基于 RegNet-CMSAM 轻量化模型的航空发动机轴承故障诊断

打开文本图片集

DOI：10.16652/j.issn.1004-373x.2026.10.020

引用格式：，.基于RegNet-CMSAM轻量化模型的航空发动机轴承故障诊断[J].现代电子技术，2026，49（10）：139-145.

中图分类号：TN911.23-34；TH133.3

文献标识码：A

文章编号：1004-373X（2026）10-0139-07

Aero-engine bearing fault diagnosis based on RegNet-CMSAM lightweight model

Jiang Jinhui， Tang Bo

（College of Metrology Measurement and Instrument， China Jiliang University， Hangzhou 310018， China）

Abstract： In allusion to the issues of model complexity， large parameter sizes， and high computational costs in conventional intelligent fault diagnosis methods， a method of aero-engine bearing fault diagnosis based on the RegNet-CMSAM lightweight model is proposed. The symmetrized dot pattern （SDP） is used to transform the vibration signals into two-dimensional time-frequency images. The channel-multi-scale attention mechanism （CMSAM） is proposed and combined with the improved RegNet model to realize the fault identification and classification. The experimental verification is conducted by means of the aero-engine bearing dataset from Politecnico di Torino， and the comparisons are conducted with several advanced fault identification methods. The experimental results demonstrate that the proposed method has significant advantages in terms of diagnostic accuracy， number of model parameters， and anti-noise robustness.

Keywords： aero-engine; rolling bearing; fault diagnosis; RegNet model; attention mechanism; symmetrized dot pattern

0 引言

航空发动机是飞机的核心部件，滚动轴承作为关键承载元件，直接影响发动机的寿命和可靠性[1]。（剩余9346字）