Over the last few years, improving power extraction from the wind energy conversion system (WECS) under varying wind speeds has become a complex task. The current study presents the optimum maximum power point tracking (MPPT) control approach integrated with neural network (NN)-based rotor speed control and pitch angle control to extract the maximum power from the WECS. So, this study presents a reference model adaptive control (RMAC) for a direct-drive (DD) permanent magnet vernier generator (PMVG)-based WECS under real wind speed conditions. Initially, the RMAC-based rotor speed tracking control is presented with adaptive terms, which tracks a reference model that guarantees the expected exponential decay of rotor speed error trajectory. Then, to reduce the wind speed measurement errors, a recurrent neural network (RNN)-based training model is presented. Moreover, the asymptotic stability of the proposed control method is mathematically proven by Lyapunov theory. In addition, the pitch angle control is presented to efficiently operate the rotor speed within the allowable operating range. Eventually, the proposed control system demonstrates its effectiveness through simulation and experimentation using a prototype of 5 kW DD PMVG-based WECS. After that, the comparative results affirm the superiority of the proposed control method over existing control methods.

This research proposes a new method to localize multiple switch-open-circuit (SOC) faults in a high-power wind turbine system with a permanent magnet synchronous generator (PMSG) and a three-level back-to-back neutral point clamped (NPC) converter. SOC faults can cause significant issues like generator torque fluctuations and distorted grid currents. Early detection and isolation of these faults are crucial for maintaining system reliability and availability. The proposed method addresses this challenge by using the estimated phase-angle deviation (EPAD) between the measured phase angle (from rotor position in case of generator and from phase-locked-loop in case of grid) and the estimated phase angle from phase currents. The EPAD possesses unique behavior for fault in each switch of the converter and is insensitive to factors like torque ripple, speed fluctuations, and parameter variations. The SOC fault detection and localization algorithms have been developed for the machine side and the grid side converters by analyzing the EPAD. The effectiveness of this method is evaluated through comparative studies, simulations, and hardware experimentation. Additionally, tests are conducted to confirm its robustness against false fault indications.

This study presents the coupling-memory-sampled data control (CMSDC) design for the Takagi–Sugeno (T-S) fuzzy system that solves the stabilization issue of a surface-mounted permanent-magnet synchronous generator (PMSG)-based wind energy conversion system (WECS). A fuzzy CMSDC scheme that includes the sampled data control (SDC) and memory-sampled data control (MSDC) is designed by employing a Bernoulli distribution order. Meanwhile, the membership-function-dependent (MFD) $H_{\infty }$ performance index is presented, mitigating the continuous-time fuzzy system’s disturbances. Then, by using the Lyapunov–Krasovskii functional with the MFD $H_{\infty }$ performance index, the data of the sampling pattern, and a constant signal transmission delay, sufficient conditions are derived. These sufficient conditions are linear matrix inequalities (LMIs), ensuring the global asymptotic stability of a PMSG-based WECS under the designed control technique. The proposed method is demonstrated by a numerical simulation implemented on the PMSG-based WECS. Finally, Rossler’s system demonstrates the effectiveness and superiority of the proposed method.

This study focuses on investigating the sampled-data (SD) H∞ consensus control problem for nonlinear multi-agent systems (MASs) modeled via Takagi-Sugeno (T-S) fuzzy rules, in the presence of external disturbances and stochastic packet dropouts, while incorporating a machine learning algorithm (MLA) technique. To do this, a fuzzy SD controller (FSDC) with zero-order hold is designed under bounded aperiodic sampling for the considered MASs, where each agent utilizes only relative state information from its neighboring agents. In addition, this controller employs a MLA to solve the optimization problem associated with the selection of the data sampling period, thereby reducing resource consumption while ensuring efficient operation under limited system bandwidth constraints. Besides, an appropriate membership-function-dependent looped Lyapunov-Krasovskii functional (LKF) is employed to analyze the SD fuzzy system, and the resulting conditions are further transformed into a common Lyapunov framework for controller design. Next, based on the constructed LKF along with the inequalities, a set of necessary conditions for achieving asymptotic stability with H∞ performance is derived through linear matrix inequalities, and then control parameters can be obtained to guarantee the less conservative stabilization results of considered closed-loop systems.