An autopilot for ships designed with fuzzy sets
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An autopilot for ships designed with the aid of fuzzy sets is investigated, and a comparison is made between the fuzzy and a conventional PID controller which is most commonly used in autopilots.
Abstract
An autopilot for ships designed with the aid of fuzzy sets is investigated. For this design the steering behaviour of a human controller is translated into a fuzzy mathematical model. The complexity of this model requires a digital computer for implementation of the autopilot. The steering problem is split up into two regions with different control algorithms, a manoeuvring or course-changing mode and a course-keeping mode. Fuzzy sets are used also in the formulation of a fuzzy performance index that is based on human appreciation of the steering. The results are tested on a simulator, and a comparison is made between the fuzzy and a conventional PID controller which is most commonly used in autopilots.