基于格拉米安角场和轻量级模型的滚动轴承故障诊断的研究
Jingtao Shen1, Zhe Wu1, Yachao Cao1
1School of Mechanical Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China.
这项研究引入了一种新的滚动轴承故障诊断方法,使用格拉米安角场 (GAF) 图像和增强的轻量级残余网络 (E-ResNet13). 该GAF-E-ResNet13模型在诊断轴承故障方面实现了卓越的准确性和效率.
科学领域:
- 机械工程 机械工程
- 人工智能的人工智能
- 信号处理 信号处理
背景情况:
- 深度学习模型在一维信号特征提取方面扎,导致高复杂性和资源消耗.
- 目前用于滚动轴承故障诊断的现有方法往往在准确性和计算效率方面面临限制.
研究的目的:
- 开发一种创新高效的滚动轴承故障诊断方法.
- 在信号处理和计算复杂性方面克服传统深度学习模型的局限性.
主要方法:
- 将一维信号转换为二维格拉米安角场 (GAF) 图像,以保持时间依赖.
- 通过优化ResNet-18,删除冗余层,并结合深度可分离卷积和高效通道注意 (ECA) 模块来开发增强的轻量级残余网络 (E-ResNet13).
- 用GAF图像训练E-ResNet13模型,用于滚动轴承故障分类.
主要成果:
- 与其他编码技术相比,GAF图像编码方法显示出更高的故障识别精度.
- 拟议的GAF-E-ResNet13模型在各种条件下表现出强大的诊断性能和概括能力.
- 增强的轻量级残余网络 (E-ResNet13) 保持了高精度,同时显著降低了计算成本.
结论:
- GAF-E-ResNet13方法为滚动轴承故障诊断提供了一种创新且实用的解决方案.
- 该方法有效地解决了深度学习中信号特征提取和模型复杂性的挑战.
- 该研究验证了GAF图像编码的优越性和E-ResNet13模型的智能诊断效率.
更多相关视频
11:51Visually Based Characterization of the Incipient Particle Motion in Regular Substrates: From Laminar to Turbulent Conditions
Published on: February 22, 2018
06:45Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
Published on: October 28, 2022
相关概念视频
Bearings: Problem Solving
Equation of Motion: General Plane motion - Problem Solving
The friction between the roller and the ground is characterized by two coefficients. The static friction coefficient is 0.15, while the kinetic friction coefficient is 0.1. These values are crucial in understanding the interaction between...
Rolling Resistance: Problem Solving
Journal Bearings
To better understand the concept of journal bearings, consider a rope winch with dry or...
Bearing Stress
Due to the intricacy of these microforces, an average value, known as bearing stress, is often used by...
General Case of Eccentric Axial Loading
Consider a member subjected to equal and opposite forces that are applied along a line that does not coincide with the member's neutral axis. In unsymmetrical...
