Performance Analysis of Advanced Metaheuristics for Optimal Design of Multi-Objective Model Predictive Control of Doubly Fed Induction Generator

Processes, Год журнала: 2025, Номер 13(1), С. 221 - 221

Опубликована: Янв. 14, 2025

Finite control set model predictive (FCS-MPC) is an attractive method for electric drives. This primarily due to the ease of implementation and robust responses. When applied rotor current Doubly Fed Induction Generator (DFIG), FCS-MPC has thus far exhibited promising results when compared conventional Proportional Integral strategy. Recently, there been research conducted regarding reduction in switching frequency FCS-MPC. Preliminary studies indicate that a will result larger ripples greater total harmonic distortion (THD). However, this area limited. The aim study two-fold. Firstly, indication into effect weighting factor magnitude on ripple provided. Thereafter, work provides insight such overall DFIG attempts determine optimal which simultaneously reduce keep within acceptable limits. To tune relevant factor, utilization swam intelligence deployed. Three swarm techniques, particle optimization, African Vulture Optimization Algorithm, Gorilla Troops Optimizer (GTO), are achieve factor. 2 MW DFIG, indicated owing their strong exploitation capability, these algorithms were able successfully frequency. GTO best results, boasting steady-state errors 0.03% 0.02% direct quadrature currents whilst reducing by up 0.7%. as expected, was minor increase ripple. A robustness test use metaheuristics still produces superior face changing operating conditions. instill confidence strategy choice, wind energy conversion systems continue penetrate sector.

Язык: Английский

---

A performance comparison of eight meta-heuristic algorithms for the optimal design of large-scale truss structures

Journal of the Brazilian Society of Mechanical Sciences and Engineering, Год журнала: 2025, Номер 47(3)

Опубликована: Фев. 12, 2025

Язык: Английский

---

A Labor Division Artificial Gorilla Troops Algorithm for Engineering Optimization

Biomimetics, Год журнала: 2025, Номер 10(3), С. 127 - 127

Опубликована: Фев. 20, 2025

The Artificial Gorilla Troops Optimizer (GTO) has emerged as an efficient metaheuristic technique for solving complex optimization problems. However, the conventional GTO algorithm a critical limitation: all individuals, regardless of their roles, utilize identical search equations and perform exploration exploitation sequentially. This uniform approach neglects potential benefits labor division, consequently restricting algorithm’s performance. To address this limitation, we propose enhanced Labor Division (LDGTO), which incorporates natural mechanisms division outcome allocation. In phase, stimulus-response model is designed to differentiate tasks, enabling gorilla individuals adaptively adjust based on environmental changes. allocation three behavioral development modes—self-enhancement, competence maintenance, elimination—are implemented, corresponding developmental stages: elite, average, underperforming individuals. performance LDGTO rigorously evaluated through benchmark test suites, comprising 12 unimodal, 25 multimodal, 10 combinatorial functions, well two real-world engineering applications, including four-bar transplanter mechanism design color image segmentation. Experimental results demonstrate that consistently outperforms variants seven state-of-the-art algorithms in most cases.

Язык: Английский

---

Comparative study on prediction of coal seam gas extraction based on Extreme Gradient Boosting and random forest model improved by optimization algorithm

Physics of Fluids, Год журнала: 2025, Номер 37(3)

Опубликована: Март 1, 2025

Gas, a silent and deadly hazard in coal mines, poses significant risk of seam gas outbursts excessive emissions. Effective drainage is crucial for mitigating these risks. This study focuses on the characteristics 21 601 transports gallery Qinglong mine, selecting stage, negative pressure, concentration as input variables, with volume output variable. We have integrated XGBoost (Extreme Gradient Boosting) random forest (RF) algorithms Bayesian, Sparrow, Scarab, Gorilla optimization algorithms—establishing composite model predicting volume. Our research indicates that predictive performance models optimized by surpasses other models. Specifically, algorithm outperforms RF Among tested, OP (Bayesian optimization) demonstrated poorest fit highest error rates. In terms validation set performance, XG-GTO (Gorilla combined algorithm) excelled, metrics MAE (mean absolute error) = 0.217 82, MAPE percentage 0.1149, MSE square 0.082 153, RMSE (root mean 0.286 62, R2 (coefficient determination) 0.920 59. Furthermore, Shapley additive explanations revealed has most impact drainage. not only furnishes robust data support construction mine big but also holds substantial value development intelligent systems enhancement technologies.

Язык: Английский

---

Tomato maturity detection based on bioelectrical impedance spectroscopy

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 227, С. 109553 - 109553

Опубликована: Ноя. 12, 2024

Язык: Английский

---