| Artificial Intelligence-Powered Energy Management of Reverse Osmosis Desalination Plants | Publication | 2022-01-01 | Mohammad Amin Soleimanzade |
| Deep learning-based energy management of a hybrid photovoltaic-reverse osmosis-pressure retarded osmosis systemThis paper investigates the energy management of a hybrid grid-connected reverse osmosis (RO) desalination process consisting of photovoltaic (PV), pressure retarded osmosis (PRO), and energy storage system. The developed intelligent energy management system (IEMS) aims to maximize the total water production and contaminant removal efficiency while keeping the grid’s supplied power as low as possible. To promote the performance of the IEMS, the prediction of PV solar power is performed by three deep neural networks based on convolutional neural networks and long short-term memory neural networks. These networks are designed to perform 5-hour-ahead PV power forecasting, and the model with the smallest error is selected. The IEMS employs the particle swarm optimization (PSO) algorithm to find the optimum solutions of the system for each time step. Four performance indices are defined through which the IEMS is evaluated. The results of the proposed technique are compared with two benchmark methods, one of which is similar to the IEMS; however, it does not incorporate the PV power predictions. The superiority of the IEMS over the first benchmark is demonstrated by studying three scenarios: two successive sunny days, two successive cloudy days, and 10 days of operation. Moreover, the simulations are executed for different forecast horizons to investigate the effects of this parameter on the optimization results. The impacts of the best-found forecaster errors are also explored by repeating the simulations with the actual PV power. Finally, the optimization is performed by two other stochastic algorithms: grey wolf optimizer (GWO) and genetic algorithm (GA). It is found that PSO outperforms GWO and GA for solving this optimization problem. University of Alberta | Publication | 2021-04-26 | Mohammad Amin Soleimanzade, Sadrzadeh, M. |
| Functionalized polyamide membranes yield suppression of biofilm and planktonic bacteria while retaining flux and selectivityBiofouling is a major challenge for desalination, water treatment, and water reuse applications using polymer-based membranes. Two classes of novel silver-based metal azolate frameworks (MAF) are proposed to decorate polyamide (PA) forward osmosis membranes and to improve numerous aspects of fouling and transport. Membranes functionalized with two concentrations of each MAF are compared with a pristine control material, with results that clearly highlight their tunability and bio-inhibitory effects. We report for the first time PA membranes yielding near complete suppression of a robust biofilm-forming bacterium (Pseudomonas aeruginosa) and inactivation of planktonic bacteria, while maintaining high selectivity. These features improve the long-term water flux performance of the membranes, tested during 24 h of accelerated biofouling and organic fouling conditions, and showing lower than 10% and 20% decline in water flux. These enhancements were achieved with only 0.03–0.06% mass of additives and little generation of hazardous waste products, indicating that low-cost and environmentally benign functionalization can prevent biofouling growth while maintaining selectivity and transport for high-performance desalination, water treatment and reuse. University of Alberta | Publication | 2022-02-01 | Sadegh Aghapour Aktij, Sadrzadeh, M. |
| Improved antifouling and antibacterial properties of forward osmosis membranes through surface modification with zwitterions and silver-based metal organic frameworksThis study investigates the effect of surface functionalization of a thin-film composite forward osmosis membrane with zwitterions and silver-based metal organic frameworks (Ag-MOFs) to improve the antifouling, anti-biofouling, and antimicrobial activity of the membrane. Two types of zwitterions, namely, 3-bromopropionic acid and 1,3-propane sultone, are chemically bonded, with and without incorporation of Ag-MOFs, over the surface of a polyamide membrane. Spectroscopy measurements indicate successful grafting of the modifying agents on the membrane surface. Contact angle measurements demonstrate a notable improvement in surface wettability upon functionalization. The performance of the membranes is evaluated in terms of water and salt fluxes in forward osmosis filtrations. The transport data show demonstrably increased water flux of around 300% compared to pristine membranes, with similar or slightly reduced salt reverse flux. The antifouling and anti-biofouling properties of the modified membranes are evaluated using sodium alginate and E. coli, respectively. These experiments reveal that functionalized membranes exhibit significant antifouling and anti-biofouling behavior, with high resilience against flux decline. University of Alberta | Publication | 2020-10-01 | Sadegh Aghapour Aktij, Sadrzadeh, M. |
| In-Situ Ag-MOFs Growth on Pre-Grafted Zwitterions Imparts Outstanding Antifouling Properties to Forward Osmosis MembranesIn this study, a polyamide forward osmosis membrane was functionalized with zwitterions followed by the in situ growth of metal–organic frameworks with silver as a metal core (Ag-MOFs) to improve its antibacterial and antifouling activity. First, 3-bromopropionic acid was grafted onto the membrane surface after its activation with N,N-diethylethylenediamine. Then, the in situ growth of Ag-MOFs was achieved by a simple membrane immersion sequentially in a silver nitrate solution and in a ligand solution (2-methylimidazole), exploiting the underlying zwitterions as binding sites for the metal. The successful membrane functionalization and the enhanced surface wettability were verified through an array of characterization techniques. When evaluated in forward osmosis tests, the modified membranes exhibited high performance and improved permeability compared to pristine membranes. Static antibacterial experiments, evaluated by confocal microscopy and colony-forming unit plate count, resulted in a 77% increase in the bacterial inhibition rate due to the activity of the Ag-MOFs. Microscopy micrographs of the Escherichia coli bacteria suggested the deterioration of the biological cells. The antifouling properties of the functionalized membranes translated into a significantly lower flux decline in forward osmosis filtrations. These modified surfaces displayed negligible depletion of silver ions over 30 days, confirming the stable immobilization of Ag-MOFs on their surface. University of Alberta | Publication | 2020-07-17 | Sadegh Aghapour Aktij, Sadrzadeh, M. |
| Nanodiamond-decorated thin film composite membranes with antifouling and antibacterial propertiesMembrane fouling is the main bottleneck that restricts the practical applications of membrane processes. In this work, we report an effective and scalable method to reduce the fouling of polyamide thin film composite (TFC) membranes by grafting amine-functionalized nanodiamond (ND) particles. The surface chemistry of ND was modified to improve the compatibility of nanoparticles with the polyamide membranes. Fouling experiments with sodium alginate (SA) and bovine serum albumin (BSA) showed that the ND layer substantially reduced fouling of the membranes. The flux of the ND-modified membrane made with a solution containing 1000 ppm ND particles declined only by 15% (SA) and 9% (BSA) after 180 min of filtration, while the flux of the pristine TFC membrane declined by 42% (SA) and 21% (BSA). The ND particles increased the antibacterial activity of the membranes, increasing the inactivation and mortality rate of Escherichia coli (E. coli) bacteria cells. Because they are easy to make and have antifouling and antibacterial properties, these membranes can be applied in a broad range of forward osmosis water reclamation applications. University of Alberta | Publication | 2022-01-15 | Sadegh Aghapour Aktij, Sadrzadeh, M. |
| Novel data-driven energy management of a hybrid photovoltaic-reverse osmosis desalination system using deep reinforcement learningThis paper proposes a novel deep reinforcement learning-accelerated energy management system for a hybrid grid-connected photovoltaic-reverse osmosis-pressure retarded osmosis desalination plant. The energy management problem is formulated as a partially observable Markov decision process by using historical photovoltaic (PV) power data in order to cope with uncertainties related to the generation of solar power and provide more information regarding the true state of the system. The soft actor-critic (SAC) algorithm is employed as the core of the energy management system to maximize water production rate and contaminant removal efficiency while minimizing the supplied power from the external grid. We introduce 1-dimensional convolutional neural networks (1-D CNNs) to the actor, critic, and value function networks of the SAC algorithm to address the partial observability dilemma involved in PV-powered energy systems, extract essential features from the PV power time series, and achieve immensely improved performance ultimately. Furthermore, it is assumed that the proposed CNN-SAC algorithm does not have access to the current output power data of the PV system. The development of more practical energy management systems necessitates this assumption, and we demonstrate that the proposed method is capable of forecasting the current PV power data. The superiority of the CNN-SAC model is verified by comparing its learning performance and simulation results with those of four state-of-the-art deep reinforcement learning algorithms: Deep deterministic policy gradient (DDPG), proximal policy optimization (PPO), twin delayed DDPG (TD3), and vanilla SAC. The results show that the CNN-SAC model outperforms the benchmark methods in terms of effective solar energy exploitation and power scheduling, manifesting the necessity of exploiting historical PV power data and 1-D CNNs. Moreover, the CNN-SAC algorithm is benchmarked against a powerful energy management system we developed in our previous investigation by studying three scenarios, and it is demonstrated that considerable improvement in energy efficiency can be obtained without using any solar power generation forecasting algorithm. By conducting ablation studies, the critical contribution of the introduced 1-D CNN is demonstrated, and we highlight the significance of providing historical PV power data for substantial performance enhancement. The average and standard deviation of evaluation scores obtained during the last stages of training reveal that the 1-D CNN significantly improves the final performance and stability of the SAC algorithm. These results demonstrate that the modifications we detail in our investigation render deep reinforcement learning algorithms extremely powerful for the energy management of PV-powered microgrids, including PV-driven reverse osmosis desalination plants. University of Alberta | Publication | 2022-05-01 | Mohammad Amin Soleimanzade, Sadrzadeh, M. |
