Artificial neural network infused quasi oppositional learning partial reinforcement algorithm for structural design optimization of vehicle suspension components

Materials Testing, Год журнала: 2024, Номер unknown

Опубликована: Авг. 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

Язык: Английский

---

Experimental and numerical investigation of crash performances of additively manufactured novel multi-cell crash box made with CF15PET, PLA, and ABS

Materials Testing, Год журнала: 2024, Номер 66(9), С. 1510 - 1518

Опубликована: Авг. 13, 2024

Abstract In this study, a novel multi-cell crash box was designed and produced using 15 % short carbon fiber reinforced polyethylene terephthalate (CF15PET), polylactic acid (PLA), acrylonitrile butadiene styrene (ABS) filaments one of the additive manufacturing methods, melt deposition method (FDM). All structures’ maximum force energy absorption performances have been investigated. As result test, it determined that box, which best meets high folding properties, expected features in boxes, has parts manufactured ABS CF15PET materials. According to test result, found is 11 higher than approximately 4.5 PLA. It response value 5 12 materials can be used boxes form an idea about design by designing analyzing finite element programs.

Язык: Английский

---

Efficient Optimization of Engineering Problems With A Particular Focus on High‐Order IIR Modeling for System Identification Using Modified Dandelion Optimizer

Optimal Control Applications and Methods, Год журнала: 2025, Номер unknown

Опубликована: Фев. 24, 2025

ABSTRACT This paper introduces the modified dandelion optimizer (mDO), a novel adaptive metaheuristic algorithm designed to address complex engineering optimization challenges, with focus on infinite impulse response (IIR) system identification. The proposed mDO incorporates three key advancements: an enhanced descending phase improve global exploration, exploration‐exploitation that balances search intensity and breadth, self‐adaptive crossover operator refines solutions dynamically. These innovations specifically target challenges associated high‐order IIR modeling, enabling deliver more precise efficient To validate its performance, was rigorously evaluated across diverse testing environments, including CEC2017 CEC2022 benchmark functions, various model identification scenarios, real‐world design problems such as multi‐product batch plant design, multiple disk clutch brake speed reducer design. Comparative analyses reveal consistently outperforms leading algorithms in terms of accuracy, robustness, computational efficiency, particularly complex, high‐dimensional landscapes. Statistical assessments further confirm mDO's superior capability accurately identifying parameters even under noise varying orders. study positions competitive versatile tool for applications, offering significant improvements accuracy adaptability advanced modeling problem‐solving.

Язык: Английский

---

Enhancing the performance of a additive manufactured battery holder using a coupled artificial neural network with a hybrid flood algorithm and water wave algorithm

Materials Testing, Год журнала: 2024, Номер 66(10), С. 1557 - 1563

Опубликована: Авг. 8, 2024

Abstract This research is the first attempt in literature to combine design for additive manufacturing and hybrid flood algorithms optimal of battery holders an electric vehicle. article uses a recent metaheuristic explore optimization holder A polylactic acid (PLA) material preferred during manufacturing. Specifically, both algorithm (FLA-SA) water wave optimizer (WWO) are utilized generate holder. The hybridized with simulated annealing algorithm. An artificial neural network employed acquire meta-model, enhancing efficiency. results underscore robustness achieving designs car components, suggesting its potential applicability various product development processes.

Язык: Английский

---

Fishing cat optimizer: a novel metaheuristic technique

Engineering Computations, Год журнала: 2025, Номер unknown

Опубликована: Фев. 10, 2025

Purpose The fishing cat's unique hunting strategies, including ambush, detection, diving and trapping, inspired the development of a novel metaheuristic optimization algorithm named Fishing Cat Optimizer (FCO). purpose this paper is to introduce FCO, offering fresh perspective on demonstrating its potential for solving complex problems. Design/methodology/approach FCO structures process into four distinct phases. Each phase incorporates tailored search strategy enrich diversity population attain an optimal balance between extensive global exploration focused local exploitation. Findings To assess efficacy algorithm, we conducted comparative analysis with state-of-the-art algorithms, COA, WOA, HHO, SMA, DO ARO, using test suite comprising 75 benchmark functions. findings indicate that achieved results 88% functions, whereas SMA which ranked second, excelled only 21% Furthermore, secured average ranking 1.2 across sets CEC2005, CEC2017, CEC2019 CEC2022, superior convergence capability robustness compared other comparable algorithms. Research limitations/implications Although performs excellently in single-objective problems constrained problems, it also has some shortcomings defects. First, structure relatively there are many parameters. value parameters certain impact Second, computational complexity high. When high-dimensional takes more time than algorithms such as GWO WOA. Third, although multimodal rarely obtains theoretical solution when combinatorial Practical implications applied five common engineering design Originality/value This innovatively proposes mimics mechanisms cats, strategies lurking, perceiving, rapid precise trapping. These abstracted closely connected iterative stages, corresponding in-depth exploration, multi-dimensional fine developmental localized refinement contraction search. enables efficient fine-tuning environments, significantly enhancing algorithm's adaptability efficiency.

Язык: Английский

---

Research and Application of Optimization of Physical Education Training Model Based on Multi-Objective Differential Evolutionary Algorithm

Systems and Soft Computing, Год журнала: 2025, Номер unknown, С. 200200 - 200200

Опубликована: Фев. 1, 2025

Язык: Английский

---

A novel pressure control method for nonlinear shell-and-tube steam condenser system via electric eel foraging optimizer

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 4, 2025

Precise pressure control in shell-and-tube steam condensers is crucial for ensuring efficiency thermal power plants. However, traditional controllers (PI, PD, PID) struggle with nonlinearities and external disturbances, while classical tuning methods (Ziegler-Nichols, Cohen-Coon) fail to provide optimal parameter selection. These challenges lead slow response, high overshoot, poor steady-state performance. To address these limitations, this study proposes a cascaded PI-PDN strategy optimized using the electric eel foraging optimizer (EEFO). EEFO, inspired by prey-seeking behavior of eels, efficiently tunes controller parameters, improved stability precision. A comparative analysis against recent metaheuristic algorithms (SMA, GEO, KMA, QIO) demonstrates superior performance EEFO regulating condenser pressure. Additionally, validation documented studies (CSA-based FOPID, RIME-based GWO-based PI, GA-based PI) highlights its advantages over existing methods. Simulation results confirm that reduces settling time 22.7%, overshoot 78.7%, error three orders magnitude, ITAE 81.2% compared based The EEFO-based achieves faster convergence, enhanced robustness precise tracking, making it highly effective solution real-world applications. findings contribute optimization-based strategies plants open pathways further bio-inspired innovations.

Язык: Английский

---

Optimization Model of Steel‐Prestressed Concrete Hybrid Wind Turbine Tower: Using a Combined Differential Whale Optimization Algorithm

The Structural Design of Tall and Special Buildings, Год журнала: 2025, Номер 34(5)

Опубликована: Март 14, 2025

ABSTRACT This study proposes a combined differential whale optimization algorithm (CDWOA) to evaluate the cost model of steel‐prestressed concrete hybrid wind turbine tower (WTT) structures: (1) For WTTs, chosen optimal scale factors F 1 = 0.005 and 2 0.03 lead fast stable WTT structures; (2) establishing relatively complete set design constraints for concrete. also effectually helps overcome key problems large amounts calculation time caused by repeated structural analysis. The results demonstrate that CDWOA offers significant advantages in optimizing WTTs compared traditional algorithms. Particularly ultrahigh exhibits superior applicability. Furthermore, savings achieved increase with height. Finite element analysis indicates primary constraint governing convergence is fatigue strength, aligning well model's calculated results.

Язык: Английский

---

A Modified Black-winged Kite Optimizer Based on Chaotic Maps for Global Optimization of Real-World Applications

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113558 - 113558

Опубликована: Апрель 1, 2025

Язык: Английский

---

Stacking Ensemble Technique Using Optimized Machine Learning Models with Boruta–XGBoost Feature Selection for Landslide Susceptibility Mapping: A Case of Kermanshah Province, Iran

Information, Год журнала: 2024, Номер 15(11), С. 689 - 689

Опубликована: Ноя. 2, 2024

Landslides cause significant human and financial losses in different regions of the world. A high-accuracy landslide susceptibility map (LSM) is required to reduce adverse effects landslides. Machine learning (ML) a robust tool for LSM creation. ML models require large amounts data predict landslides accurately. This study has developed stacking ensemble technique based on optimization enhance accuracy an while considering small datasets. The Boruta–XGBoost feature selection was used determine optimal combination features. Then, intelligent accurate analysis performed prepare using dynamic hybrid approach Adaptive Fuzzy Inference System (ANFIS), Extreme Learning (ELM), Support Vector Regression (SVR), new algorithms (Ladybug Beetle Optimization [LBO] Electric Eel Foraging [EEFO]). After model optimization, weight combine outputs increase reliability LSM. combinations were optimized LBO EEFO. Root Mean Square Error (RMSE) Area Under Receiver Operating Characteristic Curve (AUC-ROC) parameters assess performance these models. dataset from Kermanshah province, Iran, 17 influencing factors evaluate proposed approach. Landslide inventory 116 points, combined Voronoi entropy method applied non-landslide point sampling. results showed higher with EEFO AUC-ROC values 94.81% 94.84% RMSE 0.3146 0.3142, respectively. can help managers planners reliable LSMs and, as result, associated events.

Язык: Английский

---