The invention discloses an elevator traction system fault detection method based on artificial intelligence, and belongs to the technical field of intelligent elevator operation and maintenance, and the method comprises the steps of elevator traction system data collection, elevator traction system data enhancement, fault detection model construction and elevator traction system fault detection. According to the method, the recursive generative adversarial network model is adopted for data enhancement, the time sequence dependence of the data is better captured, the synthetic data is closer to actual data in the statistical property, the authenticity of the synthetic data is improved, and therefore the deviation during model training is reduced, and the fault detection accuracy and reliability of the elevator traction system are enhanced; a parallel deep convolution coupling graph convolution network is adopted, an elevator traction system fault detection model is constructed, local and global features are fully extracted, multi-scale features are effectively processed, and a complex relation between data is captured through graph structure modeling, so that the elevator traction system fault detection precision is improved, and the fault detection efficiency is improved. And more accurate data support is provided for intelligent elevator operation and maintenance.

    本发明公开了基于人工智能的电梯曳引系统故障检测方法,属于智能化电梯运维技术领域,方法包括采集电梯曳引系统数据、增强电梯曳引系统数据、构建故障检测模型和电梯曳引系统故障检测。本发明采用递归生成对抗网络模型进行数据增强,更好地捕捉数据的时序依赖性,且使合成数据在统计特性上更接近实际数据,提高合成数据真实性,从而降低模型训练时的偏差,增强电梯曳引系统故障检测准确性和可靠性;采用并行深度卷积耦合图卷积网络,构建电梯曳引系统故障检测模型,充分提取局部和全局特征,有效处理多尺度特征,并通过图结构建模捕捉数据之间的复杂关系,从而提高了电梯曳引系统故障检测的精度,为智能化电梯运维提供更精准的数据支持。


    Access

    Download


    Export, share and cite



    Title :

    Elevator traction system fault detection method based on artificial intelligence


    Additional title:

    基于人工智能的电梯曳引系统故障检测方法


    Contributors:
    XIANG CHENGYU (author) / ZENG ZE'EN (author) / ZHANG NANNAN (author) / LIANG YE (author)

    Publication date :

    2025-05-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B66B Aufzüge , ELEVATORS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Traction type elevator fault analysis method

    XU HONGRUI / CUI QIU / ZHANG WENQIANG et al. | European Patent Office | 2021

    Free access

    Fault detection method for traction system and braking system of elevator

    CHAI LELE / ZHANG YUEHONG / GAO FAN et al. | European Patent Office | 2025

    Free access

    Elevator traction machine bearing fault diagnosis method

    ZHANG YUEHONG / YUAN ZHAOCHENG / ZHENG QING et al. | European Patent Office | 2023

    Free access

    Elevator fault diagnosis method based on artificial intelligence large model

    BI ZHIYI | European Patent Office | 2024

    Free access

    Elevator fault recognition system based on artificial intelligence and automatic elimination method

    YAN WENJUN / ZHU XINLIANG / WEI ZHAOLI et al. | European Patent Office | 2023

    Free access