Research and Design of Improved Wild Horse Optimizer-Optimized Fuzzy Neural Network PID Control Strategy for EC Regulation of Cotton Field Water and Fertilizer Systems DOI Creative Commons
Hao Wang, Lixin Zhang, Huan Wang

et al.

Agriculture, Journal Year: 2023, Volume and Issue: 13(12), P. 2176 - 2176

Published: Nov. 21, 2023

Xinjiang is the largest cotton-producing region in China, but it faces a severe shortage of water resources. According to relevant studies, cotton yield does not significantly decrease under appropriate limited conditions. Therefore, this paper proposes and fertilizer integrated control system achieve conservation process field cultivation. This designs fuzzy neural network Proportional–Integral–Derivative controller based on improved Wild Horse Optimizer address system’s time-varying, lag, non-linear characteristics. The precisely controls electrical conductivity (EC) by optimizing parameters through an for initial weights from normalization layer output layer, center values membership functions, base width functions network. performance validated MATLAB simulation experimental tests. results indicate that, compared with conventional PID controllers controllers, exhibits excellent accuracy robustness, effectively achieving precise fertilization.

Language: Английский

Technical and Optimization Insights into PV Penetration in Power Distribution Systems-based Wild Horse Algorithm: Real Cases on Egyptian Networks DOI Creative Commons
Asmaa Nasef, Mohammed H. Alqahtani,

Abdullah M. Shaheen

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104603 - 104603

Published: March 1, 2025

Language: Английский

Citations

2
MRSO: Balancing Exploration and Exploitation through Modified Rat Swarm Optimization for Global Optimization DOI Creative Commons
Hemin Sardar Abdulla, Azad A. Ameen,

Sarwar Ibrahim Saeed

et al.

Algorithms, Journal Year: 2024, Volume and Issue: 17(9), P. 423 - 423

Published: Sept. 23, 2024

The rapid advancement of intelligent technology has led to the development optimization algorithms that leverage natural behaviors address complex issues. Among these, Rat Swarm Optimizer (RSO), inspired by rats’ social and behavioral characteristics, demonstrated potential in various domains, although its convergence precision exploration capabilities are limited. To these shortcomings, this study introduces Modified (MRSO), designed enhance balance between exploitation. MRSO incorporates unique modifications improve search efficiency robustness, making it suitable for challenging engineering problems such as Welded Beam, Pressure Vessel, Gear Train Design. Extensive testing with classical benchmark functions shows significantly improves performance, avoiding local optima achieving higher accuracy six out nine multimodal all seven fixed-dimension functions. In CEC 2019 benchmarks, outperforms standard RSO ten functions, demonstrating superior global capabilities. When applied design problems, consistently delivers better average results than RSO, proving effectiveness. Additionally, we compared our approach eight recent well-known using both CEC-2019 benchmarks. outperformed each algorithms, 23 four These further demonstrate MRSO’s significant contributions a reliable efficient tool tasks applications.

Language: Английский

Citations

2
Optimizing Multi-Layer Perovskite Solar Cell Dynamic Models with Hysteresis Consideration Using Artificial Rabbits Optimization DOI Creative Commons

Ahmed Saeed Abdelrazek Bayoumi,

Ragab A. El‐Sehiemy, Mahmoud Badawy

et al.

Mathematics, Journal Year: 2023, Volume and Issue: 11(24), P. 4912 - 4912

Published: Dec. 9, 2023

Perovskite solar cells (PSCs) exhibit hysteresis in their J-V characteristics, complicating the identification of appropriate electrical models and determination maximum power point. Given rising prominence PSCs due to potential for superior performance, there is a pressing need address this challenge. Existing solutions literature have not fully addressed issue, especially context dynamic modeling. To bridge gap, study introduces Artificial Rabbits Optimization (ARO) as an innovative method optimizing parameters enhanced PSC model. The proposed model constructed based on experimental data sets PSCs, ensuring that it accounts characteristics observed both forward backward scans. conducted rigorous statistical analysis validate Modified Two-Diode Model performance with Energy Balance (MTDM_E) optimized using ARO algorithm. metric utilized validation was Root mean square error (RMSE), widely recognized degree differences between values predicted by observed. encompassed 30 independent runs ensure robustness reliability results. summary statistics MTDM_E under algorithm demonstrated minimum RMSE 4.84E−04, 6.44E−04, 5.14E−04. median reported 5.07E−04, standard deviation 3.17E−05, indicating consistent tight clustering results around mean, which suggests high level precision model’s performance. Validated root (RMSE) across runs, showcased parameter model, 5.14E−04, outperforming other algorithms like GWO, PSO, SCA, SSA. This affirms ARO’s cell models.

Language: Английский

Citations

4
An improved wild horse optimization algorithm based on reinforcement learning for numerical and engineering optimizations DOI
Mengyao Xi, Hao Liu

The Journal of Supercomputing, Journal Year: 2024, Volume and Issue: 81(1)

Published: Nov. 18, 2024

Language: Английский

Citations

0
Research and Design of Improved Wild Horse Optimizer-Optimized Fuzzy Neural Network PID Control Strategy for EC Regulation of Cotton Field Water and Fertilizer Systems DOI Creative Commons
Hao Wang, Lixin Zhang, Huan Wang

et al.

Agriculture, Journal Year: 2023, Volume and Issue: 13(12), P. 2176 - 2176

Published: Nov. 21, 2023

Xinjiang is the largest cotton-producing region in China, but it faces a severe shortage of water resources. According to relevant studies, cotton yield does not significantly decrease under appropriate limited conditions. Therefore, this paper proposes and fertilizer integrated control system achieve conservation process field cultivation. This designs fuzzy neural network Proportional–Integral–Derivative controller based on improved Wild Horse Optimizer address system’s time-varying, lag, non-linear characteristics. The precisely controls electrical conductivity (EC) by optimizing parameters through an for initial weights from normalization layer output layer, center values membership functions, base width functions network. performance validated MATLAB simulation experimental tests. results indicate that, compared with conventional PID controllers controllers, exhibits excellent accuracy robustness, effectively achieving precise fertilization.

Language: Английский

Citations

0