Artificial Intelligence-Driven Control of Time Delay Systems: A Comprehensive Review, Bibliometric Analysis, and Future Research Framework

Time-delay systems (TDSs) arise in many engineering applications where sensing, actuation, computation, transport, or communication delays affect closed-loop stability and performance. Classical control methods, including predictor-based control, Lyapunov–Krasovskii functional approaches, robust control, model predictive control, and adaptive control, provide rigorous theoretical foundations for delay compensation and stability analysis. However, their effectiveness may be limited when the system is nonlinear, uncertain, poorly modeled, or subject to unknown and time-varying delays. In recent years, artificial intelligence (AI)-based methods, such as neural networks, fuzzy systems, deep learning, and reinforcement learning, have attracted increasing attention for their capabilities in learning, approximation, prediction, and adaptation. This paper presents a comprehensive review and bibliometric analysis of control strategies for TDSs, with an emphasis on the interactions among classical, AI-based, and hybrid methods. Publications indexed in the Web of Science database from 2010 to 2025 are analyzed using bibliometrix and VOSviewer to identify publication trends, influential contributors, collaboration patterns, citation structures, and thematic evolution. In addition, a unified framework is proposed to classify TDS control strategies into classical, AI-based, and hybrid categories. The results show that classical stability and robustness analysis remain central to the field, while AI-based and hybrid methods are increasingly used to address nonlinearities, uncertainties, communication delays, and real-time implementation challenges. Finally, key research gaps and future directions are discussed, including stability-guaranteed learning, learning-based delay compensation, interpretable AI control, benchmarking, and practical deployment in cyber-physical, robotic, aerospace, and networked systems.