Title: Application of light gradient boosting machine in mine water inrush source type online discriminant

Authors: Yang Yong; Li Jing; Zhang Jing; Liu Yang; Zhao Li; Guo Ruxue

Addresses: School of Information Engineering, Southeast University, Si Pailou Campus, Nanjing, China; School of Information and Electrical Engineering, Xuzhou College of Industrial Technology, Xuzhou, China ' School of Information Engineering, Nanjing Audit University, Nanjing, China ' School of Software, HanDan University, HanDan, China ' National Engineering Research Center of Turbo-generator Vibration, Southeast University, Nanjing, China ' School of Information Engineering, Southeast University, Si Pailou Campus, Nanjing, China ' School of Information Engineering, Southeast University, Si Pailou Campus, Nanjing, China; Department of Psychiatry, Vagelos College of Physicians and Surgeons, Columbia University, New York, NY, USA

Abstract: Water inrush is a kind of mine geological disaster that threatens mining safety. Type recognition of water inrush sources is an effective auxiliary method to forecast water inrush disaster. Compared with the current hydro-chemistry methodology, it spends a large amount of time on sample collection. Considering this problem, it is urgent to propose a novel method to discriminate water inrush source types online, and further to strive to create more time for evacuation before the disaster. The paper proposes an in-situ mine water sources discrimination model based on light gradient boosting machine (LightGBM). This method combined light gradient boosting (GB) with the decision tree (DT) to improve the network integrated learning ability and enhance model generalisation. The data were collected from in-situ sensors such as pH, conductivity, Ca, Na, Mg and CO₃ components in different water bodies of LiJiaZui Coal Mine in HuaiNan. The results illustrate that the accuracy of proposed method achieves 99.63% to recognise water sources in the mine. Thus, the proposed discriminant model is a timely and an effective way to recognise source types of water in a mine online.

Keywords: water inrush source; light gradient boosting machine; LightGBM; online water sources discrimination.

DOI: 10.1504/IJCSE.2021.113633

International Journal of Computational Science and Engineering, 2021 Vol.24 No.1, pp.9 - 17

Received: 23 Apr 2019
Accepted: 06 Apr 2020
Published online: 15 Mar 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article