基于AGA-DBSCAN优化的RBF神经网络构造煤厚度预测方法  

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

作　　者：吴善杰 王新[1] WU Shan-jie;WANG Xin(School of Computer Science and Technology,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China)

机构地区：[1]中国矿业大学计算机科学与技术学院,江苏徐州221116

出　　处：《计算机科学》2021年第7期308-315,共8页Computer Science

基　　金：国家自然科学基金(41704115,41774128);江苏省自然科学基金(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。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 3 D 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.

关 键 词：主成分分析 遗传算法 密度聚类 中心向量 RBF神经网络 构造煤 厚度预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]