Actuator–Fault–Tolerant Adaptive Tracking Control of Delayed Fuzzy Systems Using Reinforcement Learning

In nonlinear systems, monitoring control behavior, fault occurrence, and latency factor continue to be major obstacles. Traditional control models frequently handle edge–case situations inaccurately and are unable to adjust to dynamic changes. Reinforcement learning control is a novel intelligent framework that incorporates sophisticated modules for nonlinear models in order to overcome these constraints. First, an innovative approach to solving the adaptive tracking algorithm for a type of T–S fuzzy plant is presented in this research. Furthermore, the authors examine time–varying delay with the actuator failure for complex systems that are generally represented by the T–S fuzzy plant. Second, it has been demonstrated that the chosen performance index solves the delayed algebraic Riccati formula, which can be resolved by scheme of repetition methods, when the resultant plant with the tracking signal is constructed under the decoupling delayed T–S fuzzy framework. Third, the coupled delayed algebraic Riccati formulas are then solved using a Reinforcement Learning (RL) technique that makes use of complex model dynamics knowledge. Furthermore, the fundamental RL iteration technique’s convergence is demonstrated. Lastly, the power sector and a F–16 airplane flight examples are provided to demonstrate how the online repetition method outperforms the offline one in terms of tracking accuracy and effectiveness. Note to Practitioners—This work bridges the gap between theoretical reinforcement learning techniques and practical control applications in dynamic and uncertain environments, providing a scalable, adaptive solution for high–reliability systems. Contemporary industrial systems like those in the power sector and manned aircraft (F–16)–increasingly face challenges involving nonlinear factors, actuator faults, and communication delays. This research introduces a reinforcement learning (RL)–based control approach tailored for systems modeling using Takagi–Sugeno (T–S) fuzzy logic, which is well–suited for capturing nonlinear actions. The proposed method integrates an adaptive tracking mechanism with delay compensation and fault dealing with making it highly relevant to real–world scenarios involving uncertain and time–varying circumstances.