基于多模态时频图融合的风电机组齿轮箱故障诊断方法
摘要:特征提取是故障诊断问题的关键，风电机组齿轮箱负载多变，振动数据量大、信息密度低，导致多模态融合诊断方法的特征学习性能和计算成本难以兼顾。为此，提出了基于多模态时频图融合的风电机组齿轮箱故障诊断方法。首先，使用小波包分解算法对齿轮箱振动数据集进行故障特征分析；然后，将所得分解子信号和原始信号分别转化为二维时频图像，形成体现小波域和时频域的互补故障特征；最后，利用卷积神经网络(convolutional neural networks, CNN)分别学习图像纹理的深层特征并进行特征融合，训练基于CNN-ViT(vision transformer)的多模态故障诊断模型。以凯斯西储大学齿轮箱轴承数据进行验证，所提模型在变负载和未知故障下，相比其他单模态和多模态方法具有较高的准确率，时频图融合方法能够以较低计算成本实现小波域和时频域双模态的故障特征学习。
Abstract：Feature extraction is the key to the fault diagnosis problem, and the variable load of wind turbine gearboxes, large amount of vibration data and low information density make it difficult to balance the feature learning performance and computational cost of multimodal fusion diagnosis method. To this end, a wind turbine gearbox fault diagnosis method based on multimodal time-frequency map fusion is proposed. First, a wavelet packet decomposition algorithm is used to analyze the fault features of the gearbox vibration data set; then, the decomposed sub-signal and the original signal are transformed into two-dimensional time-frequency images to form complementary fault features reflecting the wavelet domain and the time-frequency domain; finally, a convolutional neural network (CNN) is used to learn the deep features of the image texture and fuse them separately to train a CNN-ViT (vision transformer) multimodal fault diagnosis model. The proposed model is validated with Case Western Reserve University gearbox bearing data, and has higher accuracy compared with other unimodal and multimodal methods under variable load and unknown faults, and the time-frequency map fusion method can realize the fault feature learning in both wavelet domain and time-frequency domain dual modality with lower computational cost.
标题：基于多模态时频图融合的风电机组齿轮箱故障诊断方法
title:Fault Diagnosis Method of Wind Turbine Gearbox Based on Multi-Mode Time-Frequency Image Fusion
作者：陈阳,刘永前,韩爽,王罗
authors:CHAN Yang,LIU Yongqian,HAN Shuang,WANG Luo
关键词：风电机组齿轮箱,故障诊断,小波包分析,多模态融合,图像分类,
keywords:wind turbine gear box,fault diagnosis,wavelet packet analysis,multimodal fusion,image classification,
发表日期：2023-07-26
- 文件大小:
- 1.71 MB
- 下载次数:
- 60
-
高速下载
|
|
