计算机科学 ›› 2021, Vol. 48 ›› Issue (7): 308-315.doi: 10.11896/jsjkx.200800110

• 人工智能 • 上一篇    下一篇

基于AGA-DBSCAN优化的RBF神经网络构造煤厚度预测方法

吴善杰, 王新   

  1. 中国矿业大学计算机科学与技术学院 江苏 徐州221116
  • 收稿日期:2020-08-18 修回日期:2020-09-17 出版日期:2021-07-15 发布日期:2021-07-02
  • 通讯作者: 王新(wxgrin@cumt.edu.cn)
  • 基金资助:
    国家自然科学基金(41704115,41774128);江苏省自然科学基金(BK20170273)

Prediction of Tectonic Coal Thickness Based on AGA-DBSCAN Optimized RBF Neural Networks

WU Shan-jie, WANG Xin   

  1. School of Computer Science and Technology,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China
  • Received:2020-08-18 Revised:2020-09-17 Online:2021-07-15 Published:2021-07-02
  • About author:WU Shan-jie,born in 1993,postgra-duate.His main research interests include intelligent information processing and machine learning.(1490354963@qq.com)
    WANG Xin,born in 1978,Ph.D,associa-te professor.Her research interests include intelligent information processing and machine learning.
  • Supported by:
    National Natural Science Foundation of China(41704115,41774128)and Natural Science Foundation of Jiangsu Province(BK20170273).

摘要: 在构造煤厚度的预测中,经常出现因各种限制性因素而导致预测精度不高的问题,因此提出了利用自适应遗传算法优化密度聚类(DBSCAN)优化RBF神经网络参数的方法对构造煤厚度进行预测。首先,对采区三维地震属性数据进行预处理,采用主成分分析算法(PCA)对该数据降维并消除变量之间的线性相关性。然后,构建预测构造煤厚度的RBF神经网络模型,并利用DBSCAN获取最佳核心点数据,通过计算得到k-means聚类的初始聚类中心,以此优化k-means算法,进而得到RBF神经网络隐含层基函数最优的中心向量,提高该模型预测的精准性和鲁棒性。同时,针对遗传算法存在容易陷入局部最优的问题,通过随着进化次数的增多自适应地改变交叉率和变异率来改善遗传算法的全局和局部搜索能力,使之逃离局部最优点,获得更优的进化结果。此外,为了增强模型的泛化能力,对模型权重参数加入了L2正则化项,有效避免了噪声对模型泛化能力的影响。最后,将该模型应用到芦岭煤矿II六采区8#煤层中,模型预测构造煤的厚度与实际地质资料具有较高的一致性。因此,所提构造煤厚度预测模型的实际预测精度较高、误差较小,可以推广到实际采区构造煤厚度的预测。

关键词: RBF神经网络, 构造煤, 厚度预测, 密度聚类, 遗传算法, 中心向量, 主成分分析

Abstract: In the prediction of tectonic coal thickness,the problem of low accuracy is often caused by various restrictive factors.Therefore,a method of optimizing the parameters of RBF neural networks by using adaptive genetic algorithm to optimize density clustering is used to predicte the thickness of tectonic coal.Firstly,the 3D seismic attribute data of the mining area are preprocessed,and the PCA algorithm is used to reduce the dimension and eliminate the linear correlation between variables.Then a RBF neural network model for predicting the thickness of tectonic coal is constructed,the genetic algorithm is used to optimize the density clustering to obtain the best core point,and the initial clustering center of k-means clustering is further calculated to optimize the k-means algorithm,so that the RBF neural network implicit layer basis function is obtained.An excellent center vector increases the accuracy and robustness of the model prediction.At the same time,aiming at the problem that genetic algorithm is easy to fall into local optimal problem,the global and local search ability of the genetic algorithm is improved by adaptively changing the crossover rate and the mutation rate with the increase of the number of evolutions,so that it can escape the local best advantage and obtain better evolutionary results.The L2 regularization term is added to effectively avoid the influence of noisy data for generalization performance of the model.Finally,the prosed model is applied to the 8# coal seam of the No.6 mining area of Luling Coal Mine.The predicted thickness of the model is highly consistent with the actual geological data.It is possible to promote the prediction of coal thickness in actual mining area.

Key words: Center vector, Density clustering, Genetic algorithm, Principal component analysis, Radial basis function neural network, Tectonic coal, Thickness prediction

中图分类号: 

  • TP183
[1]SHU L Y,WANG K,QI Q X,et al.Key structural body theory of coal and gas outburst[J].Chinese Journal of Rock Mechanics and Engineering,2017,36(2):347-356.
[2]YU S,BO J,HEWN L,et al.Variations in stress-sensitive mi-nerals and elements in the tectonic-deformation Early to Middle Permian coals from the Zhuxianzhuang mine,Anhui Province [J].Journal of Geochemical Exploration,2018,188:11-23.
[3]LI X J,SHEN Z H,LIU Y.Experimental study on the influence of pore structure of structural coal and primary structure coal on adsorption characteristics in northwestern Guizhou [J].Journal of Mining and Safety Engineering,2017,34(1):170-176.
[4]ZHAO Y P,SHI L Q,GAO W F,et al.Statistical analysis of coal mine accidents in China’s coal mine transformation and development period [J].Coal Technology,2016(9):321-324.
[5]CHEN T J,WANG X,GUAN Y W.Quantitative prediction of structural coal thickness based on SVR and seismic attributes [J].Chinese Journal of Coal,2015,40(5):1103-1108.
[6]TANG Z.The regional tectonic evolution and its control mechanism for structural development in Yangquan coalfield [D].Xuzhou:China University of Mining and Techonlogy,2018:46-79.
[7]YANG Y L,CHEN Y Q,GAO J X,et al.Experimental study on the effect of temperature on the gas adsorption capacity of media [J].Mining Safety and Environmental Protection,2016,43(4):6-9.
[8]ZHANG H J,ZHANG L,WANG D,et al.Gas emission characteristics of tectonic coal and microscopic explanation of pore structure[J].Journal of China Coal Society,2018,43(12):3404-3410.
[9]ZHANG Y G,WANG Y,YANG R J.Weather forecastingmodel based on radial basis neural network [J].Guiyang:Journal of Guizhou University (Natural Science Edition),2018,35(1):69-72.
[10]ZHANG P F,XU X,GE X Q.A hardware resource allocation method for multi-antenna ground station based on improved genetic algorithm[J].Computer Engineering & Science,2017,39(6):1155-1163.
[11]ZHANG X L,CUI N N,YANG T,et al.A layered adaptive fast K-means algorithm [J].Application Research of Computers,2016,33(2):421-443,427.
[12]SITTEL F,STOCK G.Robust density-based clustering to identify metastable conformational states of proteins[J].Journal of Chemical Theory & Computation,2016,12(5):1-4.
[13]SONI N,GANATRA A.AGED(automatic generation of Eps for DBSCAN)[J].International Journal of Computer Science and Information Security,2016,14(5):536-559.
[14]WANG X L,HUANG L,YANG P,et al.Dynamic RBF neural networks for model mismatch problem and its application in flotation process[J].CIESC Journal,2016,3(67):897-902.
[15]JGOUTA M,NSIRI B.GNSS Positioning performance analysis using PSO-RBF estimation model[J].Transport and Telecommunication Journal,2017,18(2):146-154.
[16]LIAN J M,LEE Y G,SCOTT D,et al.Self-organizing radial basis function network for real-time approximation of continuous-time dynamical system[J].IEEE Transactions on Neural Networks,2008,19(3):460-474.
[17]SHI K,QIN H,SIMA C,et al.Dynamic barycenter averaging kernel in RBF networks for time series classification[J].IEEE Access,2019,7:47564-47576.
[18]WEI W,WANG G B.Detection and recognition of air targets by unmanned aerial vehicle based on RBF neural network[J].Ship Electronic Engineering,2018,38(10):37-40.
[19]CHEN D.Research on traffic flow prediction in the big data environment based on the improved RBF neural network[J].IEEE Transactions on Industrial Informatics,2017,13(4):2000-2008.
[20]WU C M,FAN J L.Maximal mateix element method for determining the nnmber of hidden nodes of RBF neural networks[J].Computer Engineering and Applications,2004,20:77-79.
[21]CHEN T,WANG X.Thickness prediction of tectonically de-formed coal using calibrated seismic attributes:A case study[C]//ASEG Extended Abstracts 2016:25th International Geophysical Conference and Exhibition.Australian Society of Exploration Geophysicists,2016:817-821.
[1] 李其烨, 邢红杰.
基于最大相关熵的KPCA异常检测方法
KPCA Based Novelty Detection Method Using Maximum Correntropy Criterion
计算机科学, 2022, 49(8): 267-272. https://doi.org/10.11896/jsjkx.210700175
[2] 阙华坤, 冯小峰, 刘盼龙, 郭文翀, 李健, 曾伟良, 范竞敏.
Grassberger熵随机森林在窃电行为检测的应用
Application of Grassberger Entropy Random Forest to Power-stealing Behavior Detection
计算机科学, 2022, 49(6A): 790-794. https://doi.org/10.11896/jsjkx.210800032
[3] 杨浩雄, 高晶, 邵恩露.
考虑一单多品的外卖订单配送时间的带时间窗的车辆路径问题
Vehicle Routing Problem with Time Window of Takeaway Food ConsideringOne-order-multi-product Order Delivery
计算机科学, 2022, 49(6A): 191-198. https://doi.org/10.11896/jsjkx.210400005
[4] 沈彪, 沈立炜, 李弋.
空间众包任务的路径动态调度方法
Dynamic Task Scheduling Method for Space Crowdsourcing
计算机科学, 2022, 49(2): 231-240. https://doi.org/10.11896/jsjkx.210400249
[5] 贾琳, 杨超, 宋玲玲, 程镇, 李琲珺.
改进的否定选择算法及其在入侵检测中的应用
Improved Negative Selection Algorithm and Its Application in Intrusion Detection
计算机科学, 2021, 48(6): 324-331. https://doi.org/10.11896/jsjkx.200400033
[6] 王金恒, 单志龙, 谭汉松, 王煜林.
基于遗传优化PNN神经网络的网络安全态势评估
Network Security Situation Assessment Based on Genetic Optimized PNN Neural Network
计算机科学, 2021, 48(6): 338-342. https://doi.org/10.11896/jsjkx.201200239
[7] 郑增乾, 王锟, 赵涛, 蒋维, 孟利民.
带宽和时延受限的流媒体服务器集群负载均衡机制
Load Balancing Mechanism for Bandwidth and Time-delay Constrained Streaming Media Server Cluster
计算机科学, 2021, 48(6): 261-267. https://doi.org/10.11896/jsjkx.200400131
[8] 胡昕彤, 沙朝锋, 刘艳君.
基于随机投影和主成分分析的网络嵌入后处理算法
Post-processing Network Embedding Algorithm with Random Projection and Principal Component Analysis
计算机科学, 2021, 48(5): 124-129. https://doi.org/10.11896/jsjkx.200500058
[9] 王艺皓, 丁洪伟, 李波, 保利勇, 张颖婕.
基于聚类与特征融合的蛋白质亚细胞定位预测
Prediction of Protein Subcellular Localization Based on Clustering and Feature Fusion
计算机科学, 2021, 48(3): 206-213. https://doi.org/10.11896/jsjkx.200200081
[10] 左剑凯, 吴杰宏, 陈嘉彤, 刘泽源, 李忠智.
异构无人机编队防御及评估策略研究
Study on Heterogeneous UAV Formation Defense and Evaluation Strategy
计算机科学, 2021, 48(2): 55-63. https://doi.org/10.11896/jsjkx.191100053
[11] 高帅, 夏良斌, 盛亮, 杜宏亮, 袁媛, 韩和同.
基于投影圆度和遗传算法的空间圆柱面拟合方法
Spatial Cylinder Fitting Based on Projection Roundness and Genetic Algorithm
计算机科学, 2021, 48(11A): 166-169. https://doi.org/10.11896/jsjkx.201100057
[12] 姚泽玮, 林嘉雯, 胡俊钦, 陈星.
基于PSO-GA的多边缘负载均衡方法
PSO-GA Based Approach to Multi-edge Load Balancing
计算机科学, 2021, 48(11A): 456-463. https://doi.org/10.11896/jsjkx.210100191
[13] 高基旭, 王珺.
一种基于遗传算法的多边缘协同计算卸载方案
Multi-edge Collaborative Computing Unloading Scheme Based on Genetic Algorithm
计算机科学, 2021, 48(1): 72-80. https://doi.org/10.11896/jsjkx.200800088
[14] 吉顺慧, 张鹏程.
基于支配关系的数据流测试用例生成方法
Test Case Generation Approach for Data Flow Based on Dominance Relations
计算机科学, 2020, 47(9): 40-46. https://doi.org/10.11896/jsjkx.200700021
[15] 冯安然, 王旭仁, 汪秋云, 熊梦博.
基于PCA和随机树的数据库异常访问检测
Database Anomaly Access Detection Based on Principal Component Analysis and Random Tree
计算机科学, 2020, 47(9): 94-98. https://doi.org/10.11896/jsjkx.190800056
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!