Comparison of an ANFIS and Fuzzy PID Control Model for Performance in a Two-Axis Inertial Stabilized Platform

An adaptive neuro-fuzzy inference system (ANFIS) of soft computing is an effective method for predicting performance. An statistical analysis and soft computing scheme based on the ANFIS neuro-fuzzy proportional-integral-differential (ANFP) control is proposed to predict the performance of a fuzzy PID controller for a two-axis inertially stabilized platform system. The data are extracted from an unconventional fuzzy PID stabilization controller output of the closed loop, and the model is trained using the Levenberg–Marquardt (LM) training algorithm and compared according to the experimental data from the output results of the ANFP controller. The comparative simulations are expatiated by the statistical values of the mean squared error (MSE) and the coefficient of determination (R) as performance indicators. The experimental results validate that the ANFP soft computing approach contributes to the indispensable improvement for predicting performance in accordance with the error analysis results.