Classification prediction of coal seam bursting liability grade is a crucial prerequisite for risk assessment of coal mine rock bursts. To enhance the prediction efficiency and accuracy of coal bursting liability classification under complex conditions, a dataset comprising 221 sample cases and 49 cases with missing σc single features was constructed through deep mining and integration. Aiming at the problems of category imbalance in the statistical measured data set, such as the relative scarcity of strong and weak bursting liability samples, a meta-heuristic algorithm, intelligent optimization support vector machine (SVM), a bursting liability classification prediction method based on optimization theory under unbalanced samples was proposed. The results show that the improved SMOTE algorithm based on K-means is used for data preprocessing, such as null value filling, outlier elimination, resampling and clustering synthesis of new samples, which solves the imbalance problem of data sets. A CNN (Convolutional Neural Network)-SVM prediction model based on a new meta-heuristic optimization algorithm, CFOA (Fishing Optimization Algorithm) strategy optimization, is proposed. The kernel function of the CNN control classifier is optimized by an intelligent optimization algorithm, and further adjusts the SVM hyper-parameter optimization search strategy. The SVM tuning is improved by sample data class equalization preprocessing, and optimization algorithm. Compared with the other 8 models, the excellent performance of the proposed optimized SVM model is verified. The CFOA-CNN-SVM model, after data preprocessing, has the best comprehensive performance in the test set, with the highest accuracy rate of 96.3 %. For the three types of label samples, the prediction accuracy rates are 0.97, 0.95 and 0.97, the recall rates are 1.00, 0.95 and 0.95, and the F1 values are 0.99, 0.95 and 0.96. Finally, the generalization ability of the model is further verified by practical cases. It shows a good prediction effect in dealing with sample imbalance and feature missing statistical data, and small sample test data. The research results have important basic value for improving the database quality of coal seam bursting liability prediction and improving the model prediction performance.
DOULinming, TIANXinyuan, CAOAnye, et al. Present situation and problems of coal mine rock burst prevention and control in China [J]. Journal of China Coal Society, 2022, 47(1): 152-171.
PANJunfeng, QIQingxin, LIUShaohong, et al. Characteristics, types and prevention and control technology of rockburst in deep coal mining in China[J]. Journal of China Coal Society, 2020, 45(1): 111-121.
QIQingxin, LIYizhe, ZHAOShankun, et al. Seventy years development of coal mine rockburst in China: Establishment and consideration of theory and technology system[J]. Coal Science and Technology, 2019, 47(9): 1-40.
QIANQihu. Definition, mechanism, classification and quantitative forecast model for rockburst and pressure bump[J]. Rock and Soil Mechanics, 2014, 35(1): 1-6.
[9]
CHENC, ZHOUJ. A new empirical chart for coal burst liability classification using Kriging method[J]. Journal of Central South University, 2023, 30(4): 1205-1216.
ZHANGMan, CHENJianhong, ZHOUZhiyong. Grading prediction model of rock burst based on SVM and its R language description[J]. The Chinese Journal of Geological Hazard and Control, 2018, 29(4): 64-69.
ZHAOHongbo, RUZhongliang. PSO-SVM Model for prediction of rock burst[J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(Sup 1): 3479-3483.
[16]
SUNJ H, WANGW J, XIEL K. Predicting short-term rockburst intensity using a weighted probability stacking model with optimal feature selection and Bayesian hidden layer[J]. Tunnelling and Underground Space Technology, 2024, 153: 106021.
[17]
PUY Y, APELD B, WANGC, et al. Evaluation of burst liability in kimberlite using support vector machine[J]. Acta Geophysica, 2018, 66(5): 973-982.
YAONan, ZHANGYili, LIUYang, et al. Rock burst intensity grading prediction based on the combination of PCA, CBLOF and SVMSMOTE algorithms[J]. Chinese Journal of Rock Mechanics and Engineering, 2025, 44(5): 1230-1241.
[20]
田睿. 基于机器学习的岩爆烈度等级预测模型研究与应用[D]. 包头:内蒙古科技大学,2020.
[21]
TIANRui. Research and application of rockburst intensity classification prediction model based on machine learning algorithms[D]. Baotou: Inner Mongolia University of Science & Technology, 2020.
[22]
ZHOUJ, LIX B, SHIX Z. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines[J]. Safety Science, 2012, 50(4): 629-644.
[23]
LIM L, LIK G, QINQ C. A rockburst prediction model based on extreme learning machine with improved Harris Hawks optimization and its application[J]. Tunnelling and Underground Space Technology, 2023, 134: 104978.
WENTingxin, WANGZefeng. Prediction model of rockburst intensity levels based on K-means clustering optimization and improved dung beetle optimization algorithm[J]. Journal of Safety Science and Technology, 2024, 20(6): 140-147.
CHENJie, GAOJingkuan, PUYuanyuan, et al. Machine learning method for predicting and warning of rockbursts[J]. Journal of Mining and Strata Control Engineering, 2021, 3(1): 57-68.
DOULinming, HEXueqiu. Technique of classification forecasting rock burst in coal mines[J]. Journal of China University of Mining & Technology, 2007, 36(6): 717-722.
[30]
WUM, YEY C, WANGQ H, et al. Development of rockburst research: A comprehensive review[J]. Applied Sciences-Basel, 2022, 12(3): 974.
[31]
LIUQ S, XUEY G, LIG K, et al. Application of KM-SMOTE for rockburst intelligent prediction[J]. Tunnelling and Underground Space Technology, 2023, 138: 105180.
[32]
ZHANGH W, XIAY Y, LINM Q, et al. A three-step rockburst prediction model based on data preprocessing combined with clustering and classification algorithms[J]. Bulletin of Engineering Geology and the Environment, 2024, 83(7): 266.
[33]
XUEY G, LIG K, LIZ Q, et al. Intelligent prediction of rockburst based on Copula-MC oversampling architecture[J]. Bulletin of Engineering Geology and the Environment, 2022, 81(5): 209.
[34]
LIJ, FUH L, HUK X, et al. Data preprocessing and machine learning modeling for rockburst assessment[J]. Sustainability, 2023, 15(18): 13282.
[35]
BASNETP M S, MAHTABS, JINA, et al. A comprehensive review of intelligent machine learning based predicting methods in long-term and short-term rockburst prediction[J]. Tunnelling and Underground Space Technology, 2023, 142: 105434.
JUWenjun, LUZhiguo, GAOFuqiang, et al. Research progress and comprehensive quantitative evaluation index of coal rock bursting liability[J]. Chinese Journal of Rock Mechanics and Engineering, 2021, 40(9): 1839-1856.
GUOJindong. Application of variable weight and grey classification recognition model in rock burst tendency evaluation of coal seam[J]. Journal of North China Institute of Science and Technology, 2017, 14(1): 44-49.
PANJunfeng, JIANJunfeng, LIUShaohong, et al. Geological characteristic and control of rock burst of Huanglong Jurassic coal mine field[J]. Coal Mining Technology, 2019, 24(1): 110-115.
[42]
李岳峰. 煤样冲击倾向性分类的多指标评判模型比较及优选[D]. 昆明:昆明理工大学,2022.
[43]
LIYuefeng. Coal sample impact tendency classification multi-indicator evaluation model comparison and optimization[D]. Kunming: Kunming University of Science and Technology, 2022.
GEORGIOSD, FERNANDOB, FELIXL. Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE[J]. Information Sciences, 2018, 465: 1-20.
[46]
JIAH M, WENQ X, WANGY H, et al. Catch fish optimization algorithm: a new human behavior algorithm for solving clustering problems[J]. Cluster Computing: The Journal of Networks Software Tools and Applications, 2024, 27(9): 13295-13332.
[47]
SOWMYAR, PREMKUMARM, JANGIRP. Newton-Raphson-based optimizer: A new population-based metaheuristic algorithm for continuous optimization problems[J]. Engineering Applications of Artificial Intelligence, 2024, 128: 107532.
CHENShaojie, SHENGShouqian, HANLei, et al. Dynamic prediction of surface movement and deformation based on machine learning for overburden bed separation grouting filling: A case study of the 3801 working face in Huoerxinhe Coal Industry[J]. Journal of China University of Mining & Technology, 2025, 54(6): 1261-1275.
ZHUXiaojing, PANYishan, LIQi, et al. Softening zone energy extremum criterion and experimental study of roadway rock burst[J]. Journal of China University of Mining & Technology, 2021, 50(5): 975-982.