RESUMEN

Petrochemical wastewater is a major industrial source of pollution that produces a variety of toxic organic and inorganic pollutants, naturally present or added during the process. These pollutants are a serious threat to the soil, water, environment, and human being due to their complex and hazardous nature. Glycols such as monoethylene glycol (MEG), diethylene glycol (DEG), triethylene glycol (TEG), and aromatics (BTX-benzene, toluene, and xylene) are the most common organic impurities present in petrochemical wastewater. The objective of this paper is to recover aromatics and water from petrochemical industrial wastewater. The reclamation process is used to remove inorganic impurities such as heavy metals Fe, Zn, Pb, Mn, Al, Ni, As, Cr, Cu, Cd, and K and salts. In the present work, 1% sodium bi-carbonate (NaHCO3) is used to precipitate the inorganic impurities present in the wastewater at 40 °C atmospherically. Aspen Hysys simulation software is used for modeling and simulation for the treatment process using NRTL (non-random-two-liquid) thermodynamic model. The process generated from Aspen Hysys is validated with lab experiments. To support global sustainable development, this study is focused on reducing, reusing, and recycling separation techniques such as centrifuge separation and vacuum distillation have been used. The characterization of regenerated water was performed using ICP-OES (inductively coupled plasma-optical emission spectroscopy) to determine the reduction in heavy metals. It was found that > 99.5% of heavy metals were removed. The regeneration of these aromatics is necessary for economic and environmental reasons so that it can be reused to avoid its disposal in and contamination of natural environments.

RESUMEN

Molecularly imprinted polymer (MIP) is dedicated to the adsorption of target substances in the aqueous phase, but ignores the adsorption in a more complex environment (oily wastewater). In order to explore the application field of existing MIPs, acorn-like Janus particles were fabricated by photo-initiated seed swelling polymerization. A novel amphiphilic Janus-MIP was prepared with the acorn-like Janus particles as matrix, methacrylic acid, ethylene dimethacrylate and oxytetracycline (OTC) as functional monomers, crosslinking agents and template molecules via surface initiated-atom transfer radical polymerization (SI-ATRP). For comparison, the poly (glycidyl methacrylate-co-ethylene glycol dimethacrylate) (poly (GMA-co-EDMA)) microspheres were also utilized as the matrix to prepare common spherical-MIP. The adsorption capacity of Janus-MIP for OTC was 23.8 mg g-1 in oil-water system, while the adsorption capacity of spherical-MIP for OTC was only 12.6 mg g-1 in the same system. At the same time, through high performance liquid chromatography (HPLC) analysis, Janus-MIP can specifically recognize and adsorb trace OTC in restaurant oily wastewater samples, and the proposed method exhibited a lower limit of detection (LOD, 3 ng mL-1) and a higher OTC recovery rate (94.2 %-98.4 %). This work demonstrated great potential for the detection and control of OTC contamination from real samples in an oil-water mixed environment.

RESUMEN

In this study, low-cost tubular ceramic membranes were fabricated by using waste slag and natural raw materials in order to decrease the manufacturing carbon footprints. The effects of incorporation of phosphorus slag (PS) and blast furnace slag (BFS) in the mullite-zeolite membrane body were investigated. The structural characteristics of the fabricated membranes were evaluated using X-ray diffraction (XRD), field emission-scanning electron microscopy (FESEM), atomic force microscopy (AFM), contact angle, porosity and average pore size analyses. Thermal and mechanical stability were studied by thermogravimetric analysis (TGA) and three-point bending test, respectively. The oily wastewater treatment tests revealed that an increase in the slag percentage from 0 to 30% leads to enhancing the permeate flux from 99 l m-2 h-1 to 349 l m-2 h-1 for PS-based tubular membrane and to 244 l m-2 h-1 for BFS-based tubular membrane under 1 bar applied. The chemical oxygen demand (COD) removal percentage of all membranes was reported almost 99% for oily wastewater feed with a COD concentration of 612 mg l-1. In addition, the investigation of membrane fouling mechanisms was carried out using Hermia models indicating that the best correlation with the experimental data is observed for the complete pore blocking model. This study presents experimental foundations aimed at enhancing the performance of affordable slag-based membranes, thus fostering their applicability in engineering contexts.

Asunto(s)

RESUMEN

Interfacial solar evaporation shows great potential in clean water production, emulsions separation, and high-salinity brine treatment. However, it remains challenging for the evaporators to maintain a high evaporation rate in the high-salinity emulsions due to the co-pollution of salt and oil. Herein, we first proposed a hierarchic double-Janus solar evaporator (HDJE) with a hydrophobic salt-rejecting top layer and oil-rejecting bottom layer. Compared to the traditional one, HDJE could treat industrial high-salinity oil-in-water emulsions stably for over 70 h, with a stable average evaporation rate of 1.73 kg m-2 h-1 and a high purification efficiency of up to 99.8 % for oil and ions. It was also verified that HDJE could be used for high-efficiency purification of oily concentrated seawater outdoor. An average water production rate of 3.59 kg m-2 d-1 and a TOC removal ratio of over 98 % was obtained. In conclusion, this study provides a novel way to effectively dispose of high-salinity oily wastewater.

RESUMEN

A microfluidic strategy of smart calcium alginate (CA) capsules is presented to immobilize Pseudomonas aeruginosa to treat oil slicks effectively. The capsule wall is embedded with poly (N-isopropyl acrylamide) sub-microspheres as thermo-responsive switches. CA capsules, with a diameter of 3.26 mm and a thin wall thickness about 12.8 µm, have satisfying monodispersity, cavity structure, and dense surface structures. The capsules possess excellent encapsulation of bacteria, which are fixed in a restricted space and become more aggregated. It overcomes the disadvantages of a long fermentation production cycle, easy loss of bacteria, and susceptibility to shear effect. The smart CA capsules immobilized with bacteria treat model wastewater containing soybean oil or diesel and display favorable fermentation ability. The capsules can effectively treat oil slicks with high concentration, and it is an economical way for processing oily wastewater. PRACTITIONER POINTS: A thermo-responsive calcium alginate capsule was prepared by microfluidic strategy. Pseudomonas aeruginosa is environmentally friendly in treating oil slicks. The capsules, immobilized bacteria, treat oil slicks effectively. This study provides an economical way for processing different oily water.

Asunto(s)

RESUMEN

Reliable modeling of oily wastewater emphasizes the paramount importance of sustainable and health-conscious wastewater management practices, which directly aligns with the Sustainable Development Goals (SDG) while also meeting the guidelines of the World Health Organization (WHO). This research explores the efficiency of utilizing polypyrrole-coated ceramic-polymeric membranes to model oily wastewater separation efficiency (SE) and permeate flux (PF) based on established experimental procedures. In this area, computational simulation still needs to be explored. The study developed predictive regression models, including robust linear regression (RLR), stepwise linear regression (SWR) and linear regression (LR) for the ceramic-polymeric porous membrane, aiming to interpret its complex performance across diverse conditions and, thus, develop its utility in oily wastewater treatment applications. Subsequently, a novel, simple average ensemble paradigm was explored to reduce errors and improve prediction skills. Prior to the development of the model, stability and reliability analysis of the data was conducted based on Philip Perron tests with the Bartlett kernel estimation method. The accuracy of the SE exhibited a high consistency, averaging 99.92% with minimal variability (standard deviation of 0.026%), potentially simplifying its prediction compared to PF. The modes were validated and evaluated using metrics like MAE, RMSE, Speed, and MSE, in addition to 2D graphical and cumulative distribution function graphs. The LR model emerged as the best with the lowest RMSE =0.21951, indicating superior prediction accuracy, followed closely by RLR with an RMSE = 0.22359. SWLR, while having the highest RMSE = 0.34573, marked its dominance in prediction speed with 110 observations per second. Notably, the RLR model justified a reduction in error by approximately 35.29% compared to SWLR. Moreover, the training efficiency of the LR model exceeded, demanding a mere 2.9252 s, marking a reduction of about 32.54% compared to SWLR. The improved simple ensemble learning proved merit over the three models regarding error accuracy. This study emphasizes the essential role of soft-computing learning in optimizing the design and performance of ceramic-polymeric membranes.

Asunto(s)

RESUMEN

Oily wastewater from the oil industry and oil spill accidents has become a serious environmental problem and has attracted worldwide attention. The present study reports on the successful preparation of a novel magnetic Ni-Al oxide/Zn0.4Co0.6F2O4 mesoporous aerogel (MNA) as a highly selective adsorbent for oil removal from water. Oleic acid (OA) and Triton X-100 (TX) were used as hydrophobic agents for MNA surface modification. It was found that the attached amount of OA on the mesoporous MNA aerogel is 3.5 times larger than that of TX, giving an advantage to MNA-OA in oil separation. The MNA-OA displayed superhydrophobicity (contact angle ∼150°) and superparamagnetism properties that allowed the adsorbent to be used selectively for oil removal. The MNA-OA was found to have a high oil removal efficiency of ∼97% with an adsorption capacity of ∼2 g/g. Furthermore, the produced magnetic adsorbent has high stability due to the strong chemical binding of OA, which is demonstrated by its good reusability performance. Throughout five separate runs, the MNA-OA was shown to be a very efficient and reusable adsorbent for oily wastewater.

Asunto(s)

RESUMEN

A significant waste (e.g., high oil content and pollutants such as heavy metals, dyes, and microbial contaminants) in water is generated during crude oil extraction and industrial processes, which poses environmental challenges. This study explores the potential of Ag@Fe3O4 nanocomposite (NC) biosynthesized using the aqueous leaf extract of Laurus nobilis for the treatment of oily wastewater. The NC was characterized using ultraviolet-visible (UV-Vis) spectrophotometry, Scanning Electron Microscopy (SEM), Fourier Transformed Infrared (FTIR) and X-Ray Diffraction (XRD) spectroscopies. The crystalline structure of the NC was determined to be face-centered cubic with an average size of 42 nm. Ag@Fe3O4 NC exhibited significant degradation (96.8%, 90.1%, and 93.8%) of Rose Bengal (RB), Methylene Blue (MB), and Toluidine Blue (TB), respectively, through a reduction reaction lasting 120 min at a dye concentration of 10 mg/L. The observed reaction kinetics followed a pseudo-first-order model, with rate constants (k-values) of 0.0284 min-1, 0.0189 min-1, and 0.0212 min-1 for RB, MB, and TB, respectively. The fast degradation rate can be attributed to the low band gap (1.9 eV) of Ag@Fe3O4 NC. The NC elicited an impressive effectiveness (99-100%, 98.0%, and 91.8% within 30 min) in removing, under sunlight irradiation, several heavy metals, total petroleum hydrocarbons (TPH), and total suspended solids (TSS) from the oily water samples. Furthermore, Ag@Fe3O4 NC displayed potent antibacterial properties and a good biocompatibility. These findings contribute to the development of efficient and cost-effective methods for wastewater treatment and environmental remediation.

Asunto(s)

RESUMEN

Layered double hydroxides (LDHs) have gained significant recognition for their facile synthesis and super-hydrophilic two-dimensional (2D) structure to fabricate antifouling membranes for oily wastewater separation. However, conventional PVDF membranes, due to their hydrophobic nature and inert matrix, often exhibit insufficient permeance and compatibility. In this study, a novel NiFe-LDH@MnO2/PVDF membrane was synthesized using ultrasonic, redox, and microwave-hydrothermal processes. This innovative approach cultivated grass-like NiFe-LDH@MnO2 nanoparticles within an inert PVDF matrix, promoting the growth of highly hydrophilic composites. The presence of NiFe-LDH@MnO2 resulted in pronounced enhancements in surface morphology, interfacial wettability, and oil rejection for the fabricated membrane. The optimal NiFe-LDH@MnO2/PVDF-2 membrane exhibited an extremely high pure water flux (1364 L m-2•h-1), and increased oil rejection (from 81.2% to 93.5%) without sacrificing water permeation compared to the original PVDF membrane. Additionally, the NiFe-LDH@MnO2/PVDF membrane demonstrated remarkable antifouling properties, evident by an exceptional fouling resistance ratio of 96.8% following slight water rinsing. Mechanistic insights into the enhanced antifouling performance were elucidated through a comparative "semi-immersion" investigation. The facile synthesis method, coupled with the improved membrane performance, highlights the potential application prospects of this hybrid membrane in emulsified oily wastewater treatment and environmental remediation.

Asunto(s)

RESUMEN

One of the most dangerous types of pollution to the environment is oily wastewater, which is produced from a number of industrial sources and can cause damage to the environment, people, and creatures. To overcome this issue, membrane technology as an advanced method has been considered for treating oily wastewater due to its stability, high removal efficiency, and simplicity in scaling up. Membrane fouling, or the accumulation of oil droplets at or within the membrane pores, compromises the efficiency of membrane separation and water flux. In the last decade, the fabrication of membranes with specific wettability to reduce fouling has received much consideration. The purpose of this article is to offer a literature overview of all fabricated anti-fouling super(wetting and anti-wetting) membranes for applicable membrane processes for the separation of immiscible and emulsified oil/water mixtures. In this review, we first explain membrane fouling and discuss methods for preventing it. Afterwards, in all membrane separation processes, including pressure-driven, gravity-driven, and thermal-driven, membranes based on the form and density of oil are categorized as oil-removing or water-removing with special wettability, and then their wettability modification with different materials is particularly discussed. Finally, the prospect of anti-fouling membrane fabrication in the future is presented.

RESUMEN

The study illustrated here aims on an organic solvent tolerant lipase from Staphylococcus capitis (SCL). The gene part, encoding the mature lipase, was cloned and sequenced. The concluded polypeptide sequence, equivalent to the protein, consist of 388 amino acid residues with a molecular mass of about 45 kDa. A structure-based alignment of the SCL amino acid sequence shows high identities with those many staphylococcal lipases. From this alignment of sequences, the catalytic triad (Ser 117, Asp 308 and His 347) of SCL could be identified. The mature part of the SCL was expressed in Escherichia coli and the recombinant lipase (r-SCL) was purified to homogeneity. The purified r-SCL presented a quite interesting stability at low temperatures (< 30 °C) and the enzyme was found to be highly stable in polar organic solvent and at a pH ranging from 3 to 12. After that, we have demonstrated that the recombinant enzyme may be implicated in the biodegradability of oily wastewater from effluents of fast-food restaurants; the maximum conversion yield into fatty acids obtained at 30 °C, was 65%.

RESUMEN

The treatment of cooking oil wastewater is an urgent issue need to be solved. We aimed to screen for efficient oil-degrading bacteria and develop a new microbial agent for degrading waste cooking oil in oily wastewater. Three extremely effective oil-degrading bacteria, known as YZQ-1, YZQ-3, and YZQ-4, were found by the enrichment and acclimation of samples from various sources and separation using oil degradation plates. The 16S rRNA sequencing analysis and phylogenetic tree construction showed that the three strains were Bacillus tropicus, Pseudomonas multiresinivorans, and Raoultella terrigena. Under optimal degradation conditions, the maximal degradation rates were 67.30 ± 3.69%, 89.65 ± 1.08%, and 79.60 ± 5.30%, respectively, for YZQ-1, YZQ-3, and YZQ-4. Lipase activity was highest for YZQ-3, reaching 94.82 ± 12.89 U/L. The best bacterial alliance was obtained by adding equal numbers of microbial cells from the three strains. Moreover, when this bacterial alliance was applied to oily wastewater, the degradation rate of waste cooking oil was 61.13 ± 7.30% (3.67% ± 2.13% in the control group), and COD removal was 62.4% ± 5.65% (55.60% ± 0.71% in the control group) in 72 h. Microbial community analysis results showed YZQ-1 and YZQ-3 were adaptable to wastewater and could coexist with local bacteria, whereas YZQ-4 could not survive in wastewater. Therefore, the combination of YZQ-1 and YZQ-3 can efficiently degrade oil and shows great potential for oily wastewater treatment.

Asunto(s)

RESUMEN

Carwash wastewater (CWW) is an important source of environmental pollution. The aim of this study was to investigate the characteristics of CWW and technical comparison of its treatment methods. For this purpose, a systematic search was conducted and after three stages of screening the found articles, finally 30 articles were selected for this review. The results showed that due to the differences in the type of washing, the geological condition, the type of car, and the climatic conditions, the CWWs have temporal and spatial variation in the concentration of pollutants. However, the most important pollutants of CWW include oil, suspended solids, detergents, and organic compounds. The most widely used methods in CWW treatment in the main stages included chemical coagulation and electrocoagulation, which reduce turbidity by more than 90% and COD by more than 50% in the best efficiency. Also, membrane technology was a common method in CWW treatment systems to achieve proper effluent quality. COD reduction by ultrafiltration, nanofiltration, microfiltration, and reverse osmosis was 95-77%, more than 90%, 81-73%, and 87%, respectively. The efficiency of membrane technologies in reducing turbidity was often more than 90% and in few cases more than 50%. Sludge production in the coagulation process, energy consumption in electrochemical processes, and the low water recovery rate in membrane processes are important challenges in CWW treatment that must be managed by modifying the process or using combined methods.

RESUMEN

A template-free pyrolysis route has been developed using condensation-assembly precursors made of trimethoxyboroxane (TMB) and melamine (M) to cater the requirements of an industrial real-world environment. The precursors contain abundant B-N bonds and exhibit a high level of interconnectivity, resulting in 3D-PBN with enhanced mechanical properties and the ability to be easily customized in terms of shape. Moreover, 3D-PBN demonstrates rapid adsorption kinetics and excellent reusability, efficiently removing up to 270% of its own weight of fuel within 30 s and being readily regenerated through simple calcination. Even after undergoing 50 cycles, the mechanical properties remain at a remarkable 80%, while the adsorption performance exceed 95%. Furthermore, a comprehensive analysis of thermal behavior from precursor to 3D-PBN has been conducted, leading to the proposal of a molecular-scale evolution process comprising four major steps. This understanding enables us to control the phase reaction and regulate the composition of the products, which is crucial for determining the characteristics of the final product.

Asunto(s)

RESUMEN

Common commercial demulsifiers are typically made from ethylene oxide and propylene oxide. The production process is dangerous and complex, with poor adaptability and high cost. In this work, cotton modified with polyethylene polyamine was utilized as a demulsifier for the treatment of oily wastewater. The chemical structure and morphology of the as-prepared sample (CPN) were characterized by IR spectrum and SEM. The effect of CPN dosage, pH value, and salinity on the demulsification performance of oily wastewater was explored through the bottle tests. The results showed that the light transmittance of separated water was 81.7% and the corresponding deoiling rate was 98.5% when a CPN dosage of 25 mg/L was used at room temperature for 30 min. The interfacial properties were also systematically investigated, and the results indicated that CPN had better interfacial activity and a stronger reduction capability of interfacial tension compared to asphaltenes. The finding initiated and accelerated the demulsification process of oily wastewater. Based on the outstanding performance of this biomass-derived demulsifier, it shows promising potential for application in the treatment of oily wastewater.

RESUMEN

This study investigates the oil-water separation capability of iron-based superhydrophilic meshes. It also intends to provide an optimistic view of their potential for industrial application. Oil-water separation performance of the 150 mesh, 300 mesh, and 400 mesh is primarily examined by analyzing the efficiency and speediness of separation as well as the limit of oil intrusion using petroleum based oils. The superhydrophilic meshes are further applied for oil-water separation of locomotive wash effluent. The superhydrophilic meshes showed good oil-water separation behavior. The 300 mesh is observed to have superior separation performance. It is also tested to have good reusability and resistance in harsh conditions. The separation effectiveness of 94.7%, reduced turbidity of 21.8 NTU, and chemical oxygen demand of around 70 ppm, along with reasonable flux and intrusion pressure values of 73.28 Lm-2min-1 and 0.848 kPa, respectively, are noticed for the separation study conducted for locomotive wash effluent using the designated superhydrophilic mesh. This study hence as well demonstrates a prospective future of superhydrophilic mesh for practical utility.

Asunto(s)

RESUMEN

The oil and gas industry and related applications generate large quantities of oily wastewater, which can adversely affect the environment and human health if not properly handled. This study aims to prepare polyvinylidene fluoride (PVDF) membranes incorporated with polyvinylpyrrolidone (PVP) additives and utilize them to treat oily wastewater through the ultrafiltration (UF) process. Flat sheet membranes were prepared using PVDF dissolved in N,N-dimethylacetamide, followed by the addition of PVP ranging from 0.5 to 35 g. Characterization by scanning electron microscopy (SEM), water contact angle, Fourier transform infrared spectroscopy (FTIR), and mechanical strength tests were performed on the flat PVDF/PVP membranes to understand and compare the changes in the physical and chemical properties of the membranes. Prior to the UF process, oily wastewater was treated by a coagulation-flocculation process through a jar tester using polyaluminum chloride (PAC) as a coagulant. Based on the characterization of the membrane, the addition of PVP improves the physical and chemical properties of the membrane. The membrane's pore size becomes larger, which can increase its permeability and flux. In general, the addition of PVP to the PVDF membrane can increase the porosity and decrease the water contact angle, thereby increasing the membrane's hydrophilicity. With respect to filtration performance, the wastewater flux of the resultant membrane increases with increasing PVP content, but the rejections for TSS, turbidity, TDS, and COD are reduced.

RESUMEN

Biogranulation technology is an emerging biological process in treating various wastewater. However, the development of biogranules requires an extended period of time when treating wastewaters with high oil and grease (O&G) content. A study was therefore conducted to assess the formation of biogranules through bioaugmentation with the Serratia marcescens SA30 strain, in treating real anaerobically digested palm oil mill effluent (AD-POME), with O&G of about 4600 mg/L. The biogranules were developed in a lab-scale sequencing batch reactor (SBR) system under alternating anaerobic and aerobic conditions. The experimental data were assessed using the modified mass transfer factor (MMTF) models to understand the mechanisms of biosorption of O&G on the biogranules. The system was run with variable organic loading rates (OLR) of 0.69-9.90 kg/m3d and superficial air velocity (SAV) of 2 cm/s. After 60 days of being bioaugmented with the Serratia marcescens SA30 strain, the flocculent biomass transformed into biogranules with excellent settleability with improved treatment efficiency. The biogranules showed a compact structure and good settling ability with an average diameter of about 2 mm, a sludge volume index at 5 min (SVI5) of 43 mL/g, and a settling velocity (SV) of 81 m/h after 256 days of operation. The average removal efficiencies of O&G increased from 6 to 99.92%, respectively. The application of the MMTF model verified that the resistance to O&G biosorption is controlled via film mass transfer. This research indicates successful bioaugmentation of biogranules using the Serratia marcescens SA30 strain for enhanced biodegradation of O&G and is capable to treat real AD-POME.

Asunto(s)

RESUMEN

In order to bring the chemical oxygen demand (COD) concentration down to safe levels for widespread use, this study plans to use a state-of-the-art electrocoagulation reactor (ECR) to treat real oily wastewater discharged from the Al-Muthanna petroleum refinery. A one-side finned (1SF) cathode tube was positioned between two tubular anodes in the continuous ECR, where the active area of the cathode was much more than its submerged volume. Each of these electrodes was made of aluminum and joined in a monopolar parallel to a DC power supply. On COD elimination efficiency, the impacts of operational parameters such as electrolysis time (4-60 min), current density (0.630-5.000 mA/cm2), and flow rate (50-150 ml/min) were explored. In conclusion, Increasing current density and electrolysis duration increases COD removal efficiency, whereas increasing flow rate reduces it. COD removal efficiencies were 82% at optimal electrolysis times of 60 (min), 5 (mA/cm2) current density, and 50 (ml/min) flow rate, with energy consumption of 4.787 (kWh/kg COD) and electrode consumption of 0.544 (g). The investigation results demonstrated that the new reactor could treat oily wastewater within the specified operational limits. It might be used before other, more conventional treatments.

Asunto(s)

RESUMEN

Due to the significant energy and economic losses brought on by the global oil spill, there has been an increased interest in oil-water separation. This study presents strong non-linear machine learning models (support vector regression (SVR) and Gaussian process regression (GPR)) with the Response surface method (RSM) to predict the oil flux and oil-water separation efficiency of wastewater using ceramic membrane technology. For the model development and prediction of oil flux (OF) and oil-water separation efficiency (OSE), oil concentration (mg/L), feed flow rate (mL/min), and pH were considered as input variables. The input variables are combined in three combinations to study the most contributing input features to the models' performance. Mean square error (MSE) and Nash-Sutcliffe coefficient efficiency (NSE) were used to assess the prediction performances of the developed models with the different number of input combinations considered in the study. For the two target variables (OF and OSE), GPR and SVR models were used to separately predict them. For OF, the SVR-2 [Combo-2] model (MSE = 0.9255 and NSE = 2.7976) performed better with higher prediction accuracy compared to GPR-2 [Combo-2] model (MSE = 0.763 and NSE = 6.437). In addition, for OSE, the GPR-3 [Combo-3] model (MSE = 0.995 and NSE = 0.5544) performed slightly better than SVR-3 [Combo-3] model (MSE = 0.992 and NSE = 0.8066). The results showed that the SVR model with the combo-2 and GPR-3 models for OF and OSE variables are the proposed models with the best performance and accuracy. This machine learning study will aid in better evaluating the function of materials such as ceramic in membrane performance features such as oil flux and rejection prediction, separation efficiency, water recovery, membrane fouling, and so on. As for academics and manufacturers, this machine learning (ML) strategy will boost performance and allow a better understanding of system governance.

Asunto(s)