Forecasting Model of Coal Mine Water Inrush Based on Extreme Learning Machine

Authors

Zuopeng Zhao, School of Computer Science and Technology, China University of Mining and Technology, 221008 Xuzhou, China
Pei Li
Xinzheng Xu

Author Country (or Countries)

China

Abstract

In order to satisfy the real-time requirement of the coal mine water inrush, comprehensively considering the master influencing factors filtered out by using principal component analysis (PCA) of coal mine water inrush, a forecasting model of coal mine water inrush based on extreme learning machine (ELM) is proposed in this paper by combining with the characteristics of single hidden layer feedforward networks (SLFNs). The model is used to test the samples, and then compare the experimental results of ELM with back-propagation (BP) and support vector machine (SVM). The experimental results show that, compared with BP and SVM, this method is not only learns fast but also has good generalization performance , and thus it can satisfy the real-time requirements of coal mine water inrush effectively. The feasibility of ELM for coal mine water inrush forecast and the availability of the algorithm were validated through experiments.

Suggested Reviewers

N/A

Recommended Citation

Zhao, Zuopeng; Li, Pei; and Xu, Xinzheng (2013) "Forecasting Model of Coal Mine Water Inrush Based on Extreme Learning Machine," Applied Mathematics & Information Sciences: Vol. 07: Iss. 3, Article 49.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol07/iss3/49