Early Warning of Gas Concentration in Coal Mines Production Based on Probability Density Machine

Abstract

Gas explosion has always been an important factor restricting coal mine production safety. The application of machine learning techniques in coal mine gas concentration prediction and early warning can effectively prevent gas explosion accidents. Nearly all traditional prediction models use a regression technique to predict gas concentration. Considering there exist very few instances of high gas concentration, the instance distribution of gas concentration would be extremely imbalanced. Therefore, such regression models generally perform poorly in predicting high gas concentration instances. In this study, we consider early warning of gas concentration as a binary-class problem, and divide gas concentration data into warning class and non-warning class according to the concentration threshold. We proposed the probability density machine (PDM) algorithm with excellent adaptability to imbalanced data distribution. In this study, we use the original gas concentration data collected from several monitoring points in a coal mine in Datong city, Shanxi Province, China, to train the PDM model and to compare the model with several class imbalance learning algorithms. The results show that the PDM algorithm is superior to the traditional and state-of-the-art class imbalance learning algorithms, and can produce more accurate early warning results for gas explosion.

Gas explosion early warning method in coal mines by intelligent mining system and multivariate data analysis

“…They identified and assessed the risks of gas explosion accidents, identified potential risk sources leading to accidents, and performed a warning analysis of disaster accident levels based on setting accident risk warning intervals using Bayesian networks [11]. Cai et al (2021) thought that applying machine learning technology to the prediction and early warning of coal mine gas concentration could effectively prevent the occurrence of gas explosion accidents [2]. Li et al (2023) used Radial Basis Function (RBF) neural network to build a prediction model of roof instability under repeated mining.…”

“…In this study, the evaluation set of gas explosion disaster risk level in coal mine was established, P = {Safety; Safer; General safety; Less safe; Unsafe}, including 5 review levels. Each level corresponds to a corresponding security level vector (5,4,3,2,1). This set of methods and steps, combined with systematic analysis and professional advice, is helpful to accurately evaluate the risk of gas explosion disaster in coal mines, and turn it into an understandable safety level evaluation, which provides effective support and guidance for coal mine safety production.…”

Underground abnormal sensor condition detection based on gas monitoring data and deep learning image feature engineering

“…Through such methods, it can provide technical support for the safety management of coal mining enterprises, effectively improve the level of coal mine safety production, reduce or make early warning before accidents occur, improve coal mine safety production conditions. In particular, Cai [ 27 ] proposed a machine learning based probability density machine method for effectively prevent gas explosion accidents. Song [ 6 ] used the Hurst indices of the time series of gas indicators related to coal spontaneous combustion at monitoring sites, the temporal propensity of coal spontaneous combustion can be determined.…”

Research on Gas Outburst Prediction Model Based on Multiple Strategy Fusion Improved Snake Optimization Algorithm With Temporal Convolutional Network

“…Qingwei Xu proposed a new accident prevention technique using a novel safety assessment method based on fault tree basic event importance, grey relational analysis and the bow tie model [7]. Yadong Cai classifies gas concentration data into warning and non-warning classes based on concentration thresholds, and proposes a probability density machine (PDM) algorithm with good adaptability to unbalanced data distributions [8].…”