Artificial neural network-based adaptive control for a DFIG-based WECS

Fixed-time fuzzy adaptive control scheme for doubly fed induction generator–based wind turbine

“…The performance of the proposed FTFAC scheme is demonstrated via a set of numerical simulations. The designed control approach has been compared with vector control (Labdai et al, 2022) technique in terms of convergence-rate, robustness against parameter changes, and external disturbances. The simulated wind speed profile is depicted in Figure 3.…”

“…In such systems, the stator is directly connected to the grid, while the wound rotor is fed via a bidirectional power converter. Compared with other wind turbines, the doubly fed induction generator–based wind turbine (DFIG-WT) offers several advantages such as high-power conversion efficiency under variable-speed operation, sub- or super-synchronous operating modes and low-cost of the minimized size power converter (Kou et al, 2018; Labdai et al, 2022). However, the DFIG-WT is a complex nonlinear dynamic system which is often subject to severe operating conditions, such as parametric changes and external disturbances.…”

“…However, the DFIG-WT is a complex nonlinear dynamic system which is often subject to severe operating conditions, such as parametric changes and external disturbances. A lot of studies have been undertaken about the DFIG-WT control (Bounar et al, 2020; Evangelista et al, 2016; Kiruthiga, 2015; Kou et al, 2018; Labdai et al, 2022; Mauricio et al, 2008; Wang et al, 2021; Yang et al, 2016). The developed control methods are usually classified into two main classes, namely linear and nonlinear.…”

“…The linear methods are usually based on the field-oriented vector control with conventional proportional–integral (PI) controllers (Bounar et al, 2020; Yang et al, 2016). Unfortunately, these approaches suffer from sensitivity to the system parameter changes and inadequate rejection of external disturbances (Labdai et al, 2022; Yang et al, 2016). To deal with the insufficiencies of the classical control approaches, many nonlinear controllers were developed to achieve the desired control performance of DFIG-WT system, including adaptive control (Mauricio et al, 2008), sliding mode approach (Kiruthiga, 2015), and advanced control techniques based on artificial intelligence (Bounar et al, 2020; Labdai et al, 2022), and so on.…”

“…Unfortunately, these approaches suffer from sensitivity to the system parameter changes and inadequate rejection of external disturbances (Labdai et al, 2022; Yang et al, 2016). To deal with the insufficiencies of the classical control approaches, many nonlinear controllers were developed to achieve the desired control performance of DFIG-WT system, including adaptive control (Mauricio et al, 2008), sliding mode approach (Kiruthiga, 2015), and advanced control techniques based on artificial intelligence (Bounar et al, 2020; Labdai et al, 2022), and so on. Most of these control approaches can ensure power optimization with better tracking performances and great robustness to modeling uncertainties, external disturbances, and parametric changes.…”