【摘要】：我國(guó)煤炭產(chǎn)量居世界首位,煤礦安全事故也頻頻發(fā)生,傷亡人數(shù)僅排在因交通事故傷亡之后。隨著開采深度地不斷加深,生產(chǎn)能力地提高,地質(zhì)條件也更加復(fù)雜化,煤礦安全工作面臨著巨大的挑戰(zhàn)。瓦斯事故又是煤礦生產(chǎn)過程中的主要不安全因素,如何能準(zhǔn)確快速地預(yù)測(cè)出瓦斯涌出量,對(duì)于瓦斯防治措施的制定有著積極意義。 本文從開采因素和自然因素兩個(gè)方面分別分析煤層的瓦斯含量、埋深、瓦斯壓力、大氣壓力、風(fēng)量、產(chǎn)能等方面對(duì)瓦斯涌出量的影響,指出傳統(tǒng)預(yù)測(cè)瓦斯涌出量方法的局限性,不能將瓦斯涌出量與各個(gè)影響因素之間復(fù)雜的非線性關(guān)系清楚地表述。RBF神經(jīng)網(wǎng)絡(luò)自身的容錯(cuò)性和自適應(yīng)性以及較強(qiáng)的非線性函數(shù)逼近能力,則能很好地克服這些缺點(diǎn)。 RBF神經(jīng)網(wǎng)絡(luò)具有搜索全局最優(yōu)解和最佳逼近能力,其拓?fù)浣Y(jié)構(gòu)、隱節(jié)點(diǎn)數(shù)目、中心位置、寬度和權(quán)值是決定整個(gè)網(wǎng)絡(luò)性能的關(guān)鍵因素。遺傳算法作為一種全局優(yōu)化算法,具有強(qiáng)魯棒性,適用于解決訓(xùn)練速度慢、易陷入局部極小值等缺點(diǎn)的網(wǎng)絡(luò)結(jié)構(gòu),自適應(yīng)調(diào)整交叉概率和變異概率,能夠避免重復(fù)搜索,并提高搜索效率。本文提出采用遺傳算法優(yōu)化RBF神經(jīng)網(wǎng)絡(luò)中的隱節(jié)點(diǎn)數(shù)目、中心位置、寬度和權(quán)值,有效地彌補(bǔ)RBF神經(jīng)網(wǎng)絡(luò)的不足,最后利用Matlab軟件編程實(shí)現(xiàn)GA-RBF神經(jīng)網(wǎng)絡(luò)模型,應(yīng)用此模型分別對(duì)兩個(gè)采煤工作面進(jìn)行瓦斯涌出量預(yù)測(cè),得到了令人滿意結(jié)果。
[Abstract]:China's coal production ranks first in the world, coal mine safety accidents also occur frequently, the number of casualties only ranks behind traffic accidents. With the deepening of mining depth, the improvement of production capacity and the complication of geological conditions, the work of coal mine safety is facing great challenges. Gas accident is also the main unsafe factor in coal mine production. How to predict gas emission accurately and quickly is of positive significance to the formulation of gas prevention and control measures. This paper analyzes the influence of gas content, buried depth, gas pressure, atmospheric pressure, air volume and productivity on gas emission from two aspects of mining factors and natural factors, respectively, and points out the limitations of traditional methods for predicting gas emission. The complex nonlinear relationship between the amount of gas emission and the influence factors can not be clearly expressed. The fault tolerance and adaptability of RBF neural network and its strong nonlinear function approximation ability can not be clearly expressed. RBF neural network has the ability to search for global optimal solution and best approximation. Its topology, number of hidden nodes, center position, width and weight are the key factors to determine the network performance. As a global optimization algorithm, genetic algorithm (GA) has strong robustness, which is suitable for solving the problems of slow training speed, easy to fall into local minimum and other shortcomings of network structure, adaptively adjusts crossover probability and mutation probability, and can avoid repeated search. And improve the search efficiency. In this paper, genetic algorithm is proposed to optimize the number, center position, width and weight of hidden nodes in RBF neural network, which can effectively compensate for the deficiency of RBF neural network. Finally, the GA-RBF neural network model is realized by using Matlab software programming. The model is used to predict the gas emission in two coal mining faces, and satisfactory results are obtained.
【學(xué)位授予單位】：安徽理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TD712.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉新榮;鮮學(xué)福;;煤層瓦斯涌出量與若干地質(zhì)因素之間的關(guān)系探討[J];礦業(yè)安全與環(huán)保;2006年01期

2 夏軒;許偉明;;改進(jìn)的粒子群算法對(duì)RBF神經(jīng)網(wǎng)絡(luò)的優(yōu)化[J];計(jì)算機(jī)工程與應(yīng)用;2012年05期

3 郁云;杜杰;陸金桂;;基于人工神經(jīng)網(wǎng)絡(luò)的瓦斯涌出量預(yù)測(cè)[J];計(jì)算機(jī)仿真;2006年08期

4 桂祥友;郁鐘銘;孟絮屹;;貴州煤礦瓦斯涌出量灰色預(yù)測(cè)的應(yīng)用[J];采礦與安全工程學(xué)報(bào);2007年04期

5 張少帥;楊勝?gòu)?qiáng);鹿存榮;;基于瓦斯涌出量預(yù)測(cè)的近距離煤層群開采順序優(yōu)化選擇[J];中國(guó)安全生產(chǎn)科學(xué)技術(shù);2011年09期

6 楊勇,王喬文;影響礦井瓦斯涌出量的因素[J];內(nèi)蒙古煤炭經(jīng)濟(jì);2005年04期

7 張興華,李德洋,尚作鐵,安景順;高產(chǎn)高效工作面的瓦斯涌出量預(yù)測(cè)方法及其應(yīng)用[J];煤礦安全;2001年04期

8 陳大力,秦永洋,趙俊峰,張軍,孫曉軍,劉殿信;綜采工作面瓦斯涌出規(guī)律及影響因素分析[J];煤礦安全;2003年12期

9 章立清;秦玉金;姜文忠;井慶賀;趙光明;;我國(guó)礦井瓦斯涌出量預(yù)測(cè)方法研究現(xiàn)狀及展望[J];煤礦安全;2007年08期

10 陳洋;劉恩;陳大力;唐碩;;瓦斯涌出量分源預(yù)測(cè)法的發(fā)展與實(shí)踐研究[J];煤礦安全;2010年02期

，

本文編號(hào)：2185165