a new fault-tolerant control of wind turbine pitch system based on ann model and robust and optimal development of mrac method

In this paper, a new method is provided for faulttolerant control (ftc) of wind turbine pitch systems. one of the common faults in wind turbines is the defects of the pitch subsystem. each blade of wind turbines tracks a reference signal; it is generated by the main controller unit, defects of actuators, or disturbance decrease of the reference signal quality. classic controllers cannot deal with the disturbance and compensate for the faults to maintain system performance in normal operating conditions. for this purpose, a novel method based on optimal robust model reference adaptive control (ormrac) is presented, the output of the proposed method is a new adaptive rule. the ormrac method is robust, optimal, and fast at the same time. the proposed structure includes fault detection (fd) and ftc units. fd acts based on the generation and evaluation of residuals. the residual generation is based on artificial neural network (ann) model. when there is disturbance or fault in the pitch system and residual exceeds the certain threshold, the ft unit is activated. the proposed ft method is tested and evaluated using a wind turbine simulator based on practical data. the results indicated the proper performance of the proposed method in comparison with conventional mrac and some other methods.

A New Fault-Tolerant Control of Wind Turbine Pitch System Based on ANN Model and Robust and Optimal Development of MRAC Method

In this paper, a new method is provided for FaultTolerant Control (FTC) of wind turbine pitch systems. One of the common faults in wind turbines is the defects of the pitch subsystem. Each blade of wind turbines tracks a reference signal; it is generated by the main controller unit, defects of actuators, or disturbance decrease of the reference signal quality. Classic controllers cannot deal with the disturbance and compensate for the faults to maintain system performance in normal operating conditions. For this purpose, a novel method based on Optimal Robust Model Reference Adaptive Control (ORMRAC) is presented, the output of the proposed method is a new adaptive rule. The ORMRAC method is robust, optimal, and fast at the same time. The proposed structure includes Fault Detection (FD) and FTC units. FD acts based on the generation and evaluation of residuals. The residual generation is based on Artificial Neural Network (ANN) model. When there is disturbance or fault in the pitch system and residual exceeds the certain threshold, the FT unit is activated. The proposed FT method is tested and evaluated using a wind turbine simulator based on practical data. The results indicated the proper performance of the proposed method in comparison with conventional MRAC and some other methods.