本文選題：安全工程 + 支持向量機(jī)��； 參考：《遼寧工程技術(shù)大學(xué)》2015年碩士論文

【摘要】：為了對(duì)煤層瓦斯涌出量進(jìn)行預(yù)測(cè),提出將支持向量機(jī)(SVM)與遺傳算法(GA)相耦合。利用GA尋找SVM最優(yōu)的懲罰參數(shù)c和核函數(shù)參數(shù)g,并結(jié)合SVM具有訓(xùn)練速度快且具有良好泛華性能的特點(diǎn),建立基于GA-SVM的煤層瓦斯涌出量預(yù)測(cè)模型。煤層深度、煤層厚度、煤層傾角、開(kāi)采層原始瓦斯含量、煤層間距、采高、臨近層瓦斯含量、臨近層厚度、層間巖性、工作面長(zhǎng)度、推進(jìn)速度、采出率、日產(chǎn)量對(duì)瓦斯涌出量的影響是復(fù)雜的、非線性的,因而將其作為預(yù)測(cè)的影響參數(shù)。將瓦斯涌出量作為目標(biāo)參數(shù)。分別用影響參數(shù)和目標(biāo)參數(shù)作為GA-SVM的輸入值和輸出值進(jìn)行訓(xùn)練,訓(xùn)練后的預(yù)測(cè)輸出和期望輸出之間的誤差絕對(duì)值倒數(shù)作為GA的適應(yīng)度函數(shù)值進(jìn)行參數(shù)優(yōu)化。研究結(jié)果表明：該預(yù)測(cè)模型預(yù)測(cè)的最大相對(duì)誤差為5.91%,最小相對(duì)誤差為0.92%,平均相對(duì)誤差為2.2%,相比耦合前及其他預(yù)測(cè)模型有更強(qiáng)的泛化能力和更高的預(yù)測(cè)精度,并在鐵法集團(tuán)大平煤礦進(jìn)行了實(shí)際應(yīng)用,得出預(yù)測(cè)的最大相對(duì)誤差為6.80%,最小相對(duì)誤差為0.47%,平均相對(duì)誤差為2.89%。證明了該模型具有實(shí)際的應(yīng)用價(jià)值。
[Abstract]:In order to predict coal seam gas emission, the support vector machine (SVM) coupled with genetic algorithm (GA) is proposed. The GA is used to find the optimal penalty parameter c and kernel function parameter g of SVM, and combining the characteristics of SVM with fast training speed and good flooding performance, a prediction model of coal seam gas emission based on GA-SVM is established. Coal seam depth, coal seam thickness, seam dip angle, original gas content in mining layer, coal seam spacing, mining height, adjacent gas content, adjacent layer thickness, interlayer lithology, working face length, advance speed, extraction rate, The influence of daily production on gas emission is complex and nonlinear, so it is regarded as the influence parameter of prediction. The quantity of gas emission is taken as the target parameter. The influence parameters and target parameters are used as the input and output values of GA-SVM, and the inverse of the absolute error between the predicted and expected outputs is optimized as the fitness function of GA. The results show that the maximum relative error is 5.91, the minimum relative error is 0.92 and the average relative error is 2.2. The prediction model has a stronger generalization ability and higher prediction accuracy than before coupling and other prediction models. The results show that the maximum relative error of prediction is 6.80, the minimum relative error is 0.47 and the average relative error is 2.89. It is proved that the model has practical application value.
【學(xué)位授予單位】：遼寧工程技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：TD712.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 付濤;王大鎮(zhèn);弓清忠;祁麗;;基于混合粒子群算法的柴油機(jī)噴油器可靠性分布的參數(shù)估計(jì)[J];機(jī)械強(qiáng)度;2014年04期

2 周航;王瑛;;基于SHEL模型和神經(jīng)網(wǎng)絡(luò)的空中交通管制風(fēng)險(xiǎn)預(yù)警研究[J];安全與環(huán)境學(xué)報(bào);2014年03期

3 劉希亮;趙學(xué)勝;陸鋒;孫文彬;;基于GA-SVM的露天礦拋擲爆破拋擲率預(yù)測(cè)[J];煤炭學(xué)報(bào);2012年12期

4 董曉雷;賈進(jìn)章;樊程程;赫祥林;;粗糙集-改進(jìn)神經(jīng)網(wǎng)絡(luò)落煤瓦斯涌出量預(yù)測(cè)[J];遼寧工程技術(shù)大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年05期

5 劉敦文;崔朋波;;基于BP神經(jīng)網(wǎng)絡(luò)的新澆筑混凝土爆破安全震動(dòng)速度預(yù)測(cè)[J];安全與環(huán)境學(xué)報(bào);2014年01期

6 魏春榮;李艷霞;孫建華;米紅偉;李s，

本文編號(hào)：2018366