The invention discloses an intelligent non-pneumatic tire health monitoring method based on a multi-feature fusion deep neural network, and the method comprises the following steps: collecting an acceleration signal of a non-pneumatic tire, extracting the feature parameters of the acceleration signal, and building a high-dimensional data feature data set; dividing the high-dimensional feature data into a high-dimensional training set and a high-dimensional test set; inputting the high-dimensional test set data into the multi-feature dimension reduction model, and performing dimension reduction on the high-dimensional test set data by using the trained model; inputting the dimensionality-reduced low-dimensional feature data into a Bayesian optimization deep neural network classifier for training, and predicting the fault type of the test sample based on a trained classification model; by using the method, the increasingly huge equipment operation data with high-dimension nonlinear characteristics can be processed, the dimension of the fault data is reduced, the diagnosis performance is improved, and useful information which is hidden in the data and can reflect the health condition of the equipment can be better captured.

    本发明公开了一种基于多特征融合深度神经网络的智能非充气轮胎健康监测方法,包括以下步骤:采集非充气轮胎的加速度信号,提取加速度信号的特征参数,建立高维数据特征数据集;将高维特征数据划分为高维训练集和高维测试集;将高维测试集数据输入多特征降维模型,并利用训练好的模型对高维测试集数据降维;将降维后的低维特征数据输入贝叶斯优化深度神经网络分类器中进行训练,基于训练完成的分类模型,预测测试样本的故障类型;使用本发明能处理数量日益庞大且具有高维度非线性特性的设备运行数据,降低故障数据的维度,提升诊断性能,更好的捕获隐藏在数据中能够反映设备健康状况的有用信息。


    Access

    Download


    Export, share and cite



    Title :

    Intelligent non-pneumatic tire health monitoring method based on multi-feature fusion deep neural network


    Additional title:

    一种基于多特征融合深度神经网络的智能非充气轮胎健康监测方法


    Contributors:
    DENG YAOJI (author) / LU KEYU (author) / WANG ZHIYUE (author) / LIU TAO (author) / SHEN HUI (author) / GUAN DONG (author) / HAN QINGZHEN (author) / WU GUOQIANG (author) / ZHOU QIANGQIANG (author) / GU TIANLE (author)

    Publication date :

    2024-09-03


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B60C VEHICLE TYRES , Fahrzeugreifen / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen





    TIRE PNEUMATIC PRESSURE MONITORING SYSTEM AND TIRE PNEUMATIC PRESSURE MONITORING METHOD

    YAMAGUCHI TAICHI | European Patent Office | 2020

    Free access

    TIRE PNEUMATIC PRESSURE MONITORING SYSTEM AND TIRE PNEUMATIC PRESSURE MONITORING PROGRAM

    ICHIKAWA HIROMITSU / FUKUMORI HAJIME | European Patent Office | 2024

    Free access

    A PNEUMATIC TIRE MONITORING SYSTEM AND PNEUMATIC TIRE MONITORING METHOD USING THE SAME

    LEE DONG GYU / BAE SUNG RYUL / PARK HYUN CHEOL | European Patent Office | 2022

    Free access