엘리베이터의 동작을 제어하며 고장과 관련된 고장데이터를 실시간으로 기록하는 엘리베이터 제어반; 엘리베이터 제어반에 기록된 고장데이터를 전송받아 축적하는 클라우드; 클라우드에 저장되어 있는 고장데이터로부터 엘리베이터의 고장 발생 원인 해석에 이용될 주요데이터를 추출하고 시간대별로 나열하는 전처리를 수행하는 전처리부; 전처리부에 의해 전처리된 데이터를 엘리베이터의 실제 고장 원인을 나타내는 고장원인 레이블과 결합하여 학습데이터 셋을 구성하는 라벨링부; 학습데이터 셋으로 순환신경망 학습을 수행하여 엘리베이터의 실제 고장 원인을 추론하는 고장 진단 모델을 생성하는 학습모델링부; 및 전처리부에 의해 전처리된 데이터와 라벨링부에 의해 라벨링된 학습데이터 셋 및 학습모델링부에 의해 생성된 고장 진단 모델을 저장하고 구분하여 관리하는 저장관리부를 포함하는 순환신경망 모델을 활용한 엘리베이터 고장 진단 시스템이 개시된다.

    The invention discloses an elevator fault diagnosis system using a recurrent neural network model, and the system is characterized in that the system comprises an elevator control panel which controls the action of an elevator and records fault data related to a fault in real time; the cloud receives and accumulates the fault data recorded on the elevator control panel; a pre-processing part for executing pre-processing for extracting main data for analyzing the cause of the elevator fault from the fault data stored in the cloud and arranging the main data according to time periods; a marking unit which combines the data preprocessed by the preprocessing unit with a fault cause tag indicating the actual fault cause of the elevator to form a learning data set; a learning modeling unit for executing recurrent neural network learning by using the learning data set to generate a fault diagnosis model for estimating an actual fault cause of the elevator; and a storage management unit that stores the data pre-processed by the pre-processing unit, the learning data set marked by the marking unit, and the fault diagnosis model generated by the learning modeling unit, and performs management by distinguishing the data, the learning data set, and the fault diagnosis model.


    Access

    Download


    Export, share and cite



    Title :

    Elevator Failure Diagnosis System Using Recurrent Neural Network Model


    Additional title:

    순환신경망 모델을 활용한 엘리베이터 고장 진단 시스템


    Publication date :

    2024-09-04


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Korean


    Classification :

    IPC:    B66B Aufzüge , ELEVATORS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES



    Elevator Failure Diagnosis System Using Recurrent Neural Network Model

    SEO JIHYE | European Patent Office | 2023

    Free access

    Elevator fault diagnosis system using recurrent neural network model

    XU ZHIHUI | European Patent Office | 2023

    Free access

    ELEVATOR FAILURE DIAGNOSIS SYSTEM

    NISHIMURA SHIGERU / NONAKA HISANORI / ATSUZAWA TERUYOSHI | European Patent Office | 2019

    Free access

    ELEVATOR FAILURE DIAGNOSIS DEVICE

    FURUYA SHIRO / SHIGA SATOSHI / CHOTOKU NORIHIRO et al. | European Patent Office | 2022

    Free access

    ELEVATOR DIAGNOSIS SYSTEM AND ELEVATOR DIAGNOSIS METHOD

    ONISHI YOSUKE / NISHIE SATOSHI | European Patent Office | 2020

    Free access