摘要
随着煤炭向更深层次开采，煤矿瓦斯灾害事故频繁发生，严重威胁着煤炭行业持续发展和煤矿工人的安全。瓦斯浓度是造成瓦斯灾害的一个重要因素，当瓦斯浓度不断上升到警限值时，遇到明火会产生瓦斯爆炸或引发瓦斯突出事故，造成人员伤亡和经济损失。因此，针对煤矿安全生产的需要，对煤矿采煤工作面瓦斯浓度进行准确预测和对矿井安全状态实时预警是非常重要的研究课题。
对矿井瓦斯浓度的主要影响因素包含CO浓度、风速、温度进行分析。由于各影响因素之间具有复杂的非线性关系，如果采用单传感器进行瓦斯浓度预测，导致预测准确率较低，不能有效反应矿井真实环境状况。因此，通过多传感器融合技术对瓦斯浓度进行预测，提高瓦斯浓度预测的精度，构建多参数瓦斯浓度预测模型。该模型首先通过矿井各传感器对众影响因素进行采集原始数据。然后通过改进的小波阈值去噪方法对采集到瓦斯浓度时间序列进行滤噪。采用等距映射算法对瓦斯浓度影响因素进行维数约简，提取低维特征，然后将提取的低维特征通过LS-SVM进行数据融合。将自适应PSO算法与引入克隆、变异算子的自适应AIS算法进行有效结合，提出了并行双自适应AIS-PSO优化算法，并对LS-SVM的高斯核参数σ和正则化参数γ进行寻优。最后将上隅角瓦斯浓度作为预测模型的输出，进行瓦斯浓度预测，并与PSO-LSSVM、LS-SVM方法进行仿真对比试验。结果表明，本文提出的瓦斯浓度预测模型与另外两种方法相比，具有较高的精度。
由于瓦斯浓度预测模型，只是对瓦斯浓度未来趋势进行评估，没有对矿井的安全状况进行判断。为了对矿井安全状态进行实时评价，建立了基于CS算法优化SVM的矿井瓦斯预警模型。根据矿井瓦斯浓度、CO浓度和风速等信息的预警范围，将煤矿安全状况分为安全、较安全、报警、危险，4个预警等级。将矿井各传感器的测量值作为SVM分类器输入，4个预警等级作为输出，并与PSO-SVM、SVM及BP方法进行对比试验，结果表明，CS-SVM相较于另外3种方法对预警等级分类准确率更高。
该论文有图40幅，表8个，参考文献71篇。
关键词：预测；瓦斯浓度；人工免疫算法；支持向量机；小波变换
胶原蛋白多的食物Abstract
With coal mining going deeper, coal mine gas disasters occur frequently, which riously threatens the sustainable development of coal industry and the safety of coal miners. Gas concentration is an important factor causing gas disasters. When gas concentration continues to ri to the alarm limit, open fire will cau gas explosion or gas outburst, resulting in casualties and economic loss. Therefore, in view of the need of coal mine safety production, accurate prediction of gas concentration in coal mining face and real-time warning of mine safety state are very important rearch topics..
吃什么奶水会增多
The main influencing factors of mine gas concentration include CO concentration, wind speed and temperature. Becau of the complex non-linear relationship among the influencing factors, if the single nsor is ud to predict the gas concentration, the prediction accuracy is low, and it can not effectively reflect the real mine environment. Therefore, multi-nsor fusion technology is ud to predict gas concentration, improve the accuracy of gas concentration prediction, and build a multi-parameter gas concentration prediction model. Firstly, the model collects the original data of the influencing factors through various nsors in the mine. Then, the improved wavelet threshold denoising method is ud to denoi the collected time ries of gas concentration. The dimension of influencing factors of gas concentration is reduced by equidistant mapping algorithm, and the low-dimensional features are extracted. Then the extracted low-dimensional features are fud by LS-SVM. A parallel dual adaptive AIS-PSO optimization algorithm is propod by combining the adaptive PSO algorithm with the adaptive AIS algorithm with cloning and mutation operators. The Gauss kernel parameter γand regularization parameter σof LS-SVM are optimized. Finally, the gas concentration in the upper corner is ud as the output of the prediction model to predict the gas concentration, and the simulation experiments are carried out with PSO-LSSVM and LS-SVM methods. The results show that the propod gas concentration prediction model has higher accuracy than the other two methods..
华硕笔记本进入bios按哪个键Becau the prediction model of gas concentration only evaluates the future trend of gas concentration, and does not judge the safety condition of mine. In order to evaluate the mine safety status in real time, a mine gas early warning model bad on CS algorithm optimization SVM was established. According to the early warning range of gas concentration, CO concentration and wind speed, the coal mine safety situation is divided into four warning levels: safety, safety, alarm and danger. The measured values of each nsor in mine are ud as input of
SVM classifier and four warning levels are ud as output. Compared with PSO-SVM, SVM and BP methods, the results show that CS-SVM has higher classification accuracy than the other three methods.
Keywords:forecast; gas concentration; artificial immune system; support vector machine;
wavelet transform
目录
摘要...................................................................... I 目录..................................................................... IV 图清单................................................................. VIII 表清单..............................................................
我爱什么..... XI 变量注释表.............................................................. XII 1 绪论.. (1)
1.1 研究背景及意义 (1)
1.2 瓦斯浓度研究现状 (2)
1.3 数据融合研究现状 (3)
1.4 研究内容与技术路线 (3)
南瓜咸蛋2 矿井瓦斯灾害影响因素分析与数据融合技术 (6)
2.1 矿井瓦斯灾害影响因素分析 (6)
2.2 瓦斯数据的预处理 (6)
2.3 数据融合技术 (8)
2.4 本章小结 (9)
3 矿井瓦斯数据降噪算法与降维算法研究 (10)
3.1 煤矿井下噪声来源分析 (10)
3.2 小波变换理论 (11)
3.3 改进的小波阈值去噪方法 (13)
3.4 等距映射降维算法研究 (18)
3.5 本章小结 (19)
4 建立瓦斯浓度预测和预警模型 (21)
4.1 支持向量机（SVM）理论 (21)
4.2 建立并行双自适应AIS-PAO优化算法 (26)
4.3 基于并行双自适应PSO-AIS的瓦斯浓度预测模型 (32)
古风男网名
4.4 基于CS-SVM的瓦斯预警模型 (34)
4.5 本章小结 (37)
思念的情诗
5 仿真试验及分析 (38)
5.1 瓦斯浓度预测模型仿真试验及分析 (38)
5.2 瓦斯预警模型仿真试验与分析 (44)
5.3 煤矿瓦斯监控系统设计 (46)
5.4 本章小结 (50)
沙坡头旅游景区6 结论与展望 (51)
6.1 结论 (51)
6.2 展望 (51)
参考文献 (52)
作者简历 (56)
学位论文原创性声明 (57)
学位论文数据集 (58)
