Search

This article proposes the use of a deep reinforcement learning method—and precisely a variant of the deep deterministic policy gradient (DDPG) method known as twin delayed DDPG, or TD3—for maximum power point tracking in wind energy conversion systems that use permanent magnet synchronous generators (PMSGs). An overview of the TD3 algorithm is provided, together with a detailed description of its implementation and training for the considered application. Simulation results are provided, also including a comparison with a model‐based control method based on feedback linearization and linear‐quadratic regulation. The proposed TD3‐based controller achieves a satisfactory control performance and is more robust to PMSG parameter variations as compared to the presented model‐based method. To the best of the authors' knowledge, this article presents for the first time an approach for generating both speed and current control loops using DRL for wind energy conversion systems. [ABSTRACT FROM AUTHOR]

This article presents a comprehensive review of current Magnetic Imaging Techniques (MIT), specifically Magnetic Particle Imaging (MPI) and Magnetic Resonance Imaging (MRI) methods as well as their impacts and potential in biomedical applications. The paper particularly focuses on several perspectives of MPI and MRI techniques including technical considerations, advantages, limitations, applications, future trends. Surprisingly, there are not many review articles that focused on MPI and MRI. This review will give a complete overview of present technology, perspectives, and potential future developments for MPI and MRI. MIT has become an essential and integral part of medical diagnosis in many large medical clinics and hospitals. This area is rapidly developing and evolving to meet the huge demands in medical diagnosis and prevention. MPI and MRI are promising technologies that provide reliable and effective diagnosis for many diseases including cancer. MIT uses non‐invasive scanning to obtain a detailed image of the body's tissues or organs without the necessity for surgery. These techniques allow us to detect symptoms of serious diseases at an early stage. Early detection also gives patients the chance to get the right care before their illnesses advance to a late, incurable stage, potentially saving many lives. [ABSTRACT FROM AUTHOR]

In this article, integral servomechanism based state‐dependent Riccati equation (SDRE) nonlinear output feedback control for wind energy conversion systems (WECSs) has been proposed. The numerical off‐line solving the proposed SDRE control requires to formulate algebraic Riccati equation and algebraic Lyapunov equation. This method approximates the solution of SDRE with Taylor series expansions which are solved with MATLAB solvers. The maximum power point tracking is achieved by defining relation between the optimal angular shaft speed and maximum power providing optimal tip speed ratio in variable‐speed WECSs. The proposed control can significantly reduce the angular shaft speed errors of the permanent magnet synchronous generator (PMSG)‐based WECSs without use of disturbance observers to compensate model uncertainties, modeling errors and noise as in the conventional SDRE control method. The simulation results demonstrate the superior results under mean average errors and root mean square error evaluation methods of the angular shaft speed of PMSG. The performance of the proposed integral servomechanism based SDRE control system has been improved by 80.67% and 80.05% in both scenarios compared to the conventional SDRE control based on compensation technique with disturbance observers. [ABSTRACT FROM AUTHOR]

Recently, wind power production has been under the focus in generating power and became one of the main sources of alternative energy. Generating of maximum power from wind energy conversion system (WECS) requires accurate estimation of aerodynamic torque and uncertainties presented in the system. The current paper proposed the generalized high‐order disturbance observer (GHODO) with integral sliding mode control (ISMC) for extraction of maximum power via variable speed wind turbine by accurate estimation of wind speed. The assumption in previous works that considers the aerodynamic torque as slow‐varying is not applicable for the real system. Therefore, the high‐order disturbance observers were designed for precise estimation of uncertainties with fast‐changing behavior. A robust control system was designed to control the speed of the rotor at the optimal speed ratio. The obtained simulation results have shown the better performance characteristics than conventional linear quadratic regulator (LQR) approach. The stability of the proposed algorithm was proven by Lyapunov stability anaysis. Simulations results were obtained in Matlab/Simulink environment. [ABSTRACT FROM AUTHOR]

The issue of tracking the optimal power for wind energy conversion systems (WECSs) via regulating the rotor speed of the generator is taken into account in this study. Additionally, a novel polynomial observer is proposed for estimating not only aerodynamic torque in WECSs but also d‐axis and electromagnetic torque. Therefore, in this new approach, only the rotor speed of the generator is required to be measured instead of measuring all state variables. With the new observer form, the aerodynamic torque does not need to satisfy any constraints, which are mandatory in the previous methods. It should be noted that this methodology has not been investigated for the WECSs in any previous papers. To design a complete control system, a linear optimal control method cooperated with the polynomial observer is employed to track the optimal trajectory of a generator. Moreover, in this paper, the permanent magnet synchronous generator is used. In addition, on the basis of the Lyapunov theory and sum‐of‐square (SOS) technique, the conditions for observer synthesis are derived in the main theorems. Finally, the simulation results are provided to prove the effectiveness and merit of the proposed method. [ABSTRACT FROM AUTHOR]

Summary: Tip speed ratio control is a popular method in wind energy conversion systems in order to capture the maximum power. This method, however, requires wind speed information, which is difficult in practice to accurately measure it. Therefore, estimation methods are usually applied, where a high‐precision estimate leads to a high‐efficient system. Based on the fact that the wind speed varies in a random way, this paper proposes a generalized high‐order observer to estimate the aerodynamic torque and the wind speed accordingly. This observer algorithm releases the assumption that the wind speed should be slowly varying, which is required in previous observer designs. Moreover, two other generalized high‐order observers are also applied to estimate the uncertainties, which depend on state variables and cannot be considered as slow‐varying disturbances. Using the outputs of these observers, a robust high‐performance optimal control system is developed for the rotor speed to keep the optimal tip speed ratio. The stability analysis of the designed control system is fully presented. The effectiveness of the proposed technique is validated via simulation studies. [ABSTRACT FROM AUTHOR]