Research on Complex Multi Objective Systems Based on Intelligent Feedback Optimization Framework and Improved Genetic Algorithm
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
In complex systems characterized by nonlinear coupling and dynamic constraints, multi-objective optimization is the core challenge of intelligent decision-making. Traditional methods are difficult to meet the requirements due to limited modeling capabilities and poor algorithm convergence. Therefore, this article proposes the MIND-F intelligent feedback optimization framework to solve problems such as target conflicts and dynamic changes in constraints in high-dimensional systems. The framework includes three layers of mechanisms: multi-objective coupling modeling, intelligent evolutionary optimization, and feedback regulation. Global search and local optimization are achieved through improved genetic algorithms, and dynamic constraint perception is introduced to enhance the system's anti-interference ability. Experiments have shown that this framework outperforms traditional algorithms such as NSGA-II in terms of convergence efficiency and feasible solution ratio. It exhibits strong robustness under dynamic disturbances and provides transferable modeling and algorithm solutions for complex system optimization.
Fields of Study & Subjects
Advanced Multi-Objective Optimization Algorithms
Metaheuristic Optimization Algorithms Research
Optimization and Mathematical Programming
Publication details
- Journal / source
- IEEE International Conference on Power, Electronics and Green Energy (ICPEGE)
- Pages
- 347–354
- Publication date
- 28 January 2026
- Language
- EN