Prediction of the stability of gob‐side entry formation by roof cutting by machine learning‐based models

Abstract Gob‐side entry formation by roof cutting is a new technology for no pillar coal mining, which can maximize resources and reduce roadway drivage ratio. However, the mechanical behavior of formed complex while it crucial to ensure stability mining safety. This paper proposed machine learning‐based method predicting entry, combined artificial neural network (ANN) with particle swarm optimization (PSO) algorithm or genetic (GO) algorithm. The data set from 75 faces 2009 2022 was employed train test models. A descriptive variable dynamic unstable distance introduced evaluate state six other parameters were chosen as influence parameters. two intelligent models compared each have comprehensive assessment. Model assessment indices such R 2 , mean absolute error, percentage root square error used accuracy results both developed are promising, predictive PSO‐ANN model higher than that GO‐ANN model. Through sensitivity analyses, has been found seam thickness rock hardness most important influencing stability. provides practical tool prediction design.