Simulation and tracking control based on neural-network strategy and sliding-mode control for underwater remotely operated vehicle

In recent years, remotely operated vehicles (ROVs) play an important role in various underwater operations. In many applications, ROVs will need to be capable of maneuvering to any given point, following the object and to be controllable from the surface. The Department of Mechanical Engineering of the University of Guilan designed and fabricated an ROV for underwater exploration with special application for monitoring and studying fish behavior in the Caspian Sea. In this paper, the design, dynamic modeling, and control of the fabricated ROV are presented for four degrees of freedom (DOFs). Moreover, this study uses a sliding-mode neural-network scalar (SMNNS) control system to track the control of the ROV in order to achieve a high-precision position control. In the SMNNS control system, a neural-network controller is developed to mimic an equivalent control law in the sliding-mode control, and a robust controller and also a scalar controller are designed to curb the system dynamics on the sliding surface for guaranteeing the asymptotic stability property and achieving high-accuracy position control. Moreover, to estimate the upper bound of uncertainties, an adaptive bound estimation algorithm is employed. All adaptive-learning algorithms in the SMNNS control system are derived from the sense of the Lyapunov stability analysis. It has been shown that system-tracking stability can be guaranteed in the closed-loop system irrespective of whether uncertainties occur or not. Significant improvements are observed in tracking performance of the ROV in all controllable DOFs.