Gas Outburst Prediction Model Using Improved Entropy Weight Grey Correlation Analysis and IPSO-LSSVM. (16th November 2020)

• Record Type: Journal Article
• Authors: Liu, Haibo; Dong, Yujie; Wang, Fuzhong
• Other Names: Syed Ali M Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2020(2020)
• Publication Date: 2020-11-16
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2020/8863425
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : This paper investigates the problem of gas outburst prediction in the working face of coal mine. Firstly, based on a comprehensive analysis of influence factors of gas outburst, an improved entropy weight algorithm is introduced into a grey correlation analysis algorithm; thus, the reasonable weights and correlation order of the influencing factors are obtained to improve the objectivity of the evaluation. The main controlling factors obtained are used as the input of the prediction model. Secondly, by utilizing the improved particle swarm optimization (IPSO), the penalty factor and kernel parameter of least square support vector machine (LSSVM) are optimized to enhance the global search ability and avoid the occurrence of the local optimal solutions, and a new prediction model of gas outburst based on IPSO-LSSVM is established. At last, the prediction model is applied in the tunneling heading face 14141 of Jiuli Hill mine in Jiaozuo City, China. The case study demonstrates that the prediction accuracy of the proposed model is 92%, which is improved compared with that of the SVM model and GA-LSSVM model.