Intelligent Diagnosis of Dual-Channel Parallel Rolling Bearings Based on Feature Fusion

残余物 冗余(工程) 计算机科学 卷积神经网络 方位(导航) 特征提取 人工智能 变压器 模式识别(心理学) 工程类 算法 电压 操作系统 电气工程
作者
Haike Guo,Xiaoqiang Zhao
出处
期刊:IEEE Sensors Journal [IEEE Sensors Council]
卷期号:24 (7): 10640-10655 被引量:3
标识
DOI:10.1109/jsen.2024.3362402
摘要

In practical engineering, due to the complex and variable working conditions of rolling bearings and the highly nonlinear characteristics of fault signals, especially in the cases of limited fault samples, it is very difficult to achieve satisfactory diagnostic results with the traditional rolling bearing fault diagnosis method. Therefore, in this paper, a two-way parallel rolling bearing intelligent diagnosis method based on multi-scale center cascaded adaptive dynamic convolutional residual network (MCADCRN) and Swin transformer (SwinT) is proposed. Firstly, the original signals are transformed into the two-dimensional time-frequency map by using continuous wavelet transform to preserve the time-frequency characteristics of the original signals. Secondly, a multi-scale center-cascaded dynamic convolutional residual block (MCDCRB) and a multi-dimensional coordinate attention mechanism (MDCAM) are designed to extract the fault features. Through multi-scale convolutional operations, MCDCRB can capture the feature information in different frequency ranges and use a cascade structure to progressively extract higher-level features. At the same time, MDCAM dynamically selects and fuses the features of different scales to reduce the information redundancy and capture the key features; next, the MCADCRN network is constructed by multiple MCDCRBs and a MDCAM to capture the local features; then, the global features of the fault information are captured by using the mechanism of the moving window self-attention in the Swin transformer network; Finally, the local features are fused with the global features and the recognition results are output. The experimental validation is carried out with two different bearing datasets, and the average diagnostic accuracy of the proposed method under variable operating conditions is 99.64%, which is 1.97, 1.53, 1.71, 1.16, and 2.84 percentage points higher than that of the five advanced methods, respectively. Under limited sample conditions, especially when there are only 50 samples, the diagnostic accuracies of the proposed method are 96.42% and 90.89%, respectively. The results verifies the effectiveness of the proposed method.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
gaojing完成签到,获得积分10
刚刚
无糖零脂完成签到,获得积分10
刚刚
CC完成签到,获得积分10
刚刚
科研通AI2S应助老八的嘴采纳,获得10
1秒前
1秒前
@∞完成签到 ,获得积分10
2秒前
杰尼龟完成签到,获得积分10
2秒前
2秒前
Polaris完成签到,获得积分10
3秒前
ccyy完成签到 ,获得积分10
3秒前
研友_ngqjz8完成签到,获得积分10
3秒前
耍酷鼠标完成签到 ,获得积分0
3秒前
嘻嘻叮完成签到,获得积分10
4秒前
wxs完成签到,获得积分10
4秒前
4秒前
Ricardo完成签到,获得积分10
4秒前
5秒前
苹果初阳关注了科研通微信公众号
6秒前
昂莫达完成签到,获得积分10
6秒前
xuhanghang发布了新的文献求助10
7秒前
WTX完成签到,获得积分0
7秒前
qhjqljqd发布了新的文献求助10
7秒前
彻底的发布了新的文献求助10
7秒前
WZH完成签到 ,获得积分10
7秒前
8秒前
8秒前
清图完成签到,获得积分10
9秒前
汉堡包应助WeiBao采纳,获得10
10秒前
渴望者发布了新的文献求助10
10秒前
星星完成签到,获得积分10
10秒前
Shyne完成签到 ,获得积分10
11秒前
kai_完成签到,获得积分10
11秒前
酷炫甜瓜完成签到,获得积分10
12秒前
12秒前
康康完成签到,获得积分10
13秒前
勤劳傲安完成签到,获得积分10
14秒前
louis dai完成签到,获得积分10
14秒前
aaaaaa发布了新的文献求助10
14秒前
花生完成签到 ,获得积分10
15秒前
DYLAN_ZZ完成签到,获得积分10
15秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968603
求助须知:如何正确求助?哪些是违规求助? 3513420
关于积分的说明 11168029
捐赠科研通 3248900
什么是DOI,文献DOI怎么找? 1794540
邀请新用户注册赠送积分活动 875187
科研通“疑难数据库(出版商)”最低求助积分说明 804676