Neural network sliding mode control with time-varying delay for a variable speed wind turbine. (2017)

• Record Type: Journal Article
• Authors: Berrada, Youssef; Boumhidi, Ismail
• Is Part Of: International journal of power and energy conversion. Volume 8:Number 4(2017)
• Page Start: 343
• Page End: 356
• Publication Date: 2017
• Subjects: artificial neural network -- ANN: sliding mode control -- SMC -- time-varying delay -- online learning -- variable speed wind turbine; Energy conversion -- Periodicals; Power resources -- Periodicals; Electric power production -- Periodicals; 621.31205
• Languages: English
• ISSNs: 1757-1154

Abstract

This paper presents a real time neural network sliding mode control with time-varying delay (RNNSM) design for a variable speed wind turbine. The sliding mode control (SMC) method can be used for nonlinear uncertain systems. However, it provides some drawbacks linked to chattering, due to the higher needed switching gain in the case of large uncertainties. In order to reduce this gain, artificial neural network (ANN) is used for the estimation of model unknown parts and hence enable a lower switching gain to be used. The ANN is turned online; therefore, we cannot implement this control law in real time because of the time-varying delay generated by the ANN in online learning. This work is a proposal to compensate this delay so as to ensure the control in real time and maintain the advantage of online learning; we propose to convert the original system to a system with time-varying input delay which will practically represent the online learning time. We use Lyapunov-Krasovskii functional to prove the stability of the closed loop systems, and the effectiveness of the designed method is illustrated in simulations by the comparison with integral sliding mode control (ISMC).