Arabian Journal for Science and Engineering最新文献

Visual object tracking has been a fundamental topic of machine vision in recent years. Most trackers can hardly top the performance and work in real time. This paper presents a tracking framework based on the SiamFC network, which can be taught online from the beginning of tracking and is real time. SiamFC network has a high tracking speed but cannot be trained online. This limitation made it unable to track the target for a long time. Hybrid-Siam can be trained online to distinguish target and background by switching traditional tracking and deep learning methods. Using the traditional tracking method and a target detector based on saliency detection has led to long-term tracking. Our method runs at more than 60 frame per second during test time and achieves state-of-the-art performance on tracking benchmarks, while robust results for long-term tracking. Hybrid-Siam improves SiamFC and achieves AUC score 81.7% on LaSOT, 72.3% on OTB100, and average overlap of 66.2% on GOT-10 k.

In this study, the microstructure, hardness, tensile strength, and dry wear properties of the cast AlSi10Mg alloy as well as the effects of processing parameters on the oxidation behavior of this alloy were investigated. In this context, AlSi10Mg (wt%) alloy was produced by gravity die casting method, and then, air cooling, quenching, and T6 treatment were applied. The microstructure of the alloy was investigated using an optical microscope, SEM, and EDS. Additionally, thermogravimetric analysis (TGA) was used to determine the effect of processing parameters on the oxidation behavior of the samples. The friction and wear properties of the alloy were investigated using a ball-on-disk wear test device. It was founded that the as-cast AlSi10Mg alloy's microstructure contained phases of α(Al), Si, and β-Mg₂Si. It has been observed that the microstructure of the cast AlSi10Mg alloy gradually turns into a spherical form when quenching and air-cooling heat treatments are applied. Also, T6 heat treatment led to further spheroidization of Si particles, formation of β-Mg2Si precipitates, and elimination of the Chinese script morphology of the β-Mg₂Si phase. It was observed that the yield strength of the AlSi10Mg alloy in the as-cast state decreased negligibly compared to the air-cooled state, while there was an increase of up to 70% in the aging-treated condition. The results show that the tensile strength of the as-cast AlSi10Mg alloy increased by 115% after aging. Additionally, it was found that the AlSi10Mg alloy's wear resistance increased with the aging process.

Wire-electrical discharge machining (wire-EDM) is gaining wider acceptance for producing components of Al-matrix composites (Al-MCs) that are hard to machine by traditional methodologies. The related research is primarily limited to ex-situ Al-MCs commonly reinforced with ceramic particles; however, Al-MCs reinforced with in-situ ordered intermetallics have evolved as superior composites nowadays. This research has focused on wire-EDM of in-situ Al/Al₃Fe composites developed by the reactive stir-casting route. The influence of three machining variables (pulse-on-time, servo voltage, and peak-current) and one material parameter (vol% of reinforcement) have been studied following the L₂₇ Taguchi design. The integrity of the machined surface has been characterized via measurements of surface roughness (SR) and the alteration of surface chemistry (ASC, ΣCu + Zn + O), in addition to the evaluation of kerf width (KW) as a machining performance indicator. It has been established that all four control factors are significant for KW, while ASC is influenced by all factors except vol% of reinforcement; however, only pulse-on-time is substantial for SR. Analytical models of individual responses are developed while the desirability approach helps to accomplish the multi-response optimization; several confirmation experiments establish the authenticity of these predictions with an error < 8%. Characterizations of machined surfaces and wire electrodes by FESEM and EDS techniques reveal that the surface integrity of in-situ Al/Al₃Fe composites varies significantly with machining conditions.

The potential substitution of traditional cutting fluids with green Metalworking fluids (MWFs) is frequently explored because of their non-toxic and environmentally friendly characteristics. These green MWFs have often been evaluated for their tribological behavior and machining performance under various operating conditions. However, very few studies have analyzed the green metalworking fluids' ecological and eco-toxicological characteristics. With an aim to explore the potential impact and the related concerns of the developed green MWFs on the environment and eco-life, ecological and eco-toxicological experimental studies were performed in this research. This research study offers a comprehensive analysis of the biodegradability, soil eco-toxicity, cell viability, corrosion responsiveness, and reusability characteristics of the in-house developed nanoparticles-modified vegetable oil MWFs (MVO-MWFs). The findings from biodegradability studies demonstrate the inherent and readily biodegradable nature of the developed MWFs. Subsequently, soil eco-toxicity tests reveal the non-harmful nature of developed MWFs to the ecological organisms at the tested concentrations. Furthermore, during the cell viability assays, no evidence of cell death was observed in normal and cancer-affected cells under tested conditions. Additionally, the reusability studies on MQL imply that a considerable amount of MWF can be collected and reused to enhance the sustainability of the MWF system. This study established a decision-making approach to identify the optimal NP-based MWF combination by correlating multivariate data. Based on this work, a step-by-step methodology is recommended with four decision points to conduct a series of ecological and eco-toxicological protocols for the new or existing NP-based MWFs. This study contributes to the manufacturing research community and industry by shedding light on hitherto unexplored aspects of ecological and eco-toxicological investigations on the NP-based MVO-MWFs.

The harmful particles can cause significant health risks and need to be carefully removed from the air before they can pose a threat. One of the most effective methods for separating these particles is a cyclone separator, which can quickly and efficiently remove hazardous particles from the air. In this research, the separation of silica particles using a cyclone separator was investigated and analyzed using artificial neural networks (ANNs) and response surface methodology. The influence of process parameters, including flow rate, particle size, and speed, on cyclone efficiency was investigated. The cyclone experiments were carried out with varying rotation speeds ranging from 0 to 1900 rpm, as well as different particle sizes (15, 25, and 40 μm) and flow rates (30, 50, and 70 m³/hr). Based on the research findings, it was discovered that the ANN model that utilized the multilayer perceptron (MLP) algorithm outperformed the one that used the radial basis function (RBF) algorithm. The findings showed that a neural network with a multilayer perceptron (MLP) architecture performed well in predicting efficiency. Specifically, this MLP had one hidden layer consisting of 10 neurons, and its topology was defined as 3-10-1. The accuracy of the efficiency predictions was high, with a coefficient of determination of 0.998. After analyzing the results, it was concluded that the perceptron multilayer (MLP) model had the highest coefficient of determination value of 0.998 and the lowest error values, with a mean square error of 0.00033838.

Photocatalytic degradation is a promising emerging method for eliminating dye from contaminated water. The core of photocatalytic degradation lies in the design and preparation of high-performance catalysts that do not produce polluting secondary products. Here, we explore magnetic NiFe₂O₄ materials doped with varying amounts of Cu²⁺ ions (Cu_xNi_1−xFe₂O₄, where x = 0–0.5) via the combustion method to target rhodamine B (RhB) dye removal. To validate whether Cu²⁺ is incorporated, the structural characteristics of the catalysts were analyzed using physical techniques. The photocatalytic activity of Cu_xNi_1−xFe₂O₄ (x = 0–0.5) was evaluated based on the degradation of RhB, achieving 97.25% degradation efficiency under optimized conditions. The radical quenching results revealed that ^•OH played a pivotal factor in the photodegradation process. Additionally, chemical oxygen demand (COD) testing yielded a level of 24.67 mg L⁻¹, significantly lower than the World Health Organization (WHO) drinking water standards. Overall, our findings reached high photocatalytic activity of Cu_0.5Ni_0.5Fe₂O₄ in removing a harmful dye (RhB) from water.

Predictive maintenance in industrial settings, especially tool wear prediction, remains crucial for operational efficiency and cost reduction. This paper proposes BiLPReS, a novel predictive model leveraging a hybrid architecture integrating bidirectional long short-term memory, Performer encoder, and residual-skip connections. Compared to convolutional and recurrent neural networks, the proposed model achieves long-range dependent global sensing and parallel computing. The Performer encoder reduces the computational complexity by the FAVOR + approach compared to the Transformer encoder. Moreover, the proposed model includes residual-skip connections to enhance information flow efficiency and minimize the risk of information loss during training. The final use of the fully connected layer reduces dimensionality and generates the predicted values. Experiments on the PHM2010 dataset involve the analysis of multichannel sensor signals, including force, acceleration, and acoustic emission. The model undergoes training and validation through k-fold cross-validation. Results unequivocally demonstrate the model’s high accuracy. Furthermore, conducting comparative experiments by selectively reducing modules validates the effectiveness of the utilized modules in enhancing the model’s performance. This study provides a viable solution for optimizing maintenance schedules, reducing downtime, and real-time monitoring of tool machining.

Response surface methodology predicts the best condition of the parameters that are critical in achieving desired goal and is the statistical analysis carried out to obtain the optimized conditions of parameters. The model for the examination is developed for the flow of Casson-Carreau nanofluids over stretched curved sheet swayed by the magnetic dipole. The sheet is liable to radiation and second-order slip and melting heat conditions is contemplated. The current study reveals that the velocity regime decreases with decreasing slip effects, and the ferrohydrodynamic interaction parameter increases with increasing slip effects. Additionally, the heat dissipation parameter influences the thermal profile. By response surface methodology analyzed on the skin friction coefficient reveals that histogram for the experimental runs is normally distributed and the ({R}^{2}) is 100% promoting the accuracy of the model designed. Pareto chart has given the picture of 2.2 to be the critical point for the three parameters under consideration. The magnetic and porous parameters exhibit negative sensitivity at low and medium ({L}_{s1}) values, while at ({L}_{s1}=0.4), they demonstrate no sensitivity or negligible sensitivity. The first-order slip parameter exhibits a positive sensitivity at low and medium concentrations, but a negative sensitivity at high concentrations of (C).

Superhydrophobic surfaces have been widely studied for their self-cleaning properties. However, most of the constructed superhydrophobic surfaces had problems of changing the surface morphology and color of paper/cloth. An extremely dilute superhydrophobic solution was prepared by hybrid assembly of aminated nano-SiO₂ and high fluorine epoxy polymer P(FOEMA-r-GMA). The preparation of superhydrophobic cotton (SHC) and superhydrophobic book paper (SHBP) was studied through the optimal construction conditions of solution impregnation method. The optimal construction conditions for SHC were as follows: The concentration of fluorinated epoxy polymer was 3 mg/mL, the soaking time was 5 h, the drying time was 8 h, and the drying temperature was 120 °C. The maximum WCA was 158° ± 3°, and the minimum WRA was 4° ± 3°. SHC surface had good hydrophobic effect, acid and alkali resistance, and self-cleaning effect. Additionally, its surface morphology still remained basically unchanged. SHC could be used for oil–water separation with a maximum oil–water separation rate of 98.4%. The optimal construction conditions for SHBP were: The concentration of fluorinated epoxy polymer was 3 mg/mL, the soaking time was 9 h, the drying time was 6 h, the maximum WCA was 155° ± 3°, and the minimum WRA was 6° ± 1°. The hydrophobicity of SHBP was greatly improved; it would extract selective adsorbing oil from the oil–water mixture and slightly reduce its smoothness.

A nanofluid refers to the dispersion of nanoparticles in a regular fluid and has a unique application in various sectors, including medicine, engineering, and technology. When multiple nanoparticles are suspended in a regular fluid, it creates a hybrid nanofluid. In this study, we aim to investigate homogenous–heterogenous reactions in Bödewadt hybrid nanofluid flow over a permeable rotating disk with radiation. The base fluid chosen for this study is water (H₂O), while the nanoparticles iron oxide (Fe₃O₄) and cobalt ferrite (CoFe₂O₄) are utilized to create the hybrid nanofluid. An appropriate method of similarity transformation is executed along a set of partial differential equations (PDEs) that were reduced to a system of nonlinear ordinary differential equations (ODEs). Numerical outcomes were then obtained via bvp4c in MATLAB software, with the influence of various parameters such as nanoparticle volume fraction, homogenous/heterogenous reaction strength parameters, suction, shrinking/stretching parameters, and radiation parameter. Additionally, asymptotic analysis was conducted to show that the concentration boundary layer on the disk can be performed subject to a large number of suctions. The present findings reveal that a rise in the volume fraction of nanoparticles results in a reduction in radial velocity profiles, temperature profiles, and tangential fields. As thermal radiation levels rise, a notable reduction in the local Nusselt number is evident. Moreover, there is an observed linear escalation in wall surface concentration when the heterogeneous strength parameter attains higher values. The presented results demonstrate that all flow fields are significantly affected by the participating parameters.