首页 > 论文 > 光学学报 > 38卷 > 7期(pp:730002--1)

基于多层正则极限学习机的煤矿突水光谱判别方法

Identification Method of Coal Mine Water Inrush Spectrum Based on Multilayer Regularization Extreme Learning Machine

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了快速而准确地判别煤矿突水水源类型,提出了一种构建多层正则极限学习机(M-RELM)模型的方法,该模型融合了非线性特征提取和分类学习。以激光诱导荧光(LIF)技术获取水样荧光光谱,作为模型的输入;以改进的自动编码器(AE)提取荧光光谱特征,形成模型隐含层的特征空间。为了减少光谱中噪声和异常对分类结果的影响,对极限学习机(ELM)算法进行了正则化优化,根据是否利用未知样本构造训练集,进行L2范数正则极限学习机(L2-RELM)或基于图的流形正则极限学习机(GM-RELM)优化,实现监督或半监督的分类学习。通过不同功能的隐含层之间进行传播,构建了多层正则化模型,完成了预训练和训练两个过程的融合。以淮南区域煤矿突水水样为实验对象,与支持向量机(SVM)和单隐含层极限学习机进行性能比较。在含有混合水的样集上,该模型的平均测试准确率可达到94%以上,训练时间为0.2 s左右。在含有未知样本的所有水样集上,相比于L2-RELM模型,采用基于图的流形正则优化的GM-RELM模型的测试准确率可提升2%左右。实验结果表明,M-RELM模型更能适应煤矿突水水源的判别要求。

Abstract

In order to quickly and accurately identify the source types of coal mine water inrush, we propose a method of constructing a multilayer regularization extreme learning machine (M-RELM) model, which combines the functions of nonlinear feature extraction and classification learning. The fluorescence spectra of water samples are obtained by laser induced fluorescence (LIF) technique as the input of model. The features of fluorescence spectra are extracted by the improved auto encoder (AE) to form the feature space of the model hidden layer. In order to reduce the effect of noise and anomaly of spectra on classification results, the algorithm of extreme learning machine(ELM) is optimized regularly. According to whether the unknown samples are used to construct the training set, the model is optimized regularly by the L2 norm regularization (L2-RELM) or the graph manifold regularization (GM-RELM), which realizes the supervised or semi-supervised classification learning. By propagating between the hidden layers of different functions, M-RELM is constructed, and the integration of pre-training and training is completed. The water inrush samples in Huainan area coal mine as the experimental object, the performance compares with the support vector machine (SVM) and ELM with a single hidden layer. On the samples set containing mixed water, the average testing accuracy of the model can reach more than 94% and the training time is about 0.2 s. On all water samples containing the unknown samples, the testing accuracy of GM-RELM is increased by 2% than L2-RELM. The experimental results show that the M-RELM model is more suitable for the identification requirements of coal mine water inrush.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:O433.4

DOI:10.3788/aos201838.0730002

所属栏目:光谱学

基金项目:“十二五”国家科技支撑计划(2013BAK06B01)、国家自然科学基金(51174258)、国家安全生产重大事故防治关键技术科技项目(anhui-0001-2016AQ)、安徽省自然科学基金项目(1808085MF202,1808085QE157)、安徽省自然科学研究项目(KJ2018ZD036)

收稿日期:2018-01-10

修改稿日期:2018-03-10

网络出版日期:--

作者单位    点击查看

王亚:安徽理工大学电气与信息工程学院, 安徽 淮南 232001阜阳师范学院计算机与信息工程学院, 安徽 阜阳 236037
周孟然:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
陈瑞云:淮南矿业集团谢桥煤矿, 安徽 阜阳 236221
闫鹏程:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
胡锋:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
来文豪:安徽理工大学电气与信息工程学院, 安徽 淮南 232001

联系人作者:周孟然(mrzhou8521@163.com)

备注:王亚(1980-),女,博士研究生,副教授,主要从事光谱技术检测、模式识别方面的研究。E-mail: fync_wy80@163.com

【1】Wu Q, Cui F P, Zhao S Q, et al. Type classification and main characteristics of mine water disasters[J]. Journal of China Coal Society, 2013, 38(4): 561-565.
武强, 崔芳鹏, 赵苏启, 等. 矿井水害类型划分及主要特征分析[J]. 煤炭学报, 2013, 38(4): 561-565.

【2】Liu J M, Wang J R, Liu Y P, et al. Hydrochemistry analysis based on the source determination of coal mine water-bursts[J]. Journal of Safety and Environment, 2015, 15(1): 31-35.
刘剑民, 王继仁, 刘银朋, 等. 基于水化学分析的煤矿矿井突水水源判别[J]. 安全与环境学报, 2015, 15(1): 31-35.

【3】Chen L W, Xu D Q, Yin X X, et al. Analysis on hydrochemistry and its control factors in the concealed coal mining area in north China: a case study of dominant inrush aquifers in Suxian mining area[J]. Journal of China Coal Society, 2017, 42(4): 996-1004.
陈陆望, 许冬清, 殷晓曦, 等. 华北隐伏型煤矿区地下水化学及其控制因素分析--以宿县矿区主要突水含水层为例[J]. 煤炭学报, 2017, 42(4): 996-1004.

【4】Chu X L, Lu W Z. Research and application progress of near infrared spectroscopy analytical technology in China in the past five years[J]. Spectroscopy and Spectral Analysis, 2014, 34(10): 2595-2605.
褚小立, 陆婉珍. 近五年我国近红外光谱分析技术研究与应用进展[J]. 光谱学与光谱分析, 2014, 34(10): 2595-2605.

【5】Yagi I, Ono R, Oda T, et al. Two-dimensional LIF measurements of humidity and OH density resulting from evaporated water from a wet surface in plasma for medical use[J]. Plasma Sources Science and Technology, 2014, 24(1): 15002.

【6】Yang Y X, Kang J, Wang Y R, et al. Super sensitive detection of lead in water by laser-induced breakdown combined with laser-induced fluorescence technique[J]. Acta Optica Sinica, 2017, 37(11): 1130001.
杨宇翔, 康娟, 王亚蕊, 等. 水中铅元素的激光诱导击穿光谱-激光诱导荧光超灵敏检测[J]. 光学学报, 2017, 37(11): 1130001.

【7】Huang Z L, Li Y L, Yu C Z, et al. Analysis of effects for measurements of concentration in water by laser induced fluorescence (LIF) technique[J]. Journal of experimental mechanics, 1994(3): 232-240.
黄真理, 李玉梁, 余常昭,等. LIF技术测量浓度场的影响因素分析[J]. 实验力学, 1994(3): 232-240.

【8】Wang X, Yang J, Li K. Fluorescence feature of dissolved organic matters in groundwater of mining area-Ⅱ. Distribution features in the deep aquifers[J]. Journal of Safety and Environment, 2015, 15(6): 97-100.
王新, 杨建, 李凯. 煤矿区地下水中溶解性有机质荧光特征Ⅱ--深部含水层分布特征[J]. 安全与环境学报, 2015, 15(6): 97-100.

【9】Wang S D. Distribution characteristics of fluorescent dissolved organic matter in different aquifers of Luotuoshan coal mine[J]. Coal Geology & Exploration, 2015(2): 53-57.
王世东. 骆驼山煤矿不同含水层水中荧光性DOM分布特征[J]. 煤田地质与勘探, 2015(2): 53-57.

【10】Yan P C, Zhou M R, Liu Q M, et al. Research on the source identification of mine water inrush based on LIF technology and SIMCA algorithm[J]. Spectroscopy and Spectral Analysis, 2016, 36(1): 243-247.
闫鹏程, 周孟然, 刘启蒙, 等. LIF 技术与 SIMCA 算法在煤矿突水水源识别中的研究[J]. 光谱学与光谱分析, 2016, 36(1): 243-247.

【11】Bandos T V, Bruzzone L, Camps-Valls G. Classification of hyperspectral images with regularized linear discriminant analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(3): 862-873.

【12】Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.

【13】Li J F, Wang Y L, Hu S, et al. The comparison of spectral classification based on DBN, BP neural network and SVM[J]. Spectroscopy and Spectral Analysis, 2016, 36(10): 3261-3264.
李俊峰, 汪月乐, 胡升, 等. 基于DBN, SVM和BP 神经网络的光谱分类比较[J]. 光谱学与光谱分析, 2016, 36(10): 3261-3264.

【14】Wang J, Zhang F, Wang X P, et al. Three-dimensional fluorescence characteristics by parallel factor method coupled with self-organizing map and its relationship with water quality[J]. Acta Optica Sinica, 2017, 37(7): 0730003.
王娟, 张飞, 王小平, 等. 平行因子法结合自组织映射神经网络的三维荧光特征及其与水质关系研究[J]. 光学学报, 2017, 37(7): 0730003.

【15】Wang S T, Zhang C X, Wang Z F, et al. Application of least squares support vector machine in fluorescence detection of sodium methylparaben[J]. Laser & Optoelectronics Progress, 2017, 54(7): 073001
王书涛, 张彩霞, 王志芳, 等. 最小二乘支持向量机在对羟基苯甲酸甲酯钠荧光检测中的应用[J]. 激光与光电子学进展, 2017, 54(7): 073001.

【16】Hsu C W, Chang C C, Lin C J. A practical guide to support vector classification[EB/OL]. (2016-05-19). https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.

【17】Wang S T, Chen D Y, Wang X L, et al. Detection of polycyclic aromatic hydrocarbons combining fluorescence analysis with ABC-BP neural network[J]. Chinese Journal of Lasers, 2015, 42(11): 1115001.
王书涛, 陈东营, 王兴龙, 等. 荧光分析法和ABC-BP神经网络相结合的多环芳烃的检测[J]. 中国激光, 2015, 42(11): 1115001.

【18】Huang G B, Zhu Q Y, Siew C. Extreme learning machine: a new learning scheme of feedforward neural networks[C]. IEEE International Joint Conference on Neural Networks, 2004, 2: 985-990.

【19】Ding S F, Zhao H, Zhang Y N, et al. Extreme learning machine: algorithm, theory and applications[J]. Artificial Intelligence Review, 2015, 44(1): 103-115.

【20】Wang Y, Zhou M R, Yan P C, et al. A rapid identification model of mine water inrush based on extreme learning machine[J]. Journal of China Coal Society, 2017, 42(9): 2427-2432.
王亚, 周孟然, 闫鹏程, 等. 基于机限学习机的矿井突水水源快速识别模型[J]. 煤炭学报, 2017, 42(9): 2427-2432.

【21】Huang G, Huang G B, Song S J, et al. Trends in extreme learning machines: a review[J]. Neural Networks, 2015, 61: 32-48.

【22】Belkin M, Niyogi P, Sindhwani V. On manifold regularization[C]. AISTATS, 2005: 1.

【23】Liu B, Xia S X, Meng F R, et al. Manifold regularized extreme learning machine[J]. Neural Computing and Applications, 2016, 27(2): 255-269.

【24】Huang G B, Zhou H M, Ding X J, 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.

【25】Deng C W, Huang G B, Xu J, et al. Extreme learning machines: new trends and applications[J]. Science China(Information Sciences), 2015, 58(2): 1-16.

【26】Monti F,Boscaini D, Masci J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs[C]. Honolulu: 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017.

【27】Belkin M,Niyogi P, Sindhwani V. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples[J]. Journal of Machine Learning Research, 2006, 7(1): 2399-2434.

【28】Zhou H M, Huang G B, Lin Z P, et al. Stacked extreme learning machines[J]. IEEE Transactions on Cybernetics, 2015, 45(9): 2013-2025.

【29】Kasun L L C, Yang Y, Huang G, et al. Dimension reduction with extreme learning machine[J]. IEEE Transactions on Image Processing, 2016, 25(8): 3906-3918.

【30】Tang J X, Deng C W, Huang G B, et al. A fast learning algorithm for multi-layer extreme learning machine[C]. IEEE International Conference on Image Processing, 2014: 175-178.

【31】Kasun L L C, Zhou H M, Huang G B, et al. Representational learning with ELMs for big data[J]. IEEE Intelligent Systems, 2013, 28(6): 31-34.

【32】Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3): 27.

【33】Tang J X, Deng C W, Huang G B. Extreme learning machine for multilayer perceptron[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(4): 809-821.

【34】Melacci S, Belkin M. Laplacian support vector machines trained in the primal[J]. Journal of Machine Learning Research, 2011, 12(3): 1149-1184.

引用该论文

Wang Ya,Zhou Mengran,Chen Ruiyun,Yan Pengcheng,Hu Feng,Lai Wenhao. Identification Method of Coal Mine Water Inrush Spectrum Based on Multilayer Regularization Extreme Learning Machine[J]. Acta Optica Sinica, 2018, 38(7): 0730002

王亚,周孟然,陈瑞云,闫鹏程,胡锋,来文豪. 基于多层正则极限学习机的煤矿突水光谱判别方法[J]. 光学学报, 2018, 38(7): 0730002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF