Multi-Step Ahead Prediction for Electromechanical Device Using Multivariate SVM Predictor

Abstract:

Electromechanical device driven by motor plays a crucial role in the operation of modern industry. A reliable time series predictor can be a very useful tool in the field of Condition-Based Maintenance (CBM) to forecast the behavior of motor. This paper presents an approach to predict the operating conditions of motor based on support vector machine (SVM). In order to improve the accuracy of prediction, a multivariate SVM predictor is built using multi-source multi-attribute information for time series prediction. The advantages of the multivariate SVM predictor is verified by empirical results derived from a real system of motor in power plant.

• Periodical: Advanced Materials Research (Volumes 706-708)
• Pages: 878-881
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.706-708.878
• Online since: June 2013
• Authors: Zheng Kai Zhang, Li Chen Gu, Ping Zhang
• Keywords: Multi-Step Ahead Prediction, Multivariate Time Series, Support Vector Machine (SVM)

References

[1] V.T. Tran, B.S. Yang, A.C. Tan, Expert Syst Appl Vol. 36 (2009) , p.9378.

[2] H.H. Nguyen, C.W. Chan, M. Wilson, Intell Data Anal Vol.8 (2004), p.183.

[3] Lijuan Cao, Neurocomputing Vol.51 (2003), p.321.

[4] Johann du Preez , Stephen F. Witt, Int J Forcasting Vol.19 (2003), p.435.

[5] U. Thissen, etc, Chemometr Intell Lab Vol.69 (2003), p.35.