and in nuclear material yield stress [Long et al., 2019]. ...
Low-pressure membrane (LPM) filtration, including microfiltration (MF) and ultrafiltration (UF), is a promising technology for the treatment of surface water for drinking and other purposes. Various configurations and operational sequences have been developed to ensure the sustainable provision of clean water by overcoming fouling problems. In the literature, various periodic physical and/or chemical approaches to the cleaning of LPMs have been reported, but little data is available on the aging of MF/UF membranes that results from the interaction between the foulants and the cleaning agent. Periodic physical cleaning of the membrane is expected to return the membrane to its original performance capacity, but it only recovers to a certain level because the remaining foulants cause irreversible fouling. Chemical cleaning can then be employed to recover the membrane from this irreversible fouling but, in the process, it can cause irrecoverable damage to the membrane. In this review, the foulants responsible for irrecoverable damage to MF/UF membranes are summarized, and their interaction with cleaning agents and other foulants is described. The impact of these foulants on various membrane parameters, including filtration efficiency, flux decline, permeability, membrane characterization, and membrane integrity are also summarized and discussed in detail. In addition, mitigation options and future prospects are also discussed with regard to increasing the operational life span of a membrane in a cost-effective manner. Ultimately, this review suggests an advanced control system based on membrane-foulant interactions under the impact of various operational parameters to mitigate the integrity loss of membranes.
Membrane technologies are becoming increasingly versatile and helpful today for sustainable development. Machine Learning (ML), an essential branch of artificial intelligence (AI), has substantially impacted the research and development norm of new materials for energy and environment. This review provides an overview and perspectives on ML methodologies and their applications in membrane design and discovery. A brief overview of membrane technologies is first provided with the current bottlenecks and potential solutions. Through an applications-based perspective of AI-aided membrane design and discovery, we further show how ML strategies are applied to the membrane discovery cycle (including membrane material design, membrane application, membrane process design, and knowledge extraction), in various membrane systems, ranging from gas, liquid, and fuel cell separation membranes. Furthermore, the best practices of integrating ML methods and specific application targets in membrane design and discovery are presented with an ideal paradigm proposed. The challenges to be addressed and prospects of AI applications in membrane discovery are also highlighted in the end.
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.
Performance modelling of wastewater treatment systems has now become an attractive area of investigation for the design, analysis, and optimization of operations. Membrane bioreactor (MBR) is a complex system, composed of different processes such as biological process and membrane filtration. Various models have been developed over the years to individually describe each of these processes. Activated sludge model no. 1 (ASM1), was introduced in 1987, primarily for the design and operation of the biological wastewater treatment processes for ammonia and organic matter removal. In 1995, ASM2 was proposed capturing the removal of phosphorus from wastewater. Finally in 1999, ASM3 was developed as a more accurate model to correct the deficiencies associated with ASM1. ASMs have been widely employed during the last decade to simulate the bioprocess/biomass kinetics in the MBR systems. To incorporate the membrane fouling phenomenon in the modelling approach as well as to better understand the individual and collective foulants, the ASM approaches were modified in 1989 by introducing a main foulant contributing to the membrane fouling phenomenon, the so-called soluble microbial products (SMP) concept. This represents the inception of the hybrid models. Mechanistic modelling of the MBR filtration process is mainly performed using resistance-in-series (RIS) model as one of the extensively used approaches with different subdivisions of total resistance corresponding to the fouling mechanisms. To further improve the knowledge about the system behavior, a combination of the hybrid models with fouling models (mostly RIS) known as integrated models were developed in 2002. Numerous studies have been subsequently devoted to utilizing the integrated models as a best-case scenario for forecasting the MBR process behavior. Moreover in recent years, connectionist tools such as artificial intelligence (AI) and machine learning (ML) have attracted significant attention as reliable modelling methods to predict complex processes associated with the membrane separation by providing linear and nonlinear relationships between the variables.
In this paper, we provide a comprehensive review of the literature associated with biomass kinetics developments as well as membrane filtration modelling. A wide range of models proposed for system optimization, from empirical/system identification to mechanistic/analytical mathematical models are reviewed in this paper. The challenges/limitations with the available models as well as recommendations for future work on MBR modelling and optimization are also highlighted.
Inspired by the strong adhesion of mussels, a super-hydrophobic sponge was designed and prepared by a simple and inexpensive one-pot solution immersion method. The prepared superhydrophobic sponge can not only efficiently separate the oil–water mixture, more importantly, but also remove volatile organic compounds in the atmospheric environment. Polydopamine (PDA) enables polydivinylbenzene (PDVB) particles to be firmly and tightly attached to the melamine sponge skeleton, thereby making the hydrophilic sponge superhydrophobic and providing adsorption sites for volatile organic compounds in the air. The synergy enables the sponge/PDA/PDVB to quickly adsorb oils and organic substances, and it has high stability and capacity even after 20 cycles. In addition, superhydrophobic sponges can still perform outstanding adsorption performance even under highly acidic and alkaline environments. Meanwhile, the static adsorption capacity of the sponge/PDA/PDVB for gaseous toluene is 5.7 times that of activated carbon. Compared with pure PDVB, the super-hydrophobic sponge in the dynamic experiment has a penetration time increased from 6 to 390 min, which is 65 times longer than that of the PDVB, and the adsorption performance has been greatly improved. Therefore, our strategy may achieve a new effect, which can quickly and easily separate oil–water mixtures and remove volatile gaseous pollutants, and it can provide potential options for practical applications
