A new neural network–assisted hybrid chaotic hiking optimization algorithm for optimal design of engineering components DOI
Ahmet Remzi Özcan, Pranav Mehta, Sadiq M. Sait

et al.

Materials Testing, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

Abstract In the era of artificial intelligence (AI), optimization and parametric studies engineering structural systems have become feasible tasks. AI ML (machine learning) offer advantages over classical techniques, which often face challenges such as slower convergence, difficulty handling multiobjective functions, high computational time. Modern techniques may not effectively address all critical design problems despite these advancements. Nature-inspired algorithms based on physical phenomena in nature, human behavior, swarm intelligence, evolutionary principles present a viable alternative for multidisciplinary challenges. This article explores various using newly developed modified hiking algorithm (HOA). The is inspired by hill climbing hiker speed. HOA are compared with those several famous from literature, demonstrating superior results terms statistical measures.

Language: Английский

A novel hybrid Fick’s law algorithm-quasi oppositional–based learning algorithm for solving constrained mechanical design problems DOI
Pranav Mehta, Betül Sultan Yıldız, Sadiq M. Sait

et al.

Materials Testing, Journal Year: 2023, Volume and Issue: 65(12), P. 1817 - 1825

Published: Sept. 13, 2023

Abstract In this article, a recently developed physics-based Fick’s law optimization algorithm is utilized to solve engineering challenges. The performance of the further improved by incorporating quasi-oppositional–based techniques at programming level. modified was applied optimize rolling element bearing system, robot gripper, planetary gear and hydrostatic thrust bearing, along with shape vehicle bracket system. Accordingly, realizes promising statistical results compared rest well-known algorithms. Furthermore, required number iterations comparatively less attain global optimum solution. Moreover, deviations in were least even when other optimizers provided better or more competitive results. This being said that can be adopted for critical wide range industrial real-world challenges optimization.

Language: Английский

Citations

25
Artificial neural network infused quasi oppositional learning partial reinforcement algorithm for structural design optimization of vehicle suspension components DOI
Sadiq M. Sait, Pranav Mehta, Nantiwat Pholdee

et al.

Materials Testing, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 30, 2024

Abstract This paper introduces and investigates an enhanced Partial Reinforcement Optimization Algorithm (E-PROA), a novel evolutionary algorithm inspired by partial reinforcement theory to efficiently solve complex engineering optimization problems. The proposed combines the (PROA) with quasi-oppositional learning approach improve performance of pure PROA. E-PROA was applied five distinct design components: speed reducer design, step-cone pulley weight optimization, economic cantilever beams, coupling bolted rim vehicle suspension arm An artificial neural network as metamodeling is used obtain equations for shape optimization. Comparative analyses other benchmark algorithms, such ship rescue algorithm, mountain gazelle optimizer, cheetah demonstrated superior in terms convergence rate, solution quality, computational efficiency. results indicate that holds excellent promise technique addressing

Language: Английский

Citations

9
Recent applications and advances of African Vultures Optimization Algorithm DOI Creative Commons
Abdelazim G. Hussien, Farhad Soleimanian Gharehchopogh, Anas Bouaouda

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(12)

Published: Oct. 17, 2024

Language: Английский

Citations

9
A multi-strategy enhanced African vultures optimization algorithm for global optimization problems DOI Creative Commons
Rong Zheng, Abdelazim G. Hussien, Raneem Qaddoura

et al.

Journal of Computational Design and Engineering, Journal Year: 2022, Volume and Issue: 10(1), P. 329 - 356

Published: Dec. 14, 2022

Abstract The African vultures optimization algorithm (AVOA) is a recently proposed metaheuristic inspired by the vultures’ behaviors. Though basic AVOA performs very well for most problems, it still suffers from shortcomings of slow convergence rate and local optimal stagnation when solving complex tasks. Therefore, this study introduces modified version named enhanced (EAVOA). EAVOA uses three different techniques namely representative vulture selection strategy, rotating flight selecting accumulation mechanism, respectively, which are developed based on AVOA. strategy strikes good balance between global searches. mechanism utilized to improve quality solution. performance validated 23 classical benchmark functions with various types dimensions compared those nine other state-of-the-art methods according numerical results curves. In addition, real-world engineering design problems adopted evaluate practical applicability EAVOA. Furthermore, has been applied classify multi-layer perception using XOR cancer datasets. experimental clearly show that superiority over methods.

Language: Английский

Citations

30
A systematic review of the emerging metaheuristic algorithms on solving complex optimization problems DOI
Oğuz Emrah Turgut, Mert Sinan Turgut, Erhan Kırtepe

et al.

Neural Computing and Applications, Journal Year: 2023, Volume and Issue: 35(19), P. 14275 - 14378

Published: March 26, 2023

Language: Английский

Citations

20
Optimum design of a composite drone component using slime mold algorithm DOI

Mehmet Kopar,

Ali Rıza Yıldız, Betül Sultan Yıldız

et al.

Materials Testing, Journal Year: 2023, Volume and Issue: 65(12), P. 1857 - 1864

Published: Sept. 22, 2023

Abstract Composite materials have a wide range of applications in many industries due to their manufacturability, high strength values, and light filling. The sector where composite are mostly used is the aviation industry. Today, as result development systems, drones started be actively used, studies carried out mitigate them. In this study, subcarrier part, which part drone, was designed using glass carbon fiber–reinforced materials. Using data obtained at end analysis, stacking angle with optimal displacement stress value determined by genetic algorithm (GA), gray wolf (GWO), slime mold optimization (SMO) techniques order develop carrier minimum more than 60 MPa. As optimization, it that artificial intelligence algorithms could effectively determining materials, optimum values were algorithm.

Language: Английский

Citations

16
A Novel Fault Diagnosis Method for a Power Transformer Based on Multi-Scale Approximate Entropy and Optimized Convolutional Networks DOI Creative Commons
Haikun Shang, Zhidong Liu,

Yanlei Wei

et al.

Entropy, Journal Year: 2024, Volume and Issue: 26(3), P. 186 - 186

Published: Feb. 22, 2024

Dissolved gas analysis (DGA) in transformer oil, which analyzes its content, is valuable for promptly detecting potential faults oil-immersed transformers. Given the limitations of traditional fault diagnostic methods, such as insufficient characteristic components and a high misjudgment rate faults, this study proposes diagnosis model based on multi-scale approximate entropy optimized convolutional neural networks (CNNs). This introduces an improved sparrow search algorithm (ISSA) optimizing CNN parameters, establishing ISSA-CNN model. The dissolved oil are analyzed, content under different modes calculated. computed values then used feature parameters to derive results. Experimental data demonstrates that effectively characterizes significantly improving efficiency. Comparative with BPNN, ELM, CNNs validates effectiveness superiority proposed across various evaluation metrics.

Language: Английский

Citations

7
The application of project management methodology in the training of college students' innovation and entrepreneurship ability under sustainable education DOI Creative Commons
Hailing Wei,

Ailing Ding,

Zhiqiang Gao

et al.

Systems and Soft Computing, Journal Year: 2024, Volume and Issue: 6, P. 200073 - 200073

Published: Jan. 25, 2024

With the rapid development of society and rise knowledge economy, cultivating innovation entrepreneurship abilities college students has gradually become an important task higher education. However, in current educational environment, cultivation among faces a series issues, such as disconnect between practice, singularity training methods. To address these analysis existing education was conducted using project management method. A combination model for constructed Analytic Hierarchy Process (AHP) entropy Considering that talent belongs to complex nonlinear solving problem, advanced ABC-BP adopted handle linear data problem model. Among them, Back Propagation (BP) used train refine parameters model, explore optimal factors. BP is prone local convergence parameterization problems, Artificial Bee Colony (ABC) algorithm optimized improved effect enhanced application abilities. In test compared with classic Particle Swarm Optimization (PSO) proposed had lower overall RMSE, greater optimization precision faster speed terms results. Compared PSO increased by 14%. The selected solve According solution results, highest comprehensive score scheme 1 0.57, finally best training. This study reference significance innovative entrepreneurial talents China. Through AHP methods, effectiveness can be improved, more cultivated meet needs rapidly developing economy.

Language: Английский

Citations

6
A Comprehensive Survey on African Vulture Optimization Algorithm DOI
Buddhadev Sasmal, Arunita Das, Krishna Gopal Dhal

et al.

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 31(3), P. 1659 - 1700

Published: Nov. 30, 2023

Language: Английский

Citations

13
Quantum Chimp Optimization Algorithm: A Novel Integration of Quantum Mechanics Into the Chimp Optimization Framework for Enhanced Performance DOI Open Access

Meng Yu,

Mohammad Khishe,

Leren Qian

et al.

Journal of Artificial Intelligence and Soft Computing Research, Journal Year: 2024, Volume and Issue: 14(4), P. 321 - 359

Published: July 1, 2024

Abstract This research introduces the Quantum Chimp Optimization Algorithm (QChOA), a pioneering methodology that integrates quantum mechanics principles into (ChOA). By incorporating non-linearity and uncertainty, QChOA significantly improves ChOA’s exploration exploitation capabilities. A distinctive feature of is its ability to displace ’chimp,’ representing potential solution, leading heightened fitness levels compared current top search agent. Our comprehensive evaluation includes twenty- nine standard optimization test functions, thirty CEC-BC CEC06 suite, ten real-world engineering challenges, IEEE CEC 2022 competition’s dynamic problems. Comparative analyses involve four ChOA variants, three quantum-behaved algorithms, state-ofthe-art eighteen benchmarks. Employing non-parametric statistical tests (Wilcoxon rank-sum, Holm-Bonferroni, Friedman average rank tests), results show outperforms counterparts in 51 out 70 scenarios, exhibiting performance on par with SHADE CMA-ES, equivalence jDE100 DISHchain1e+12. The study underscores QChOA’s reliability adaptability, positioning it as valuable technique for diverse intricate challenges field.

Language: Английский

Citations

5