Recurrent Auto-Encoder Model for Large-Scale Industrial Sensor Signal Analysis

被引:9
|
作者
Wong, Timothy [1 ]
Luo, Zhiyuan [1 ]
机构
[1] Univ London, Royal Holloway, Egham TW20 0EX, Surrey, England
关键词
Recurrent auto-encoder; Multidimensional time series; Industrial sensors; Signal analysis;
D O I
10.1007/978-3-319-98204-5_17
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recurrent auto-encoder model summarises sequential data through an encoder structure into a fixed-length vector and then reconstructs the original sequence through the decoder structure. The summarised vector can be used to represent time series features. In this paper, we propose relaxing the dimensionality of the decoder output so that it performs partial reconstruction. The fixed-length vector therefore represents features in the selected dimensions only. In addition, we propose using rolling fixed window approach to generate training samples from unbounded time series data. The change of time series features over time can be summarised as a smooth trajectory path. The fixed-length vectors are further analysed using additional visualisation and unsupervised clustering techniques. The proposed method can be applied in large-scale industrial processes for sensors signal analysis purpose, where clusters of the vector representations can reflect the operating states of the industrial system.
引用
收藏
页码:203 / 216
页数:14
相关论文
共 50 条
  • [41] Change Detection Based on Auto-encoder Model for VHR Images
    Xu, Yuan
    Xiang, Shiming
    Huo, Chunlei
    Pan, Chunhong
    MIPPR 2013: PATTERN RECOGNITION AND COMPUTER VISION, 2013, 8919
  • [42] Modeling and augmenting of fMRI data using deep recurrent variational auto-encoder
    Qiang, Ning
    Dong, Qinglin
    Liang, Hongtao
    Ge, Bao
    Zhang, Shu
    Sun, Yifei
    Zhang, Cheng
    Zhang, Wei
    Gao, Jie
    Liu, Tianming
    JOURNAL OF NEURAL ENGINEERING, 2021, 18 (04)
  • [43] An Enhanced Gated Recurrent Unit with Auto-Encoder for Solving Text Classification Problems
    Muhammad Zulqarnain
    Rozaida Ghazali
    Yana Mazwin Mohmad Hassim
    Muhammad Aamir
    Arabian Journal for Science and Engineering, 2021, 46 : 8953 - 8967
  • [44] A novel ECG signal compression method using spindle convolutional auto-encoder
    Wang, Fei
    Ma, Qiming
    Liu, Wenhan
    Chang, Sheng
    Wang, Hao
    He, Jin
    Huang, Qijun
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2019, 175 : 139 - 150
  • [45] Compression of PPG Signal Through Joint Technique of Auto-Encoder and Feature Selection
    Shankar, Shiva K. N.
    Shankar, Shiva
    Keshavamurthy
    INTERNATIONAL JOURNAL OF HEALTHCARE INFORMATION SYSTEMS AND INFORMATICS, 2021, 16 (04)
  • [46] A unified auto-encoder method for gait recognition under different sensor locations
    Chang, Ying
    Wang, Lan
    Lin, Lingjie
    Liu, Ming
    INTERNET TECHNOLOGY LETTERS, 2023, 6 (05)
  • [47] MIXTURE FACTORIZED AUTO-ENCODER FOR UNSUPERVISED HIERARCHICAL DEEP FACTORIZATION OF SPEECH SIGNAL
    Peng, Zhiyuan
    Feng, Siyuan
    Lee, Tan
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 6774 - 6778
  • [48] Simultaneous spatial-temporal decomposition for connectome-scale brain networks by deep sparse recurrent auto-encoder
    Li, Qing
    Dong, Qinglin
    Ge, Fangfei
    Qiang, Ning
    Wu, Xia
    Liu, Tianming
    BRAIN IMAGING AND BEHAVIOR, 2021, 15 (05) : 2646 - 2660
  • [49] An event related potential electroencephalogram signal analysis method based on denoising auto-encoder neural network
    Wang H.-T.
    Huang H.
    He Y.-B.
    Liu X.-C.
    Li T.
    Kongzhi Lilun Yu Yingyong/Control Theory and Applications, 2019, 36 (04): : 589 - 595
  • [50] Multi-sensor signal fusion for tool wear condition monitoring using denoising transformer auto-encoder Resnet
    Wang, Hui
    Wang, Shuhui
    Sun, Weifang
    Xiang, Jiawei
    JOURNAL OF MANUFACTURING PROCESSES, 2024, 124 : 1054 - 1064