A SYSTEMATIC REVIEW AND META-ANALYSIS OF GENETIC ALGORITHMS, PARTICLE SWARM OPTIMIZATION, AND HYBRID AI-BASED METAHEURISTICS IN STRUCTURAL DYNAMIC DESIGN AND VIBRATION CONTROL

Abstract

Structural dynamic design and vibration control are critical challenges in engineering, where metaheuristic optimization algorithms have emerged as powerful tools for performance enhancement. This systematic review and meta-analysis aimed to evaluate the effectiveness of genetic algorithms, particle swarm optimization, and hybrid artificial intelligence-based methods in improving structural performance under dynamic loading and vibration conditions. We systematically examined studies that reported computational efficiency metrics, specifically convergence generations or function evaluations, as primary outcomes. The meta-analysis incorporated data from multiple eligible studies, and we computed standardized mean differences to quantify the relative performance gains. Results indicated that hybrid approaches significantly outperformed standalone algorithms, with an overall effect size of  (95% confidence interval: , ). A subgroup analysis revealed that particle swarm optimization achieved the fastest convergence rates (), while hybrid methods demonstrated the greatest robustness in vibration control applications. The heterogeneity across studies was substantial, suggesting that algorithmic efficacy is highly dependent on structural complexity and loading conditions. Our findings further showed that convergence performance improvements were statistically significant in 82% of the included comparisons. These results lead to the conclusion that metaheuristic algorithms, particularly hybrid configurations, provide reliable and efficient solutions for structural dynamic design problems. However, the observed variability underscores the need for standardized benchmarking frameworks and more extensive validation studies. This review synthesizes current evidence and offers practical guidance for selecting appropriate optimization strategies in structural engineering applications.