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.     

Relationships between gas reservoir and the evolution of stope surrounding rock fracture at the process of mining the closed distance protection layer

Overburden rock movements and fracture developments occur during mining activities. Consequently, relief gas reservoirs and migration in coal seams being mined as well as in near distant coal seams appear. We considered a gas disaster management project and rules on stope relief of gas flows together and explored a gas reservoir and the evolution of stope surrounding rock fractures in the process of mining near distant protective layers by physical simulation, numerical simulation and field testing. Different techniques provide evidence of the rules of interaction of gas reservoirs and the evolution of surrounding rock fractures and are able to find accurately the gas-rich regions around the stope. Finally, we found that these rules can provide a basis for taking measures to prevent gas accidents in the protective layer of the coalface as well as for demonstrating and designing programs to drain high concentrations of gas from the gob.     

简易放顶煤工作面瓦斯综合治理技术

不稳定煤层采用单体液压支柱放顶煤开采技术,无疑是一种高效采煤方法。由于工作面采高大、单产高,且底层落煤与顶层放煤同时进行或工序间隔时间短,相应的采煤工作面瓦斯涌出量明显增大,采空区上部和工作面上方顶煤裂隙中易形成瓦斯积聚,从而严重威胁工作面的安全生产。本文通过分析简易放顶煤采煤工作面各生产工艺中瓦斯涌出规律,提出并实施有效的针对性综合瓦斯治理技术措施,实现了工作面的安全生产。     

新型燃煤烟气汞吸附剂的评价研究

利用汞蒸气发生器产生的单质汞,与压缩空气组成模拟烟气,在吸附剂评价实验台上进行吸附剂脱汞实验,研究不同吸附剂对单质汞的脱除效率．实验结果表明,活性炭对汞的吸附效率在60％左右,未改性的燃煤飞灰吸附效率在10％～20％,改性后的燃煤飞灰比表面积有很大程度的提高,吸附效率可以达到25％,与活性炭吸附效率相比仍有不小的差距．     

凝析气藏注气过程中露点压力变化特征研究

在凝析气藏循环注气和注气吞吐解除近井带反凝析堵塞的注气过程中,凝析气流体的露点压力变化较大,而在目前的凝析气藏开发过程中,对凝析气露点压力变化考虑较少.作者利用Nemeth.L.K和Kennedy.H.T.的露点压力计算经验公式,研究了向凝析气中注入N2、甲烷、CO2和丙烷等介质的过程中露点压力变化规律,并分析了衰竭式开发和注气过程中凝析气井近井带露点压力变化特征.结果表明,注甲烷使露点压力有较小幅度的减小;注入CO2和丙烷均可使凝析气露点压力有较大幅度降低;而注入N2将使露点压力升高.在凝析气藏衰竭式开发过程中,当近井带压力下降至露点压力以下时,距井筒越近,凝析气中重质组分含量越低,露点压力也越低.在注气吞吐的焖井阶段,反蒸发作用会引起凝析气中重质组分增加,露点压力将升高.     

旋流板塔煤浆法烟气脱硫研究

煤浆法烟气脱硫是以煤浆洗涤含二氧化硫的烟气,二氧化硫溶于浆液形成亚硫酸,煤中黄铁矿与亚硫酸、氧气发生反应,亚硫酸被氧化为硫酸,从而实现烟气脱硫.反应过程中,煤中的黄铁矿硫也被转化为硫酸而浸出,反应产生的Fe3＋/Fe2＋又对脱硫反应起到了催化剂的作用.以旋流板塔为吸收设备,研究了煤浆法烟气脱硫过程中浆液温度、液气比、空塔气速及浆液固液比等操作参数对脱硫率的影响规律.试验表明,在其他条件不变的情况下,适当提高液气比、空塔气速及浆液固液比均有利于提高脱硫效果.随着烟气脱硫过程的进行,脱硫浆液中的总铁含量不断增加,说明煤中黄铁矿被不断浸出,故此法在脱除烟气中的二氧化硫的同时也降低了煤中黄铁矿硫含量.     

太阳能集热器及其适用性浅析

对目前常用的平板型、全玻璃真空管及热管式真空管等太阳能集热器的优缺点进行了介绍,并对各种太阳能集热器进行了综合评价,对其在太阳能热水供应、太阳能采暖和太阳能空调系统中的适用性进行了分析,为太阳能集热器的选择提供了参考.     

自来水管网的可靠性分析与优化设计

以某科技园区自来水管网为例,分析研究了城市供水管网的可靠性和优化设计,提出了供水管网可靠性优化设计的数学模型．在确保供水管网系统可靠性的基础上建立优化模型,寻求最经济管径,从而建立最经济、最可靠的供水管网系统．对现有供水管网系统进行了优化,给出了优化设计方案．     

LDPE／SiO2复合膜性能的研究

以LDPE／EVA（质量比为90／10）为基材,添加SiO2制备了LDPE／SiO2复合膜,对该复合膜进行了力学性能,透气、透湿性能和结晶性能的测试．结果表明：添加SiO2后,LDPE／SiO2复合体系的力学性能有所下降;O2和CO2气体透过系数先增加后下降;水蒸气透过系数先增加后趋缓;LDPE复合体系的成核速率和结晶速率增加,结晶温度略有提高．形成的球晶尺寸变小,数量增多．     

管道内穿管修复技术的应用

为解决城市地下金属管道由于常年连续运行时间长、防腐技术落后情况下产生漏铁、穿孔腐蚀等问题,阐述了利用管内穿管的先进技术解决地下管道的修复问题.该技术经应用后,施工质量满足使用要求,具有推广价值.