Comparison of Semi-supervised Deep Neural Networks for Anomaly Detection in Industrial Processes

被引:0
|
作者
Chadha, Gavneet Singh [1 ]
Rabbani, Arfyan [1 ]
Schwung, Andreas [1 ]
机构
[1] South Westphalia Univ Appl Sci, Dept Automat Technol, Soest, Germany
关键词
Semi-supervised learning; Anomaly detection; autoencoders; deep learning; REPRESENTATIONS;
D O I
10.1109/indin41052.2019.8972172
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Anomaly detection methods are used for fast and reliable detection of abnormal events in industrial processes. The early detection of anomalies can avoid critical process breakdowns and hence can increase the overall productivity of the system. The availability of labelled datasets for all the possible faulty scenarios is generally not possible, as most of the industrial systems operate in a non-faulty condition. Deep learning architectures that can be trained in an unsupervised setting such as deep autoencoders, denoising autoencoder and variational autoencoder provide an appropriate solution to this problem of unlabelled data for industrial anomaly detection. We investigate and compare the applicability of these architectures on the benchmark Tennessee Eastman fault detection study. The deep architectures are trained to model only the normal operating condition with its threshold set by kernel density estimation. A detailed comparison from the experimental results shows superior anomaly detection capabilities of the variational autoencoder as compared to the other methods.
引用
收藏
页码:214 / 219
页数:6
相关论文
共 50 条
  • [1] SEMI-SUPERVISED TRAINING OF DEEP NEURAL NETWORKS
    Vesely, Karel
    Hannemann, Mirko
    Burget, Lukas
    [J]. 2013 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2013, : 267 - 272
  • [2] Semi-supervised Deep Learning for Network Anomaly Detection
    Sun, Yuanyuan
    Guo, Lili
    Li, Ye
    Xu, Lele
    Wang, Yongming
    [J]. ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2019, PT II, 2020, 11945 : 383 - 390
  • [3] Semi-Supervised Anomaly Detection Via Neural Process
    Zhou, Fan
    Wang, Guanyu
    Zhang, Kunpeng
    Liu, Siyuan
    Zhong, Ting
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (10) : 10423 - 10435
  • [4] Semi-supervised anomaly detection in dynamic communication networks
    Meng, Xuying
    Wang, Suhang
    Liang, Zhimin
    Yao, Di
    Zhou, Jihua
    Zhang, Yujun
    [J]. Information Sciences, 2021, 571 : 527 - 542
  • [5] Semi-supervised anomaly detection in dynamic communication networks
    Meng, Xuying
    Wang, Suhang
    Liang, Zhimin
    Yao, Di
    Zhou, Jihua
    Zhang, Yujun
    [J]. INFORMATION SCIENCES, 2021, 571 : 527 - 542
  • [6] SAKMR: Industrial control anomaly detection based on semi-supervised hybrid deep learning
    Shijie Tang
    Yong Ding
    Meng Zhao
    Huiyong Wang
    [J]. Peer-to-Peer Networking and Applications, 2024, 17 : 612 - 623
  • [7] SAKMR: Industrial control anomaly detection based on semi-supervised hybrid deep learning
    Tang, Shijie
    Ding, Yong
    Zhao, Meng
    Wang, Huiyong
    [J]. PEER-TO-PEER NETWORKING AND APPLICATIONS, 2024, 17 (02) : 612 - 623
  • [8] SSCL: Semi-supervised Contrastive Learning for Industrial Anomaly Detection
    Cai, Wei
    Gao, Jiechao
    [J]. PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT IV, 2024, 14428 : 100 - 112
  • [9] Phishing Web Page Detection with Semi-Supervised Deep Anomaly Detection
    Ouyang, Linshu
    Zhang, Yongzheng
    [J]. SECURITY AND PRIVACY IN COMMUNICATION NETWORKS, SECURECOMM 2021, PT II, 2021, 399 : 384 - 393
  • [10] SEMI-SUPERVISED TRAINING STRATEGIES FOR DEEP NEURAL NETWORKS
    Gibson, Matthew
    Cook, Gary
    Zhan, Puming
    [J]. 2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2017, : 77 - 83