A new enhanced mountain gazelle optimizer and artificial neural network for global optimization of mechanical design problems

Materials Testing, Год журнала: 2024, Номер 66(4), С. 544 - 552

Опубликована: Янв. 24, 2024

Abstract Nature-inspired metaheuristic optimization algorithms have many applications and are more often studied than conventional techniques. This article uses the mountain gazelle optimizer, a recently created algorithm, artificial neural network to optimize mechanical components in relation vehicle component optimization. The family formation, territory-building, food-finding strategies of gazelles serve as major inspirations for algorithm. In order various engineering challenges, base algorithm (MGO) is hybridized with Nelder–Mead (HMGO-NM) current work. considered was applied solve four different categories, namely automobile, manufacturing, construction, tasks. Moreover, obtained results compared terms statistics well-known algorithms. findings show dominance over rest optimizers. being said HMGO can be common range industrial real-world problems.

Язык: Английский

---

Enhancing the structural performance of engineering components using the geometric mean optimizer

Materials Testing, Год журнала: 2024, Номер 66(7), С. 1063 - 1073

Опубликована: Апрель 30, 2024

Abstract In this article, a newly developed optimization approach based on mathematics technique named the geometric mean algorithm is employed to address challenge of robot gripper, airplane bracket, and suspension arm automobiles, followed by an additional three engineering problems. Accordingly, other challenges are ten-bar truss, three-bar tubular column, spring systems. As result, demonstrates promising statistical outcomes when compared well-established algorithms. Additionally, it requires less iteration achieve global optimum solution. Furthermore, exhibits minimal deviations in results, even techniques produce better or similar outcomes. This suggests that proposed paper can be effectively utilized for wide range critical industrial real-world challenges.

Язык: Английский

---

Crash performance of a novel bio-inspired energy absorber produced by additive manufacturing using PLA and ABS materials

Materials Testing, Год журнала: 2024, Номер 66(5), С. 696 - 704

Опубликована: Фев. 19, 2024

Abstract Thin-walled structures are one of the important safety components used in vehicles. They placed front parts vehicles to minimize impacts that occur event a collision, and they absorb impact force by changing shape collision. Crash boxes have high-impact absorption, low weight, low-cost expectations. In design crash boxes, thin-walled preferred due their high deformation capability. this study, additive manufacturing method was produce structures. were produced methods using PLA ABS materials. The manufactured tested an test. experimental results, energy absorption ability from materials examined, fragility observed. results verified finite element analysis made

Язык: Английский

---

Optimization of electric vehicle design problems using improved electric eel foraging optimization algorithm

Materials Testing, Год журнала: 2024, Номер 66(8), С. 1230 - 1240

Опубликована: Июль 5, 2024

Abstract This paper introduces a novel approach, the Modified Electric Eel Foraging Optimization (EELFO) algorithm, which integrates artificial neural networks (ANNs) with metaheuristic algorithms for solving multidisciplinary design problems efficiently. Inspired by foraging behavior of electric eels, algorithm incorporates four key phases: interactions, resting, hunting, and migrating. Mathematical formulations each phase are provided, enabling to explore exploit solution spaces effectively. The algorithm’s performance is evaluated on various real-world optimization problems, including weight engineering components, economic pressure handling vessels, cost welded beams. Comparative analyses demonstrate superiority MEELFO in achieving optimal solutions minimal deviations computational effort compared existing methods.

Язык: Английский

---

Experimental analysis of the effects of different production directions on the mechanical characteristics of ABS, PLA, and PETG materials produced by FDM

Materials Testing, Год журнала: 2024, Номер 66(2), С. 198 - 206

Опубликована: Янв. 8, 2024

Abstract One of the most researched technologies among used for producing complex and diverse parts today is additive manufacturing. In manufacturing, production can be carried out using thermoplastic metal materials without requiring an additional process. Among manufacturing technologies, Fused Filament Fabrication (FFF) method widely worldwide due to its affordability broad application area. FFF a in which part formation achieved by depositing melted on each other. recent years, polymer such as polylactic acid (PLA), polyethylene terephthalate glycol (PETG), acrylonitrile butadiene styrene (ABS) have been frequently many industrial areas because they are lightweight, inexpensive, sustainable, provide sufficient strength engineering applications. This study conducted tensile, three-point bending, Charpy, compression tests PLA, PETG, ABS at angles 15°–75° 30°–60°, results were compared.

Язык: Английский

---

Experimental Investigation on Mechanical properties of CF15PET and GF30PP materials produced with different raster angles

Materials Testing, Год журнала: 2024, Номер 66(6), С. 847 - 855

Опубликована: Март 22, 2024

Abstract In recent years, additive manufacturing (AM) technologies have been used in many industries, such as automotive, defense, space, and aviation. Depending on the development of this technology, effect relationship between parameters, raster angles, production speed, melting temperature during materials, has an important issue mechanical properties materials. study, effects ±45° 0–90° angles 15 % short carbon fiber reinforced polyethylenetereflatate (CF15PET) 30 glass polypropylene (GF30PP) materials were investigated. As a result it was determined that different affect both

Язык: Английский

---

A regularized constrained two-stream convolution augmented Transformer for aircraft engine remaining useful life prediction

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108161 - 108161

Опубликована: Март 11, 2024

Язык: Английский

---

Solving Engineering Optimization Problems Based on Multi-Strategy Particle Swarm Optimization Hybrid Dandelion Optimization Algorithm

Biomimetics, Год журнала: 2024, Номер 9(5), С. 298 - 298

Опубликована: Май 17, 2024

In recent years, swarm intelligence optimization methods have been increasingly applied in many fields such as mechanical design, microgrid scheduling, drone technology, neural network training, and multi-objective optimization. this paper, a multi-strategy particle hybrid dandelion algorithm (PSODO) is proposed, which based on the problems of slow speed being easily susceptible to falling into local extremum ability algorithm. This makes whole more diverse by introducing strong global search unique individual update rules (i.e., rising, landing). The ascending descending stages also help introduce changes explorations space, thus better balancing search. experimental results show that compared with other algorithms, proposed PSODO greatly improves optimal value ability, convergence speed. effectiveness feasibility are verified solving 22 benchmark functions three engineering design different complexities CEC 2005 comparing it algorithms.

Язык: Английский

---

Deep learning based multi-source heterogeneous information fusion framework for online monitoring of surface quality in milling process

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108043 - 108043

Опубликована: Фев. 13, 2024

Язык: Английский

---

Transfer learning for improved generalizability in causal physics-informed neural networks for beam simulations

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108085 - 108085

Опубликована: Фев. 18, 2024

This paper proposes a novel framework for simulating the dynamics of beams on elastic foundations. Specifically, partial differential equations modeling Euler–Bernoulli and Timoshenko Winkler foundation are simulated using causal physics-informed neural network (PINN) coupled with transfer learning. Conventional PINNs encounter challenges in handling large space–time domains, even problems closed-form analytical solutions. A causality-respecting PINN loss function is employed to overcome this limitation, effectively capturing underlying physics. However, it observed that lacks generalizability. We propose solutions similar instead training from scratch by employing learning while adhering causality accelerate convergence ensure accurate results across diverse scenarios. The primary contribution lies introducing context structural engineering coupling enhance generalizability Numerical experiments beam highlight efficacy proposed approach various initial conditions, including those noise data. Furthermore, potential method demonstrated an extended spatial temporal domain. Several comparisons suggest accurately captures inherent dynamics, outperforming state-of-the-art methods under standard L2-norm metric accelerating convergence.

Язык: Английский

---