Simulación y Comparación de Controladores Pid, Liapunov y Redes Neuronales Artificiales: Abordando El Rechazo de Perturbaciones en Sistemas no Lineales a Través de Modelado Computacional

The control of complex systems is based on solving problems in nonlinear systems, which are generally unstable. One example of such a system is the two wheeled self-balancing robot, a typical problem in the area of systems modeling and control, and an intriguing one to understand and control. This article aims to observe the different characteristics of three existing control methods in a general sense, starting with classical control using the well-known PID, followed by the mathematics of Liapunov candidate functions, and finally reviewing the contribution of artificial neural network algorithms. PID, Liapunov control, and artificial neural network control are three different control techniques that can be used to reject disturbances in nonlinear systems. Each of these techniques has its own advantages and disadvantages in terms of their ability to reject disturbances in nonlinear systems. PID control is a well-established control technique that can be used to control a wide variety of systems, including nonlinear systems, but may not be as effective in rejecting disturbances in nonlinear systems, as the controller's response may not be sufficiently fast or accurate to compensate for the disturbances. Liapunov control is a control technique based on mathematical stability theory and uses a Liapunov function to ensure system stability. Artificial neural network control is based on machine learning and uses a neural network to model the system's behavior and generate a suitable control signal. This article makes a comparison between these controllers, taking a step from classical control to some of the current control techniques.