Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Calibrated Deep-Learning Risk Indexing and Latent Behavioural Profiling for Occupational Mental-Health Risk Assessment.

Bioengineering (Basel, Switzerland)·2026
Same author

Multi-Fluid Pipeline Leak Detection and Classification Using Savitzky-Golay Scalograms and Lightweight Vision Transformer Featuring Streamlined Self-Attention.

Sensors (Basel, Switzerland)·2025
Same author

A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines.

Sensors (Basel, Switzerland)·2025
Same author

Acoustic Emission-Based Pipeline Leak Detection and Size Identification Using a Customized One-Dimensional DenseNet.

Sensors (Basel, Switzerland)·2025
Same author

Enhanced Fault Diagnosis in Milling Machines Using CWT Image Augmentation and Ant Colony Optimized AlexNet.

Sensors (Basel, Switzerland)·2024
Same author

Deep Learning and IoT-Based Ankle-Foot Orthosis for Enhanced Gait Optimization.

Healthcare (Basel, Switzerland)·2024

相关实验视频

Updated: May 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

438

一种混合深度学习方法用于轴承故障诊断,使用连续波形变换和注意力增强的时空特征提取.

Muhammad Farooq Siddique1, Faisal Saleem1, Muhammad Umar1

  • 1Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea.

Sensors (Basel, Switzerland)
|May 14, 2025
PubMed
概括

本研究引入了用于轴承故障诊断的混合深度学习模型,将连续波波变换 (CWT) 与高级特征提取相结合. 该方法实现了精确的故障识别,显示了实时工业预测维护的巨大潜力.

关键词:
1D卷积剩余网络的残余网络双向长期短期记忆 双向长期短期记忆连续波形变换连续波形变换.错误诊断 错误诊断 错误诊断 是一个问题.多头自我注意的多头自我注意.

更多相关视频

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design 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

1.5K

相关实验视频

Last Updated: May 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

438
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design 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

1.5K

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:

  • 轴承故障在工业机械中至关重要,导致故障和停机时间.
  • 准确的故障诊断对于预测性维护和运营效率至关重要.
  • 传统的方法难以处理复杂的,非静止的振动信号.

研究的目的:

  • 开发一个强大的混合深度学习模型,用于准确的轴承故障诊断.
  • 为了增强从非静止和非线性振动信号的特征提取.
  • 在不同的轴承数据集上验证模型的概括能力.

主要方法:

  • 集成连续波形变换 (CWT) 用于时间频率分析.
  • 开发一个注意力增强的时空特征提取框架.
  • 使用多头自我注意 (MHSA),双向长期短期记忆 (BiLSTM) 和1D卷积残余网络 (1D conv ResNet).

主要成果:

  • 混合模型有效地捕捉了振动信号的空间和时间依赖性.
  • 证明了强大的抗噪力和精确的特征提取.
  • 在实验室和Paderborn数据集上实现了高精度和故障类别之间的清晰分离性.

结论:

  • 拟议的混合深度学习方法提供了精确可靠的轴承故障诊断.
  • 该模型具有强大的概括能力,适合各种工业条件.
  • 在复杂环境中实时预测性维护应用的巨大潜力.