Boosting COVID-19 Image Classification Using MobileNetV3 and Aquila Optimizer Algorithm.

Currently, the world is still facing a COVID-19 (coronavirus disease 2019) classified as a highly infectious disease due to its rapid spreading. The shortage of X-ray machines may lead to critical situations and delay the diagnosis results, increasing the number of deaths. Therefore, the exploitation of deep learning (DL) and optimization algorithms can be advantageous in early diagnosis and COVID-19 detection. In this paper, we propose a framework for COVID-19 images classification using hybridization of DL and swarm-based algorithms. The MobileNetV3 is used as a backbone feature extraction to learn and extract relevant image representations as a DL model. As a swarm-based algorithm, the Aquila Optimizer (Aqu) is used as a feature selector to reduce the dimensionality of the image representations and improve the classification accuracy using only the most essential selected features. To validate the proposed framework, two datasets with X-ray and CT COVID-19 images are used. The obtained results from the experiments show a good performance of the proposed framework in terms of classification accuracy and dimensionality reduction during the feature extraction and selection phases. The Aqu feature selection algorithm achieves accuracy better than other methods in terms of performance metrics.

Designing Lightweight 3D-Printable Bioinspired Structures for Enhanced Compression and Energy Absorption Properties.

Recent progress in additive manufacturing, also known as 3D printing, has offered several benefits, including high geometrical freedom and the ability to create bioinspired structures with intricate details. Mantis shrimp can scrape the shells of prey molluscs with its hammer-shaped stick, while beetles have highly adapted forewings that are lightweight, tough, and strong. This paper introduces a design approach for bioinspired lattice structures by mimicking the internal microstructures of a beetle's forewing, a mantis shrimp's shell, and a mantis shrimp's dactyl club, with improved mechanical properties. Finite element analysis (FEA) and experimental characterisation of 3D printed polylactic acid (PLA) samples with bioinspired structures were performed to determine their compression and impact properties. The results showed that designing a bioinspired lattice with unit cells parallel to the load direction improved quasi-static compressive performance, among other lattice structures. The gyroid honeycomb lattice design of the insect forewings and mantis shrimp dactyl clubs outperformed the gyroid honeycomb design of the mantis shrimp shell, with improvements in ultimate mechanical strength, Young's modulus, and drop weight impact. On the other hand, hybrid designs created by merging two different designs reduced bending deformation to control collapse during drop weight impact. This work holds promise for the development of bioinspired lattices employing designs with improved properties, which can have potential implications for lightweight high-performance applications.

Mechanical Behavior of Selective Laser Melting (SLM) Parts with Varying Thicknesses in a Saline Environment under Different Exposure Times.

A promising method for additive manufacturing that makes it possible to produce intricate and personalized parts is selective laser melting (SLM). However, the mechanical properties of as-corroded SLM parts are still areas of concern. This research investigates the mechanical behavior of SLM parts that are exposed to a saline environment containing a 3.5% NaCl solution for varying lengths of time. The exposure times chosen for this study were 10 days, 20 days, and 30 days. The results reveal that the tensile strength of the parts is significantly affected by the duration of exposure. Additionally, the study also examined the influence of porosity on the corrosion behavior of the parts. The analysis included studying the mass loss of the parts over time, and a regression analysis was conducted to analyze the relationship between exposure time and mass loss. In addition, the utilization of scanning electron microscopy (SEM) and X-ray photo spectroscopy (XPS) techniques yielded valuable insights into the fundamental mechanisms accountable for the observed corrosion and mechanical behavior. It was found that the presence of corrosion products (i.e., oxide layer) and pitting contributed to the degradation of the SLM parts in the saline environment. This research emphasizes the importance of considering part thickness in the design of SLM components for corrosive environments and provides insights for enhancing their performance and durability.

Effect of a Multiaxial Load of Reverse Torsion on Open-Cell Aluminum Foams Behavior.

As a main goal of this work, a novel generation of cellular materials has been developed and manufactured by the kelvin cell model to be offered for different multifunctional applications. These Open-Cell Aluminum Foams (OCAF) have 85% porosities of spherical-shaped pores with a diameter of 11 mm. Several foamed square-section specimens were used. This work investigated the impact of different new quasi-static biaxial loading complexities on the mechanical behavior of such foams. Thus, new S-profiled rigs were already designed for examining the behavior of tested foams under biaxial loading conditions with different reverse torsional components named ACTP-S. After testing, their high specific strength and high energy absorption abilities have been characterized. Thus, in addition to the reference uniaxial test, all other tests were conducted at a speed of 5 mm/min. Thus, the mechanical responses of this foam are affected by loading complexities which are simple uniaxial, intermediate-biaxial (Bi-45°), and sever-biaxial (Bi-60°). These results were compared to the classical Absorption using Compression-Torsion Plastique (ACTP) responses. It was concluded that the highest dissipated energy increases with the increase in loading path complexity. Note that the energy absorption of the foam is essentially governed by its collapse mode.

Optimising Surface Roughness and Density in Titanium Fabrication via Laser Powder Bed Fusion.

The Ti6Al4V alloy has many advantages, such as being lightweight, formal, and resistant to corrosion. This makes it highly desirable for various applications, especially in the aerospace industry. Laser Powder Bed Fusion (LPBF) is a technique that allows for the production of detailed and unique parts with great flexibility in design. However, there are challenges when it comes to achieving high-quality surfaces and porosity formation in the material, which limits the wider use of LPBF. To tackle these challenges, this study uses statistical techniques called Design of Experiments (DoE) and Analysis of Variance (ANOVA) to investigate and optimise the process parameters of LPBF for making Ti6Al4V components with improved density and surface finish. The parameters examined in this study are laser power, laser scan speed, and hatch space. The optimisation study results show that using specific laser settings, like a laser power of 175 W, a laser scan speed of 1914 mm/s, and a hatch space of 53 µm, produces Ti6Al4V parts with a high relative density of 99.54% and low top and side surface roughness of 2.6 µm and 4.3 µm, respectively. This promising outcome demonstrates the practicality of optimising Ti6Al4V and other metal materials for a wide range of applications, thereby overcoming existing limitations and further expanding the potential of LPBF while minimising inherent process issues.

Hybrid Finite Element-Smoothed Particle Hydrodynamics Modelling for Optimizing Cutting Parameters in CFRP Composites.

Carbon-fibre-reinforced plastic (CFRP) is increasingly being used in various applications including aerospace, automotive, wind energy, sports, and robotics, which makes the precision modelling of its machining operations a critical research area. However, the classic finite element modelling (FEM) approach has limitations in capturing the complexity of machining, particularly with regard to the interaction between the fibre-matrix interface and the cutting edge. To overcome this limitation, a hybrid approach that integrates smoothed particle hydrodynamics (SPHs) with FEM was developed and tested in this study. The hybrid FEM-SPH approach was compared with the classic FEM approach and validated with experimental measurements that took into account the cutting tool's round edge. The results showed that the hybrid FEM-SPH approach outperformed the classic FEM approach in predicting the thrust force and bounce back of CFRP machining due to the integrated cohesive model and the element conversion after failure in the developed approach. The accurate representation of the fibre-matrix interface in the FEM-SPH approach resulted in predicting precise chip formation in terms of direction and morphology. Nonetheless, the computing time of the FEM-SPH approach is higher than the classic FEM. The developed hybrid FEM-SPH model is promising for improving the accuracy of simulation in machining processes, combining the benefits of both techniques.

LCF and HCF of Short Carbon Fibers Reinforced AE42 Mg Alloy.

Lightweight magnesium alloys and magnesium matrix composites have recently become more widespread for high-efficiency applications, including automobile, aerospace, defense, and electronic industries. Cast magnesium and magnesium matrix composites are applied in many highly moving and rotating parts, these parts can suffer from fatigue loading and are consequently subjected to fatigue failure. Reversed tensile-compression low-cycle fatigue (LCF) and high-cycle fatigue (HCF) of short fibers reinforced and unreinforced AE42 have been studied at temperatures of 20 °C, 150 °C, and 250 °C. To select suitable fatigue testing conditions, tensile tests have been carried out on AE42 and the composite material AE42-C at temperatures of up to 300 °C. The Wohler curves σa (NF) have shown that the fatigue strength of the reinforced AE42-C in the HCF range was double that of unreinforced AE42. In the LCF range at certain strain amplitudes, the fatigue life of the composite materials is much less than that of the matrix alloys, this is due to the low ductility of this composite material. Furthermore, a slight temperature influence up to 150 °C has been established on the fatigue behavior of the AE42-C. The fatigue life curves Δεtotal (NF) were described using the Basquin and Manson-Coffin approaches. Fracture surface investigations showed a mixed mode of serration fatigue pattern on the matrix and carbon fibers fracturing and debonding from the matrix alloy.

Chip Formation and Orthogonal Cutting Optimisation of Unidirectional Carbon Fibre Composites.

This study presents a thorough experimental investigation utilising the design of experiments and analysis of variance (ANOVA) to examine the impact of machining process parameters on chip formation mechanisms, machining forces, workpiece surface integrity, and damage resulting from the orthogonal cutting of unidirectional CFRP. The study identified the mechanisms behind chip formation and found it to significantly impact the workpiece orientation of fibre and the tool's cutting angle, resulting in increased fibre bounceback at larger fibre orientation angles and when using smaller rake angle tools. Increasing the depth of cut and fibre orientation angle results in an increased damage depth, while using higher rake angles reduces it. An analytical model based on response surface analysis for predicting machining forces, damage, surface roughness, and bounceback was also developed. The ANOVA results indicate that fibre orientation is the most significant factor in machining CFRP, while cutting speed is insignificant. Increasing fibre orientation angle and depth leads to deeper damage, while larger tool rake angles reduce damage. Machining workpieces with 0° fibre orientation angle results in the least subsurface damage, and surface roughness is unaffected by the tool rake angle for fibre orientations between 0° to 90° but worsens for angles greater than 90°. Optimisation of cutting parameters was subsequently carried out to improve machined workpiece surface quality and reduce forces. The experimental results showed that negative rake angle and cutting at moderately low speeds (366 mm/min) are the optimal conditions for machining laminates with a fibre angle of θ = 45°. On the other hand, for composite materials with fibre angles of θ = 90° and θ = 135°, it is recommended to use a high positive rake angle and cutting speeds.

Additively Manufactured Parts from AA2011-T6 Large-Diameter Feedstocks Using Friction Stir Deposition.

The current work investigates the possibility of fabricating additive manufacturing products in solid-state form, from AA2011-T6 of 40 mm diameter rods as a feedstock, using an additive friction stir deposition (A-FSD) technique. The use of large diameter feedstocks, especially high-strength aluminum alloys (2XXX series), is a challenge, as it necessitates high power and the critical selection of the optimal A-FSD parameters, such as feed rate and spindle rotation speed. The study included applying a wide range of spindle rotation speeds, ranging from 400 to 1200 rpm, at three levels of feeding rates of 1, 3, and 5 mm/min. The AA2011-T6 friction stir deposited parts (FSDPs) were visually evaluated. This was followed by an examination of macrostructures through the thickness of the fabricated specimens. The characterization of microstructures was also carried out using optical microscopy and a scanning electron microscope equipped with advanced EDS analysis. Furthermore, the mechanical properties in terms of hardness and compressive strength of the AA2011-T6 base material (BM) and deposited materials were evaluated. Sound, additively manufactured products were successfully fabricated from 40 mm diameter AA2011-T6 feedstocks using the suggested deposition variables of 600 and 800 rpm spindle speeds and feeding rates of 1, 3, and 5 mm/min. The results indicated that the spindle speed and feeding rate govern the quality of the FSDPs. Furthermore, the axial load during the A-FSD process increased with increasing these parameters. In comparison to the AA2011-T6 BM, the additively deposited materials showed a refined grain structure and uniform dispersion of the fragment precipitates in their continuous multi-layers. The reduction ratio in grain size attains 71.56%, 76%, and 81.31% for the FSDPs processed at 800 rpm spindle speed and feeding rates of 1, 3 and 5 mm/min, respectively, compared to the grain size of BM. The Al2Cu and Al7Cu2Fe intermetallics are detected in the AA2011-T6 BM, and their deposited parts are in different shapes of spherical, almost spherical, irregular, and rod-like shapes. The compressive strength and hardness of the deposited parts increased with increasing spindle speed and feeding speeds. At a spindle speed of 800 rpm and a 5 mm/min feeding rate, the higher hardness and compressive strength gained were 85% and 93%, respectively, from that of the AA2011-T6 feedstock.

Comparative Study of FSW, MIG, and TIG Welding of AA5083-H111 Based on the Evaluation of Welded Joints and Economic Aspect.

Selecting an economically suitable welding technique and optimizing welding parameters to obtain high joint quality is considered a challenge for expanding the 5xxx aluminum alloy series in various industrial applications. This work aims to investigate the effect of applying different welding techniques, tungsten inert gas (TIG) and metal inert gas (MIG), as fusion welding processes compared to friction stir welding (FSW), a solid-state joining process, on the joint performance of the produced 5 mm thick similar AA5083-H111 butt weldments at different welding conditions. Different methods were used to evaluate the quality of the produced joints, including visual inspection, radiographic testing (RT), and macrostructure evaluation, in addition to hardness and tensile tests. The fracture surface of the tensile-failed specimens was also investigated using a scanning electron microscope (SEM). Furthermore, the current study ended with an economic analysis of the welding techniques used. The results showed that, for the friction stir-welded joints, the radiographic films revealed defect-free joints at the two applied travel speeds of 100 mm/min and 400 mm/min and a constant tool rotating speed of 400 rpm. In addition, only one joint was welded by MIG at a welding current of 130 Amp, with a 19 L/min flow rate of pure argon. In contrast, the radiographic films showed internal defects such as lack of fusion (LOF), lack of penetration (LOP), and porosity (P) for the two joints welded by TIG and one joint welded by MIG. The hardness of the welded joints was enhanced over the AA5083-H111 base material (BM) by 24-29, 31-35, and 46-50% for the MIG, TIG, and FSW joints, respectively. The maximum ultimate tensile strength was obtained for the FSW joint welded at a 400 mm/min travel speed. Adopting FSW in shipbuilding applications can further produce the AA5083-H11 joints with higher quality and efficiency than fusion welding techniques such as MIG and TIG processes. In addition, time and cost comparisons between TIG, MIG, and FSW were performed for five-millimeter-thick and one-meter-long AA5083-H111.

Fabrication and Optimisation of Ti-6Al-4V Lattice-Structured Total Shoulder Implants Using Laser Additive Manufacturing.

This work aimed to study one of the most important challenges in orthopaedic implantations, known as stress shielding of total shoulder implants. This problem arises from the elastic modulus mismatch between the implant and the surrounding tissue, and can result in bone resorption and implant loosening. This objective was addressed by designing and optimising a cellular-based lattice-structured implant to control the stiffness of a humeral implant stem used in shoulder implant applications. This study used a topology lattice-optimisation tool to create different cellular designs that filled the original design of a shoulder implant, and were further analysed using finite element analysis (FEA). A laser powder bed fusion technique was used to fabricate the Ti-6Al-4V test samples, and the obtained material properties were fed to the FEA model. The optimised cellular design was further fabricated using powder bed fusion, and a compression test was carried out to validate the FEA model. The yield strength, elastic modulus, and surface area/volume ratio of the optimised lattice structure, with a strut diameter of 1 mm, length of 5 mm, and 100% lattice percentage in the design space of the implant model were found to be 200 MPa, 5 GPa, and 3.71 mm-1, respectively. The obtained properties indicated that the proposed cellular structure can be effectively applied in total shoulder-replacement surgeries. Ultimately, this approach should lead to improvements in patient mobility, as well as to reducing the need for revision surgeries due to implant loosening.

A Novel Friction Stir Deposition Technique to Refill Keyhole of Friction Stir Spot Welded AA6082-T6 Dissimilar Joints of Different Sheet Thicknesses.

Joining dissimilar sheet thicknesses of AA6082-T6 alloys by friction stir spot welding (FSSW) provides many advantages in automotive and aerospace applications. The formed keyhole at the end of the FSSW process is one of the typical features after the welding process, which owns the same size as the rotating pin that remains at the joint center. This keyhole destroys the joint continuity and can stimulate serious stress concentration when the FSSW joint bears an external force. To solve this issue, a novel refilling technique was developed for the FSSW keyholes using a friction stir deposition (FSD) technique. The FSSW joints of AA6082-T6 sheets were welded at various rotation speeds from 400 to 1000 rpm and a constant dwell time of 3 s, where a 2 mm sheet thickness was an upper sheet, and a 1 mm sheet thickness was a lower sheet. All the keyhole refilling processes were achieved using a specially designed AA2011-T6 consumable rod to be used for friction stir deposition of continuous layers at a constant deposition parameter of 400 rpm consumable rod rotation speed and a 1 mm/min feed rate. The heat input energy for both the FSSW and refilled FSSW lap joints was calculated. In addition, the FSSW and the FSD temperatures were measured. Macrostructure, microstructure, and mechanical properties in terms of hardness and tensile shear maximum load were evaluated for both the friction stir spot welded (FSSWed) and the refilled FSSW lap joints. The obtained results showed that the keyhole could be successfully refilled with defect-free continuous multilayers after the refill friction stir spot welding (RFSSW) process. All the RFSSW lap joints showed higher tensile shear loads than that given by the FSSW (before refill) lap joints. The RFSSW joint (welded at 600 rpm/3 s and refilled at 400 rpm/1 mm/min) showed a higher tensile shear load of 5400 N ± 100 compared with that recorded by the unrefilled joint (4300 N ± 80). The fracture location and fracture surface of the FSSW and RFSSW were examined and discussed.

Wear Characteristics of Mg Alloy AZ91 Reinforced with Oriented Short Carbon Fibers.

Light-weight metal matrix composites, especially magnesium-based composites, have recently become more widespread for high-efficiency applications, including aerospace, automobile, defense, and telecommunication industries. The squeeze cast AZ91 base material (AZ91-BM) and its composites having 23 vol.% short carbon fibers were fabricated and investigated. The composite specimens were machined normal to the reinforced plane (Composite-N) and parallel to the reinforced plane (Composite-P). All the as-casted materials were subjected to different tests, such as hardness, compression, and wear testing, evaluating the mechanical properties. Dry wear tests were performed using a pin-on-disk machine at room temperature under different applied wear loads (1−5 N) and different sliding distances (0.4461×104−3.12×104 m). The microstructures and worn surfaces of the fabricated AZ91-BM and the two composite specimens were investigated using a scanning electron microscope (SEM) equipped with an energy dispersive spectroscopy (EDS) advanced analysis system. The wear debris was collected and investigated also under the SEM. The results showed significant improvement in hardness, compressive strength, and wear resistance of the composite specimens (Composite-N and Composite-P) over the AZ91-BM. The compressive strength and wear resistance are more fibers orientation sensitive than the hardness results. When the fiber orientation is parallel to the sliding direction (Composite-N), the weight loss is somewhat lower than that of the fiber orientation perpendicular to the sliding direction (Composite-P) at a constant wear load of 2 N and the sliding distances of 0.4461×104, 1.34×104 , and 2.23×104 m. In contrast, the weight loss of Composite-P is lower than Composite-N, especially at the highest sliding distance of 3.12×104 m due to the continuous feeding of graphite lubricant film and the higher compressive strength. Plastic deformation, oxidation, and abrasive wear are the dominant wear mechanisms of AZ91-BM; in contrast, abrasive and delamination wear are mainly the wear mechanisms of the two composites under the applied testing conditions.

Optimization of Abrasive Water Jet Machining of SiC Reinforced Aluminum Alloy Based Metal Matrix Composites Using Taguchi-DEAR Technique.

Since the importance of introducing new engineering materials is increasing, the need for machining such higher strength materials has also considerably increased. In the present research, an endeavor was made to introduce a Taguchi-DEAR methodology for the abrasive water-jet machining process, while machining a SiC-reinforced aluminum composite. Material removal rate, taper angle, and surface roughness were considered as the quality measures. The optimal arrangement of input process factors in the AWJM process was found to be 2800 bar (WP), 400 mg/min (AF), 1000 mm/min (FR), and 4 mm (SOD), among the chosen factors, with an error accuracy of 0.8%. The gas pressure had the most significance for formulating the performance measures, owing to its ability to modify the impact energy and crater size of the machined specimen.

Artificial Intelligence for Forecasting the Prevalence of COVID-19 Pandemic: An Overview.

Since the discovery of COVID-19 at the end of 2019, a significant surge in forecasting publications has been recorded. Both statistical and artificial intelligence (AI) approaches have been reported; however, the AI approaches showed a better accuracy compared with the statistical approaches. This study presents a review on the applications of different AI approaches used in forecasting the spread of this pandemic. The fundamentals of the commonly used AI approaches in this context are briefly explained. Evaluation of the forecasting accuracy using different statistical measures is introduced. This review may assist researchers, experts and policy makers involved in managing the COVID-19 pandemic to develop more accurate forecasting models and enhanced strategies to control the spread of this pandemic. Additionally, this review study is highly significant as it provides more important information of AI applications in forecasting the prevalence of this pandemic.