| 矿井瓦斯浓度Lagrange-ARIMA实时预测模型研究 |
| |
| 引用本文： | 王鹏,伍永平,王栓林,宋超,吴学明. 矿井瓦斯浓度Lagrange-ARIMA实时预测模型研究[J]. 煤炭科学技术, 2019, 0(4): 141-146 |
| |
| 作者姓名： | 王鹏 伍永平 王栓林 宋超 吴学明 |
| |
| 作者单位： | 西安科技大学安全科学与工程学院;煤炭绿色安全高效开采国家地方联合工程研究中心;陕西煤业化工技术研究院有限责任公司现代煤炭开采技术研究所;西安科技大学能源学院;西安科技大学西部矿井开采及灾害防治教育部重点实验室;煤炭科学技术研究院有限公司安全分院;煤炭资源高效开采与洁净利用国家重点实验室 |
| |
| 基金项目： | 国家重点研究发展计划资助项目(2018YFC0808001-003);国家自然科学基金资助项目(51504137) |
| |
| 摘 要： | 矿井瓦斯浓度监测是瓦斯事故最直接有效的防控手段之一,为提高监测信息的利用效率,提出了一种瓦斯浓度Lagrange-ARIMA实时预测模型。首先应用拉伊达准则实现瓦斯浓度监测缺失值构建,其次采用滑动Lagrange插值方法进行缺失值预测,最后基于自回归差分移动平均模型(ARIMA)序贯学习,依据L1范数最小化原则,确定出Lagrange-ARIMA序贯学习窗口合适尺度,进行瓦斯浓度实时预测。实例仿真显示:Lagrange-ARIMA实时预测模型处理瓦斯浓度时间序列缺失值平均误差为1.397%,当序贯学习窗口尺度为85时,预测的瓦斯浓度序列平均绝对误差(MAE)为0.011 8。相比传统ARIMA静态学习模型,建立的Lagrange-ARIMA模型学习窗口尺度降低了90.3%,建模复杂度显著降低,MAE降低了16.3%,预测精度能满足现场需求。
|
| 关 键 词： | 数据预处理 LAGRANGE插值 瓦斯浓度 自回归差分移动平均模型(ARIMA) 实时预测 |
Study on Lagrange-ARIMA real-time prediction model of mine gas concentration |
| |
| WANG Peng,WU Yongping,WANG Shuanlin,SONG Chao,WU Xueming. Study on Lagrange-ARIMA real-time prediction model of mine gas concentration[J]. Coal Science and Technology, 2019, 0(4): 141-146 |
| |
| Authors: | WANG Peng WU Yongping WANG Shuanlin SONG Chao WU Xueming |
| |
| Affiliation: | (College of Safety Science and Engineering,Xi’an University of Science and Technology,Xi’an 710054,China;National & Local United Engineering ResearchCenter of Green Safety Efficient Mining, Xi’an 710065, China;Institute of Modern Coal Mining Technology,Shaanxi Coal Chemical Industry TechnologyResearch Institute Company Limited,Xi’an 710065;College of Energy Engineering,Xi’an University of Science and Technology,Xi’an 710054,China;Key Laboratory of Western Mine Exploitation and Hazard Prevention Ministry of Education,Xi’an University of Science and Technology,Xi’an 710054,China;Safety Branch,China Coal Research Institute,Beijing 100013,China;State Key Laboratory of Coal Mining and Clean Utilization,Beijing 100013,China) |
| |
| Abstract: | WANG Peng;WU Yongping;WANG Shuanlin;SONG Chao;WU Xueming(College of Safety Science and Engineering,Xi’an University of Science and Technology,Xi’an 710054,China;National & Local United Engineering ResearchCenter of Green Safety Efficient Mining, Xi’an 710065, China;Institute of Modern Coal Mining Technology,Shaanxi Coal Chemical Industry TechnologyResearch Institute Company Limited,Xi’an 710065;College of Energy Engineering,Xi’an University of Science and Technology,Xi’an 710054,China;Key Laboratory of Western Mine Exploitation and Hazard Prevention Ministry of Education,Xi’an University of Science and Technology,Xi’an 710054,China;Safety Branch,China Coal Research Institute,Beijing 100013,China;State Key Laboratory of Coal Mining and Clean Utilization,Beijing 100013,China) |
| |
| Keywords: | data preprocessing Lagrange interpolation gas concentration Autoregressive Integrated Moving Average Model real-time prediction |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
