The invention discloses an elevator fault diagnosis method based on a convolutional neural network, and the method comprises the steps: constructing an active learning framework based on a query strategy, and enabling the active learning framework to comprise a data management module, a query strategy module and a convolutional neural network model; training an initial convolutional neural network by using a small amount of labeled data; obtaining the prediction probability of the model to all the label-free data sets, and calculating the gradient embedding vector of the model; using a K-means + + algorithm to further screen out a label-free data set with high contribution degree and diversity, performing manual labeling, using the label-free data set with high contribution degree and diversity to re-train the model, and circulating the process until the label-free data set is used up or the model reaches specified test accuracy; according to the method, information implied in unlabeled samples is mined from the aspects of a network model framework, a loss function, a query strategy and the like, importance sorting is performed on the samples which are most difficult to understand in the model, experts are enabled to concentrate on providing the most useful information, and the training cost of model construction is reduced.

    本发明公开了一种基于卷积神经网络的电梯故障诊断方法,构建基于查询策略的主动学习框架,包括数据管理模块、查询策略模块与卷积神经网络模型;使用少量有标签数据训练初始卷积神经网络;获取该模型对所有无标签数据集的预测概率,并计算其梯度嵌入向量;使用K‑means++算法进一步筛选出兼具高贡献度和多样性的无标签数据集,交由人工标注,再使用兼具高贡献度和多样性的无标签数据集重新训练模型,循环这个过程直至耗尽无标签数据集或者模型到达指定测试准确度;本发明从网络模型框架、损失函数和查询策略等层面发掘无标签样本中隐含的信息,对模型最难理解的样本进行重要性排序,让专家集中精力提供最有用的信息,以降低构建模型的训练成本。


    Access

    Download


    Export, share and cite



    Title :

    Elevator fault diagnosis method based on convolutional neural network


    Additional title:

    一种基于卷积神经网络的电梯故障诊断方法


    Contributors:
    ZHANG YUEHONG (author) / YUAN ZHAOCHENG (author) / CHEN FANG (author) / MA JIAHAO (author) / LI JIBO (author) / LI KUN (author) / YANG WENHUI (author) / CHEN YONGXIAN (author) / LIU SHU (author) / WU CHUNPENG (author)

    Publication date :

    2025-01-07


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B66B Aufzüge , ELEVATORS



    Elevator fault diagnosis method based on one-dimensional convolutional neural network and meta learning

    DONG TIANWEI / ZANG CHUANZHI / ZHAO BAOJUN et al. | European Patent Office | 2023

    Free access

    Elevator fault diagnosis method based on graph neural network

    HE YUCHEN / HU WENHAO / WANG QIBING et al. | European Patent Office | 2023

    Free access

    Elevator fault diagnosis device and elevator fault diagnosis method

    TAKAGAMI RYOMA | European Patent Office | 2022

    Free access

    Elevator fault diagnosis system using recurrent neural network model

    XU ZHIHUI | European Patent Office | 2023

    Free access

    Multi-scale convolutional capsule network elevator fault diagnosis method based on data enhancement and attention mechanism

    LU JIAWEI / ZHANG WEICHAO / WANG QIBING et al. | European Patent Office | 2024

    Free access