Coal and Gas Outburst Prediction Combining a Neural Network with the Dempster-Shafter Evidence

  • Authors:

  • Yanzi Miao;Jianwei Zhang;Houxiang Zhang;Xiaoping Ma;Zhongxiang Zhao

  • Affiliations:

  • China University of Mining and Technology, Xuzhou, P.R.China 221008 and TAMS Group, University of Hamburg, Hamburg, Germany 22527;TAMS Group, University of Hamburg, Hamburg, Germany 22527;TAMS Group, University of Hamburg, Hamburg, Germany 22527;China University of Mining and Technology, Xuzhou, P.R.China 221008;China University of Mining and Technology, Xuzhou, P.R.China 221008

  • Venue:
  • ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

A novel prediction method combing a neural network with the D-S evidence theory for coal and gas outbursts is put forward in this paper. We take advantage of the fact that the non-linear input-output mapping function of the neural network can handle the non-linear parameters from coal and gas outburst monitor systems. And the output of the neural network is taken as the basic probability of the assignment function of the D-S evidence theory, which resolves the main problem of establishing the BPAF for the D-S evidence theory. The results from our experiments show that it is feasible and effective to combine the neural network with the D-S evidence theory for deciding on predictions. And using this method, we can make a more certain and credible prediction decision than witheach independent method.