Search results

This paper aims to determine the optimum parametric settings for yielding superior mechanical properties, namely, ultimate tensile strength (UTS), yield strength (YS) and percentage elongation (EL) of AZ91D/AgNPs/TiO₂ hybrid composite fabricated by friction stir processing.

An empirical model has been developed to govern crucial influencing parameters, namely, rotation speed (RS), tool transverse speed (TS), number of passes (NPS) and reinforcement fraction (RF) or weight percentage. Box Behnken design (BBD) with four input parameters and three levels of each parameter was used to design the experimental work, and analysis of variance (ANOVA) was used to check the acceptability of the developed model. Desirability function analysis (DFA) for a multiresponse optimization approach is integrated with response surface methodology (RSM). The individual desirability index (IDI) was calculated for each response, and a composite desirability index (CDI) was obtained. The optimal parametric settings were determined based on maximum CDI values. A confirmation test is also performed to compare the actual and predicted values of responses.

The relationship between input parameters and output responses (UTS, YS, and EL) was investigated using the Box-Behnken design (BBD). Silver nanoparticles (AgNPs) and nano-sized titanium dioxide (TiO₂) enhanced the ultimate tensile strength and yield strength. It was observed that the inclusion of AgNPs led to an increase in ductility, while the increase in the weight fraction of TiO₂ resulted in a decrease in ductility.

AZ91D/AgNPs/TiO₂ hybrid composite finds enormous applications in biomedical implants, aerospace, sports and aerospace industries, especially where lightweight materials with high strength are critical.

In terms of optimum value through desirability, the experimental trials yield the following results: maximum value of UTS (318.369 MPa), maximum value of YS (200.120 MPa) and EL (7.610) at 1,021 rpm of RS, 70 mm/min of TS, 4 NPS and level 3 of RF.

Through the use of the Markov Decision Model (MDM) approach, this study uncovers significant variations in the availability of machines in both faulty and ideal situations in small and medium-sized enterprises (SMEs). The first-order differential equations are used to construct the mathematical equations from the transition-state diagrams of the separate subsystems in the critical part manufacturing plant.

To obtain the lowest investment cost, one of the non-traditional optimization strategies is employed in maintenance operations in SMEs in this research. It will use the particle swarm optimization (PSO) algorithm to optimize machine maintenance parameters and find the best solutions, thereby introducing the best decision-making process for optimal maintenance and service operations.

The major goal of this study is to identify critical subsystems in manufacturing plants and to use an optimal decision-making process to adopt the best maintenance management system in the industry. The optimal findings of this proposed method demonstrate that in problematic conditions, the availability of SME machines can be enhanced by up to 73.25%, while in an ideal situation, the system's availability can be increased by up to 76.17%.

The proposed new optimal decision-support system for this preventive maintenance management in SMEs is based on these findings, and it aims to achieve maximum productivity with the least amount of expenditure in maintenance and service through an optimal planning and scheduling process.

Toner is a crucial dry colorant composite used in printing based on the electrophotographic process. The quality of printed images is greatly influenced by the toner production method and material formulation. Chemically in situ polymerization methods are currently preferred. This paper aims to optimize the characteristics of a composite produced through emulsion polymerization using common raw materials for electrophotographic toner production.

Emulsion polymerization provides the possibility to optimize the physical and color properties of the final products. Response surface methodology (RSM) was used to optimize variables affecting particle size (PS), PS distribution (PSD), glass transition temperature (T_g°C), color properties (ΔE) and monomer conversion. Box–Behnken experimental design with three levels of styrene and butyl acrylate monomer ratios, carbon black pigment and sodium dodecyl sulfate surfactant was used for RSM optimization. Additionally, thermogravimetric analysis and surface morphology of composite particles were examined.

The results indicated that colorants with small PS, narrow PSDs, spherical shape morphology, acceptable thermal and color properties and a high percentage of conversion could be easily prepared by optimization of material parameters in this method. The anticipated outcome of the present inquiry holds promise as a guiding beacon toward the realization of electrographic toner of superior quality and exceptional efficacy, a vital factor for streamlined mass production.

To the best of the authors’ knowledge, for the first time, material parameters were evaluated to determine their impact on the characteristics of emulsion polymerized toner composites.

With the rapid growth of the domestic lending industry, assessing whether the borrower of each loan is at risk of default is a pressing issue for financial institutions. Although there are some models that can handle such problems well, there are still some shortcomings in some aspects. The purpose of this paper is to improve the accuracy of credit assessment models.

In this paper, three different stages are used to improve the classification performance of LSTM, so that financial institutions can more accurately identify borrowers at risk of default. The first approach is to use the K-Means-SMOTE algorithm to eliminate the imbalance within the class. In the second step, ResNet is used for feature extraction, and then two-layer LSTM is used for learning to strengthen the ability of neural networks to mine and utilize deep information. Finally, the model performance is improved by using the IDWPSO algorithm for optimization when debugging the neural network.

On two unbalanced datasets (category ratios of 700:1 and 3:1 respectively), the multi-stage improved model was compared with ten other models using accuracy, precision, specificity, recall, G-measure, F-measure and the nonparametric Wilcoxon test. It was demonstrated that the multi-stage improved model showed a more significant advantage in evaluating the imbalanced credit dataset.

In this paper, the parameters of the ResNet-LSTM hybrid neural network, which can fully mine and utilize the deep information, are tuned by an innovative intelligent optimization algorithm to strengthen the classification performance of the model.

The metallic alloys and their components fabricated via laser powder bed fusion (LPBF) suffer from the microvoids formed inevitably due to the extreme solidification rate during fabrication, which are impossible to be removed by heat treatment. This paper aims to remove those microvoids in as-built AlSi10Mg alloys by hot forging and enhance their mechanical properties.

AlSi10Mg samples were built using prealloyed powder with a set of optimized LPBF parameters, viz. 350 W of laser power, 1,170 mm/s of scan speed, 50 µm of layer thickness and 0.24 mm of hatch spacing. As-built samples were preheated to 430°C followed by immediate pressing with two different thickness reductions of 10% and 35%. The effect of hot forging on the microstructure was analyzed by means of X-ray diffraction, scanning electron microscopy, electron backscattered diffraction and transmission electron microscopy. Tensile tests were performed to reveal the effect of hot forging on the mechanical properties.

By using hot forging, the large number of microvoids in both as-built and post heat-treated samples were mostly healed. Moreover, the Si particles were finer in forged condition (∼150 nm) compared with those in heat-treated condition (∼300 nm). Tensile tests showed that compared with heat treatment, the hot forging process could noticeably increase tensile strength at no expense of ductility. Consequently, the toughness (integration of tensile stress and strain) of forged alloy increased by ∼86% and ∼24% compared with as-built and heat-treated alloys, respectively.

Hot forging can effectively remove the inevitable microvoids in metals fabricated via LPBF, which is beneficial to the mechanical properties. These findings are inspiring for the evolution of the LPBF technique to eliminate the microvoids and boost the mechanical properties of metals fabricated via LPBF.

Factor investment is booming in global asset management, especially environmental, social, and governance (ESG), dividend yield, and volatility factors. In this chapter, we use data from the US securities market from 2003 to 2019 to predict dividends and volatility factors through machine learning and historical data–based methods. After that, we utilize particle swarm optimization to construct the Markowitz portfolio with limits on the number of assets and weight restrictions. The empirical results show that that the prediction ability using XGBoost is superior to the historical factor investment method. Moreover, the investment performance of our portfolio with ESG, high-yield, and low-volatility factors outperforms baseline methods, especially the S&P 500 ETF.

The purpose of this paper is to study Al-based green composite. To make composite samples of aluminium alloy (AA3105) with different weight percentages of rice husk ash (RHA) and eggshell (ES) particles as reinforcement, stir casting method was used.

Several other aspects, including the weight percent of reinforcing agent particles, the applied stress and the sliding speed, were taken into consideration. During the course of the wear test, the sliding distance that was recorded varied from a minimum of 1,000 m all the way up to a maximum of 3,135 m (10, 15, 20, 25 and 30 min). The typical range for normal loads is 8–24 N, and their speed is 1.58 m/s.

With the AA/ES/RHA composite, the wear rates decreases when the grain size of the reinforcing particles enhanced. Scanning electron microscopy images of worn surfaces show that at low speeds, delaminating and ploughing are the main causes of wear. At high speeds, ploughing is major cause of wear. Composites with better wear-resistant properties can be used in wide range of tribological applications, especially in the automotive industry. It was found that hardness increases at the same time as the weight of the reinforcement increases. Tensile and hardness were maximized at 10% reinforcement mix in Al3105.

In this work, ES and RHA has been used to develop green metal matrix composite to support green revolution as promoted/suggested by United Nations thus reducing the environmental pollution.

The purpose of this paper is to elucidate the extent to which the mechanisms of polymer melt viscous flow and finish layer powder particle adhesion influence the top surface topographies of laser sintered polyamide (PA12) components.

Laser sintered specimens were manufactured at varying laser parameters in accordance with a full factorial design of experiments. Focus variation microscopy was used to ascertain insight into their top surface heights and peak/valley distributions. Subsequently, regression expressions were generated to model the former with respect to applied laser parameters. Auxiliary experimental analysis was also performed to validate the proposed mechanisms and statistical models.

Within the parameter range tested, this work found the root mean square (S_q) and skewness (S_sk) roughness responses of laser sintered PA12 top surfaces to be inversely related to one another, and both also principally influenced by beam spacing. Furthermore, it was demonstrated that using optimised laser parameters (to promote polymer melt dispersion) and building without finish layers (to avert subsequent powder particle adhesion) reduced the mean S_q roughness of resultant topographies by 30.8% and 47.9% relative to standard laser sintered PA12 top surfaces, respectively.

The scope to which laser sintered PA12 top surfaces can be modified was highlighted.

This research demonstrated the impact the mechanisms of polymer melt viscous flow and finish layer powder particle adhesion have on laser sintered PA12 top surfaces.

Bayesian cubature (BC) has emerged to be one of most competitive approach for estimating the multi-dimensional integral especially when the integrand is expensive to evaluate, and alternative acquisition functions, such as the Posterior Variance Contribution (PVC) function, have been developed for adaptive experiment design of the integration points. However, those sequential design strategies also prevent BC from being implemented in a parallel scheme. Therefore, this paper aims at developing a parallelized adaptive BC method to further improve the computational efficiency.

By theoretically examining the multimodal behavior of the PVC function, it is concluded that the multiple local maxima all have important contribution to the integration accuracy as can be selected as design points, providing a practical way for parallelization of the adaptive BC. Inspired by the above finding, four multimodal optimization algorithms, including one newly developed in this work, are then introduced for finding multiple local maxima of the PVC function in one run, and further for parallel implementation of the adaptive BC.

The superiority of the parallel schemes and the performance of the four multimodal optimization algorithms are then demonstrated and compared with the k-means clustering method by using two numerical benchmarks and two engineering examples.

Multimodal behavior of acquisition function for BC is comprehensively investigated. All the local maxima of the acquisition function contribute to adaptive BC accuracy. Parallelization of adaptive BC is realized with four multimodal optimization methods.

Robotic arms’ interactions with the external environment are growing more intricate, demanding higher control precision. This study aims to enhance control precision by establishing a dynamic model through the identification of the dynamic parameters of a self-designed robotic arm.

This study proposes an improved particle swarm optimization (IPSO) method for parameter identification, which comprehensively improves particle initialization diversity, dynamic adjustment of inertia weight, dynamic adjustment of local and global learning factors and global search capabilities. To reduce the number of particles and improve identification accuracy, a step-by-step dynamic parameter identification method was also proposed. Simultaneously, to fully unleash the dynamic characteristics of a robotic arm, and satisfy boundary conditions, a combination of high-order differentiable natural exponential functions and traditional Fourier series is used to develop an excitation trajectory. Finally, an arbitrary verification trajectory was planned using the IPSO to verify the accuracy of the dynamical parameter identification.

Experiments conducted on a self-designed robotic arm validate the proposed parameter identification method. By comparing it with IPSO1, IPSO2, IPSOd and least-square algorithms using the criteria of torque error and root mean square for each joint, the superiority of the IPSO algorithm in parameter identification becomes evident. In this case, the dynamic parameter results of each link are significantly improved.

A new parameter identification model was proposed and validated. Based on the experimental results, the stability of the identification results was improved, providing more accurate parameter identification for further applications.