The present invention relates to a system and method for estimating various performance coefficients displaying the performance of a ship. According to the present invention, to address the problems of the conventional methods for estimating ship performance based on statistics, which have had limitations in reflecting minute changes in the shape since the methods have had predicted performance only by using variables representing linear shapes mostly with major data of a ship as an input, provided are a system and method for estimating a ship performance coefficient using a convolutional neural network (CNN), which is able to convert offset data showing shape information of a ship (offset cross-section information) into image data by using the deep learning and the CNN technology, and match the image data with major data variables, speed variables, and bulb shape information of the ship to perform the learning process by applying a two-dimensional or three-dimensional CNN. Here, by adding a dropout and an L2 regularization for preventing an overfitting as needed, the system and method are able to output a desired performance variable by using the offset data of a random linear shape the major data variables, bow bulb variables, and speed variables as an input.

    본 발명은, 선박의 성능을 나타내는 각종 성능계수를 추정하기 위한 장치 및 방법에 관한 것으로, 본 발명에 따르면, 선박의 주요 제원을 입력으로 하여 성능을 예측하는 기존의 방법들은 대부분 선형을 대표하는 변수로만 성능을 예측함으로 인해 미세한 형상의 변화를 반영하기 어려운 한계가 있었던 종래기술의 통계기반 선박 성능 추정방법들의 문제점을 해결하기 위해, 딥러닝(Deep Learning) 및 컨벌루션 신경망(Convolutional Neural Network ; CNN) 기술을 활용하여, 선박의 형상정보(오프셋 단면정보)를 나타내는 오프셋 데이터를 이미지 데이터로 변환하고, 이미지 데이터에 선박의 주요 제원변수와 속도변수, 벌브형상정보를 매칭하여 2차원 CNN 또는 3차원 CNN을 적용하여 학습을 수행하며, 이때, 필요에 따라 과적합을 방지하기 위한 드롭아웃(dropout)과 정규화(L2 regularization)를 추가하는 것에 의해, 임의의 선형의 오프셋 데이터와 주요 제원변수, 선수 벌브변수, 속력변수를 입력으로 하여 원하는 성능변수가 출력될 수 있도록 구성되는 컨벌루션 신경망을 이용한 선박 성능계수 추정시스템 및 방법이 제공된다.


    Access

    Download


    Export, share and cite



    Title :

    System and method for estimating ship performance coefficient using convolutional neural network


    Additional title:

    컨벌루션 신경망을 이용한 선박 성능계수 추정시스템 및 방법


    Contributors:

    Publication date :

    2024-01-09


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Korean


    Classification :

    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




    SYSTEM AND METHOD FOR ESTIMATING SHIP PERFORMANCE COEFFICIENT BY USING CONVOLUTIONAL NEURAL NETWORK

    KIM YOO CHUL / KIM MYOUNG SOO / HWANG SEUNG HYUN et al. | European Patent Office | 2024

    Free access

    Visual Explainable Convolutional Neural Network for Aerodynamic Coefficient Prediction

    Yanxuan Zhao / Chengwen Zhong / Fang Wang et al. | DOAJ | 2022

    Free access


    Ship Identification on Satellite Image Using Convolutional Neural Network and Random Forest

    Endang Anggiratih / Agfianto Eko Putra | DOAJ | 2019

    Free access