Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 6

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

A concept of the marine engine room monitoring and control system for simulating real processes on a ship

100%

Smierzchalski R.

nr 2

The use of backstepping method to ship course controller

63%

Witkowska A. , Smierzchalski R.

tom Vol. 1, no. 3

313--318

The article systematises and perform approaches the new concept of the ship autopilot in which control rules are derived for nonlinear controllers designed with the aid of the backstepping method and used for controlling the ship’s motion on its course. The objectives, approaches and problems were described. The design is very interesting has goals to create closed-loop systems with desirable stability properties in the regulation and tracking problems with a uniform asymptotic stability, rather than analyze the properties of a given system. The symulation were performed on the tanker model and were comparised in the system with PD controller.

An analysis of MultiOobjective Evolutionary techniques applicable to weather routing

63%

Szlapczyńska J. , Smierzchalski R.

tom z. 160

277-284

This document describes possible applicationof MultiObjective Evolutionary Algorithms (MOEAs) to a problem of finding the most sutiable vesel route taking into account changeable weather conditions and several navigational constraints. The paper includes a review of MOEA-specific techniques and presents a proposal of their utilizaytion in a weather routing evolutionary algorithm.

A new approach of genetic algorithms to tuning parameters of backstepping ship course controller

63%

Witkowska A. , Smierzchalski R.

tom z. 160

301-307

One of the methods wich can be used for designing a nonlinear control structures were tuned to optimise the operation of the control system. The optimisation was performed using genetic algorithms. The quality of operation of the designed control algorithms was checked in simulation tests performed on the mathematical model of the tanker completed by steering gear. The goal of this paper is not to present or propose any new solusion in programming of genetic algorithm. It will be rather focused on possibility of use genetic algorithm in backstepping method.

Supporting navigator's decisions by visualizing ship collision risk

63%

Szlapczynski R. , Smierzchalski R.

nr 1

The paper introduces a visualization method that enables the navigator to estimate an encounter situation and choose collision avoidance manoeuvre, if necessary. It is based on the Collision Threat Parameters Area method and offers new features: fuzzy sectors of forbidden speed and course values, the possibility to use any given ship domain and a new formula of collision risk assessment. All these elements result in a method, which enables the navigator to differentiate between varying levels of risk and to point out the direct threats. The method is fast enough to be applied in the real-time decision support system

Experimental Research on Evolutionary Path Planning Algorithm with Fitness Function Scaling for Collision Scenarios

51%

Kolendo P. , Smierzchalski R. , Jaworski B.

2011

tom Vol. 5, no. 4

489--495

This article presents typical ship collision scenarios, simulated using the evolutionary path planning system and analyses the impact of the fitness function scaling on the quality of the solution. The function scaling decreases the selective pressure, which facilitates leaving the local optimum in the calculation process and further exploration of the solution space. The performed investigations have proved that the use of scaling in the evolutionary path planning method makes it possible to preserve the diversity of solu-tions by a larger number of generations in the exploration phase, what could result in finding better solution at the end. The problem of avoiding collisions well fitted the algorithm in question, as it easily incorporates dynamic objects (moving ships) into its simulations, however the use scaling with this particular problem has proven to be redundant.