Energy Out-of-distribution Based Fault Detection of Multivariate Time-series Data

离群值 Softmax函数 异常检测 能量(信号处理) 计算机科学 人工神经网络 航程(航空) 人工智能 模式识别(心理学) 断层(地质) 自编码 多元统计 功能(生物学) 数据挖掘 机器学习 统计 数学 工程类 航空航天工程 地质学 地震学 生物 进化生物学
作者
Umang Goswami,Jyoti Rani,Deepak Kumar,Hariprasad Kodamana,Manojkumar Ramteke
出处
期刊:Computer-aided chemical engineering 卷期号:: 1885-1890 被引量:4
标识
DOI:10.1016/b978-0-443-15274-0.50299-7
摘要

A major challenge faced by the chemical process industry is carrying out operations safely and safely. The proposed work entails a fault detection approach for a multivariate time series dataset by utilizing the energy scores instead of the traditional approach. This work proposes a loss function which utilizes the concept of in-distribution and out of the distribution of data. Energy scores are more theoretically aligned with the probability density of the inputs and can be used as a scoring function. For a pre-trained neural network, energy can be utilized as a scoring function and can also be used as a trainable cost function. The concept of out-of-distribution is similar to that of any outlier identification method. Similarly, for energy out of distribution, an energy value which falls below a certain threshold can be considered an outlier and is addressed as out-of-distribution. The values within the range are in-distribution. Higher energy values imply a lower likelihood of occurrence and vice versa. The proposed approach is compared with different deep learning approaches like Auto-encoders (AEs), LSTMs and LSTM-AEs that are traditionally used for anomaly detection and utilize the softmax scores. The Proposed methodology is also compared with some state-of-the-art fault detection methods, such as the PCA and DPCA and returns encouraging results. Energy based out of distribution is coupled with various deep learning methods to identify faulty and normal points. When teamed with the Auto-encoder network, energy-based scoring proved to be of significant dominance compared to other methods. The study was validated for the benchmark Tennessee Eastman data for fault detection.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
失眠的夜梦完成签到,获得积分10
1秒前
谓风完成签到,获得积分10
2秒前
恋雅颖月应助乐观的寻绿采纳,获得10
2秒前
Shrine完成签到,获得积分10
2秒前
英姑应助紫色奶萨采纳,获得10
4秒前
5秒前
6秒前
希望天下0贩的0应助Jay采纳,获得10
7秒前
7秒前
爆米花应助zewangguo采纳,获得10
8秒前
斯文败类应助loong采纳,获得10
9秒前
深情安青应助Xin采纳,获得10
10秒前
和花花发布了新的文献求助10
10秒前
摩卡完成签到,获得积分10
11秒前
12秒前
13秒前
端庄毛巾完成签到,获得积分10
13秒前
14秒前
14秒前
14秒前
张雯思发布了新的文献求助10
16秒前
ding应助Nugget采纳,获得10
16秒前
幸福大白发布了新的文献求助30
19秒前
wdy111举报ZZZ求助涉嫌违规
20秒前
zewangguo发布了新的文献求助10
20秒前
21秒前
高大的冰双完成签到,获得积分10
22秒前
24秒前
987完成签到 ,获得积分10
25秒前
loong完成签到,获得积分10
25秒前
紫色奶萨发布了新的文献求助10
26秒前
zewangguo完成签到,获得积分10
26秒前
27秒前
如意手链完成签到,获得积分10
28秒前
DongWei95发布了新的文献求助30
29秒前
锦诗完成签到,获得积分10
30秒前
isojso发布了新的文献求助10
31秒前
32秒前
科研通AI2S应助科研通管家采纳,获得10
36秒前
共享精神应助科研通管家采纳,获得10
36秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174