Files
Abstract
Ship Signature Management Systems (SSMS) aims to support the crew on board of naval vessels with real time information on the susceptibility of the ship in relation to various threats. The underwater acoustic signature is relevant for various underwater threats and a dominant contributor to this signature is propeller cavitation.
Within SSMS a Cavitation Management System (CaMaS) is being developed. CaMaS consists of two main parts: cavitation monitoring and an advice function. Based on the output of on board installed accelerometers combined with algorithms cavitation can be determined. The online-assessed cavitation status shall be stored in a dynamic database as function of the sea and platform conditions. Artificial Intelligence (AI) and self-learning technology will be applied to deliver the operator advice to avoid cavitation.
A demonstrator on board a navy vessel is installed to incrementally develop an SSMS and its CaMaS-functionality. For the CaMaS demonstrator accelerometers have been placed on the hull plates above the propeller where multiple algorithms were tested to detect cavitation giving relevant results. The operator has a major role in the development of the functionalities and its Human Machine Interface.
CaMaS is dual use technology; it can be exploited for naval applications as well by commercial shipping to satisfy the developing international regulation of undersea noise. This paper describes the development of CaMaS and presents the unclassified results regarding full-scale experiments on board of various vessels.