Soft Computing Using an HPSOGWO variant for Functions Optimization and PMSM Drive Control DOI

S. Bazi,

Redha Benzid,

MS. Nait Said

et al.

Published: Nov. 3, 2024

Language: Английский

Using Crafted Features and Polar Bear Optimization Algorithm for Short-Term Electric Load Forecast System DOI Creative Commons

Mansi Bhatnagar,

Gregor Rozinaj, Radoslav Vargic

et al.

Energy and AI, Journal Year: 2025, Volume and Issue: unknown, P. 100470 - 100470

Published: Jan. 1, 2025

Language: Английский

Citations

1
Optimal distributed generation placement and sizing using modified grey wolf optimization and ETAP for power system performance enhancement and protection adaptation DOI Creative Commons

Nasreddine Bouchikhi,

Fethi Boussadia, Riyadh Bouddou

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 22, 2025

Language: Английский

Citations

0
Research on multi-time scale Volt/VAR optimization in active distribution networks based on NSDBO and MPC approach DOI

Jinhua Zhang,

Jiaxi Wang, Jie Yan

et al.

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 238, P. 111141 - 111141

Published: Oct. 10, 2024

Language: Английский

Citations

3
MHO: A Modified Hippopotamus Optimization Algorithm for Global Optimization and Engineering Design Problems DOI Creative Commons
Tao Han, Haiyan Wang, Tingting Li

et al.

Biomimetics, Journal Year: 2025, Volume and Issue: 10(2), P. 90 - 90

Published: Feb. 5, 2025

The hippopotamus optimization algorithm (HO) is a novel metaheuristic that solves problems by simulating the behavior of hippopotamuses. However, traditional HO may encounter performance degradation and fall into local optima when dealing with complex global engineering design problems. In order to solve these problems, this paper proposes modified (MHO) enhance convergence speed solution accuracy introducing sine chaotic map initialize population, changing factor in growth mechanism, incorporating small-hole imaging reverse learning strategy. MHO tested on 23 benchmark functions successfully three According experimental data, obtains optimal 13 exits optimum faster, has better ordering stability than other nine metaheuristics. This study algorithm, which offers fresh insights practical parameter optimization.

Language: Английский

Citations

0
Development of intelligent controller for high performance electric drives with hybrid CSA and RERNN technique DOI Creative Commons

J. Prabhakaran,

P. Thirumoorthi,

M Mathankumar

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 23, 2025

Language: Английский

Citations

0
Modified Sparrow Search Algorithm by Incorporating Multi-Strategy for Solving Mathematical Optimization Problems DOI Creative Commons
Yunpeng Ma,

Wang Meng,

Xiaolu Wang

et al.

Biomimetics, Journal Year: 2025, Volume and Issue: 10(5), P. 299 - 299

Published: May 8, 2025

The Sparrow Search Algorithm (SSA), proposed by Jiankai Xue in 2020, is a swarm intelligence optimization algorithm that has received extensive attention due to its powerful optimization-seeking ability and rapid convergence. However, similar other algorithms, the SSA problem of being prone falling into local optimal solutions during process, which limits application effectiveness. To overcome this limitation, paper proposes Modified (MSSA), enhances algorithm’s performance integrating three strategies. Specifically, Latin Hypercube Sampling (LHS) method employed achieve uniform distribution initial population, laying solid foundation for global search. An adaptive weighting mechanism introduced producer update phase dynamically adjust search step size, effectively reducing risk optima later iterations. Meanwhile, cat mapping perturbation Cauchy mutation operations are integrated further enhance exploration development efficiency, accelerating convergence process improving quality solutions. This study systematically validates MSSA through multi-dimensional experiments. demonstrates excellent on 23 benchmark test functions CEC2019 standard function set. Its practical engineering problems, namely design welded beams, reducers, cantilever successfully verifies effectiveness real-world scenarios. By comparing it with deterministic algorithms such as DIRET BIRMIN, based five-dimensional generated GKLS generator, thoroughly evaluated. In addition, successful robot path planning highlights advantages complex Experimental results show that, compared original SSA, achieved significant improvements terms speed, accuracy, robustness, providing new ideas methods research algorithms.

Language: Английский

Citations

0
An innovative deep reinforcement learning-driven cutting parameters adaptive optimization method taking tool wear into account DOI

Zhilie Gao,

Ni Chen,

Yingfei Yang

et al.

Measurement, Journal Year: 2024, Volume and Issue: unknown, P. 116075 - 116075

Published: Oct. 1, 2024

Language: Английский

Citations

3
An Early Warning Model for Turbine Intermediate-Stage Flux Failure Based on an Improved HEOA Algorithm Optimizing DMSE-GRU Model DOI Creative Commons
Ming Cheng, Qiang Zhang, Yue Cao

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(15), P. 3629 - 3629

Published: July 24, 2024

As renewable energy sources such as wind and photovoltaics continue to enter the grid, their intermittency instability leads an increasing demand for peaking frequency regulation. An efficient dynamic monitoring method is necessary improve safety level of intelligent operation maintenance power stations. To overcome insufficient detection accuracy poor adaptability traditional methods, a novel fault early warning with careful consideration characteristics model optimization proposed. A combined loss function proposed based on time warping mean square error from perspective both shape similarity similarity. prediction steam turbine intermediate-stage extraction temperature gate recurrent unit then proposed, change in residuals utilized criterion. In order further diagnostic accuracy, human evolutionary algorithm lens opposition-based learning parameter adaptive optimization. Experiments real-world normal faulty operational data demonstrate that can by average 1.31% 1.03% compared long short-term memory network, convolutional neural back propagation extreme machines, gradient boosting decision tree, LightGBM models.

Language: Английский

Citations

2
Model free adaptive control of strip temperature in continuous annealing furnace based on quantum-behaved particle swarm optimization DOI

Hongfei Ding,

Hao Shen,

Ju H. Park

et al.

Nonlinear Dynamics, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 5, 2024

Language: Английский

Citations

2
Design and multiobjective optimization of a two‐point contact ladder‐climbing robot using a genetic algorithm DOI Open Access

Darshita Shah,

Jatin Dave, Mihir Chauhan

et al.

Journal of Field Robotics, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 7, 2024

Abstract This paper presents the design and optimization of a climbing robot. The ladder‐climbing robot is done with fundamental mathematical considerations. designed robust enough to manage all environmental calamities, at same time, it optimized for lightweight reduce actuator's cost ease transportation. An analytical evaluation carried out both static dynamic conditions determine strength motion characteristics. multiobjective parameters obtain values parameters. formulation an problem that considers minimization weight natural frequency performed. Using evolutionary genetic algorithm (GA) multicriteria solved, Pareto front solution obtained. optimal are decided based on knee selection technique. As objective functions contradictory, optimum results significantly improve robot's performance. Controlling proportional–integral–derivative (PID) crucial as climbs two‐point contact gait pattern. controlling impart stability PID like proportional, integral derivative gain tunned using GA. Finally, developed prototype tested ladders tower, satisfactory achieved.

Language: Английский

Citations

1