Prediction of slope instability in open-pit mine waste dumps based on GA-BP neural network

doi:10.16265/j.cnki.issn1003-3033.2026.03.0427

Abstract

Abstract:

To improve the prediction accuracy and reliability of slope instability in mine waste dumps, a hybrid GA-BP model was developed by integrating an improved GA with a BP neural network. The model employed GA to globally optimize the initial weights and thresholds of the BP network, and incorporated the Levenberg-Marquardt (LM) algorithm to enhance convergence speed. Ten key parameters—including bench slope angle, geotechnical internal stress, bench height, surface displacement, and pore water pressure—were selected as inputs, with the slope safety factor as the output. Training and validation was performed using 150 field case datasets. The results show that GA-BP model reduces the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by 46.9%, 25.4%, and 5.38%, respectively, compared to the conventional BP model. Predictions are closer to the safety threshold (F_s = 1.2), indicating enhanced sensitivity and stability. Pearson correlation analysis confirms strong relationships between surface and internal displacement (0.98) and between pore water pressure and rainfall (0.75), supporting the rationality of the input indicators. The study demonstrates that GA-BP model effectively overcomes local optima and gradient vanishing issues in BP networks, providing a reliable tool for intelligent slope stability assessment.

Key words: genetic algorithm (GA), backpropagation (BP) neural network, open-pit mine, waste dumps, slope instability prediction, safety factor

CLC Number:

X936

XIE Zunxian, MA Haohao, JIANG Song, WU Xiaoyun. Prediction of slope instability in open-pit mine waste dumps based on GA-BP neural network[J]. China Safety Science Journal, 2026, 36(3): 81-88.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Fig.5

Table 2

Table 3

Fig.6

Fig.7

Fig.8

Table 4

References 19

[1]	LIANG Zuchao, WANG Dong, LI Guanghe, et al. Three-dimensional stability calculation method for high and large composite slopes formed by mining stope and inner dump in adjacent open pits[J]. International Journal of Mining Science and Technology, 2024, 34(4): 507-520. doi: 10.1016/j.ijmst.2024.04.007
[2]	YANG Zhonggao, LIU Xin, QIAN Weimin, et al. Investigation of steep waste dump slope stability of iron ore mine-a case study[J]. Applied Sciences, 2024, 14(8): DOI: 10.3390/app14083430.
[3]	DUAN Xiangfeng. Research on prediction of slope displacement based on a weighted combination forecasting model[J]. Results in Engineering, 2023, 18:DOI: 10.1016/j.rineng.2023.101013.
[4]	ZHONG Kai, TAN Xiaohui, LIU Shanwei, et al. Prediction of slope failure probability based on machine learning with genetic-ADASYN algorithm[J]. Engineering Geology, 2025, 346:DOI: 10.1016/j.enggeo.2024.107885.
[5]	周怡, 彭国文, 黄召, 等. 基于SBAS-InSAR和BPNN的铀尾矿坝形变智能监测与预测[J]. 中国安全科学学报, 2024, 34(4): 145-152. doi: 10.16265/j.cnki.issn1003-3033.2024.04.1693
	ZHOU Yi, PENG Guowen, HUANG Zhao, et al. Intelligent monitoring and prediction of deformation of uranium tailings dam based on SBAS-InSAR and BPNN[J]. China Safety Science Journal, 2024, 34(4): 145-152. doi: 10.16265/j.cnki.issn1003-3033.2024.04.1693
[6]	谢尊贤, 张志远. 基于GA优化BP神经网络的矿工不安全行为预警研究[J]. 采矿技术, 2024, 24(2):137-142.
[7]	MT/T 1185—2020, 露天煤矿排土场技术规范[S].
	MT/T 1185-2020, Technical specification for open-pit coal mine dump[S].
[8]	王团辉, 王超, 吴顺川, 等. 基于MISSA-SVM模型的边坡稳定性预测及应用[J]. 中国安全科学学报, 2024, 34(4):135-144. doi: 10.16265/j.cnki.issn1003-3033.2024.04.1275
	WANG Tuanhui, WANG Chao, WU Shunchuan, et al. Slope stability prediction and application based on MISSA-SVM model[J]. China Safety Science Journal, 2024, 34(4): 135-144. doi: 10.16265/j.cnki.issn1003-3033.2024.04.1275
[9]	杨胜利, 王云鹏. 排土场稳定性影响因素分析[J]. 露天采矿技术, 2009(3):4-7.
	YANG Shengli, WANG Yunpeng. Analysis of factors affecting dump stability[J]. Opencast Mining Technology, 2009(3):4-7.
[10]	栾婷婷, 吕则恺, 马政, 等. 基于安全流变-突变理论的排土场滑坡预警指标体系构建研究[J]. 北京石油化工学院学报, 2017, 25(3):38-42.
	LUAN Tingting, LYU Zekai, MA Zheng, et al. research on building early warning index system of dump landslide based on safety rheology-mutation theory[J]. Journal of Beijing Institute of Petrochemical Technology, 2017, 25(3):38-42.
[11]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型[J]. 中国安全科学学报, 2022, 32(1):27-33. doi: 10.16265/j.cnki.issn1003-3033.2022.01.004
	SHI Juan, CHANG Dingyi, ZHENG Peng. An early warning model of unsafe behaviors of construction workers based on BP neural network[J]. China Safety Science Journal, 2022, 32(1): 27-33. doi: 10.16265/j.cnki.issn1003-3033.2022.01.004
[12]	谢尊贤, 郭琰, 蒲涛. 基于BIM-GA-BN的养老社区施工安全评价模型[J]. 中国安全科学学报, 2018, 28(9):19-25. doi: 10.16265/j.cnki.issn1003-3033.2018.09.004
	XIE Zunxian, GUO Yan, PU Tao. Research on BIM-GA-BN based model for evaluating elderly care community construction safety[J]. China Safety Science Journal, 2018, 28(9): 19-25. doi: 10.16265/j.cnki.issn1003-3033.2018.09.004
[13]	马欣蔚, 牟兴森, 龙珠, 等. 基于GA-BP神经网络的横管降膜蒸发传热系数预测[J]. 化工学报, 2023, 74(12):4840-4851. doi: 10.11949/0438-1157.20231037
	MA Xinwei, MU Xingsen, LONG Zhu, et al. Prediction of heat transfer coefficient of horizontal tube falling film evaporation based on GA-BP neural network[J]. CIESC Journal, 2023, 74(12): 4840-4851.
[14]	戴妙林, 屈佳乐, 刘晓青, 等. 基于GA-BP算法的岩质边坡稳定性和加固效应预测模型及其应用研究[J]. 水利水电技术, 2018, 49(5):165-171.
	DAI Miaolin, QU Jiale, LIU Xiaoqing, et al. Study on GA-BP hybrid algorithm-based prediction model and its application to rock slope stability and reinforcement effect[J]. Water Resources and Hydropower Engineering, 2018, 49(5): 165-171.
[15]	GB/T 37573—2019, 露天煤矿边坡稳定性年度评价技术规范[S].
	GB/T 37573—2019, The technical standards for annual evaluation of slope stability in open-pit coal mines[S].
[16]	CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. Peerj Computer Science, 2021, 7:DOI:10.7717/peerj-cs.623.
[17]	赵允坤, 胡军, 杨斌. 基于IPSO-ELM的边坡稳定性分析[J]. 有色金属工程, 2022, 12(1):122-128.
	ZHAO Yunkun, HU Jun, YANG Bin. Slope stability analysis based on IPSO-ELM[J]. Nonferrous Metals Engineering, 2022, 12(1): 122-128.
[18]	冯小鹏, 李勇, 袁于思, 等. 基于AdaBoost卷积神经网络的矿山边坡稳定性预测[J]. 有色金属:矿山部分, 2022, 74(3):65-70,77.
	FENG Xiaopeng, LI Yong, YUAN Yusi, et al. Forecasting of mine slope stability based on AdaBoost convolutional neural network[J]. Nonferrous Metals (Mining), 2022, 74(3): 65-70,77.
[19]	曹念, 孙华芬, 史朝阳, 等. 基于鲸鱼算法优化支持向量机的露天煤矿边坡稳定性预测[J]. 矿冶, 2023, 32(6):9-14.
	CAO Nian, SUN Huafen, SHI Chaoyang, et al. Slope stability prediction based on whale algorithm optimizing support vector machine for open-pit coal slopes[J]. Mining and Metallurgy, 2023, 32(6):9-14.

样本编号	台阶坡面角/ (°)	黏聚力/ kPa	平台宽度/ m	台阶高度/ m	内部位移/ mm	岩土内应力/ kPa	地表位移/ mm	孔隙水压力/ kPa	地震烈度/ M	降雨量/mm	边坡安全系数	边坡状态	数据来源
1	33.6	60.5	24	3.8	12.6	550	44.2	12.7	4.3	111	1.420	安全	X露天矿
2	31.1	55.8	18.5	5.3	14.7	543	36.3	13.3	3.7	124	1.120	失稳	文献[17]
3	32.9	64.1	25	7.6	16.4	576	43.5	11.5	3.3	108	1.300	安全	X露天矿
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
75	31.5	63.4	27	6.7	13.7	536	37.3	13.1	4	116	0.960	失稳	文献[18]
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
149	30.3	63.6	28	7.3	17.4	524	48.3	8.4	3.2	125	1.200	安全	X露天矿
150	29.4	60.2	26	5.7	15.1	516	34.2	9.2	4.1	133	1.110	失稳	文献[19]

预测模型	性能指标
预测模型	MSE	MAE	MAPE/%
BP	0.035 6	0.124 3	15.23
GA-BP	0.018 9	0.092 7	9.85