This paper attempts to present a genetic algorithm-based counter-flooding decision support system for survivability evaluation and decision support in shipboard flooding accident. The developed system is also thought to useful as a crew training one, which is composed of a model base, a database and a man–machine interaction system structurally. The model base is of paramount importance to the system, which comprises three sub-models: a damaged floating position calculation model, a loading condition calculation model and a counter-flooding scheme optimization model. In order to solve the optimal strategy model, genetic algorithm, which is developed with roulette wheel selection, one-point crossover and mutation, is used to choose the set of counter-flooding tanks should be filled or evacuated in order to achieve an optimal response to a flooding accident. The proposed evolutionary strategy enhances the diversity of population and the capability of search for the global optimum, which accelerates the evolution process of algorithm. The computational results validate the effectiveness of genetic algorithm.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Genetic algorithm-based counter-flooding decision support system for damaged surface warship


    Erschienen in:

    Erscheinungsdatum :

    2008-01-01


    Format / Umfang :

    15 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Genetic algorithm-based counter-flooding decision model for damaged warship

    Hu, Li-fen / Tian, Zhongmin / Sun, Zhongyu et al. | IOS Press | 2015



    An Assessment of Current Warship Damaged Stability Criteria

    Surko, S. W. / American Society of Naval Engineers | British Library Conference Proceedings | 1994


    An Assessment of Current Warship Damaged Stability Criteria

    Surko, Stephen W. | Online Contents | 1994