煤与瓦斯突出IGSA-SVM预测模型及其应用

发布时间：2018-06-09 13:01

本文选题：IGSA-SVM模型 + 煤与瓦斯突出　；参考：《太原理工大学》2016年硕士论文

【摘要】：随着煤矿开采深度的增加和开采强度的增大,煤矿瓦斯问题也越来越严重,解决矿井瓦斯灾害刻不容缓。煤与瓦斯突出是煤矿最为严重的灾害之一,严重威胁着井下作业人员的生命安全,因此,对突出事故的精准预测与防治是一项非常重要的工作。本文对目前国内外主要瓦斯突出预测方法进行了梳理,在翻阅大量文献和事故报告的基础上,将煤与瓦斯突出影响因素分为6个一级因素和12个二级因素,进一步探讨了煤与瓦斯突出过程中各影响因素所起的作用,为煤与瓦斯突出的预测工作提供了一定的理论基础。在万有引力算法(GSA)、支持向量机(SVM)和差分进化算法(DE)的相关理论的基础上,进一步改善了GSA算法前期全局搜寻能力和后期局部搜寻能力较弱的不足,将DE算法的群体搜寻与协同搜寻能力的变异思维引入了万有引力算法,提出改进的万有引力算法(IGSA),并与支持向量机相结合,建立了IGSA-SVM煤与瓦斯突出预测模型。利用所建立的预测模型,以多个煤矿具有代表性的实测数据为研究对象,对用传统单一指标预测法判定具有突出危险性的区域进行了重新预测,并与SVM模型和GSA-SVM模型预测结果相比较,结果表明:IGSA-SVM煤与瓦斯突出预测模型比SVM模型和GSA-SVM模型具有更高的预测准确率和更广的适用性等优点。选取屯兰煤矿掘进工作面和沙曲煤矿回采工作面的煤与瓦斯突出实测数据作为研究对象,根据煤矿地质条件和突出影响因素的分析,最终确定屯兰煤矿掘进工作面筛选出煤的坚固性系数(f)、钻孔瓦斯涌出初速度(q0)、瓦斯放散初速度(p)、钻屑瓦斯解吸指标(K1)和最大钻屑量(S)5个突出预测指标,而沙曲煤矿回采工作面筛选出最大钻屑量(S)、煤的坚固性系数(f)、钻屑瓦斯解吸指标(K1)、钻孔瓦斯涌出初速度(q0)4个突出预测指标,并将其作为预测模型的输入数据。通过预测模型数值模拟,输出结果与实际结果测量结果相符,说明运用该方法来预测煤与瓦斯突出是可行的。本文建立的IGSA-SVM突出预测模型与传统的预测方法相比,不仅可以实现煤与瓦斯突出的高精度预测,而且为保障煤矿的安全生产奠定了坚实的基础。
[Abstract]:With the increase of mining depth and mining intensity, the problem of coal mine gas is becoming more and more serious, so it is urgent to solve mine gas disaster. Coal and gas outburst is one of the most serious disasters in coal mines, which seriously threatens the safety of underground operators. Therefore, accurate prediction and prevention of outburst accidents is a very important task. In this paper, the main gas outburst prediction methods at home and abroad are combed out. On the basis of reading a large number of literatures and accident reports, the influencing factors of coal and gas outburst are divided into 6 primary factors and 12 secondary factors. The influence factors of coal and gas outburst are discussed, which provides a theoretical basis for the prediction of coal and gas outburst. Based on the related theories of GSA (support Vector Machine (SVM) and differential Evolution algorithm (DEE), the global search ability and local search ability of GSA algorithm are further improved. The mutation thinking of the ability of group search and cooperative search of DE algorithm is introduced into the gravitation algorithm. An improved universal gravity algorithm (IGSAA) is proposed, and a prediction model of IGSA-SVM coal and gas outburst is established by combining with support vector machine (SVM). Based on the established prediction model and taking the representative measured data of many coal mines as the research object, the traditional single index prediction method is used to predict the area with outstanding danger. Compared with the prediction results of SVM and GSA-SVM model, the results show that the prediction model of coal and gas outburst with the ratio of IGSA-SVM has higher prediction accuracy and wider applicability than the SVM model and GSA-SVM model. Taking the measured data of coal and gas outburst in tunneling face and Shaqu coal face of Tunlan coal mine as the research object, according to the analysis of geological conditions and the influence factors of outburst, Finally, five outburst prediction indexes, such as the coefficient of solidity of coal selected from tunneling face of Tunlan coal mine, the initial velocity of gas emission from borehole and Q _ 0, the initial velocity of gas release, the desorption index of gas from drilling cuttings and the maximum amount of cuttings, are determined. In Shaqu coal mining face, four outburst prediction indexes are screened out, such as the maximum amount of cuttings, the coefficient of solidity of coal, the desorption index of gas from drilling cuttings, the initial velocity of gas emission from borehole, Q0), and it is used as the input data of the prediction model. Through the numerical simulation of the prediction model, the output results are in agreement with the actual results, which shows that it is feasible to use this method to predict coal and gas outburst. The IGSA-SVM outburst prediction model established in this paper can not only realize the high precision prediction of coal and gas outburst, but also lay a solid foundation for ensuring the safety of coal mine production.
【学位授予单位】：太原理工大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TD713

【相似文献】