A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis

人工智能 计算机科学 深度学习 学习迁移 自编码 原始数据 断层(地质) 人工神经网络 滤波器(信号处理) 机器学习 代表(政治) 编码器 模式识别(心理学) 试验数据 数据挖掘 地质学 计算机视觉 地震学 操作系统 政治学 政治 法学 程序设计语言
作者
Long Wen,Liang Gao,Xinyu Li
出处
期刊:IEEE transactions on systems, man, and cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:49 (1): 136-144 被引量:905
标识
DOI:10.1109/tsmc.2017.2754287
摘要

Fault diagnosis plays an important role in modern industry. With the development of smart manufacturing, the data-driven fault diagnosis becomes hot. However, traditional methods have two shortcomings: 1) their performances depend on the good design of handcrafted features of data, but it is difficult to predesign these features and 2) they work well under a general assumption: the training data and testing data should be drawn from the same distribution, but this assumption fails in many engineering applications. Since deep learning (DL) can extract the hierarchical representation features of raw data, and transfer learning provides a good way to perform a learning task on the different but related distribution datasets, deep transfer learning (DTL) has been developed for fault diagnosis. In this paper, a new DTL method is proposed. It uses a three-layer sparse auto-encoder to extract the features of raw data, and applies the maximum mean discrepancy term to minimizing the discrepancy penalty between the features from training data and testing data. The proposed DTL is tested on the famous motor bearing dataset from the Case Western Reserve University. The results show a good improvement, and DTL achieves higher prediction accuracies on most experiments than DL. The prediction accuracy of DTL, which is as high as 99.82%, is better than the results of other algorithms, including deep belief network, sparse filter, artificial neural network, support vector machine and some other traditional methods. What is more, two additional analytical experiments are conducted. The results show that a good unlabeled third dataset may be helpful to DTL, and a good linear relationship between the final prediction accuracies and their standard deviations have been observed.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
wanci应助De_Frank123采纳,获得10
刚刚
结实的芷文完成签到,获得积分20
刚刚
刚刚
Pipper完成签到,获得积分10
刚刚
1秒前
sabre1980完成签到 ,获得积分10
1秒前
陈小强应助爱听歌的青筠采纳,获得10
1秒前
1秒前
1秒前
2秒前
GGBond发布了新的文献求助10
2秒前
2秒前
3秒前
呼延慕晴完成签到,获得积分20
3秒前
大个应助tt采纳,获得10
3秒前
小二郎应助学习。。采纳,获得10
4秒前
4秒前
踏实的幻珊完成签到 ,获得积分10
4秒前
anagenesis发布了新的文献求助30
4秒前
4秒前
爆爆完成签到,获得积分10
4秒前
梦XING完成签到,获得积分10
5秒前
善学以致用应助现代雪柳采纳,获得10
5秒前
Qingwenxin发布了新的文献求助10
6秒前
周亭完成签到,获得积分10
6秒前
Lynn发布了新的文献求助10
6秒前
呼延慕晴发布了新的文献求助10
7秒前
华仔应助想瘦的海豹采纳,获得10
7秒前
安详的梦旋完成签到,获得积分10
7秒前
研友_VZG7GZ应助GGBond采纳,获得10
7秒前
ding应助阳光曼冬采纳,获得10
7秒前
xxxx完成签到 ,获得积分10
7秒前
刘昀鑫发布了新的文献求助10
7秒前
JamesPei应助代骜珺采纳,获得10
8秒前
8秒前
8秒前
杨震完成签到 ,获得积分10
9秒前
赏你半斤地瓜烧完成签到,获得积分20
9秒前
梦XING发布了新的文献求助10
9秒前
9秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 1000
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3245070
求助须知:如何正确求助?哪些是违规求助? 2888780
关于积分的说明 8255477
捐赠科研通 2557124
什么是DOI,文献DOI怎么找? 1385882
科研通“疑难数据库(出版商)”最低求助积分说明 650248
邀请新用户注册赠送积分活动 626457