Prediction model for coal-gas outburst using the genetic projection pursuit method
by Yueqiang Liang; Deyong Guo; Zhanfeng Huang; Xihui Jiang
International Journal of Oil, Gas and Coal Technology (IJOGCT), Vol. 16, No. 3, 2017

Abstract: This paper proposes to solve the coupling result problem of individual indexes and to improve the prediction accuracy of coal-gas outburst. According to gas geology research, the prediction index system is established from the context of an outburst-prone tectonophysical environment. A new model for coal-gas outburst prediction is developed through genetic algorithm and projection pursuit method. This model indicates the dangerous degree of occurrence of potential coal-gas outburst by calculating a one-dimensional projection eigenvalue which reflects the dangerous degree of coal-gas outburst. The prediction model is applied in the tunnelling working face 31041 of the Chaohua coal mine, and the dangerous degree of prediction is primarily identical with the in situ records. The case study demonstrates the reliability of the genetic projection pursuit method in predicting coal-gas outburst. [Received: October 16, 2015; Accepted: October 6, 2016]

Online publication date: Thu, 05-Oct-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Oil, Gas and Coal Technology (IJOGCT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com