Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “POROSITY”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

Experimental investigation of the relationship between thermal barrier coating structured porosity and homogeneous charge compression ignition engine combustion

Heat transfer has a monumental influence on homogeneous charge compression ignition combustion. When a thermal barrier coating is applied to the combustion chamber, the insulating effect magnifies the wall temperature swing, decreasing heat transfer during combustion. This enables improvements in both thermal and combustion efficiency without the detrimental impacts of intake charge heating. Increasing the temperature swing requires coatings with lower thermal conductivity and heat capacity. An enticing avenue for simultaneously decreasing both thermal conductivity and capacity is to increase the porosity fraction. A proprietary solution precursor plasma spray process enables discrete organization of the porosity structure, called inter-pass boundaries, which in turn produces a step-reduction in thermal conductivity for a given porosity level. In this investigation, yttria-stabilized zirconia is used to create four different thermal barrier coatings to study the potential of structured porosity as means of improving the “temperature swing” behavior in a homogeneous charge compression ignition engine. The baseline coating is “dense YSZ,” applied using a standard air-plasma spray process. Furthermore, significant reductions of the thermal conductivity are achieved by utilizing the solution precursor plasma spray process to create inter-pass boundaries with a moderate overall porosity. Performance, efficiency, and emissions are compared against both a baseline configuration with a metal piston and an air-plasma spray “dense YSZ” coating. Experiments are carried out in a single-cylinder gasoline homogeneous charge compression ignition engine with exhaust re-induction. Experiments indicate that incorporating structured porosity into thermal barrier coatings produces tangible gains in combustion and thermal efficiencies. However, there is an upper limit to porosity levels acceptable for homogeneous charge compression ignition engine application because an elevated porosity fraction leads to excessive surface roughness and undesirable fuel interactions. Comparison of the coatings showed the best results with coating thickness of up to 150 µm. Thicker coatings led to slower surface temperature response and attenuated swing temperature magnitude.

33 ADVANCED PROPULSION SYSTEMS↗

Energy-Saving Melting and Revert Reduction Technology (E-SMARRT), Task 5.3: Casting Porosity-Free Grain Refined Magnesium Alloys

The objective of this project was to identify the root causes for micro-porosity in magnesium alloy castings and recommend remedies that can be implemented in production. Three casting magnesium alloys were used to determine the causes of porosity that is a common problem in the magnesium casting industry. These alloys were AM50A, AM60A, and AZ91D, and all were grain refined with C 2 Cl 6 . Gas porosity was found to have little effect if proper degassing methods and foundry practices were used. It was found that sound gating practice, directional solidification towards the riser and generous risering should always dominate in order to produce sound castings. In sand cast magnesium, thermal gradients were found to be an important indicator of heat transfer in the mold. A minimum thermal gradient was found for each alloy that would produce sound castings. There were 2.02°C/cm for AM50A, 1.99°C/cm for AM60A, and 1.97°C/cm for AZ91D. If these gradients are met or exceeded when an area of the casting reaches 50°C below the liquidus for the alloy, the casting will be free of shrinkage porosity in that area. The cooling rates measured during casting magnesium alloys in a pre-heated step permanent mold ranged from 12°F/min in the three inches thick step to 200o F/min in the one inch step. The effect of the cooling rate on the grain size and the mechanical properties was noticeable but not substantial. Grain refining with C 2 Cl 6 had a marked effect on the grain size of the permanent mold step casting. It reduced it by 10-15% in AM50A and by a factor of six in AZ91E from 300 µm to around 55 µm. The mechanical properties of both permanent mold cast AZ91E and AM50A were improved by grain refinement. The most prominent increase was in the elongation of AM50A that more than doubled from 8% to 17%. Computer simulation of porosity was conducted for a well gated commercial wheel casting. The simulation did not predict significant porosity in the wheel. The mechanical testing of tensile specimens excised from the wheel indeed confirmed good properties, in line with the specifications for this alloy. Evidence of minimal micro-porosity was detected in sections cut from the wheel and investigated under optical microscopy. This finding confirms the key role played by utilizing optimal gating and risering practices in minimizing porosity in magnesium castings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Effects of Peclet Number on Pore-Scale Mixing and Channeling of a Tracer and on Directional Advective Porosity

Field tracer tests indicate that advective porosity, the quantity relating advective velocity to Darcy flux, may exhibit directional dependence. Theory [Neuman, 2005a, 2005b] suggests that directional variations in advective porosity could arise from incomplete mixing of an inert tracer between directional flow channels within a sampling volume of soil or rock that may be hydraulically isotropic or anisotropic, rendering advective porosity a function of Peclet number. Whereas Neuman was able to quantify the process for idealized intersecting fracture sets, his theory is too abstract to allow doing the same for more complex systems of fractures or pores. We use Smoothed Particle Hydrodynamics [e.g. Tartakovsky and Meakin, 2005, 2006] to simulate advective-diffusive transport of a passive tracer in the interior of an idealized pore space between impermeable circular or elliptical solid grains of random sizes, arranged randomly within a square domain. Our numerical experiments reveal a transition from complete mixing of tracer at small Peclet numbers to the gradual evolution of pore-scale channels of tracer which allow less and less mixing as Peclet numbers grow. Advective porosity, computed as the ratio between total water flux across the domain boundaries and migration rate of the tracer center of mass, is found to diminish asymptotically from a value equal to the total porosity at a Peclet number of zero (pure diffusion) to a constant dominated entirely by advection at large Peclet numbers. When total porosity is kept constant, channeling is less pronounced and mixing more prominent when flow takes place parallel to the longer axes of elliptical grains as compared to when the grains are circular. On the other hand, channeling is more pronounced and mixing less so when flow takes place perpendicular to the longer elliptical grain axes. Correspondingly, the rate at which advective porosity diminishes with increasing Peclet number is slower and the asymptote is larger when flow takes place parallel to the longer axes of elliptical grains than when the grains are circular. However, the rate is much faster and the asymptote much smaller when flow takes place perpendicular to the longer elliptical grain axes.

54 ENVIRONMENTAL SCIENCES↗

Engineering Redox Flow Battery Electrodes with Spatially Varying Porosity Using Non‐Solvent‐Induced Phase Separation

Redox flow batteries (RFBs) are a promising electrochemical platform for efficiently and reliably delivering electricity to the grid. Within the RFB, porous carbonaceous electrodes facilitate electrochemical reactions and distribute the flowing electrolyte. Tailoring electrode microstructure and surface area can improve RFB performance, lowering costs. Electrodes with spatially varying porosity may increase electrode utilization and provide surface area in reaction‐limited zones; however, the efficacy of such designs remains an open area of research. Herein, a non‐solvent‐induced phase‐separation (NIPS) technique that enables the reproducible synthesis of macrovoid‐free electrodes with well‐defined across‐thickness porosity gradients is described. The monotonically varying porosity profile is quantified and the physical properties and surface chemistries of porosity‐gradient electrodes are compared with macrovoid‐containing electrode, also synthesized by NIPS. Then, the electrochemical and fluid dynamic performance of the porosity‐gradient electrodes is evaluated, exploring the effect of changing the direction of the porosity gradient and benchmarking against the macrovoid‐containing electrode. Lastly, the performance is examined in a vanadium RFB, finding that the porosity‐gradient electrode outperforms the macrovoid electrode, is independent of gradient direction, and performs favorably compared to advanced electrodes in the contemporary literature. It is anticipated that the approach motivates further exploration of microstructurally tailored electrodes in electrochemical systems.

25 ENERGY STORAGE↗

Effect of Thermoelectric Magnetic Convection on Shrinkage Porosity at the Final Stage of Solidification of GCr18Mo Steel Under Axial Static Magnetic Field

Adopting effective strategies to eliminate the shrinkage porosity at the final stage of steel solidification is one of the most attractive research subjects for metallurgists. Despite the progress in understanding the thermoelectric magnetic convection (TEMC) in the solidification process, utilization of TEMC for modifying the solidification feeding of steel has been ignored. The effects of TEMC on the shrinkage porosity at the final stage of solidification of GCr18Mo steel were investigated under an axial static magnetic field (ASMF). The morphology and porosity of GCr18Mo steel were investigated quantitatively by X-ray microtomography. We found that the amount of porosity first decreases and then increases with increasing intensity of the ASMF. Meanwhile, the shape of the porosity changed from tortuous to elliptic under the ASMF. On the basis of both the experimental and simulated results, the decrease in porosity is attributed to an adequate development of the TEMC leading to sufficient feeding. This study sheds light on an alternative technique for eliminating the shrinkage porosity at the final stage of steel solidification in industrial applications.

36 MATERIALS SCIENCE↗

Effects of Pouring Temperature and Electromagnetic Stirring on Porosity and Mechanical Properties of A357 Aluminum Alloy Rheo-Diecasting

Semisolid slurry of A357 aluminum alloy was prepared using a temperature-controllable electromagnetic stirrer and rheo-diecast at different temperatures. The effects of pouring temperature and electromagnetic stirring (EMS) on the porosity in rheo-diecast samples, as well as the relation between porosity and mechanical properties, were investigated. The results show that pouring temperature and EMS had minor influences on rheo-diecast microstructure but marked influence on the porosity. With decreasing slurry pouring temperature, the porosity decreased first and then increased, whereas the maximum pore ratio (ratio of shape factor to diameter of the largest pore) increased first and then decreased. The maximum pore ratio determines the level of tensile strength and elongation, and higher mechanical properties can be obtained with smaller and rounder pores in samples. The mechanical properties of the rheo-diecast samples increased linearly with increasing maximum pore ratio. The maximum pore ratio was 1.43 µm{sup −1}, and the minimum porosity level was 0.37% under EMS condition for the rheo-diecast samples obtained at a pouring temperature of 608 °C. With this porosity condition, the maximum tensile strength and elongation were achieved at 274 MPa and 4.9%, respectively. It was also revealed that EMS improves mechanical properties by reduction in porosity and an increase in maximum pore ratio.

36 MATERIALS SCIENCE↗

Effects of spatial energy distribution-induced porosity on mechanical properties of laser powder bed fusion 316L stainless steel

Laser powder bed fusion (LPBF) additive manufacturing (AM) offers a variety of advantages over traditional manufacturing, however its usefulness for manufacturing of high-performance components is currently hampered by internal defects (porosity) created during the LPBF process that have an unknown impact on global mechanical performance. By inducing porosity distributions through variations in print energy density and inspecting the resulting tensile samples using computed tomography, nearly 50,000 pores across 75 samples were identified. Porosity characteristics were quantitatively extracted from inspection data and compared with mechanical properties to understand the strength of relationships between porosity and global tensile performance. Useful porosity characteristics were identified for prediction of part performance. Results indicate that ductility and strain at ultimate tensile strength are the global tensile properties most significantly impacted by porosity and can be predicted with reasonable accuracy using simple porosity shape descriptors such as volume, diameter, and surface area. Moreover, it was found that the largest pores influenced behavior most significantly. Specifically, pores in excess of 125 µm in diameter were found to be a sufficient threshold for property estimation. These results establish an initial understanding of the complex defect-performance relationship in AM 316L stainless steel and can be leveraged to develop certification standards and improve confidence in part quality and reliability for the broader set of engineering alloys.

36 MATERIALS SCIENCE↗

The impact of infill percentage and layer height in small-scale material extrusion on porosity and tensile properties

We report material extrusion additive manufacturing is prone to introducing porosity within the structure due to the layer-by-layer construction using elliptical beads of material. This open porosity ultimately plays a role in determining the mechanical properties of printed parts. The shape, size, and amount of porosity within a printed part is influenced by a variety of factors, including nozzle diameter, infill percentage, layer height, raster orientation, and print speed. While several studies have investigated these and other parameters’ effects on mechanical performance and porosity, better understanding the interconnected relationships is crucial in balancing the various input parameters to achieve maximum strength. This work initially examined the influence of key print parameters (infill percentage and layer height) on the internal porosity of a printed Acrylonitrile Butadiene Styrene (ABS) part. Then, the print parameters and internal porosity were statistically correlated to final mechanical properties. Porosity was further classified as either open or closed to differentiate between connected voids in the mesostructure from isolated voids within the material itself. Mechanical performance increased with an increasing density and infill percentage, displaying a 224 % increase in elastic modulus and a 150 % increase in ultimate tensile strength. The contribution of layer height was found to be conditional upon the infill percentage.

3D Printing↗

Benchmarking image processing techniques for porosity measurement in polymer additive manufacturing: Review and experimental analysis

An image processing workflow is proposed for porosity measurement in polymer additive manufacturing. Various techniques, including global and local thresholding, region growing, and K-means clustering, were applied to microscopic images of carbon fiber reinforced acrylonitrile butadiene styrene (CF-ABS) and benchmarked for their ability to accurately measure porosity. Global methods included Otsu, minimum error, iterative, and entropy-based thresholding, while local methods included Niblack, Bernsen, Sauvola, and Bradley-Roth algorithms. Artificial uneven illumination was introduced to test local adaptive thresholds. Results showed significant differences in porosity values across methods. Otsu, region growing, and K-means clustering excelled under uniform illumination, while Sauvola and Bradley-Roth performed better with uneven illumination. Comparison with X-ray computed tomography (XCT) revealed slightly lower porosity values (2.55 %) than optimized methods (2.73–2.79 %) due to XCT's lower resolution excluding smaller pores. While XCT offers finer pore detection, it limits sample volume and underestimates porosity due to spatial variation. Validation using artificial grayscale images with 5 % porosity confirmed that Otsu, Bradley-Roth, region growing, and Sauvola algorithms produced accurate results. Although tested on a single material system, these methods can be adapted to others with optimization. In conclusion, given XCT's high computational and time costs, this study highlights suitable image processing techniques as cost-effective alternatives for porosity analysis in polymer composites.

Additive manufacturing↗

Generation and healing of porosity in high purity copper by high-pressure torsion

Highlights: • Direct characterization of severe plastic deformation induced and healed porosities. • HPT process of disk with pre-fabricated holes reveals healing of porosity. • Ultrafine grains coexisting with shear bands and pores exhibit high stability. • Excess vacancies and pores cause drag effect on the grain boundary motion. • Accelerated vacancy diffusion leads to the generation and growth of pores. - Abstract: Generation and healing of pores in metals under loading or during processing have long been important research topics, and their mechanisms are still debatable. In recent years, unexpected percolating networks of pores acting as ultra-fast diffusion paths were found in ultrafine-grained metals processed by severe plastic deformation. Herein, we conducted a systematic study of the mechanisms of generation and healing of pores in ultrahigh-purity copper (99.9995 wt%) during high-pressure torsion (HPT). In addition to a solid Cu disk, the disk with holes that were drilled before processing, resulting in nominal initial porosity of 4.48%, was processed by HPT. After HPT, the percolating porosities of 0.07 ± 0.01% and 0.04 ± 0.01% were found in the solid disk, and in the disk with pre-fabricated holes, respectively. Thus, higher initial porosity resulted in lower percolating porosity in the HPT-processed disk. Systemic characterization using scanning electron microscopy revealed that in both cases shear bands and ultra-fine grains are located in the regions with induced and healed pores. We discussed the mechanisms of porosity evolution in both cases. In the end, to verify the possibility of pores nucleation and growth by vacancy agglomeration, vacancy diffusivity during HPT processing was estimated. This work sheds a new light on the mechanisms of pores nucleation and evolution during severe plastic deformation.

36 MATERIALS SCIENCE↗

Secondary porosity prediction in complex carbonate reefs using 3D CT scan image analysis and machine learning

Development and preservation of carbonate porosity and permeability are critical to characterizing reservoirs. However, secondary porosity, such as vugs and fractures, are difficult to identify and require collection of expensive wireline tools or core sampling. Wireline logs and cores have traditionally been used to identify the presence of secondary porosity but fail to quantify the contribution to total reservoir porosity. Additionally, advanced wireline logs and core are not readily available for most wells. Dual energy CT scans were collected on whole core from the A-1 Carbonate and Brown Niagaran formations drawn from six wells in northern Michigan. 3D analysis techniques were applied to identify and isolate secondary porosity features. A series of machine learning and data analytics techniques were applied to the dataset to predict secondary porosity features on basic wireline logs. The predictive model successfully predicted secondary porosity with high confidence.

02 PETROLEUM↗

Porosity of additive manufacturing parts for process monitoring

Some metal additive manufacturing processes can produce parts with internal porosity, either intentionally (with careful selection of the process parameters) or unintentionally (if the process is not well-controlled.) Material porosity is undesirable for aerospace parts - since porosity could lead to premature failure - and desirable for some biomedical implants, since surface-breaking pores allow for better integration with biological tissue. Changes in a part's porosity during an additive manufacturing build may also be an indication of an undesired change in the process. We are developing an ultrasonic sensor for detecting changes in porosity in metal parts during fabrication on a metal powder bed fusion system, for use as a process monitor. This paper will describe our work to develop an ultrasonic-based sensor for monitoring part porosity during an additive build, including background theory, the development and detailed characterization of reference additive porosity samples, and a potential design for in-situ implementation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

NUMERICAL MODELING OF THE COAGULATION AND POROSITY EVOLUTION OF DUST AGGREGATES

Porosity evolution of dust aggregates is crucial in understanding dust evolution in protoplanetary disks. In this study, we present useful tools to study the coagulation and porosity evolution of dust aggregates. First, we present a new numerical method for simulating dust coagulation and porosity evolution as an extension of the conventional Smoluchowski equation. This method follows the evolution of the mean porosity for each aggregate mass simultaneously with the evolution of the mass distribution function. This method reproduces the results of previous Monte Carlo simulations with much less computational expense. Second, we propose a new collision model for porous dust aggregates on the basis of our N-body experiments on aggregate collisions. As the first step, we focus on 'hit-and-stick' collisions, which involve neither compression nor fragmentation of aggregates. We first obtain empirical data on porosity changes between the classical limits of ballistic cluster-cluster and particle-cluster aggregation. Using the data, we construct a recipe for the porosity change due to general hit-and-stick collisions as well as formulae for the aerodynamical and collisional cross sections. Our collision model is thus more realistic than a previous model of Ormel et al. based on the classical aggregation limits only. Simple coagulation simulations using the extended Smoluchowski method show that our collision model explains the fractal dimensions of porous aggregates observed in a full N-body simulation and a laboratory experiment. By contrast, similar simulations using the collision model of Ormel et al. result in much less porous aggregates, meaning that this model underestimates the porosity increase upon unequal-sized collisions. Besides, we discover that aggregates at the high-mass end of the distribution can have a considerably small aerodynamical cross section per unit mass compared with aggregates of lower masses. This occurs when aggregates drift under uniform acceleration (e.g., gravity) and their collision is induced by the difference in their terminal velocities. We point out an important implication of this discovery for dust growth in protoplanetary disks.

79 ASTRONOMY AND ASTROPHYSICS↗

Detection of Part Porosity in Additive Manufacturing Using Machining

Monitoring of part porosity in additive manufacturing is critical for part qualification and process parameter development. This article describes the monitoring of porosity in additive manufacturing using machining. Grade 91 steel samples with different levels of porosity were additively manufactured using a laser blown-powder process. The samples were machined, and the tool position and cutting power were monitored using the machine controller and an external power transducer, respectively. Results show that the power transducer is sensitive to machining porosities. A novel approach using the standard deviation of cutting power was developed to determine the location of porosities along the length of the machining pass. Test cuts were completed at different machining process parameters. Results showed that the probability of detection was one for pore volume greater than 0.3 mm 3 at different machining parameters. In conclusion, although the detection of porosity using machining is a destructive method for evaluation, it offers a low-cost and fast approach for monitoring porosity in additive manufacturing.

36 MATERIALS SCIENCE↗

ThermoPore: Predicting part porosity based on thermal images using deep learning

Part qualification is often a critical and labor-intensive process in additive manufacturing, particularly in the detection of defects such as porosity, which stands to benefit significantly from advancements in machine learning. We present a deep learning approach for quantifying and localizing ex-situ porosity within Laser Powder Bed Fusion fabricated samples utilizing in-situ thermal image monitoring data. Our goal is to build the real time porosity map of parts based on thermal images acquired during the build. The quantification task builds upon the established Convolutional Neural Network model architecture to predict pore count and the localization task leverages the spatial and temporal attention mechanisms of the novel Video Vision Transformer model to indicate areas of expected porosity. Our model for porosity quantification achieved a R 2 score of 0.57 and our model for porosity localization produced an average Intersection over Union (IoU) score of 0.32 and a maximum of 1.0. This work is setting the foundations of part porosity “Digital Twins” based on additive manufacturing monitoring data and can be applied downstream to reduce time-intensive post-inspection and testing activities during part qualification and certification. In addition, we seek to accelerate the acquisition of crucial insights normally only available through ex-situ part evaluation by means of machine learning analysis of in-situ process monitoring data.

Deep learning↗

Mitigation of spall fracture by evolving porosity

Ductile materials subject to impact loading conditions can undergo spall fracture when an incoming compressive stress wave reflects off interfaces and free surfaces as a tensile stress wave. Experimental observations suggest that in ductile materials, spall fracture is driven by the evolution of porosity. However, the presence of initial porosity in ductile materials also introduces plastic compressibility, which can attenuate the incoming compressive stress wave and, as a result, reduce the amplitude of the reflected tensile stress wave. This, in turn, can mitigate or delay spall fracture. In this work, we report on finite deformation finite element calculations that analyze the response of porous ductile materials subjected to impact loading conditions. Two sets of calculations are carried out, in the first set the material contains initial porosity values ranging from 0% to 5% while in the second set the material also undergoes stress-controlled porosity nucleation. Both sets of calculations are carried out for a wide range of imposed impact velocities. Here, our results show that porosity in ductile materials can, under certain circumstances, mitigate spall fracture by attenuating stress waves. Results correlating the effects of impact velocity, initial porosity, and porosity nucleation on spall fracture are presented and the underlying mechanisms are discussed.

36 MATERIALS SCIENCE↗

Quantification of Organic Porosity and Water Accessibility in Marcellus Shale Using Neutron Scattering

Pores within organic matter (OM) are a significant contributor to the total pore system in gas shales. These pores contribute most of the storage capacity in gas shales. Here we present a novel approach to characterize the OM pore structure (including the porosity, specific surface area, pore size distribution, and water accessibility) in Marcellus shale. By using ultrasmall and small-angle neutron scattering, and by exploiting the contrast matching of the shale matrix with suitable mixtures of deuterated and protonated water, both total and water-accessible porosity were measured on centimeter-sized samples from two boreholes from the nanometer to micrometer scale with good statistical coverage. Samples were also measured after combustion at 450 °C. Analysis of scattering data from these procedures allowed quantification of OM porosity and water accessibility. OM hosts 24–47% of the total porosity for both organic-rich and -poor samples. This porosity occupies as much as 29% of the OM volume. In contrast to the current paradigm in the literature that OM porosity is organophilic and therefore not likely to contain water, our results demonstrate that OM pores with widths >20 nm exhibit the characteristics of water accessibility. In conclusion, our approach reveals the complex structure and wetting behavior of the OM porosity at scales that are hard to interrogate using other techniques.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Application of a new hybrid particle swarm optimization-mixed kernels function-based support vector machine model for reservoir porosity prediction: A case study in Jacksonburg-Stringtown oil field, West Virginia, USA

Porosity is a fundamental property that characterizes the storage capability of fluid and gas-bearing formations in a reservoir. An accurate porosity value can be measured from core samples in the laboratory; however, core analysis is expensive and time consuming. Well-log data can be used to calculate porosity, but the availability of log suites is often limited in mature fields. Therefore, robust porosity prediction requires integration of core-measured porosity with available well-log suites to control for changes in lithology and fluid content. A support vector machine (SVM) model with mixed kernel function (MKF) is used to construct the relationship between limited conventional well-log suites and sparse core data. Porosity is the desired output, and two conventional well-log responses (gamma ray [GR] and bulk density) and three well-log-derived parameters (the slope of GR, the slope of density, and [Formula: see text]) are input parameters. A global stochastic searching algorithm, particle swarm optimization (PSO), is applied to improve the efficiency of locating the appropriate values of five control parameters in MKF-SVM model. The results of SVM with different traditional kernel functions were compared, and the MKF-SVM model provided an improvement over the traditional SVM model. To confirm the advantage of the hybrid PSO-MKF-SVM model, the results from three models: (1) radial basis function (RBF)-based least-squares SVM, (2) multilayer perceptron artificial neural network (ANN), and (3) RBF ANN, are compared with the result of the hybrid PSO-MKF-SVM model. The results indicate that the hybrid PSO-MKF-SVM model improves porosity prediction with the highest correlation coefficient ([Formula: see text] of 0.9560), the highest coefficient of determination ([Formula: see text] of 0.9140), the lowest root-mean-square error (1.6505), average absolute error value (1.4050), and maximum absolute error (2.717).

Geochemistry & Geophysics↗