南京师范大学学报（工程技术版）2025，Vol.25Issue(2)：88-95,8.DOI:10.3969/j.issn.1672-1292.2025.02.008
基于CNN和LSTM的旋转轴承故障检测方法
Rolling Bearing Fault Detection Method Based on CNN and LSTM:WDC-LSTM
陈莹洁 1刘利达 2孙玫 3林培光 1王琦淼1
作者信息
- 1. 山东财经大学计算机与人工智能学院,山东 济南 250014
- 2. 山东润一智能科技有限公司,山东 济南 250013||清华大学深圳国际研究生院,广东 深圳 518055
- 3. 山东财经大学财政税务学院,山东 济南 250014
- 折叠
摘要
Abstract
Mechanical fault diagnosis is a key factor in ensuring for the reliability and safety of modern automated mechanical systems that are becoming increasingly complex.As a core component of modern mechanical system,the health status of rolling bearings directly affects the performance and lifespan of the bearing-driven machinery,and has always been a popular topic in the field of fault diagnosis.Traditional bearing fault detection methods often rely on manual feature extraction and classifier design,and their efficiency and accuracy are limited.In this paper,we propose a deep learning method based on convolutional neural network(CNN)and long short-term memory network(LSTM):WDC-LSTM.CNNs extract key local features from vibration signals,while LSTMs process these feature sequences to capture continuity and dynamic changes over time,and the combination of the two enables the model to account for both the spatial and temporal characteristics of bearing failure data to achieve end-to-end bearing fault detection.To validate the performance of the method,we conducted experiments using the Case Western Reserve University bearing fault dataset and compared it to other common methods.The experimental results show that the bearing fault detection method based on CNN and LSTM(WDC-LSTM)has high accuracy and strong generalization ability in bearing fault classification.关键词
振动信号/卷积神经网络/长短期记忆网络/轴承故障诊断/深度学习应用Key words
vibration signal/CNN/LSTM/bearing fault diagnosis/deep learning applications分类
计算机与自动化引用本文复制引用
陈莹洁,刘利达,孙玫,林培光,王琦淼..基于CNN和LSTM的旋转轴承故障检测方法[J].南京师范大学学报（工程技术版）,2025,25(2):88-95,8.
