This work focuses on the control of the pitch angle of wind turbines. This is not an easy task due to the nonlinearity, the complex dynamics, and the coupling between the variables of these renewable energy systems. This control is even harder for floating offshore wind turbines, as they are subjected to extreme weather conditions and the disturbances of the waves. To solve it, we propose a hybrid system that combines fuzzy logic and deep learning. Deep learning techniques are used to estimate the current wind and to forecast the future wind. Estimation and forecasting are combined to obtain the effective wind which feeds the fuzzy controller. Simulation results show how including the effective wind improves the performance of the intelligent controller for different disturbances. For low and medium wind speeds, an improvement of 21% is obtained respect to the PID controller, and 7% respect to the standard fuzzy controller. In addition, an intensive analysis has been carried out on the influence of the deep learning configuration parameters in the training of the hybrid control system. It is shown how increasing the number of hidden units improves the training. However, increasing the number of cells while keeping the total number of hidden units decelerates the training.

Data about wind are usually available from different databases, for different locations. In general, this information is the average of the wind speed over time. The wind reports are crucial for designing wind turbine controllers. But when working with floating offshore wind turbines (FOWT), two problems arise regarding the wind measurement. On the one hand, there are no buoys at deep sea, but near the coast where the wind is not so strong neither so stable; so the measurements do not fully correspond to reality. On the other hand, these floating devices are subjected to extreme environmental conditions (waves, currents, ...) that produce disturbances and thus may distort wind measurements. To address this problem, this work presents a novel pitch neuro-control architecture based on neuro-estimators of the effective wind. The control system is composed of a proportional-integral-derivative (PID) controller, a lookup table, a neuro-estimator, and a virtual sensor. The neuro-estimator is used to estimate the effective wind in the FOWT and to forecast its future value. Both current and future wind signals are combined and power the controller. The virtual sensor also provides a measure of the effective wind based on other available signals related to the wind turbine, such as the pitch angle and the angular velocity of the generator. Neural networks are trained online to adapt to changes in the environment. Intensive simulations are carried out to validate the effectiveness of this neuro control approach. Controller performance is compared to a PID, obtaining better results. Indeed, an improvement of 16% for sinusoidal wind and an average improvement of 8% are observed.

With the rapid growth of logistics transportation in the framework of Industry 4.0, automated guided vehicle (AGV) technologies have developed speedily. These systems present two coupled control problems: the control of the longitudinal velocity, essential to ensure the application requirements such as throughput and tag time, and the trajectory tracking control, necessary to ensure the proper accuracy in loading and unloading manoeuvres. When the paths are very short or have abrupt changes, the kinematic constraints play a restrictive role, and the tracking control becomes more challenging. In this case, advanced control strategies such as those based on intelligent techniques, including machine learning (ML) can be useful. Hence, in this work, we present an intelligent hybrid control scheme that combines reinforcement learning‐based control (RLC) with conventional PI regulators to face both control problems simultaneously. On the one hand, PIs are used to control the speed of each wheel. On the other hand, the input reference of these regulators is calculated by the RLC in order to reduce the guiding error of the path tracking and to maintain the longitudinal speed. The latter is compared with a PID path following controller. The PID regulators have been tuned by genetic algorithms. The RLC allows the vehicle to learn how to improve the trajectory tracking in an adaptive way and thus, the AGV can face disturbances or unknown physical system parameters that may change due to friction and degradation of AGV mechanical components. Extensive simulation experiments of the proposed intelligent control strategy on a hybrid tricycle and differential AGV model, that considers the kinematics and the dynamics of the vehicle, prove the efficiency of the approach when following different demanding trajectories. The performance of the RL tracking controller in comparison with the optimized PID gives errors around 70% smaller, and the average maximum error is also 48% lower.

El control del ángulo de las palas de las turbinas eólicas es complejo debido al comportamiento no lineal de los aerogeneradores, y a las perturbaciones externas a las que están sometidas debido a las condiciones cambiantes del viento y otros fenómenos meteorológicos. Esta dificultad se agrava en el caso de las turbinas flotantes marinas, donde también les afectan las corrientes marinas y las olas. Las redes neuronales, y otras técnicas del control inteligente, han demostrado ser muy útiles para el modelado y control de estos sistemas. En este trabajo se presentan diferentes configuraciones de control inteligente, basadas principalmente en redes neuronales y aprendizaje por refuerzo, aplicadas al control de las turbinas eólicas. Se describe el control directo del ángulo de las palas del aerogenerador y algunas configuraciones híbridas de control. Se expone la utilidad de los neuro-estimadores para la mejora de los controladores. Finalmente, se muestra un ejemplo de aplicación de algunas de estas técnicas en un modelo de turbina terrestre.