Abstract
Multivariate time series is widely used to evaluate and predict the health state of system. To focus on the importance of prediction accuracy for multivariate time series, many a research have been done on improving the performance of predictive model. However, for multivariate time series, the prediction accuracy depends not only on predictive model but also on the input information. In this paper, we combine data fusion with ESN to improve the prediction accuracy of multivariate time series, which focuses on both the processing of the input information of predictive model and the optimizing of predictive model. First, multi-sources data fusion is presented to obtain the new input for prediction model before predicting; phase space reconstruction and self-adaptive weighted fusion algorithm are adopted to fuse multivariate time series and obtain more complete information. Then, leaky rectifier liner units are used to replace the original activation function, tanh, and locality preserving projection is employed to optimize the state matrix of the reservoir. Finally, the effectiveness of the proposed method is verified by an analysis of one case study of real compressor groups data sets in chemical production system. The results and a comparison with the traditional method show that the proposed method can greatly enhance the prediction accuracy of multivariate time series and the one-step ahead prediction accuracy is improved by three orders of magnitude as well as a better generalization ability is obtained in the multi-steps ahead prediction.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Antonelo EA, Flesch CA, Schmitz F (2017) Reservoir computing for detection of steady state in performance tests of compressors. Neurocomputing 275:598–607. https://doi.org/10.1016/j.neucom.2017.09.005
Bianchi FM, Santis ED, RizziI A, Sadeghian A (2015) Short-term electric load forecasting using echo state networks and PCA decomposition. IEEE Access 3:1931–1943. https://doi.org/10.1109/ACCESS.2015.2485943
Cheng S, Tom K, Thomas L, Pecht M (2010) A wireless sensor system for prognostics and health management. IEEE Sens J 10(4):856–862. https://doi.org/10.1109/JSEN.2009.2035817
Chouikhi N, Ammar B, Rokbani N, Alimi AM (2017) PSO-based analysis of Echo State Network parameters for time series forecasting. Appl Soft Comput J 55:211–225. https://doi.org/10.1016/j.asoc.2017.01.049
Cui H, Feng C, Chai Y, Liu RP, Liu Y (2014) Effect of hybrid circle reservoir injected with wavelet-neurons on performance of echo state network. Neural Netw 57(9):141–151. https://doi.org/10.1016/j.neunet.2014.05.013
Elattar HM, Elattar HK, Riad AM (2016) Prognostics: a literature review. Complex Intell Syst 2(2):125–154. https://doi.org/10.1007/s40747-016-0019-3
Fan HT, Wang W, Jin ZP (2017) Performance optimization of echo state networks through principal neuron reinforcement. In: International joint conference on neural networks, pp 1717–1723. https://dx.doi.org/10.1109/IJCNN.2017.7966058
Fong B, Ansari N, Fong ACM (2012) Prognostics and health management for wireless telemedicine networks. IEEE Wirel Commu 19(5):83–89. https://doi.org/10.1109/MWC.2012.6339476
Han F (2014) Short-term traffic flow prediction based on multivariable phase space reconstruction and LSSVM. J Inf Comput Sci 11(9):3209–3217. https://doi.org/10.12733/jics20103884
Han M, Xu M (2015) Predicting multivariate time series using subspace echo state network. Neural Process Lett 41(2):201–209. https://doi.org/10.1007/s11063-013-9324-7
Han M, Xu M (2018) Laplacian echo state network for multivariate time series prediction. IEEE Trans Neural Netw Learn Syst 29(1):238–244. https://doi.org/10.1109/TNNLS.2016.2574963
Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 308:78–80. https://doi.org/10.1126/science.1091277
Jaeger H, Lukosevicius M, Dan P, Siewert U (2007) Optimization and applications of echo state networks with leaky-integrator neurons. Neural Netw 20(3):335–352. https://doi.org/10.1016/j.neunet.2007.04.016
Jeong JY, Kim JS, Jun CH (2015) Effect of dimension reduction on prediction performance of multivariate nonlinear time series. Ind Eng Manag Syst 14(3):312–317. https://doi.org/10.7232/iems.2015.14.3.312
Ji Z, Pang Y, He Y, Zhang H (2015) Semi-supervised LPP algorithms for learning-to-rank-based visual search reranking. Inf Sci 302(1):83–93. https://doi.org/10.1016/j.ins.2014.10.037
Junxia SU (2007) The social cognitive optimization Applied in nonlinear programming problems. Comput Simulation 24(9):261–264
Kodba S, Perc M, Marhl M (2005) Detecting chaos from a time series. Eur J Phys J Eur Phys Soc 26(26):205–215. https://doi.org/10.1088/0143-0807/26/1/021
Kostic S, Perc M, Vasovic N, Trajkovic S (2013) Predictions of experimentally observed stochastic ground vibrations induced by blasting. PLoS One 8(12):82056. https://doi.org/10.1371/journal.pone.0082056
Liu D, Wang JL, Wang H (2015) Short-term wind speed forecasting based on spectral clustering and optimized echo state network. Renew Energy 78:599–608. https://doi.org/10.1016/j.renene.2015.01.022
Liu S, Xu L, Li D (2016) Multi-scale prediction of water temperature using empirical mode decomposition with back-propagation neural networks. Comput Electr Eng 49:1–8. https://doi.org/10.1016/j.compeleceng.2015.10.003
Lokse S, Bianchi FM, Jenssen R (2017) Training echo state networks with regularization through dimensionality reduction. Cogn Comput 9(3):364–378. https://doi.org/10.1007/s12559-017-9450-z
Perc M (2005) Nonlinear time series analysis of the human electrocardiogram. Eur J Phys 26(5):757–768. https://doi.org/10.1088/0143-0807/26/5/008
Rigamonti M, Baraldi P, Zio E, Roychoudhury I, Kai G et al (2017) Ensemble of optimized echo state networks for remaining useful life prediction. Neurocomputing 281:121–138. https://doi.org/10.1016/j.neucom.2017.11.062
Rui C, Lin SL, Rui M (2008) Approach to phase space reconstruction from multivariate data based on data fusion. Acta Phys Sin 57(12):7487–7493
Shen L, Chen J, Zeng Z, Yang J, Jin J (2017) A novel echo state network for multivariate and nonlinear time series prediction. Appl Soft Comput 62:524–535. https://doi.org/10.1016/j.asoc.2017.10.038
Sun X, Li T, Li Q, Huang Y, Li Y (2017) Deep belief echo-state network and its application to time series prediction. Knowl Based Syst 130:17–29. https://doi.org/10.1016/j.knosys.2017.05.022
Wang RX, Gao JM, Gao ZY, Gao X, Jiang HQ (2016) Complex network theory-based condition recognition of electromechanical system in process industry. Sci China Technol Sci 59(4):604–617. https://doi.org/10.1007/s11431-016-6025-2
Wang HS, Ni CJ, Yan XF (2017) Optimizing the echo state network based on mutual information for modeling fed-batch bioprocesses. Neurocomputing 225:111–118. https://doi.org/10.1016/j.neucom.2016.11.007
Xue FZ, Li Q, Li XM (2017) The combination of circle topology and leaky integrator neurons remarkably improves the performance of echo state network on time series prediction. PLoS One 12(7):e0181816. https://doi.org/10.1371/journal.pone.0181816
Yin Y, Shang P (2016) Forecasting traffic time series with multivariate predicting method. Appl Math Comput 291:266–278. https://doi.org/10.1016/j.amc.2016.07.017
Acknowledgements
The authors sincerely thank the referees for their helpful suggestions and comments, which greatly improved the quality of the paper. This research was supported by the National Natural Science Foundation of China (Grant by no. 51375375).
Author information
Authors and Affiliations
Contributions
All authors contributed equally and significantly in writing this article. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that they have no competing interest.
Additional information
Communicated by Cristina Turner.
Rights and permissions
About this article
Cite this article
Liang, Y., Gao, Z., Gao, J. et al. Data fusion combined with echo state network for multivariate time series prediction in complex electromechanical system. Comp. Appl. Math. 37, 5920–5934 (2018). https://doi.org/10.1007/s40314-018-0669-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40314-018-0669-4
Keywords
- Echo state network
- Multivariate time series prediction
- Adaptive weighted fusion estimating
- Phase space reconstruction
- Locality preserving projection