As a key sensor for real-time monitoring of coal-rock mass stress, borehole stress gauges are persistently affected by complex factors such as strong electromagnetic interference and mining-induced disturbances in underground environments. The reliability of their performance and data directly impacts the accuracy of disaster risk identification. To address the challenge of identifying sensor failure states, a failure detection method for borehole stress gauges was proposed based on multi-criteria fusion and attribution analysis. A five-dimensional criterion system was established, incorporating the proportion of abnormal data, prolonged consecutive identical values, overall coefficient of variation, segmented coefficient of variation anomalies, and leakage trend ratios, to systematically characterize diverse failure modes. A logistic regression model was further integrated to construct a quantitative failure risk assessment function. This method was implemented as a failure detection module within a coal mine disaster intelligent early-warning platform. Validation using field data from 582 monitoring points at Zhaozhuang Coal Mine demonstrate that the proposed method achieves an accuracy rate of 91.89%, precision rate of 96.97%, and an AUC value of 0.945 2. Compared to deep learning models based on raw data, the method significantly improves discrimination accuracy, effectively overcoming the challenge of capturing failure patterns under complex mining-induced stress conditions. SHAP-based attribution analysis quantified the marginal contributions of each criterion to failure detection, with feature importance distributions aligning closely with the physical mechanisms of sensor failure. This validated the model’s interpretability and field adaptability. The research outcomes provide critical technical support for the intelligent upgrading of coal mine safety monitoring systems and can be directly applied to on-site maintenance practices.
QIN Kai, DENG Zhi-gang, WEI Shuai-hao.
Failure Discrimination of Borehole Stress Meters Based on Multi-criteria Fusion and Attribution Analysis[J].
Science Technology and Engineering, 2026, 26(28): 12114-12125 DOI:10.12404/j.issn.1671-1815.2506822
YuanLiang. Research progress of mining response and disaster prevention and control in deep coal mines[J]. Journal of China Coal Society, 2021, 46(3): 716-725.
WangHaijun, QiQingjie, LiangYuntao, et al. Statistical analysis and countermeasures of major accidents in coal mines in China[J]. China Safety Science Journal, 2024, 34(9): 9-18.
JiangJunjun, DengZhigang, ZhangGuanghui, et al. Preliminary classification and laboratory test method on bursting liability of floor strata[J]. Science Technology and Engineering, 2024, 24(35): 14968-14975.
LiShidong, XiaFangqian, YuanTengfei, et al. Analysis of mining stress concentration area based on deep coal body stress monitoring[J]. China Mining Magazine, 2024, 33(9): 147-157.
ZhaoTongbin, ZhaoZhigang, QiYanshan, et al. Research on coal stress measurement and assessment while drilling method based on multiple drilling parameters in large diameter drilling[J]. Coal Science and Technology, 2025, 53(1): 122-132.
[11]
ShenR X, HouZ H, YuanZ C, et al. Development of a three-dimensional stress monitoring system for coal rock and its application in a mine[J]. Rock Mechanics and Rock Engineering, 2023, 57(3): 1983-1996.
ZhuSitao, JiangFuxing, LiuJinhai, et al. Types, occurrence mechanism and prevention of overall instability induced rockbursts in China coal mines[J]. Journal of China Coal Society, 2020, 45(11): 3667-3677.
QinRuxiang, ShenTao, LiShihui. Dynamic evolutionary game model for coal mine safety monitoring and control and its application[J]. Safety in Coal Mines, 2025, 56(8): 246-256.
[16]
ChenD D, JiangZ S, XieS R. Mechanism and key parameters of stress load-off by innovative asymmetric hole-constructing on the two sides of deep roadway[J]. International Journal of Coal Science & Technology, 2023, 10(1): 82-101.
XuHailiang, WeiYabo, DuYu. Multi-factor analysis of the effectiveness of stress monitoring in rock boreholes[J]. Mining Technology, 2025, 25(2): 259-264.
XuShuai, HanMingfei, LiJiahou, et al. Current situation and development trend of relative geostress measurement equipment[J]. Metal Mine, 2021(2): 1-8.
TanZhanglu, WangMeijun, YeZihan. Methodological system and implementation framework of data governance for intelligent coal mines[J]. Coal Science and Technology, 2025, 53(1): 284-295.
LiXueming, LiuKan, ChenZhiwen, et al. Real-time joint diagnosis method of multi sensor fault for traction drive system based on structural analysis and extreme learning machine[J]. Control and Decision, 2025, 40(5): 1590-1598.
ZhouXuan, YanXuecheng, YanJunwei, et al. Bias fault detection of temperature sensor in cold system based on BOA-SVM[J]. Control Theory & Applications, 2025, 42(5): 921-930.
[31]
LiL, LiuG, ZhangL, et al. FS-LSTM-based sensor fault and structural damage isolation in SHM[J]. IEEE Sensors Journal, 2020, 21(3): 3250-3259.
[32]
LeeC Y, ChangK, HoC. Autoencoder-based detector for distinguishing process anomaly and sensor failure[J]. International Journal of Production Research, 2024, 62(19): 7130-7145.
LiQiming, LiXueming, HuangQing, et al. Fault diagnosis and fault tolerant control of current sensor for motor drive system[J]. Science Technology and Engineering, 2020, 20(32): 13265-13272.
[35]
李祺隆. 冲击地压煤层钻孔应力计-围岩耦合规律研究[D]. 徐州: 中国矿业大学, 2023.
[36]
LiQilong. Study on coupling law of stress meter and surrounding rock in rockburst coal seam[D]. Xuzhou: China University of Mining and Technology, 2023.
QiZicheng, NiPeijun, ZhangWeiguo, et al. A method for quantifying small defects in industrial CT detection[J]. Science Technology and Engineering, 2021, 21(3): 958-964.
LiuJie, ZhengWeiyun, LiuQingkuan, et al. Damage identification of cable-stayed bridge based on wavelet packet energy transfer rate variation coefficient[J]. China Civil Engineering Journal, 2023, 56(8): 37-46.
LüNing, LuoQian. A telecom customer churn prediction model integrating XGBoost and logistic regression algorithms[J]. Modern Electronics Technique, 2025, 48(11): 136-143.
GaoShuzhi, ChenYidan, ZhangYimin, et al. Reliability evaluation of rolling bearings based on stochastic proximity embedding and logistic regression[J]. Machinery Design & Manufacture, 2024(10): 1-4.
ChuTianshu, YanHaowen, LuXiaomin, et al. Revealing the importance of features in road network selection using the SHAP framework[J]. Journal of Geo-information Science, 2025, 27(5): 1068-1080.
ShengWu, WangLingzi. A traceability model for upper corner gas in fully mechanized mining faces based on XGBoost-SHAP[J]. Journal of Mine Automation, 2025, 51(6): 21-27, 140.