Search results

This paper aims to investigate three low-evaluation-budget optimization techniques: output space mapping (OSM), manifold mapping (MM) and Kriging-OSM. Kriging-OSM is an original approach having high-order mapping.

The electromagnetic device to be optimally sized is a five-phase linear induction motor, represented through two levels of modeling: coarse (Kriging model) and fine.The optimization comparison of the three techniques on the five-phase linear induction motor is discussed.

The optimization results show that the OSM takes more time and iteration to converge the optimal solution compared to MM and Kriging-OSM. This is mainly because of the poor quality of the initial Kriging model. In the case of a high-quality coarse model, the OSM technique would show its domination over the other two techniques. In the case of poor quality of coarse model, MM and Kriging-OSM techniques are more efficient to converge to the accurate optimum.

Kriging-OSM is an original approach having high-order mapping. An advantage of this new technique consists in its capability of providing a sufficiently accurate model for each objective and constraint function and makes the coarse model converge toward the fine model more effectively.

The purpose of this paper is to present a low evaluation budget optimization strategy for expensive simulation models, such as 3D finite element models.

A 3D finite element electromagnetic model and a thermal model are developed and coupled in order to simulate the linear induction motor (LIM) to be conceived. Using the 3D finite element coupling model as a simulation model, a multi‐objective optimization with a progressive improvement of a surrogate model is proposed. The proposed surrogate model is progressively improved using an infill set selection strategy which is well‐suited for the parallel evaluation of the 3D finite element coupling model on an eight‐core machine, with a maximum of four models running in parallel.

The proposed strategy allows for a significant gain of optimization time. The 3D Pareto front composed of the finite element model evaluation results is obtained, which provides the designer with a set of optimal trade‐off solutions for him/her to make the final decision for the engineering design.

An infill set selection strategy is proposed, which allows the parallel evaluation of the finite element model, and at the same time guides the progressive construction of an improved surrogate model during the multi‐objective optimization run. The paper may stand as a good reference for researchers/engineering designers who have to deal with optimal design problems implying costly simulation models.

The purpose of this paper is to apply some surrogate-assisted optimization techniques in order to improve the performances of a five-phase permanent magnet machine in the context of a complex model requiring computation time.

An optimal control of four independent currents is proposed in order to minimize the total losses with the respect of functioning constraints. Moreover, some geometrical parameters are added to the optimization process allowing a co-design between control and dimensioning.

The optimization results prove the remarkable effect of using the freedom degree offered by a five-phase structure on iron and magnets losses. The performances of the five-phase machine with concentrated windings are notably improved at high speed (16,000 rpm).

The effectiveness of the method allows solving the challenge which consists in taking into account inside the control strategy the eddy-current losses in magnets and iron. In fact, magnet losses are a critical point to protect the machine from demagnetization in flux-weakening region.

This study aims to explore the adoption of FinTech payment services among women. It assesses the phenomenon through the impact of personality traits and financial services knowledge and investigates the moderated-mediation role of the artificial intelligence.

Adopting the technology acceptance model, this study implied a quantitative survey to collect data from the women (N = 220). The relationship among the variables were assessed through Hayes’ PROCESS moderation-mediation model, with a robustness check through structural equation modeling (SEM) that substantiates the study’s findings.

The results showed that the women with high agreeableness and openness are inclined to use FinTech payment services. Moreover, high-level banking services and FinTech usage knowledge positively correlated to the usage of FinTech payment services. In addition, artificial intelligence positively influences the use of FinTech payment services among women.

This study offers policymakers a roadmap to make FinTech payment services more accessible among women through financial services knowledge and the use of artificial intelligence. This will advance the progress toward United Nations’ Sustainable Development Goals on gender equality and innovation.

This study reinforces the prospect of women’s empowerment through FinTech, paving way to explore the prospective mechanism for a complete shift to digitalization of economy to promote economic transparency.

To the best of the authors’ knowledge, this is amongst the first studies that investigates the role of big-five personality traits and artificial intelligence in enhancing the usage of FinTech payment services among women. The innovative nature of this study promotes financial inclusion among the female population and opens up new research avenues to promote FinTech adoption.