The invention discloses an elevator fault detection method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a current signal of an elevator through a non-intrusive sensor, and dividing the current signal into training set data and test set data; establishing a self-supervised learning model based on a long-short-term memory artificial neural network and an automatic encoder by taking the minimum value of the reconstruction error and the latent layer feature representation vector error as a target; performing deep learning on the self-supervised learning model through the training set data to obtain a trained self-supervised learning model; performing test output on the trained self-supervised learning model by using the test set data; and judging whether the elevator has a fault or not based on a test output result. According to the method, the self-supervised learning model is established by comprehensively considering the reconstruction error and the latent layer feature representation vector error, and an abnormal score value is output for subsequent input data, so that reference is provided for the real-time running state and fault diagnosis of the elevator.

    本发明公开了一种电梯故障检测方法、装置、计算机设备及存储介质,该方法包括:利用非侵入式传感器获取电梯的电流信号,并将所述电流信号划分为训练集数据和测试集数据;以重构误差和潜层特征表示向量误差最小值为目标,基于长短期记忆人工神经网络和自动编码器建立自监督学习模型;通过所述训练集数据对所述自监督学习模型进行深度学习,得到训练后的自监督学习模型;利用所述测试集数据对训练后的自监督学习模型进行测试输出;基于所述测试输出的结果判断电梯是否存在故障。本发明通过综合考虑重构误差与潜层特征表示向量误差来建立自监督学习模型,对后续的输入数据输出异常分数值,从而为电梯的实时运行状态以及故障诊断提供参考。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Elevator fault detection method and device, computer equipment and storage medium


    Weitere Titelangaben:

    一种电梯故障检测方法、装置、计算机设备及存储介质


    Beteiligte:
    WANG GUIBIN (Autor:in) / HUANG WENJIA (Autor:in) / CHAI SONGJIAN (Autor:in) / WANG HUAIZHI (Autor:in) / PENG JIANCHUN (Autor:in)

    Erscheinungsdatum :

    2022-05-27


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / B66B Aufzüge , ELEVATORS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Elevator fault detection method and device, computer equipment and storage medium

    YANG MING | Europäisches Patentamt | 2020

    Freier Zugriff

    Elevator fault detection method and device, computer device, and storage medium

    YANG MING | Europäisches Patentamt | 2020

    Freier Zugriff

    Elevator fault detection method and device and computer readable storage medium

    JIA YOUWEI / GUO YUJIA / CHAI SONGJIAN | Europäisches Patentamt | 2022

    Freier Zugriff

    Elevator fault detection method, device and system and computer readable storage medium

    FAN YUCHUAN / WU BIN / FAN BO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Elevator detection method, elevator detection device, electronic equipment and storage medium

    JIA YOUWEI / CHEN JIAWEN / CHAI SONGJIAN | Europäisches Patentamt | 2022

    Freier Zugriff