School of Electrical and Information Engineering,Beijing University of Civil Engineering and Architecture

为了解决不平衡地震属性数据集中陷落柱识别准确率较低的问题,提出了一种基于轻梯度提升机(LightGradientBoostingMachine,LightGBM)和利用焦点损失(FocalLoss)改进深度神经网络(DeepNeuralNetworks,DNN)相结合的陷落柱识别方法LightGBM-DNNF。首先通过相关性分析和重要性分析进行属性优选;其次提取LightGBM叶子节点的路径作为新的特征,并与原始数据集组合成新的数据集;最后输入到DNNFL模型中进行分类训练,预测地质构造类型。引入精确率(P)、召回率(R)、F1分数(F1-score)、曲线下面积(AUC)作为评价指标,基于3个矿区的数据集开展对比实验和消融实验。实验结果表明,与传统的机器学习和单一的集成学习算法相比,LightGBM-DNNFL模型的F1-score和AUC值均在93%以上,能有效识别陷落柱,且模型泛化能力更强。

In order to solve the problem of low recognition accuracy of collapse column in unbalanced seismic attribute datasets,a novel collapse column recognition method named “ LightGBM - DNNF” was proposed, which based on the light gradient boosting machine (LightGBM) and the use of focal loss to improve deep neural networks ( DNN). Firstly,attribute selection was performed through correlation and importance analysis. Then,the paths of LightGBM leaf nodes were extracted as new features,which were combined with the original dataset to form a new dataset. Finally,the new dataset was input into the DNNFL model for classification training and prediction of geological structure types. Precision ( P),Recall ( R),F1 - score (F ),and area under the curve (A ) were introduced as evaluation metrics,and comparative experiments and ablation experiments were conducted based on datasets from three mining areas. The experimental results show that compared with the traditional machine learning and single ensemble learning algorithm,the F and A values of the LightBM-DNNFL model are both above 93%,indicating its effectiveness in recognizing collapse column and exhibiting stronger generalization ability.

国家重点研发计划项目(2018YFC0807806)

王怀秀,王慧.基于LightGBM和DNNFL的陷落柱识别方法研究与应用[J].矿业安全与环保,2024,51(5):125-131.

WANG Huaixiu,WANG Hui. Research and application of recognition method for collapse column based on LightGBM and DNNFL[J]. Mining Safety & Environmental Protection,2024,51(5):125-131.