过度拟合
卷积神经网络
计算机科学
人工智能
模式识别(心理学)
断层(地质)
特征(语言学)
方位(导航)
频道(广播)
特征提取
人工神经网络
算法
计算机网络
语言学
哲学
地震学
地质学
作者
Linlin Xue,Chunli Lei,Mengxuan Jiao,Jiashuo Shi,Jianhua Li
出处
期刊:IEEE Sensors Journal
[Institute of Electrical and Electronics Engineers]
日期:2023-05-01
卷期号:23 (9): 10206-10214
被引量:15
标识
DOI:10.1109/jsen.2023.3260208
摘要
Aiming at the problem of poor fault diagnosis performance of rolling bearings under small sample conditions, a novel method based on a self-calibrated coordinate attention mechanism and multi-scale convolutional neural network (SC-MSCNN) is proposed in this article. First, the Markov transition field (MTF) is used to convert the original vibration signals into MTF images with temporal correlation. Then, the self-calibrated coordinate attention mechanism is presented, which obtains feature location information and feature channel information from two directions and locates useful features more accurately. Finally, the SC-MSCNN model is built, and the MTF images are input into the model to complete the classification. The SC-MSCNN model simplifies the structure of the model by adding jump connections, which greatly reduces the number of learnable parameters and thus alleviates the overfitting problem. The approach is demonstrated using two bearing datasets, and the results show that SC-MSCNN can accurately diagnose different fault modes using small samples under given and variable working conditions, which is superior to other popular convolutional neural networks (CNNs).
科研通智能强力驱动
Strongly Powered by AbleSci AI