面向凿岩台车随钻数据的不平衡围岩等级智能识别方法OA
Intelligent identification of unbalanced surrounding rock grades using in-situ drilling data from drill jumbo
围岩等级的准确识别是保障隧洞施工安全与支护设计的核心环节.三臂凿岩台车作为钻爆法最常用的施工机械,其随钻数据可以连续反映岩体力学特性,但实际工程中普遍存在的样本不均衡与复杂非线性特征,导致传统数据驱动模型易陷入"多数类偏好",对高风险少数类围岩识别乏力.为此,本文提出一种融合合成少数类过采样技术(SMOTE)与灰狼优化(GWO)算法的 LightGBM 集成学习模型.首先通过 SMOTE 算法在特征空间内进行局部插值以重构数据平衡的分布,进而利用GWO算法对LightGBM的关键超参数进行自适应全局寻优,以提升模型在不平衡条件下的分类精度与泛化能力.结果表明,所建模型的整体识别准确率达94.58%,相较于RF与GBDT方法分别提升了11.78%与12.23%,有效突破了不平衡数据对围岩智能识别的制约,为高风险少数类围岩的精准预警与动态支护提供了可靠的决策引擎,推动了隧洞工程的智能施工与安全管控.
Accurate classification of surrounding rock is essential for tunnel safety and optimal support design;Its mechanical properties can be collected consecutively using a three-boom jumbo that generates measurement-while-drilling(MWD)data.However,conventional data-driven models often suffer from a majority class bias,because of the inherent sample imbalances and complicated nonlinearities,and it fails to identify the classes of high-risk minority rock.This paper presents a LightGBM model that is integrated with Synthetic Minority Over-sampling Technique(SMOTE)and Grey Wolf Optimizer(GWO).SMOTE reconstructs a balanced data distribution via local feature interpolation,while GWO optimizes the LightGBM's hyperparameters adaptively,improving both the model's accuracy and generalization in handling imbalanced datasets.Results show this new model achieves an overall accuracy of 94.6%,outperforming Random Forest(RF)and Gradient Boosting Decision Tree(GBDT)by 11.8%and 12.2%respectively.This approach overcomes data imbalance limitations effectively,and offers a reliable decision-making engine for accurate early warning,dynamic support of high-risk minority rock classes,and intelligent safety management in tunnel construction.
贺林森;陈云;胡其林;陈述;晋良海
水电工程施工与管理湖北省重点实验室(三峡大学),湖北 宜昌 443002||三峡大学 水利与环境学院,湖北 宜昌 443002水电工程施工与管理湖北省重点实验室(三峡大学),湖北 宜昌 443002||三峡大学 水利与环境学院,湖北 宜昌 443002中国水利水电第五工程局有限公司,成都 610207水电工程施工与管理湖北省重点实验室(三峡大学),湖北 宜昌 443002||三峡大学 水利与环境学院,湖北 宜昌 443002水电工程施工与管理湖北省重点实验室(三峡大学),湖北 宜昌 443002||三峡大学 水利与环境学院,湖北 宜昌 443002
信息技术与安全科学
地质类型识别三臂凿岩台车掘进参数LightGBM集成学习SMOTE算法
geological type identificationthree-arm rock drilling rigtunneling parametersLightGBM ensemble learningSMOTE algorithm
《水力发电学报》 2026 (10)
12-21,10
国家自然科学基金(52209163)
评论