• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.2
• /
• pp.125-133
• /
• 2022

This paper proposes a fault detection method for a Unmanned Surface Vehicle (USV) with overactuated system. Current status information for fault detection is expressed as a scalogram image. The scalogram image is obtained by wavelet-transforming the USV's control input and sensor information. The fault detection scheme is based on Convolutional Neural Network (CNN) algorithm. The previously generated scalogram data was transferred learning to GoogLeNet algorithm. The data are generated as scalogram images in real time, and fault is detected through a learning model. The result of fault detection is very robust and highly accurate.

• Journal of Ocean Engineering and Technology
• /
• v.32 no.1
• /
• pp.68-75
• /
• 2018

This study deals with the heading angle and depth keeping control technique for an ROV with multiple horizontal and vertical thrusters by thrust allocation. The light work class ROV URI-L, which is under development at KRISO, is a redundant actuating system with multiple thrusters that are larger than the ROV's degree of freedom. In the redundant actuating system, there are several solutions for a specific ROV motion to be performed. Therefore, a thrust allocation algorithm that considers the entire propulsion system should be regarded as important. First, this paper describes the propulsion system of the ROV and introduces the thrust allocation method of each motion controller. In addition, the performance of the controller is examined using a heading angle and depth keeping control test in a stationary state.