改进的支持向量机方法在矿山地质环境质量评价中的应用

doi:10.13278/j.cnki.jjuese.201605207

摘要/Abstract

摘要：

传统支持向量机（SVM）评价模型中网格搜索法对参数的选择受到主观因素的影响，选用粒子群算法对SVM模型进行优化，并应用改进的SVM模型（PSO-SVM）对长吉图经济区135个矿山进行地质环境质量评价。PSO-SVM模型的评价结果与综合评价结果的相同率（注：该相同率是指两个评价结果相同的个数占所有评价样本数的百分比）达到95.56%，与SVM模型评价结果的相同率达到91.11%。结合研究区实际情况并分析三种评价结果得出，PSO-SVM模型的评价结果更符合实际情况。改进的支持向量机方法能够避免人为因素影响，提高矿山地质环境评价水平，在评价中具有可行性和有效性。基于改进的支持向量机方法评价结果表明，研究区矿山地质环境受矿山开采等人为活动的影响，54.1%的矿山遭受严重破坏（III级），25.9%为中度破坏（II级）。评价结果可为研究区矿山环境恢复治理提供决策支持。

关键词: 支持向量机(SVM), 粒子群优化(PSO), 矿山地质环境质量评价, 长吉图经济区

Abstract:

The grid search method, as on kind of traditional evaluation model of SVM, can be influenced by subjective factors on selecting parameters. So in this study, particle swarm algorithm was chosen to optimize the SVM model and optimized SVM model (PSO-SVM) was used to evaluate geological environment of 135 mines in the Chang-Ji-Tu economic zone. It showed that the evaluation results were almost consistent with comprehensive evaluation results, the similiarity reached to 95.56%. Compared to traditional SVM, itreached to 91.11%. Based on the actual situation and comprehensive analysis of three kinds of evaluation results, we found out that PSO-SVM evaluation results were more in line with the actual situation. Optimized SVM model could effectively avoid the influence of human factors and improve the level of mine geological environment assessment, it was feasible and effective in the evaluation. Evaluation results based on the optimized SVM model showed that mine geological environment was affected by human activities in the study area such as mining, 54.1% of the mine suffered serious damage (III grade), 25.9% suffered moderate damage (II level). The evaluation results can provide decisions for environmental restoration in the study area.

Key words: support vector machine (SVM), particle swarm optimization (PSO), mine geological environment quality evaluation, Chang-Ji-Tu economic zone

中图分类号:

卢文喜, 郭家园, 董海彪, 张宇, 林琳. 改进的支持向量机方法在矿山地质环境质量评价中的应用[J]. 吉林大学学报(地球科学版), 2016, 46(5): 1511-1519.

Lu Wenxi, Guo Jiayuan, Dong Haibiao, Zhang Yu, Lin Lin. Evaluating Mine Geology Environmental Quality Using Improved SVM Method[J]. Journal of Jilin University(Earth Science Edition), 2016, 46(5): 1511-1519.

参考文献

[1] 孔志召, 董双发, 姜雪, 等. 基于层次分析法的矿山环境评价:以阜新矿集区为例[J]. 世界地质, 2012,31(2):420-425. Kong Zhizhao, Dong Shuangfa, Jiang Xue, et al. Mine Environmental Assessment by Analytic Hierarchy Process:Taking Fuxin Mine as an Example[J]. Global Geology, 2012,31(2):420-425.

[2] 黄永泉, 危超, 何景媛. 基于灰色关联分析法的江西省矿山环境质量评价[J]. 资源调查与环境, 2012, 33(4):268-273. Huang Yongquan, Wei Chao, He Jingyuan. Mine Environmental Quality Evaluation by Grey Relational Analysis Method in Jiangxi Province[J]. Resources Survey and Environment, 2012, 33(4):268-273.

[3] 罗娟, 陈守余.矿山环境质量评价指标体系及层次分析法评价[J]. 安全与环境工程, 2005, 12(1):9-12. Luo Juan, Chen Shouyu. Mine Environmental Quality Evaluation Index System and Assessment of Analytic Hierarchy Process[J]. Safety and Environmental Engineering, 2005, 12(1):9-12.

[4] 杨梅忠, 刘亮, 高礼让. 模糊综合评判在矿山环境影响评价中的应用[J]. 西安科技大学学报, 2006, 26(4):439-442. Yang Meizhong, Liu Liang, Gao Lirang. Application of Fuzzy Synthesis Evaluation to the Environmental Influence of the West Mineral Exploration[J]. Journal of Xi'an University of Science and Technology, 2006, 26(4):439-442.

[5] 蒋复量, 周科平, 李书娜, 等. 基于粗糙集-神经网络的矿山地质环境影响评价模型及应用[J]. 中国安全科学学报, 2009, 19(8):126-132. Jiang Fuliang, Zhou Keping, Li Shuna, et al. Study on the Model of Mines' Geological Environment Impact Assessment Based on Rough Set and Artificial Neural Network and Its Application[J]. China Safety Science Journal, 2009, 19(8):126-132.

[6] 韩舸, 龚威, 吴婷, 等. 利用粗糙集的滑坡分段位移预测方法:以白家包滑坡为例[J]. 吉林大学学报(地球科学版), 2014,44(3):925-931. Han Ge, Gong Wei, Wu Ting, et al. Using Rough Set Landslide Segment Displacement Prediction Methods:White House Pack Landslide, for Example[J]. Journal of Jilin University(Earth Science Edition), 2014,44(3):925-931.

[7] 何芳, 徐友宁, 袁汉春. 矿山环境地质问题综合评价客观权值确定方法探讨[J]. 中国地质, 2008, 35(2):337-343. He Fang, Xu Youning, Yuan Hanchun. Method for the Determination of Objective Weight-Values in the Comprehensive Evaluation of Mine Environmental Geological Problems[J]. Geology in China, 2008, 35(2):337-343.

[8] 郭凤仪, 郭长娜, 王爱军, 等. 基于粒子群优化支持向量机的煤矿水位预测模型[J]. 计算机工程与科学, 2012, 34(7):177-181. Guo Fengyi, Guo Changna, Wang Aijun, et al. The Forecast Model of Mine Water Discharge Based on Particle Swarm Optimization and Support Vector Machines[J]. Computer Engineering and Science, 2012, 34(7):177-181.

[9] 张俊才, 张静. 使用粒子群算法进行特征选择及对支持向量机参数的优化[J]. 微电子学与计算机, 2012, 29(7):138-141. Zhang Juncai, Zhang Jing. Use PSO to Perform Feature Selection and Parameter Optimization of SVM[J]. Microelectronics and Computer, 2012, 29(7):138-141.

[10] Yan Z,Zhang H R,Du P J.Application of SVM in Analy-zing the Headstream of Gushing Water in Coal Mine[J]. Journal of China University of Mining & Technology(English Edition), 2006, 16(4):433-438.

[11] 李海生. 支持向量机回归算法与应用研究[D]. 广州:华南理工大学, 2005. Li Haisheng.Algorithm and Application Research of Support Vector Machine Regression[D]. Guangzhou:Technology Master Thesis of South China University, 2005.

[12] Zhong Y H, Zhao L, Liu Z B. Using a Support Vector Machine Method to Predict the Development Indices of Very High Water Cut Oilfields[J]. Petroleum Science, 2010(3):379-384.

[13] 原立峰, 周启刚, 马泽忠. 支持向量机在泥石流危险度评价中的应用研究[J]. 中国地质灾害与防治学报, 2007, 18(4):29-33,39. Yuan Lifeng, Zhou Qigang, Ma Zezhong. Application of SVM on Debris Flow Hazard Assessment[J]. The Chinese Journal of Geological Hazard and Control, 2007, 18(4):29-33,39.

[14] 黄鹤, 卢文喜, 伊燕平, 等. 基于支持向量机模型的水质评价研究[J]. 节水灌溉, 2012(2):57-59,63. Huang He, Lu Wenxi, Yi Yanping, et al. Assessment of Water Quality Based on Support Vector Machine Model[J]. Irrigation, 2012(2):57-59,63.

[15] 雷开友. 粒子群算法及其应用研究[D]. 重庆:西南大学, 2006. Lei Kaiyou. Research on Particle Swarm Optimization and Its Application[D]. Chongqing:Southwestern University, 2006.

[16] 张丽平. 粒子群优化算法的理论及实践[D]. 杭州:浙江大学, 2005. Zhang Liping. The Theorem and Practice Apon the Particle Swarm Optimization Algorithm[D]. Hangzhou:Zhejiang University, 2005.

[17] 李娇. 支持向量机参数优化研究[D]. 武汉:华中师范大学, 2011. Li Jiao. Research of Parameter Optimization for Support Vector Machine[D]. Wuhan:Central China Normal University, 2011.

[18] 高卫东, 王正帅. 基于粒子群优化支持向量机的煤层底板突水量等级预测[J]. 煤田地质与勘探, 2012, 40(6):44-47. Gao Weidong, Wang Zhengshuai. Forecast of Inrushed Water Volume Grade from Coal Floor Based on Support Vector Machine with Particle Swarm Optimization[J]. Coal Geology and Exploration, 2012, 40(6):44-47.

[19] 朱裕生, 郑大瑜, 韦昌山, 等. 矿山危机程度评价的指标体系[J]. 资源产业, 2004, 6(4):30-32. Zhu Yusheng, Zheng Dayu, Wei Changshan, et al. The Index System of the Crisis Level Evaluation for Resources Crisis Mines[J]. Resources and Industries, 2004, 6(4):30-32.

[20] 矿山地质环境保护与恢复治理方案编制规范(2011版):DZ/T 0223-2011[S].北京:中国标准出版社,2011. Mine Geological Environment Protection and Recovery Control Scheme Compilation Specification(2011 Edition):DZ/T 0223-2011[S].Beijing:China Standard Publisher,2011.

[21] 郭小荟, 马小平. 基于Matlab的支持向量机工具箱[J]. 计算机应用与软件, 2007, 24(12):57-59. Guo Xiaohui, Ma Xiaoping. Support Vector Machines Toolbox in Matlab Environment[J]. Computer Applications and Software, 2007, 24(12):57-59.

相关文章 15

[1]	周孙超, 宋腾蛟, 王琰, 蔡宗佑. 基于小龙虾优化算法的BP神经网络模型在滑坡易发性评价中的应用[J]. 吉林大学学报(地球科学版), 2026, 56(3): 937-950.
[2]	贺金鑫, 涵雅, 周俊宏, 杨永斌, 李煜. 基于知识图谱的火星季节性斜坡纹线时空特征分析[J]. 吉林大学学报(地球科学版), 2026, 56(1): 252-265.
[3]	刘波, 李诗浓, 李伟, 王文鹏, 鲁程鹏, 束龙仓. 基于栅格信息量法的区域地面沉降风险评价：以河北省沧州市为例[J]. 吉林大学学报(地球科学版), 2025, 55(3): 919-929.
[4]	周琨超, 王志远, 翟金榜, 张泽, 孟祥熙, 袁名扬. 振动荷载作用下近相变区冰-水相变迁移规律 [J]. 吉林大学学报(地球科学版), 2025, 55(2): 550-562.
[5]	束龙仓, 黄蕾, 陈华伟, 鲁程鹏, 刘波. 基于AHP-EWM的莱州市海岸带海水入侵灾害风险评价与区划[J]. 吉林大学学报(地球科学版), 2023, 53(6): 1864-1879.
[6]	张琦, 杨忠年, 时伟, 凌贤长, 涂志斌. 冻融循环下初始含水率对非饱和膨胀土剪切特性试验[J]. 吉林大学学报(地球科学版), 2021, 51(5): 1544-1550.
[7]	王宇晴, 董春艳, 白文倩, 颉颃强, 万渝生. 鲁西莲花山地区新太古代晚期二长花岗岩中的表壳岩包体——SHRIMP锆石U-Pb定年和地球化学特征[J]. 吉林大学学报(地球科学版), 2021, 51(1): 141-153.
[8]	辛欣, 陈圣波, 覃文汉, 李东辉, 陆天启, 田粉粉. Apollo16登月区Hapke模型参数反演及模型敏感性分析[J]. 吉林大学学报(地球科学版), 2018, 48(3): 934-940.
[9]	刘菁华, 王文华, 陈圣波, 周大鹏. CE3玉兔号月球车APXS特征X射线能谱信息分析[J]. 吉林大学学报(地球科学版), 2018, 48(2): 445-450.
[10]	徐则民, 梅雪峰, 王礼荣, 张有为, 曾强, 郭丽丽. 滑坡预警中的降水时空变异性——以云南头寨沟为例[J]. 吉林大学学报(地球科学版), 2017, 47(1): 154-162.
[11]	宋志, 邓荣贵, 陈泽硕, 冯伟. 磨西河泥石流堵断大渡河物理模拟与早期识别[J]. 吉林大学学报(地球科学版), 2017, 47(1): 163-170.
[12]	苏生瑞，李鹏，王琦，苏卫卫，张莹. 叠瓦状逆断层的变形规律和力学机理物理模拟试验：以龙门山断裂带为例[J]. 吉林大学学报(地球科学版), 2014, 44(1): 249-258.
[13]	薛群威，刘艳辉，唐灿. 突发地质灾害气象预警统计模型与应用[J]. 吉林大学学报(地球科学版), 2013, 43(5): 1614-1622.
[14]	王洪德，高幼龙，薛星桥，金枭豪，王刚. 典型滑坡监测点优化布置[J]. 吉林大学学报(地球科学版), 2013, 43(3): 858-866.
[15]	彭帅英，李广杰，彭文，马建全，王雪冬，秦胜伍. 基于改进遗传算法的Holt-Winters模型在采空沉陷预测中的应用[J]. 吉林大学学报(地球科学版), 2013, 43(2): 515-520.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed