首页|基于深度卷积神经网络的齿轮箱健康状态识别

基于深度卷积神经网络的齿轮箱健康状态识别

扫码查看
齿轮箱为许多机械设备的重要传动部件,其健康运行状态识别对于设备稳定运行、安全运转等具有非常重要的意义.为准确地评价齿轮箱的健康状态,提出一种基于深度卷积神经网络的齿轮箱健康状态识别方法.本文首先采用变分模态分解(Variational Mode Decomposition,VMD)与小波阈值(Wavelet Threshold,WT)结合的方式对采集的齿轮箱振动信号进行降噪.其次,对降噪后的信号进行线性及非线性特征提取.最后,采用深度卷积神经网络(Deep Convolutional Neural Network,DCNN)建立齿轮箱的健康状态识别模型.实验结果表明,所提方法对齿轮箱健康状态的正确识别率达到 97.5%以上.
Identification of Gearbox Health Status Based on Deep
Gearbox is a crucial transmission component in many types of mechanical equipment,and recognizing its operation is of utmost importance to ensure the stability and safety of the equipment.To accurately assess the health status of gearboxes,a method of identifying the gearbox health state was put forward based on deep convolution-al neural network(DCNN).Firstly,the collected vibration signal of the gearbox was denoised by using Variational Mode Decomposition(VMD)and Wavelet Threshold(WT).Secondly,linear and nonlinear feature extraction was per-formed on the signal.Finally,a DCNN was used to construct a model to identify the health state of the gearbox.Exper-iment results demonstrate that the proposed method achieves a correct recognition rate of over 97.5%for the health status of the gearbox.

GearboxVariational mode decompositionDeep convolutional neural networkHealth recognition

董洋、王琳、张驰、赵群

展开 >

沈阳工程学院能源与动力学院,辽宁 沈阳 110136

沈阳工程学院机械学院,辽宁 沈阳 110136

大连理工大学生物医学工程学院,辽宁 大连 116024

齿轮箱 变分模态分解 深度卷积神经网络 健康识别

国家自然科学基金辽宁省博士科研启动基金辽宁省教育厅科研项目辽宁省科技计划

NSFC 620013122019-BS-172JL-19092021-MS-269

2024

计算机仿真
中国航天科工集团公司第十七研究所

计算机仿真

CSTPCD
影响因子:0.518
ISSN:1006-9348
年,卷(期):2024.41(5)
  • 9