Wind energy is the strongest renewable energy source developed in recent decades. Being systems that are directly connected to the grid of the electrical system, it is essential to use the maximum available power of the wind and obtain the maximum electrical power converted from the turbine. In this paper, the fundamental problem of the wind turbine is how to obtain at all times the maximum output power of the turbine in a wide range of wind speed. The randomness of the wind adds an intrinsic difficulty to be able to plan the available wind energy in advance. To solve this problem, it is not necessary to know the dynamic operation of the system; we must anticipate the control response to each one of the different probable scenarios. An expert control system can be used based on human knowledge and experience, which, through proper management of its variables and adequate control of criteria to manipulate stored data, provides a way to determine solutions. In other words, it is a model of the experience of professionals in this field. The more variables in the system are considered, the more complete the model will be, and the more information will be available for decision-making, with a more efficient system and higher results in power generation as a response. For this reason, the objective of this paper is to present expert systems developed in recent years and, thus, offer a control solution that approximates the conditions of different wind turbines.INDEX TERMS Artificial neural network, fuzzy logic, genetic algorithms, wind power generation, control systems.
It is well known that the inverted pendulum can describe a variety of inherently unstable systems, which is a major reason to consider it as a benchmark problem in control and identification. In this paper, a comparison between two different kinds of neural networks is presented, on one hand the feedforward multilayer network with back-propagation learning method, and in the other hand the Volterra polynomial basis function network. A Fuzzy Logic controller was implemented to stabilize the system around its operation point. Both neural networks were trained using the error between the model's output and the plant's actual output. The polynomial network shows better performance against the multilayer network.
The inverted pendulum problem is one of the most important problems in control theory and has been studied excessively in control literatures. When control systems have strong requirements, the adjustment of the controller is a complex problem. The nonlinear model is useful for control design. In the present work, Volterra polynomial basis function (VPBF) networks have been used to identify a single inverted pendulum on a moving cart (SIPC) system. The inverted pendulum is a benchmark problem of nonlinear multivariable systems with inherent instability. The multivariable system has been considered with a force produced by a DC motor as the input, and four states variables as the outputs. A Fuzzy Logic controller has been used to stabilize the system for closed-loop identification. Here, the nonlinear model of the inverted pendulum has been implemented. The offline structure selection through orthogonal least square algorithm is used for the nonlinear system identification via the basis function selection of Volterra polynomial networks. The neural network is trained using the error between the model's outputs and the plant's actual outputs. The results show good match between predicted and actual outputs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.