Search

Given the difficulties in measuring the effective wind speed of wind turbine during the maximum power point tracking (MPPT) process and the unknown nature of the system, this paper proposes a neural network super-twisted sliding mode control (NNST-SMC) method with echo state network (ESN) wind speed estimation. The rotor speed and electromagnetic power are taken as ESN inputs, and the effective wind speed is estimated through the inverse model of wind turbine dynamics. The super-twisted algorithm (STA) can effectively improve the chattering problem of the traditional sliding mode control (SMC) system. The RBF neural network is introduced to compensate for disturbance and uncertainty characteristics of the wind turbine. Results show that compared with the neural network first-order sliding mode control (NNSMC) and super-twisted sliding mode control (ST-SMC), the proposed method can improve the efficiency of wind energy utilization. [ABSTRACT FROM AUTHOR]

A robust approximation-based event-triggered control method is presented for single input single output (SISO) nonlinear continuous-time systems with unmeasurable states and external disturbance. In the whole system, just one neural network (NN) is designed to approximate the unknown part in the controller, and output errors are directly used to construct the system controller and event-triggered mechanism to relieve the burden of system communication. The controller with a simple structure is easier to be realized in practical engineering. The system control signals and adaptive parameters are updated only if the event trigger condition is met, and this way further reduces the waste of network resources caused by frequent system sampling. The application of stability theory of Lyapunov proves that the weight estimation of the NN and tracking errors are ultimate and uniform boundedness, and the efficacy of the proposed scheme is verified with numerical results on a robot. [ABSTRACT FROM AUTHOR]