Title: Coal-rock dynamic disaster assessment model based on electromagnetic emission and least-squares support vector machine
Authors: Chen Wenxue, He Xueqiu, Nie Baisheng
Addresses: School of Resource and Safety Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China; State Key Lab of Coal Resources and Safe Mining, China University of Mining and Technology, Beijing 100083, China. ' School of Resource and Safety Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China; State Key Lab of Coal Resources and Safe Mining, China University of Mining and Technology, Beijing 100083, China. ' School of Resource and Safety Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China; State Key Lab of Coal Resources and Safe Mining, China University of Mining and Technology, Beijing 100083, China
Abstract: A new non-linear assessment model for coal-rock dynamic disasters is reported in this paper. Coal-rock dynamic disaster assessment parameters are difficult to obtain because assessment samples are usually rare. The least-squares, a non-linear and few sample assessment methods can satisfy requirements on the availability of few samples. Based on the electromagnetic emission (EME) testing results and multiple classification theory of support vector machine, an EME least-squares support vector machine assessment model is built. In a case study, the results show that the EME least-squares support vector machine assessment model for coal and gas outburst is reliable and accurate, and can be applied to the assessment of coal-rock dynamic disasters in coal mines.
Keywords: coal-rock dynamic disasters; electromagnetic emission; EME testing; least-squares method; support vector machine; SVM; coal and gas outburst; risk assessment; disaster assessment; nonlinear assessment modelling; coal mines.
DOI: 10.1504/IJRAM.2010.037084
International Journal of Risk Assessment and Management, 2010 Vol.14 No.6, pp.459 - 467
Accepted: 28 Apr 2010
Published online: 23 Nov 2010 *