| 基于HHT方法的矿井瓦斯体积分数预测 |
| |
| 引用本文： | 董丁稳,李树刚,常心坦,林海飞. 基于HHT方法的矿井瓦斯体积分数预测[J]. 中国安全科学学报, 2011, 21(9) |
| |
| 作者姓名： | 董丁稳 李树刚 常心坦 林海飞 |
| |
| 作者单位： | 西安科技大学能源学院,陕西西安,710054 |
| |
| 基金项目： | 国家自然科学基金资助，高等学校博士学科点专项科研基金资助 |
| |
| 摘 要： | 为有效分析煤矿瓦斯监测数据以实现较准确的瓦斯浓度预测,研究应用希尔伯特-黄变换(HHT)方法进行瓦斯浓度时间序列分析与预测的方法。应用经验模态分解(EMD)方法将瓦斯浓度时间序列分解成不同频率的固有模态函数(IMF)分量的叠加,以获取瓦斯浓度时间序列的瞬时特征;通过Hilbert变换求得各IMF分量的瞬时频率,依据各IMF分量瞬时频率的均值将分解得到的IMF划分成较高频和低频2类新的分量,选取适合于各分量特征的预测模型分别进行预测,以消除局部随机性对预测精度的影响,结合自回归(AR)、径向基函数(RBF)神经网络和支持向量机(SVM)3种预测模型实现瓦斯浓度预测。实例分析表明:应用该方法所得预测结果比较准确,降低了预测复杂度,提高了预测精度。
|
| 关 键 词： | 经验模态分解(EMD) Hilbert变换 时间序列 预测 瓦斯体积分数 |
Mine Gas Concentration Prediction Based on HHT Method |
| |
| DONG Ding-wen,LI Shu-gang,CHANG Xin-tan,LIN Hai-fei. Mine Gas Concentration Prediction Based on HHT Method[J]. China Safety Science Journal, 2011, 21(9) |
| |
| Authors: | DONG Ding-wen LI Shu-gang CHANG Xin-tan LIN Hai-fei |
| |
| Affiliation: | DONG Ding-wen LI Shu-gang CHANG Xin-tan LIN Hai-fei(School of Energy Engineering,Xi'an University of Science & Technology,Xi'an Shaanxi 710054,China) |
| |
| Abstract: | For the purpose of achieving more accurate gas prediction result through effective analysis of gas measuring data in mines,a method for gas concentration time series analysis and prediction was studied based on HHT(Hilbert-Huang Transform) method.EMD method was applied to dividing gas concentration time series into IMF(Intrinsic Mode Function) component with different frequency so as to abstract the instantaneous characteristics of gas concentration time series;the instantaneous frequency of each IMF was so... |
| |
| Keywords: | empirical mode decomposition(EMD) Hilbert transform time series prediction gas concentration |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
