多策略改进SSA优化KELM的边坡稳定性预测模型

doi:10.16265/j.cnki.issn1003-3033.2025.03.0134

中国安全科学学报 ›› 2025, Vol. 35 ›› Issue (3): 92-98.doi: 10.16265/j.cnki.issn1003-3033.2025.03.0134

多策略改进SSA优化KELM的边坡稳定性预测模型

祁云¹^,²^,³(), 薛凯隆⁴^,⁵^,^**(), 李绪萍¹^,²^,⁴, 汪伟¹^,²^,³, 白晨浩⁵, 吉准泽⁶

¹ 内蒙古科技大学矿业与煤炭学院,内蒙古包头 014010
² 内蒙古自治区矿业工程重点实验室,内蒙古包头 014010
³ 内蒙古自治区煤炭安全开采与利用工程技术研究中心,内蒙古包头 014010
⁴ 内蒙古煤炭绿色开采与绿色利用协同创新中心,内蒙古包头 014010
⁵ 山西大同大学煤炭工程学院,山西大同 037000
⁶ 内蒙古科技大学材料与冶金学院,内蒙古包头 014010

收稿日期:2024-10-20 修回日期:2024-12-28 出版日期:2025-03-28
通信作者:
** 薛凯隆(2000—),男,山西吕梁人,硕士研究生,主要研究方向为矿山灾害监测预警、应急技术与管理。E-mail:xuekailong22@163.com。
作者简介:
祁云 (1988—),男,安徽淮北人,博士,副教授,硕士生导师,主要从事矿井灾害防治、安全评价、应急技术与管理等方面的研究。E-mail:qiyun_sx@163.com。
李绪萍，教授；
汪伟，副教授
基金资助:
国家自然科学基金地区基金资助(52464020); 内蒙古自然科学基金资助(2024LHMS05012); 山西省高等学校科技创新计划项目(2022L448); 山西省高等学校科技创新计划项目(2022L449); 山西大同大学研究生教育创新项目(23CX49)

Slope stability prediction model based on multi-strategy improved SSA for optimizing KELM

QI Yun¹^,²^,³(), XUE Kailong⁴^,⁵^,^**(), LI Xuping¹^,²^,⁴, WANG Wei¹^,²^,³, BAI Chenhao⁵, JI Zhunze⁶

¹ School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China
² Inner Mongolia Key Laboratory of Mining Engineering, Baotou Inner Mongolia 014010, China
³ Inner Mongolia Research Center for Coal Safety Mining and Utilization Engineering and Technology, Baotou Inner Mongolia 014010, China
⁴ Inner Mongolia Cooperative Innovation Center for Coal Green Mining and Green Utilization, Baotou Inner Mongolia 014010, China
⁵ School of Coal Engineering, Shanxi Datong University, Datong Shanxi 037000, China
⁶ School of Materials and Metallurgy, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China

Received:2024-10-20 Revised:2024-12-28 Published:2025-03-28

摘要/Abstract

摘要：

为了能够更加精准地预测边坡稳定状态,从而有效预防边坡失稳事故,提出改进麻雀搜索算法(ISSA)与核极限学习机(KELM)相结合的ISSA-KELM边坡稳定性预测模型。首先,将边坡失稳特征中的容重、黏聚力等6个主要影响因素作为预测指标,建立边坡稳定性评价数据集;其次,引入Sine混沌映射、Levy飞行策略、动态自适应权重以及融合最优爆炸策略和反向学习改进麻雀搜索算法(SSA),以提高其全局搜索能力和稳定性;而后利用ISSA优化KELM中的核参数ψ和正则化系数C,提升其预测精度,同时避免KELM出现过拟合现象;最后,对比分析ISSA-KELM模型与SSA-KELM、粒子群优化算法(PSO)-KELM以及PSO-支持向量机(SVM)模型的预测结果,并将ISSA-KELM模型应用于山西某露天煤矿。结果表明:ISSA-KELM模型的准确率、精确率、召回率和F₁分数分别达到了0.945 9、1、0.866 7和0.929,均优于SSA-KELM、PSO-KELM和PSO-SVM模型,模型的预测结果与实际值最为接近,表明所建ISSA-KELM模型具有较强的泛化能力。

关键词: 边坡稳定性, 预测模型, 改进麻雀搜索算法(ISSA), 核极限学习机(KELM), 预测指标, 混淆矩阵

Abstract:

In order to predict the slope state more accurately and effectively prevent the slope instability accident, an improved ISSA-KELM slope stability prediction model was proposed. Firstly, six main factors such as bulk density and cohesion in slope instability characteristics were used as prediction indexes to establish a data set for slope stability evaluation. Secondly, SSA was enhanced by incorporating Sine chaotic mapping, Levy flight strategy, dynamic adaptive weights, and fusion of optimal explosion strategy and reverse learning. These improvements aimed at enhancing the global search capability and stability of SSA. Subsequently, ISSA was employed to optimize the kernel parameter ψ and regularization coefficient C in KELM for improved prediction accuracy while avoiding overfitting issues associated with KELM. The results show that the accuracy rate, precision, recall rate and F₁ score of ISSA-KELM model reached 0.945 9, 1, 0.866 7 and 0.929, respectively, which are superior to SSA-KELM, PSO-KELM and PSO-SVM models, and the predicted results of the model are the closest to the actual values. It shows that the established ISSA-KELM model has strong generalization ability.

Key words: slope stability, prediction model, improved sparrow search algorithm (ISSA), kernel extreme learning machine (KELM), prediction index, confusion matrix

中图分类号:

X936

祁云, 薛凯隆, 李绪萍, 汪伟, 白晨浩, 吉准泽. 多策略改进SSA优化KELM的边坡稳定性预测模型[J]. 中国安全科学学报, 2025, 35(3): 92-98.

QI Yun, XUE Kailong, LI Xuping, WANG Wei, BAI Chenhao, JI Zhunze. Slope stability prediction model based on multi-strategy improved SSA for optimizing KELM[J]. China Safety Science Journal, 2025, 35(3): 92-98.

图/表 10

表1

标准测试函数

测试函数	维度	取值范围
$f 1 = - ∑ i = 1 n (x i s i n (\| x i \|))$	30	[-500, 500]
$f 2 = ∑ i = 1 n [x i 2 - 10 c o s (2 π x i + 10)]$	30	[-5.12, 5.12]
$f 3 = - ∑ i = 1 n [(x - a i) (x - a i) T + c i] - 1$	30	[0, 10]
$f 4 = ∑ i = 1 n a i - x 1 (b i 2 + b i x 2) b i 2 + b i x 3 + x 4$	30	[-5, 5]

表1

图1

表2

图2

表3

图3

图4

表4

表5

图5

参考文献 13

[1]	WEI Zhenlei, LU Qing, SUN Hongyue, et al. Estimating the rainfall threshold of a deep seated landslide by integrating models for predicting the groundwater level and stability analysis of the slope[J]. Engineering Geology, 2019, 253: 14-26. doi: 10.1016/j.enggeo.2019.02.026
[2]	胡少伟, 李原昊, 单常喜, 等. 基于改进的PSO-BP神经网络的边坡稳定性研究[J]. 防灾减灾工程学报, 2023, 43(4):854-861.
	HU Shaowei, LI Yuanhao, SHAN Changxi, et al. Research on slope stability based on improved PSO-BP neural network[J]. Journal of Disaster Prevention and Mitigation Engineering, 2023, 43(4):854-861.
[3]	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.
[4]	薛建凯. 一种新型的群智能优化技术的研究与应用[D]. 上海: 东华大学, 2020.
	XUE Jiankai. Research and application of a new swarm intelligent optimization technique[D]. Shanghai: Donghua University, 2020.
[5]	SEYEDALI M. SCA: a sine cosine algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2016, 96: 120-133.
[6]	余修武, 彭威, 余员琴, 等. 基于SSO的铀尾矿库无线传感器网络定位算法[J]. 中国安全科学学报, 2023, 33(4):84-90. doi: 10.16265/j.cnki.issn1003-3033.2023.04.0264
	YU Xiuwu, PENG Wei, YU Yuanqin, et al. Localization algorithm for uranium tailings reservoir based on SSO in wireless sensor network[J]. China Safety Science Journal, 2023, 33(4): 84-90. doi: 10.16265/j.cnki.issn1003-3033.2023.04.0264
[7]	毛清华, 张强. 融合柯西变异和反向学习的改进麻雀算法[J]. 计算机科学与探索, 2021, 15(6):1155-1164. doi: 10.3778/j.issn.1673-9418.2010032
	MAO Qinghua, ZHANG Qiang. Improved sparrow algorithm combining Cauchy mutation and opposition-based learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(6): 1155-1164.
[8]	吴大飞, 杨光永, 樊康生, 等. 多策略融合的改进粒子群优化算法[J]. 计算机应用研究, 2022, 39(11):3358-3364.
	WU Dafei, YANG Guangyong, FAN Kangsheng, et al. Improved particle swarm optimization algorithm with muti-strategy fusion[J]. Application Research of Computers, 2022, 39(11):3358-3364.
[9]	HUANG Guangbin, ZHOU Hongming, DING Xiaojian, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2); 513-529.
[10]	FENG Xianda, LI Shuchen, YUAN Chao, et al. Prediction of slope stability using naive Bayes classifier[J]. KSCE Journal of Civil Engineering, 2018, 22(3): 941-950.
[11]	SAMUI P. Support vector classifier analysis of slope[J]. Geomatics, Natural Hazards and Risk, 2013, 4 (1): 1-12.
[12]	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
[13]	祁云, 薛凯隆, 汪伟, 等. 矿井煤与瓦斯突出事故应急救援能力评估模型[J]. 中国安全科学学报, 2024, 34(2):225-230. doi: 10.16265/j.cnki.issn1003-3033.2024.02.0983
	QI Yun, XUE Kailong, WANG Wei, et al. Assessment model of emergency response capability for coal and gas outburst accidents in mines[J]. China Safety Science Journal, 2024, 34(2): 225-230. doi: 10.16265/j.cnki.issn1003-3033.2024.02.0983

预测结果	实际结果
预测结果	破坏	稳定
破坏	TP	FP
稳定	FN	TN

编号	γ/ (kN·m^-3)	c /kPa	φ/ (°)	β/ (°)	H /m	r_u/ kPa
1	17.93	78.20	18.49	33.42	120.79	0.00
2	18.02	40.92	21.18	21.86	21.86	0.10
︙	︙	︙	︙	︙	︙	︙
149	21.03	0.00	17.72	5.79	57.31	0.00
150	25.74	0.00	17.23	30.03	80.53	0.40
151	22.40	10.00	35.00	45.00	10.00	0.40
152	19.63	11.98	20.00	22.00	12.19	0.25
︙	︙	︙	︙	︙	︙	︙
256	18.84	14.36	25.00	20.00	30.50	0.45
257	19.97	19.96	36.00	45.50	50.00	0.50

模型	模型性能
模型	A_c	P	R	F₁
ISSA-KELM	0.980 8	1	0.966 7	0.983
SSA-KELM	0.942 3	0.965 5	0.933 3	0.949
PSO-KELM	0.884 6	0.928 6	0.866 7	0.897
PSO-SVM	0.826 9	0.920 0	0. 766 7	0.836

模型	模型性能
模型	A_c	P	R	F₁
ISSA-AKELM	0.945 9	1	0.866 7	0.929
SSA-AKELM	0.916 7	0.923 0	0.857 1	0.889
PSO-AKELM	0.864 9	0.857 1	0.800 0	0.828
PSO-ASVM	0.810 8	0.785 7	0.733 3	0.828

[1]	汪伟, 崔欣超, 祁云, 李绪萍, 王璜瑞, 齐庆杰. 改进SSA优化BPNN的煤体瓦斯渗透率预测模型[J]. 中国安全科学学报, 2025, 35(2): 137-143.
[2]	滕春阳, 李庆健, 陈金刚, 张建飞, 薛国庆. 基于N-BEATS的托辊滚动轴承剩余寿命预测[J]. 中国安全科学学报, 2024, 34(S1): 246-252.
[3]	高飞, 梁宁, 贾喆, 侯青. 基于SSA-RBF神经网络的煤自然发火预测模型[J]. 中国安全科学学报, 2024, 34(8): 128-137.
[4]	赵川, 刘思棋, 赵晓一. 手过头姿势下钻孔作业肌肉疲劳MET预测模型[J]. 中国安全科学学报, 2024, 34(8): 238-246.
[5]	王团辉, 王超, 吴顺川, 王琦玮, 徐健珲. 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.
[6]	王文超, 何健, 宋佰胜, 汪磊. 基于LSTM的航线飞行员操纵平稳性预测模型[J]. 中国安全科学学报, 2024, 34(12): 48-55.
[7]	马辉, 贺鹰霞, 陈杨杨. 基于XGBoost的城市污水管道缺陷发生概率预测[J]. 中国安全科学学报, 2024, 34(11): 163-171.
[8]	李德龙, 成钰, 李友东. 突发公共卫生事件下地铁安检员需求预测模型[J]. 中国安全科学学报, 2023, 33(S1): 228-234.
[9]	温惠英, 黄坤火, 赵胜. 基于机器学习的高速公路大型货车追尾风险预测[J]. 中国安全科学学报, 2023, 33(9): 173-180.
[10]	汪伟, 梁然, 祁云, 贾宝山, 武泽伟. 基于PSO-BPNN的煤自燃危险性预测模型[J]. 中国安全科学学报, 2023, 33(7): 127-132.
[11]	赵伟, 李书全. 基于机器学习的建筑施工人员安全能力预测模型[J]. 中国安全科学学报, 2023, 33(7): 51-57.
[12]	李帅, 练章华, 丁亮亮, 廖涛. 多因素耦合作用下的气井持续环空压力预测模型[J]. 中国安全科学学报, 2023, 33(2): 166-172.
[13]	孟祥海, 由冰玉, 邱志雄, 李之啸, 张明扬. 基于事故修正系数的山区高速公路事故预测模型[J]. 中国安全科学学报, 2023, 33(1): 10-17.
[14]	杨佩佩, 熊坚, 何扬帆. 公路小半径曲线路段驾驶人焦虑水平模型[J]. 中国安全科学学报, 2023, 33(1): 227-232.
[15]	晋良海, 陈颖, 杨应柳, 邵波. 电梯设备安全事故率的广义代数差分预测模型[J]. 中国安全科学学报, 2023, 33(1): 64-69.

多策略改进SSA优化KELM的边坡稳定性预测模型

Slope stability prediction model based on multi-strategy improved SSA for optimizing KELM

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 13

相关文章 15

编辑推荐

Metrics

本文评价