基于TrAdaBoost-GBDT模型的排土场边坡稳定状态判别

doi:10.16265/j.cnki.issn1003-3033.2024.11.0124

摘要/Abstract

摘要：

针对露天矿排土场失稳数据获取困难,样本数据量少等问题,提出基于迁移学习算法的露天矿排土场边坡稳定状态判别模型;结合陕西省F露天矿排土场边坡的实际地质条件和降雨情况,设计降雨条件下排土场不同土石混合比边坡的相似模拟试验方案,并采集和处理试验中边坡模型的含水率、土压力和孔隙水压力数据;考虑到小样本数据集对梯度提升回归树(GBDT)模型分类精度的影响,运用迁移学习思想,利用迁移自适应增强算法(TrAdaBoost)对源域数据集和目标域数据集样本权重进行迭代更新,以GBDT模型作为数据样本训练的弱学习器,最终根据弱学习器的分类结果,通过加权多数表决法生成一种基于迁移学习的TrAdaBoost-GBDT排土场边坡稳定状性判别模型,以提高小样本数据标签类别的判别准确率。结果表明:相对其他算法模型,提出的排土场边坡稳定状态判别模型在稳定状态判别上有更好的表现,准确率、精准率、召回率和曲线下面积值(AUC)分别达到93.3%、87.5%、100%和93.8%,能够作为边坡稳定状态判别的分类器。该模型相对其他算法模型可以提高小样本数据集的边坡稳定状态判别的准确性,弥补机器学习对小样本数据集分类结果精度较低的不足。

关键词: 排土场边坡, 稳定状态判别, 迁移自适应增强梯度提升回归树(TrAdaBoost-GBDT), 迁移学习, 小样本

Abstract:

In view of the difficulties in obtaining instability data of open-pit mine dump and the small amount of sample data, a discrimination model of slope stability state of open-pit mine dump based on migration learning algorithm was proposed. According to the actual geological conditions and rainfall conditions of the dump slope of F open-pit mine in Shaanxi Province, a similar simulation test scheme of slope with different soil-rock mixing ratio was designed under the condition of rainfall. The data of water content, earth pressure and pore water pressure of the slope model were collected and processed. Considering the influence of small sample data set on the classification accuracy of GBDT model, using the idea of transfer learning, the sample weight of source domain data set and target domain data set was iteratively updated by TrAdaBoost algorithm, and the GBDT model was used as the weak learner for data sample training. Finally, according to the classification result of the weak learner, the weighted majority voting method was used to generate a TrAdaBoost-GBDT dump slope stability discrimination model based on transfer learning to improve the discrimination accuracy of small sample data label categories. The results show that the proposed dump slope stability state discrimination model has a better performance in judging the stable state than other algorithm models, and the values of accuracy, precision, recall and area under curve(AUC) are 93.3%, 87.5%, 100% and 93.8%, respectively. Compared with other algorithm models, this model can improve the accuracy of slope stability discrimination of small sample data sets, and make up for the low accuracy of machine learning classification results of small sample data sets.

Key words: dump slope, stability state discrimination, transfer adaptive boosting-gradient boosting decision tree (TrAdaBoost-GBDT), transfer learning, small samples

中图分类号:

X936

江松, 李涛, 李锦源, 李研博, 张存良, 张立杰. 基于TrAdaBoost-GBDT模型的排土场边坡稳定状态判别[J]. 中国安全科学学报, 2024, 34(11): 89-98.

JIANG Song, LI Tao, LI Jinyuan, LI Yanbo, ZHANG Cunliang, ZHANG Lijie. Discrimination of dump slope stability state based on TrAdaBoost-GBDT model[J]. China Safety Science Journal, 2024, 34(11): 89-98.

图/表 15

图1

图2

表1

表2

图3

图4

图5

图6

图7

图8

表3

表4

图9

表5

图10

参考文献 24

[1]	张萌, 刘宏磊, 乔文光, 等. 排土场稳定性影响因素显著性研究[J]. 中国安全科学学报, 2021, 31(2):69-75. doi: 10.16265/j.cnki.issn 1003-3033.2021.02.010
	ZHANG Meng, LIU Honglei, QIAO Wenguang, et al. Signifiacnt research on influencing factors of dump stability[J]. China Safety Science Journal, 2021, 31(2): 69-75. doi: 10.16265/j.cnki.issn 1003-3033.2021.02.010
[2]	LIU Xin, WANG Yu. Bayesian selection of slope hydraulic model and identification of model parameters using monitoring data and subset simulation[J]. Computers and Geotechnics, 2021, 139: DOI:10.1016/j.compgeo.2021.104428.
[3]	ZHANG Chengye, LI Feiyu, LI Jun, et al. Assessing the effect, attribution, and potential of vegetation restoration in open-pit coal mines' dumping sites during 2003-2020 utilizing remote sensing[J]. Ecological Indicators, 2023, 155: DOI: 10.1016/j.econlind.2023.111003.
[4]	张凯, 张科. 基于LightGBM算法的边坡稳定性预测研究[J]. 中国安全科学学报, 2022, 32(7): 113-120. doi: 10.16265/j.cnki.issn1003-3033.2022.07.1473
	ZHANG Kai, ZHANG Ke. Prediction study on slope stability based on LightGBM algorithm[J]. China Safety Science Journal, 2022, 32(7): 113-120. doi: 10.16265/j.cnki.issn1003-3033.2022.07.1473
[5]	CHAULYA S K, SINGH R S, CHAKRABORTY M K, et al. Quantification of stability improvement of a dump through biological reclamation[J]. Geotechnical and Geological Engineering. 2000, 18: 193-207.
[6]	张豪, 罗亦泳. 基于人工免疫算法的边坡稳定性预测模型[J]. 煤炭学报, 2012, 37(6): 911-917.
	ZHANG Hao, LUO Yiyong. Prediction model for slope stability based on artificial immune algorithm[J]. Journal of China Coal Society, 2012, 37(6): 911-917.
[7]	陶志刚, 李华鑫, 曹辉, 等. 降雨条件下全段高排土场边坡稳定性实验研究[J]. 煤炭学报, 2020, 45(11): 3 793-3 805.
	TAO Zhigang, LI Huaxin, CAO Hui, et al. Test on the slope stability of full-section high dump under rainfall[J]. Journal of China Coal Society, 2020, 45(11): 3 793-3 805.
[8]	蔡跃, 三谷泰浩, 江琦哲郎. 反倾层状岩体边坡稳定性的数值分析[J]. 岩石力学与工程学报, 2008, 27(12): 2 517-2 522.
	CAI Yue, MITANI Y, ESAKI T. Numerical analysis of stabilty for an antidip stratified rock slope[J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(12): 2 517-2 522.
[9]	杨杰, 马春辉, 程琳, 等. 高陡边坡变形及其对坝体安全稳定影响研究进展[J]. 岩土力学, 2019, 40(6): 2 341-2 353,2 368.
	YANG Jie, MA Chunhui, CHENG Lin, et al. Research advances in the deformation of high-steep slopes and its influence on dam safety[J]. Rock and Soil Mechanics, 2019, 40(6): 2 341-2 353, 2 368.
[10]	王振伟, 郝哲, 王来贵, 等. 基于极限平衡与突变理论的边坡综合评价方法[J]. 煤矿安全, 2009, 40(8): 103-105.
[11]	XU Mingyang, ZHOU Yang, PANG Rui, et al. Seismic collaborative reliability evaluation of slopes using subset simulation via support vector machine[J]. Soil Dynamics and Earthquake Engineering, 2023, 165: DOI: 10.1016/j.soildyn.2022.107673.
[12]	KARDANI N, ZHOU Annan, NAZEM M, et al. Improved prediction of slope stability using a hybrid stacking ensemble method based on finite element analysis and field data[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(1): 188-201.
[13]	CHANG Zhilu, CATANI F, HUANG Faming, et al. Landslide susceptibility prediction using slope unit-based machine learning models considering the heterogeneity of conditioning factors[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2023, 15(5): 1 127-1 143.
[14]	GAO Wei, GE Shangshang. A comprehensive review of slope stability analysis based on artificial intelligence methods[J]. Expert Systems with Applications, 2024, 239:DOI:10.1016/j.eswa.2023.122400.
[15]	KHAJEHZADEH M, KEAWSAWASVONG S. Predicting slope safety using an optimized machine learning model[J]. Heliyon, 2023, 9(12):DOI: 10.1016/j.heliyon.2023.e23012.
[16]	ZHANG Sheng, DING Li, XIE Menglong, et al. Reliability analysis of slope stability by neural network (NN), principal component analysis (PCA), and transfer learning (TL) techniques[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2023, 16(10): DOI: 10.1016/j.jrmge.2023.06.023.
[17]	何泊延. 基于GBDT的数据分类方法的研究及其应用[D]. 吉林: 东北电力大学, 2021.
	HE Boyan. Research and application of data classification method based on GBDT[D]. Jilin: Northeast Electric Power University, 2021.
[18]	张西良, 焦灏恺, 李二宝. 基于迁移学习算法的深部爆破振动速度预测[J]. 中国安全科学学报, 2023, 33(6): 64-72. doi: 10.16265/j.cnki.issn1003-3033.2023.06.0337
	ZHANG Xiliang, JIAO Haokai, LI Erbao. Prediction of vibration velocity of deep blasting based on transfer learning algorithm[J]. China Safety Science Journal, 2023, 33(6): 64-72. doi: 10.16265/j.cnki.issn1003-3033.2023.06.0337
[19]	秦雅琴, 李秋谷, 赵鹏燕, 等. 基于多分类Adaboost算法的驾驶人风险感知倾向研究[J]. 中国安全科学学报, 2022, 32(4):141-147. doi: 10.16265/j.cnki.issn1003-3033.2022.04.021
	QIN Yaqin, LI Qiugu, ZHAO Pengyan, et al. Research on risk perception tendency of drivers based on multi-class Adaboost algorithm[J]. China Safety Science Journal, 2022, 32(4): 141-147. doi: 10.16265/j.cnki.issn1003-3033.2022.04.021
[20]	戴文渊. 基于实例和特征的迁移学习算法研究[D]. 上海: 上海交通大学, 2009.
	DAI Wenyuan. Instance-based and feature-based transfer learning[D]. Shanghai: Shanghai Jiaotong University, 2009.
[21]	罗亦泳, 姚宜斌, 张立亭, 等. 基于HIOA-MK-TCRVM算法的边坡稳定性估计模型[J]. 中国安全科学学报, 2017, 27(1):116-121. doi: 10.16265/j.cnki.issn1003-3033.2017.01.021
	LUO Yiyong, YAO Yibin, ZHANG Liting, et al. Slope stability estimation model based on HIOA-MK-TCRVM[J]. China Safety Science Journal, 2017, 27(1): 116-121. doi: 10.16265/j.cnki.issn1003-3033.2017.01.021
[22]	徐晓滨, 施凡, 冯静, 等. 基于AdaBoost的地下采掘工程高韧性安全评估方法[J]. 中国安全科学学报, 2023, 33(增1):112-118.
	XU Xiaobin, SHI Fan, FENG Jing, et al. High-resilience safety assessment method of underground coal mining using AdaBoost[J]. China Safety Science Journal, 2023, 33(S1): 112-118. doi: 10.16265/j.cnki.issn1003-3033.2023.S1.1304
[23]	张梦涵, 魏进, 卞海丁. 基于机器学习的边坡稳定性分析方法:以国内618个边坡为例[J]. 地球科学与环境学报, 2022, 44(6):1 083-1 095.
	ZHANG Menghan, WEI Jin, BIAN Haiding. Slope stability analysis method based on machine learning: taking 618 slopes in China as examples[J]. Journal of Earth Sciences and Environment, 2022, 44(6): 1 083-1 095.
[24]	GB51016—2014, 非煤露天矿边坡工程技术规范[S].
	GB51016-2014, Technical code for non-coal open-pit mine slope engineering[S].

试验编号	土石质量比	降雨强度/ (mm·h^-1)	降雨停止时信号
工况1	9:1	49	坡体大范围破坏
工况2	9:1	83
工况3	4:1	49
工况4	4:1	83

标签变量	含义	标签变量	含义
H₁	坡底含水率	K₃	坡顶孔隙水压力
H₂	坡中含水率	T₁	坡底土压力
H₃	坡顶含水率	T₂	坡中土压力
K₁	坡底孔隙水压力	T₃	坡顶土压力
K₂	坡中孔隙水压力	Class	边坡稳定状态

真实情况	判别结果
真实情况	稳定情况	失稳情况
稳定情况	TP	FN
失稳情况	FP	TN

判别模型	A	P	R	AUC
TrAdaBoost-GBDT	0.933	0.875	1	0.938
GBDT	0.869	0.857	0.857	0.867
AdaBoost	0.802	0.838	0.717	0.796
SVM	0.773	0.754	0.747	0.723