The present invention provides a method of estimating ship resistance performance through deep machine learning, which comprises the steps of: constructing a DB by composing ship type information of a ship and resistance performance information corresponding to the ship type information as a data set (S110); calling C_p distribution and a surplus resistance performance curve, which are shape information data of the ship, from the DB, and extracting a coefficient a_n of the called surplus resistance performance curve (S120); and composing the C_p distribution, which is the shape information data of the ship, and the coefficient a_n of the called surplus resistance performance curve as a training data set and applying the training data set to deep machine learning. The present invention estimates the resistance performance for the ship type with a known C_p distribution (S130) and reflects the resistance performance in a ship type design (S140). The present invention is capable of estimating surplus resistance performance with high accuracy using fewer resources compared to a method using empirical formulas or CFDs.

    본 발명은 선박의 선형정보와, 상기 선형정보에 대응하는 저항성능정보를 데이터세트로 구성하여 DB를 구축하는 단계(S110)와, 상기 DB로부터, 선박의 형상정보 데이터인 Cp분포와 잉여저항성능곡선을 호출하여, 상기 호출된 잉여저항성능곡선의 계수 an을 추출하는 단계(S120)와, 상기 선박의 형상정보 데이터인 Cp분포와 상기 호출된 잉여저항성능곡선의 계수 an을 트레이닝 데이터세트로 구성하여 심층기계학습에 적용하는 단계;를 포함하여, 임의의 Cp분포를 알고 있는 선형에 대해 저항성능을 추정하여(S130) 선형설계에 반영(S140)하도록 하는, 심층기계학습을 통한 선박저항성능 추정 방법으로, 경험식 또는 CFD를 활용하는 방법에 비해 적은 자원으로 정확도 높은 잉여저항성능을 추정할 수 있는, 심층기계학습을 활용한 선박저항성능 추정 방법을 제공한다.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    METHOD FOR ESTIMATING HYDRODYNAMIC RESISTANCE PERFORMANCE THROUGH DEEP MACHINE LEARNING


    Weitere Titelangaben:

    심층기계학습을 통한 선박저항성능 추정 방법


    Beteiligte:
    KIM JEONG MIN (Autor:in)

    Erscheinungsdatum :

    2021-05-04


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Koreanisch


    Klassifikation :

    IPC:    B63B Schiffe oder sonstige Wasserfahrzeuge , SHIPS OR OTHER WATERBORNE VESSELS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Estimating Satellite Orientation through Turbulence with Deep Learning

    Lucas, Jacob | British Library Conference Proceedings | 2020


    Method for controlling hydrodynamic machine and hydrodynamic machine

    LAUKEMANN DIETER / LEHR MATTHIAS | Europäisches Patentamt | 2021

    Freier Zugriff

    Method for controlling a hydrodynamic machine and hydrodynamic machine

    LAUKEMANN DIETER / LEHR MATTHIAS | Europäisches Patentamt | 2023

    Freier Zugriff

    METHOD FOR CONTROLLING A HYDRODYNAMIC MACHINE AND HYDRODYNAMIC MACHINE

    LAUKEMANN DIETER / LEHR MATTHIAS | Europäisches Patentamt | 2021

    Freier Zugriff

    Hydrodynamic machine

    MENNE ACHIM / LAUKEMANN DIETER / SCHADE RAVI et al. | Europäisches Patentamt | 2018

    Freier Zugriff