The invention discloses an elevator traction machine bearing fault diagnosis method, and relates to the field of fault diagnosis, and the method comprises the steps: S1, obtaining a vibration acceleration signal; s2, extracting time-frequency domain characteristics of the vibration acceleration signal, and converting the time-frequency domain characteristics into a time-frequency domain grey-scale map; s3, constructing a classifier evaluation auxiliary generative adversarial network; s4, training an optimization classifier to evaluate the auxiliary generative adversarial network; s5, generating a training generation sample by the optimized generator, and mixing the training generation sample with a real sample to form a training set; s6, constructing a classification model, training and optimizing the classification model, and taking the optimized classification model as a fault diagnosis model; s7, acquiring real-time monitoring data; s8, the fault diagnosis model outputs a fault diagnosis result; the quality of bearing fault data generated by the auxiliary generative adversarial network is evaluated by using a classifier, and the problem of sample imbalance is solved by using a data expansion technology; the classifier and the discriminator adopt independent convolutional layers and pooling layers to realize feature extraction, so that different networks can respectively learn features suitable for different tasks, and the risk of model overfitting is reduced.

    本发明公开了电梯曳引机轴承故障诊断方法,涉及故障诊断领域,包括S1获取振动加速度信号;S2提取振动加速度信号的时频域特征,转化为时频域灰度图;S3构建分类器评价辅助生成对抗网络;S4训练优化分类器评价辅助生成对抗网络;S5优化后的生成器生成训练生成样本,并与真实样本混合构成训练集;S6构建分类模型,并训练优化,优化的分类模型作为故障诊断模型;S7获取实时监测数据;S8故障诊断模型输出故障诊断结果;利用分类器评价辅助生成对抗网络生成的轴承故障数据的质量,使用数据扩充技术来解决样本不均衡的问题;分类器与判别器采用独立的卷积层与池化层实现特征提取,可使不同网络分别学习适合于不同任务的特征,降低模型过拟合的风险。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Elevator traction machine bearing fault diagnosis method


    Weitere Titelangaben:

    电梯曳引机轴承故障诊断方法


    Beteiligte:
    ZHANG YUEHONG (Autor:in) / YUAN ZHAOCHENG (Autor:in) / ZHENG QING (Autor:in) / ZHAO DING (Autor:in) / ZHANG KAI (Autor:in) / LI KUN (Autor:in) / HUANG FENGFEI (Autor:in) / YANG WENHUI (Autor:in)

    Erscheinungsdatum :

    2023-07-25


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B66B Aufzüge , ELEVATORS / G01M TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES , Prüfen der statischen oder dynamischen Massenverteilung rotierender Teile von Maschinen oder Konstruktionen / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Bearing temperature measuring device for elevator traction machine

    LI GE / DING AIQIN / ZHU DONGJUN | Europäisches Patentamt | 2015

    Freier Zugriff

    Elevator traction machine

    ZHOU XIAOXUE / NI MINHUA | Europäisches Patentamt | 2020

    Freier Zugriff

    Elevator traction machine

    FANG KAI / LI WEI | Europäisches Patentamt | 2016

    Freier Zugriff

    Traction type elevator fault analysis method

    XU HONGRUI / CUI QIU / ZHANG WENQIANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Elevator traction machine

    LI HONGWEI | Europäisches Patentamt | 2015

    Freier Zugriff