Fast Training Algorithm for Genetic Fuzzy Controllers and Application to an Inverted Pendulum with Free Cart

The classical control theory cannot be applied in those systems whose complexity is too high to be analytically modeled. In these cases, mathematical methods with more degrees of freedom are used because they provide better adaptation. One method widely used in control problems is the Fuzzy Inferencing Systems. However, the process of calibration of the parameters required may involve a high computational cost. Among them, Genetic Algorithms have demonstrated great convergence towards ideal solutions. As the dimensions of the control problem (input features) increase, the optimization process requires much more time. Therefore, the present work proposes a gradual search and parameter update criteria for Genetic Fuzzy Controllers that improves several orders of magnitude the processing time. The algorithm developed has been applied to the control problem of the Inverted Pendulum with Free Cart. The results obtained demonstrate an effective parameter calibration in seconds, while the traditional method of tuning for the same problem takes more than 2 h. Currently, many of the mechanical systems of the different industries undergo sudden changes in their properties during use, therefore an instant effective recalibration of the controllers is necessary. This method allows fast adaptation and also guarantees the same performance in the control process.