Model Identification of an Underwater Remotely Operated Vehicle Using System Identification Approach Based on NNPC

摘要

This paper described the development of modeling of an unmanned underwater vehicle (UUV) using system identification toolbox based on neural network model. The set of data based on neural network model generated by open-loop model of UUV and the input-output data produced using neural network predictive control technique. The model of UUV is an underwater Remotely Operated Vehicle (ROV) will be used in this study. Open-loop model of ROV created using system identification technique with implemented in real time experiment for open-loop system. Two data will be used such as the input and output neural network data for validation and training for infer a model of the ROV using system identification toolbox. The data re-generated using graph digitizer software. The accuracy of this software almost 90%. Then, the model obtained in this system will be controlled using conventional PID controller in MATLAB Simulink. The comparison between two models from different techniques of the ROV will be described. When the number of samples used in this project reduced, the best fit will be increased. A model obtained based on neural network model is acceptable to use in simulation and will be improved the best fit when reduced number of samples.