煤矿安全2026，Vol.57Issue(7)：81-97,17.DOI:10.13347/j.cnki.mkaq.20260175
基于因果发现与多任务稀疏学习框架的高温岩石强度预测研究
Research on high-temperature rock strength prediction based on causal discovery and multi-task sparse learning framework
摘要
Abstract
With the development of deep resources and the extension of underground engineering to the deep Earth,the accurate pre-diction of rock mechanical properties under high temperature has become the key to ensuring engineering safety.The strength,mod-ulus and failure mode of rocks under high temperature exhibit highly nonlinear evolution characteristics,which are difficult to be fully described by traditional theoretical models.Existing data-driven methods are mostly modeled based on statistical correlation,with the common limitation of"emphasizing correlation over causality",resulting in weak interpretability and insufficient general-ization ability,which can hardly meet the practical requirements of prediction accuracy for deep engineering.On this basis,an intelli-gent analysis framework integrating causal discovery,multi-task sparse learning and counterfactual explanation is proposed.Firstly,through physics-informed causal graph learning combined with prior knowledge of rock thermodynamics,key features causally re-lated to strength are screened from data to eliminate interference from irrelevant variables.On this basis,a multi-task sparse learning network is constructed to realize the collaborative prediction of rock strength,elastic modulus and failure mode.The parameter shar-ing mechanism is used to mine the inherent coupling relationship among mechanical parameters,and sparse constraints are adopted to focus on core causal features.Finally,a counterfactual reasoning module is introduced to quantify the causal effects of variables and their action paths,enabling the model to have transparent decision logic.The results show that the coefficient of determination(R2)of strength prediction on the test set reaches 0.935 with the mean absolute error(MAE)of only 6.2 MPa,which is significantly better than traditional machine learning and causal inference models(R2=0.721-0.893,MAE=8.7-18.6 MPa).In out-of-distribution intervention experiments,the model shows strong robustness,and the causal paths revealed by counterfactual reasoning are highly consistent with rock thermodynamic mechanisms.This study results provide an analytical tool with high accuracy,strong generaliza-tion and mechanism transparency for deep high-temperature rock engineering.关键词
岩石强度预测/因果发现/多任务学习/稀疏编码/反事实解释Key words
rock strength prediction/causal discovery/multi-task learning/sparse coding/counterfactual explanation分类
矿业与冶金引用本文复制引用
李亚洪,李世民,李民晟,宋朝阳,高峰,倪苏黔,于见水..基于因果发现与多任务稀疏学习框架的高温岩石强度预测研究[J].煤矿安全,2026,57(7):81-97,17.基金项目
天地科技股份有限公司科技创新创业资金重点资助项目(2025-TD-QZ025) （2025-TD-QZ025）
