Abstract
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.
Supported by Centrica plc. Registered office: Millstream, Maidenhead Road, Windsor SL4 5GD, United Kingdom.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
A simplified process diagram of the compression train can be found in Fig. 6 at the appendix.
- 2.
A list of sensors is available in the appendix.
References
Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E.: The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min. Knowl. Discov. 31(3), 606–660 (2017). https://doi.org/10.1007/s10618-016-0483-9
Cho, K., van Merrienboer, B., Gülçehre, Ç., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR abs/1406.1078 (2014). http://arxiv.org/abs/1406.1078
Chung, Y., Wu, C., Shen, C., Lee, H., Lee, L.: Audio word2vec: Unsupervised learning of audio segment representations using sequence-to-sequence autoencoder. CoRR abs/1603.00982 (2016). http://arxiv.org/abs/1603.00982
D’Avino, D., Cozzolino, D., Poggi, G., Verdoliva, L.: Autoencoder with recurrent neural networks for video forgery detection. CoRR abs/1708.08754 (2017). http://arxiv.org/abs/1708.08754
Gillian, N.E., Knapp, R.B., O’Modhrain, M.S.: Recognition of multivariate temporal musical gestures using n-dimensional dynamic time warping. In: NIME (2011)
Giorgino, T.: Computing and visualizing dynamic time warping alignments in R: the dtw package. J. Stat. Softw. 31(7), 1–24 (2009). https://doi.org/10.18637/jss.v031.i07
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
ten Holt, G., Reinders, M., Hendriks, E.: Multi-dimensional dynamic time warping for gesture recognition (2007)
Hsu, D.: Time series compression based on adaptive piecewise recurrent autoencoder. CoRR abs/1707.07961 (2017). http://arxiv.org/abs/1707.07961
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs/1412.6980 (2014). http://arxiv.org/abs/1412.6980
Ko, M.H., West, G., Venkatesh, S., Kumar, M.: Online context recognition in multisensor systems using dynamic time warping. In: 2005 International Conference on Intelligent Sensors, Sensor Networks and Information Processing, pp. 283–288, December 2005. https://doi.org/10.1109/ISSNIP.2005.1595593
Lee, D.: Anomaly Detection in Multivariate Non-stationary Time Series for Automatic DBMS Diagnosis. ArXiv e-prints, August 2017
Liu, J., Wang, Z., Zhong, L., Wickramasuriya, J., Vasudevan, V.: uWave: accelerometer-based personalized gesture recognition and its applications. In: 2009 IEEE International Conference on Pervasive Computing and Communications, pp. 1–9, March 2009. https://doi.org/10.1109/PERCOM.2009.4912759
Malhotra, P., TV, V., Vig, L., Agarwal, P., Shroff, G.: TimeNet: pre-trained deep recurrent neural network for time series classification. CoRR abs/1706.08838 (2017). http://arxiv.org/abs/1706.08838
Petitjean, F., Inglada, J., Gancarski, P.: Satellite image time series analysis under time warping. IEEE Trans. Geosci. Remote Sens. 50(8), 3081–3095 (2012). https://doi.org/10.1109/TGRS.2011.2179050
Shokoohi-Yekta, M., Hu, B., Jin, H., Wang, J., Keogh, E.: Generalizing DTW to the multi-dimensional case requires an adaptive approach. Data Min. Knowl. Discov. 31(1), 1–31 (2017). https://doi.org/10.1007/s10618-016-0455-0
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014). http://jmlr.org/papers/v15/srivastava14a.html
Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using lstms. CoRR abs/1502.04681 (2015). http://arxiv.org/abs/1502.04681
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. CoRR abs/1409.3215 (2014). http://arxiv.org/abs/1409.3215
Vlachos, M., Hadjieleftheriou, M., Gunopulos, D., Keogh, E.: Indexing multidimensional time-series. VLDB J. 15(1), 1–20 (2006). https://doi.org/10.1007/s00778-004-0144-2
Wang, J., Balasubramanian, A., Mojica de la Vega, L., Green, J., Samal, A., Prabhakaran, B.: Word recognition from continuous articulatory movement time-series data using symbolic representations (2013)
Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. CoRR abs/1409.2329 (2014). http://arxiv.org/abs/1409.2329
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
Appendix A
The rotary components are driven by industrial RB-211 jet turbine on a single shaft through a gearbox. Incoming natural gas passes through the low pressure (LP) stage first which brings it to an intermediate pressure level, it then passes through the high pressure (HP) stage and reaches the pre-set desired pressure level. The purpose of the suction scrubber is to remove any remaining condensate from the gas prior to feeding through the centrifugal compressors. Once the hot compressed gas is discharged from the compressor, its temperature is lowered via the intercoolers (Fig. 7).
A simplified process diagram of the two-stage centrifugal compression train which is located at a natural gas terminal.
Locations of key components around the centrifugal compressor.
Appendix B
The sensor measurements used in the analysis are listed below:
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wong, T., Luo, Z. (2018). Recurrent Auto-Encoder Model for Large-Scale Industrial Sensor Signal Analysis. In: Pimenidis, E., Jayne, C. (eds) Engineering Applications of Neural Networks. EANN 2018. Communications in Computer and Information Science, vol 893. Springer, Cham. https://doi.org/10.1007/978-3-319-98204-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-98204-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98203-8
Online ISBN: 978-3-319-98204-5
eBook Packages: Computer ScienceComputer Science (R0)