概率积分法预计参数选取的神经网络模型

在综合分析概率积分法参数与地质采矿条件之间关系的基础上,采用人工神经网络方法建立了概率积分法参数选取的模型．模型采用改进的BP优化算法,运用我国典型的地表移动观测站资料作为学习训练样本和测试样本。对网络模型的计算结果与实测值进行了对比分析．分析结果表明：用人工神经网络方法求算概率积分法参数结果更接近于实际．对提高开采沉陷预计精度具有积极意义．     

Superposition model for analyzing the dynamic ground subsidence in mining area of thick loose layer

The dynamic ground subsidence due to underground mining is a complicated time-dependent and ratedependent process. Based on the theory of rock rheology and probability integral method, this study developed the superposition model for the prediction and analysis of the ground dynamic subsidence in mining area of thick loose layer. The model consists of two parts(the prediction of overlying bedrock and the prediction of thick loose layer). The overlying bedrock is regarded as visco-elastic beam, of which the dynamic subsidence is predicted by the Kelvin visco-elastic rheological model. The thick loose layer is regarded as random medium and the ground dynamic subsidence is predicted by the probability integral model. At last, the two prediction models are vertically stacked in the same coordinate system, and the bedrock dynamic subsidence is regarded as a variable mining thickness input into the prediction model of ground dynamic subsidence. The prediction results obtained were compared with actual movement and deformation data from Zhao I and Zhao II mine, central China. The agreement of the prediction results with the field measurements show that the superposition model(SM) is more satisfactory and the formulae obtained are more effective than the classical single probability integral model(SPIM), and thus can be effectively used for predicting the ground dynamic subsidence in mining area of thick loose layer.     

开采沉陷动态参数预计的三次指数平滑法

在我国,概率积分法是应用最多的一种开采沉陷预计方法．该方法中的预计参数在不同采动程度下是变化的．能否准确获知动态参数的变化规律将决定着开采沉陷的预计精度．为较好地解决这一问题,引入了一种动态参数预计的新方法,即三次指数平滑法．应用此方法对实测资料进行了预计和比较,结果表明,各预计参数的平均相对误差都小于4％．由此可见,该方法对开采沉陷的预测具有一定的应用价值．     

Mine water discharge prediction based on least squares support vector machines

In order to realize the prediction of a chaotic time series of mine water discharge,an approach incorporating phase space reconstruction theory and statistical learning theory was studied.A differential entropy ratio method was used to determine embedding parameters to reconstruct the phase space.We used a multi-layer adaptive best-fitting parameter search algorithm to estimate the LS-SVM optimal parameters which were adopted to construct a LS-SVM prediction model for the mine water chaotic time series.The results show that the simulation performance of a single-step prediction based on this LS-SVM model is markedly superior to that based on a RBF model.The multi-step prediction results based on LS-SVM model can reflect the development of mine water discharge and can be used for short-term forecasting of mine water discharge.     

开采沉陷动态参数预计的三次指数平滑法

在我国,概率积分法是应用最多的一种开采沉陷预计方法.该方法中的预计参数在不同采动程度下是变化的.能否准确获知动态参数的变化规律将决定着开采沉陷的预计精度.为较好地解决这一问题,引入了一种动态参数预计的新方法,即三次指数平滑法.应用此方法对实测资料进行了预计和比较,结果表明,各预计参数的平均相对误差都小于4%.由此可见,该方法对开采沉陷的预测具有一定的应用价值.     

时序分析在开采沉陷动态参数预计中的应用

应用时间序列分析法,对开采沉陷动态过程的概率积分法预计参数进行分析,建立动态预计模型。用该模型可对参数的未来值进行预计,然后利用预计结果进一步预计地表的移动变形,解决了开采沉陷的动态预计问题。应用此法,地表下沉的相对预计误差一般为４％左右,与传统方法相比,预计精度可提高５％～１５％。     

Evaluation of the use of sublevel open stoping in the mining of moderately dipping medium-thick orebodies

The flow of blasted ore during mining of moderately dipping medium-thick orebodies is a challenge. Selecting a suitable mining system for such ore bodies is difficult. This paper proposes a diamond layout sublevel open stoping system using fan blastholes with backfilling to mine such orebodies. To evaluate the performance of system the relationships between ore recovery and stope footwall dip angle, footwall surface roughness, drawpoint spacing and production blast ring burden were investigated. An ore recovery data set from 81 laboratory physical model experiments was established from combinations of the listed factors. Various modules in a back propagation neural network structure were compared, and an optimal network structure identified. An ore recovery backpropagation neural network (BPNN) forecast model was developed. Using the model and sensitivity analysis of the factors affecting the proposed open stope mining system, the significance of each factor on ore recovery was studied. The study results were applied to a case study at the Shandong Gold Group Jiaojia Gold Mine. The results showed that the application of a BPNN and sensitivity analysis models for ore recovery prediction in the proposed mining system and field experimental results confirm that the suggested mining method is feasible.     

等维新息模型在矿井井架基础沉降中的应用

为了对矿井井架基础进行沉降预测,介绍了灰色预测理论模型的建模方法与模型精度评定方法,阐述了采用等维新息模型进行沉降数据分析的特点;并以某煤矿矿井井架基础沉降监测为实例,利用等维新息模型对其沉降趋势进行预测,分析了等维新息模型的合理雏数,取得了较好的预测结果,并得到了具有实用价值的预测模型。     

人工神经网络在煤矿开采沉陷预计中的应用研究

提出了利用人工神经网络技术进行开采沉陷定量预测的新方法 .研究了影响因素的选取、开采沉陷预计模型的建立以及模型的应用等问题 .采用 BP神经网络算法对开采沉陷量进行了建模和预测 .结果表明 ,用神经网络模型对复杂的开采沉陷系统进行模拟预测 ,具有理论上的可行性和现实意义 ,说明人工神经网络技术在开采沉陷预计领域中具有实用价值     

最小二乘向量机在自动测试设备计量参数稳定性评估中的应用

针对自动测试设备(ATE)计量参数的非线性时变,提出一种基于最小二乘支持向量机(LS-SVM)的计量参数稳定性评估方法。该方法将ATE的参数变化量建模为非线性时间序列。用径向基函数作为LS-SVM的核函数,建立计量参数非线性时变的预测模型。根据预测模型的计算结果,采用模糊层次分析法对计量参数的稳定性进行评估。仿真结果表明,该方法能够对ATE计量参数的非线性时变进行预测,从而实现ATE计量参数稳定性的评估。     

基于遗传规划的采空区地面沉陷预测分析

针对地下开采引起的岩层移动与变形,提出一种基于遗传规划的采空区地面沉陷预测新方法.基于MTLAB工具编制的遗传规划程序,选取影响地面沉陷的主要因素,搜集学习样本对程序进行了训练,建立了采空区地面沉陷预测的遗传规划模型.最后,利用有关实测数据,对模型进行了实例检验.结果表明,预测误差在工程允许范围之内,应用遗传规划方法进...     

基于最小二乘支持向量机的时变信道建模

基于2.55 GHz市区微蜂窝多输入多输出信道实测数据,将机器学习中的最小二乘支持向量机（LS-SVM）算法应用于时变信道参数的建模中,建立了基于遗传算法（GA）优化的LS-SVM信道参数预测模型,对信道参数如时延扩展、接收端的水平角度扩展和垂直角度扩展的数据特征进行了学习,并实现了准确预测;同时通过与反向传播神经网络模型以及传统的LS-SVM模型进行比较,验证了算法的有效性.基于GA优化的LS-SVM模型能够在有限数据量下对信道参数的变化有着良好的适应性,可实现非线性时变信道参数的准确预测.     

应用最小二乘支持向量机预测煤的发热量

为解决现有的煤发热量预测神经网络法的过学习与局部极小点问题,通过对煤热量数据的分析,在统计学习理论和结构风险最小化准则的基础上,建立了基于最小二乘支持向量机(LS-SVM)的煤发热量预测数学模型。在算例分析中与BP神经网络、RBF神经网络预测法进行对比,发现该方法比BP和RBF神经网络具有更高的预测精度,且具有收敛速度快、泛化能力强等优点,为燃煤发热量的预测提供了一种有效的方法。     

An influence function method based subsidence prediction program for longwall mining operations in inclined coal seams

The distribution of the final surface subsidence basin induced by longwall operations in inclined coal seam could be significantly different from that in flat coal seam and demands special prediction methods. Though many empirical prediction methods have been developed, these methods are inflexible for varying geological and mining conditions. An influence function method has been developed to take the advantage of its fundamentally sound nature and flexibility. In developing this method, significant modifications have been made to the original Knothe function to produce an asymmetrical influence function. The empirical equations for final subsidence parameters derived from US subsidence data and Chinese empirical values have been incorporated into the mathematical models to improve the prediction accuracy. A corresponding computer program is developed. A number of subsidence cases for longwall mining operations in coal seams with varying inclination angles have been used to demonstrate the applicability of the developed subsidence prediction model.     

基于最小二乘支持向量机的锅炉对流受热面清洁吸热量预测

针对神经网络拓扑结构复杂、易出现过度训练、仅获局部最优解的问题,为提高锅炉对流受热面清洁时潜在吸热量预测的准确度,更好地进行受热面污染监测,提出了一种新的基于最小二乘支持向量机的对流受热面清洁时潜在吸热量预测方法。依据最小二乘支持向量机预测原理,建立对流受热面清洁时潜在吸热量最小二乘支持向量机预测模型,同时建立神经网络预测模型进行对比研究,实例研究结果表明,最小二乘支持向量机较神经网络具有更高的拟合度,预测各性能都高于神经网络,其在对流受热面清洁时潜在吸热量预测方面明显优于神经网络,将成为对流受热面清洁时潜在吸热量预测也即受热面污染监测方面更为有利的工具。     

水平煤层半无限开采时沉陷参数误差对下沉预计结果精度的影响

本文依据误差理论，系统地分析了水平煤层半无限开采时概率积分法、威布尔分布法和样条概率积分法的参数误差对下沉预计结果精度的影响，弄清了预计结果精度的分布规律，评述了它们的优缺点，并指出了改进措施。本文的研究结果对开采沉陷观测站设计、开采沉陷参数及计算模型的识别具有指导意义。     

基于最小二乘支持向量机的军用软件开发成本测算研究

利用最小二乘支持向量机（least squares support vector ma-chines,LS-SVM）适用于小样本预测的优势,将该方法运用到军用软件开发成本测算领域,建立了基于LS-SVM的军用软件开发成本测算模型并进行了实例分析。结果表明：在同样的样本数据条件下,该模型有效提高了测算精度,为军用软件早期开发的成本测算提供了新的有效方法。     

A new approach to predicting mining induced surface subsidence

1 INTRODUCTIONMining induced surface subsidence often re-sults in various kinds of damages to the structuresandinfrastructures in the subsidence area[1 4]. Thepipes will be broken and fractured,the buildingswill be caused to tilt or collapse and the roadfoun-dation and acequia will be damaged because of thesubsidence . Especially in the case of open stopemining under hard rock formation,this subsidencewill suddenly occurr . For example , at about 11p.m.on December 27 ,1999 ,large scale of…     

基于改进粒子群优化LS-SVM的变压器故障气体预测

最小二乘支持向量机(LS-SVM)能较好的解决小样本、非线性数据特征的多分类问题,适用于电力变压器油色谱故障气体预测,但参数c与σ2的选取对预测结果影响较大,有必要对其进行优化选择.提出一种基于改进粒子群(MPSO)的参数寻优方法,并将其应用到变压器油中故障气体预测.改进粒子群算法在每次迭代中,将粒子群进行分类,不同类...     

On-line least squares support vector machine algorithm in gas prediction

Traditional coal mine safety prediction methods are off-line and do not have dynamic prediction functions. The Support Vector Machine (SVM) is a new machine learning algorithm that has excellent properties. The least squares support vector machine (LS-SVM) algorithm is an improved algorithm of SVM. But the common LS-SVM algorithm, used directly in safety predictions, has some problems. We have first studied gas prediction problems and the basic theory of LS-SVM. Given these problems, we have investigated the affect of the time factor about safety prediction and present an on-line prediction algorithm, based on LS-SVM. Finally, given our observed data, we used the on-line algorithm to predict gas emissions and used other related algorithm to com- pare its performance. The simulation results have verified the validity of the new algorithm.