Active disturbance rejection control with neural network-based ESO for gas turbine control system by fractional...

In this study, an enhanced Active Disturbance Rejection Control (ADRC) strategy is developed for gas turbine systems to achieve superior dynamic performance and robustness. The proposed scheme employs a linear ADRC for fuel regulation and a novel nonlinear ADRC for rotor speed control. Specifically, a multilayer perceptron neural network is integrated with an adaptive term into the extended state observer architecture, effectively handling unmodeled dynamics and external disturbances. To ensure optimal control performance, a fractional-order fuzzy particle swarm optimization algorithm is introduced as a high-dimensional tuning framework. By dynamically adjusting learning factors through fuzzy logic and utilizing fractional-order calculus, this framework overcomes the convergence limitations of standard optimization techniques when tuning multiple interdependent parameters. Simulation results demonstrate that the proposed method yields faster transient responses and significantly higher robustness against disturbances and uncertainties compared to conventional approaches.