Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems

Yaoyu Han

doi:10.47297/taposatWSP2633-456914.20250609

PDF
导出
分享
收藏
专辑

Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems

6卷第9期

浏览量: 0 Downloads: 2

Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems
Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems
School of Marine Engineering, Dalian Maritime University, Marine Engineering (Onshore), Dalian, Liaoning, 116026, China
2025年6卷第9期页码：71-74
纸质出版：2025-09-30
DOI：10.47297/taposatWSP2633-456914.20250609
Accepted：

Scan QR Code

Yaoyu Han. (2025). Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems. 科技理论与实践（英文版）, 6(9), 71-74.

Han Yaoyu.Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems[J].Theory and Practice of Science and Technology,2025,06(09):71-74.
Yaoyu Han. (2025). Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems. 科技理论与实践（英文版）, 6(9), 71-74. DOI： 10.47297/taposatWSP2633-456914.20250609.

Han Yaoyu.Research on Dynamic Optimization and Intelligent Control Methods for Ship Exhaust Gas Treatment Systems[J].Theory and Practice of Science and Technology,2025,06(09):71-74. DOI： 10.47297/taposatWSP2633-456914.20250609.

摘要

Abstract

This study addresses the fluctuations in efficiency and high energy consumption of ship exhaust gas treatment systems under complex operating conditions by proposing dynamic optimization and intelligent control methods. Emission prediction is conducted using a Bi-LSTM (Bidirectional Long Short-Term Memory) network enhanced with an attention mechanism. An improved multi-objective particle swarm optimization algorithm (IMOPSO) is introduced to balance removal efficiency

energy consumption

and reagent usage. Furthermore

a hierarchical reinforcement learning framework combining feedforward and feedback mechanisms is constructed to achieve adaptive regulation. Simulation results demonstrate that this approach improves prediction accuracy and control flexibility

ensures high removal efficiency

and reduces energy and reagent consumption

providing a feasible pathway for intelligent and green ship exhaust gas treatment.

关键词

Keywords

references

Chen Yue. Optimization Design and Simulation Analysis of Hydrogen Fuel Cell-Lithium Ion Battery Hybrid Power System for Ships [D]. Guangxi: Guangxi Normal University, 2024.

Chen Hao, Sun Gang, Peng Shuang, et al. Dynamic Rescheduling Method for Measurement, Control, and Data Transmission Resources Based on Multi-Objective Optimization [J]. Systems Engineering and Electronics, 2024, 46(11): 3744-3753.

Song Weiwei, Xu Yuebing, Duan Xuejing, et al. Research on Intelligent Control of Ship Bow Thruster Based on Real-Time Feedback Reinforcement Learning Neural Network [J]. Modern Information Technology, 2024, 8(8): 83-88.

Zhou Yi, Li Meng, Zhao Zhongqiu, et al. Green Upgrade Route of a Fleet Based on IMO Greenhouse Gas Reduction Strategy [J]. Marine Engineering Equipment and Technology, 2025, 12(2): 173-178.

Mylonopoulos F, Polinder H, Coraddu A. A Comprehensive Review of Modeling and Optimization Methods for Ship Energy Systems [J]. IEEE Access, 2023, 11: 38108–38128.

文章被引用时，请邮件提醒。

Submit

An overview of the optimization of motor protection mechanisms

Related Author

Junyan Xia College of Mechanical and Electrical Engineering, HoHai University

Related Institution

College of Mechanical and Electrical Engineering, HoHai University

⁰