瓦斯浓度动态在线预测模型
|
摘要
为有效预测采煤工作面的瓦斯浓度,针对具有高度非线性、不确定性、时变性及复杂性的瓦斯浓度序列,提出在线序贯极限学习机理论的瓦斯浓度动态预测模型,该模型可以实时更新监测信息,并根据历史数据和当前数据进行模型的离线训练和在线学习以完成对未来时刻瓦斯浓度的动态预测.同时,引入自适应萤火虫算法优化预测模型参数.实验结果表明:该方法通过实时更新样本数据,降低了复杂度,耗时小,学习影射能力强.该模型的预测误差比BPNN和ELM网络模型低,具备良好的预测精度与更强的泛化能力.
In order to effectively predict the gas concentration of coal mining face, the dynamic forecasting model of gas concentration based on online-sequence extreme-learning machine is proposed in connection with the feature of high nonlinearity, uncertainty, time-varying and complexity of gas concentration sequence, which can update the monitoring information real-time, and offline training and online learning models can be completed based on the historical data and current data to predict the future time gas concentration dynamically. At the same time, the adaptive step glowworm swarm optimization algorithm is introduced to optimize the model parameters.The experimental results show that the proposed method updates sample data in real time, which reduce the complexity, time-consuming, and has strong learning innuendo ability. The prediction error of this model is lower than that of the BP network and ELM models, which has better prediction accuracy and stronger generalization ability.
In order to effectively predict the gas concentration of coal mining face, the dynamic forecasting model of gas concentration based on online-sequence extreme-learning machine is proposed in connection with the feature of high nonlinearity, uncertainty, time-varying and complexity of gas concentration sequence, which can update the monitoring information real-time, and offline training and online learning models can be completed based on the historical data and current data to predict the future time gas concentration dynamically. At the same time, the adaptive step glowworm swarm optimization algorithm is introduced to optimize the model parameters.The experimental results show that the proposed method updates sample data in real time, which reduce the complexity, time-consuming, and has strong learning innuendo ability. The prediction error of this model is lower than that of the BP network and ELM models, which has better prediction accuracy and stronger generalization ability.
引文
[1]邵良杉.基于粗糙集理论的煤矿瓦斯预测技术[J].煤炭学报,2009,34(3):371-375.SHAO Liangshan.Disaster prediction of coal mine gas based on rough[J].Journal of China Coal Society,2009,34(3):371-375.
[2]张宝燕,李茹,穆文瑜.基于混沌时间序列的瓦斯浓度预测研究[J].计算机工程与应用,2011,47(10):244-248.ZHANG Baoyan,LI Ru,MU Wenyu.Study on gas concentration prediction based on chaotic time series[J].Computer Engineering and Applications,2011,47(10):244-248.
[3]程健,白静宜,钱建生,等.基于混沌时间序列的煤矿瓦斯浓度短期预测[J].中国矿业大学学报,2008,37(2):231-235.CHENG Jian,BAI Jingyi,QIAN Jiansheng,et al.Short-term forecasting method of coalmine gas concentration based on chaotic time series[J].Journal of China University of Mining&Technology,2008,37(2):231-235.
[4]李刚.瓦斯浓度的分形分析与混沌预测模型研究[D].北京:中国矿业大学(北京),2009.
[5]董丁稳,李树刚,常心坦,等.瓦斯浓度区间预测的灰色聚类与高斯过程模型[J].中国安全科学学报,2011,21(5):40-45.DONG Dingwen,LI Shugang,CHANG Xintan,et al.Grey clustering and gaussian process model for gas concentration interval prediction[J].China Safety Science Journal,2011,21(5):40-45.
[6]李晋文.采煤工作面瓦斯浓度的LMD-SVM预测[J].煤矿开采,2012,17(6):17-20.LI Jinwen.Methane concentration prediction with LMD-SVM model in mining face[J].Coal Mining Technology,2012,17(6):17-20.
[7]刘俊娥,杨晓帆,郭章林.基于FIG-SVM的煤矿瓦斯浓度预测[J].中国安全科学学报,2013,23(2):80-84.LIU June,YANG Xiaofan,GUO Zhanglin.Prediction of coal mine gas concentration based on FIG-SVM[J].China Safety Science Journal,2013,23(2):80-84.
[8]郭瑞,徐广璐.基于信息融合与GA-SVM的煤矿瓦斯浓度多传感器预测模型研究[J].中国安全科学学报,2013,23(9):33-38.GUO Rui,XU Guanglu.Research on coal mine gas concentration multi-sensor prediction model based on information fusion and GA-SVM[J].China Safety Science Journal,2013,23(9):33-38.
[9]付华,李文娟,孟祥云,等.IGA-DFNN在瓦斯浓度预测中的应用[J].传感技术学报,2014,27(2):262-266.FU Hua,LI Wenjuan,MENG Xiagyun,et al.Application of IGA-DFNNfor predicting coal mine gas concentration[J].Chinese Journal of Sensors and Actuators,2014,27(2):262-266.
[10]付华,刘雨竹,李海霞,等.煤矿瓦斯浓度的CAPSO-ENN短期预测模型[J].传感技术学报,2015,28(5):717-722.FU Hua,LIU Yuzhu,LI Haixia,et al.Short term forecasting model of gas concentration in coal mine using the CAPAO-ENN[J].Chinese Journal of Sensors and Actuators,2015,28(5):717-722.
[11]WANG Q,CHENG J.Forecast of coalmine gas concentration based on the immune neural network model[J].Journal of the China Coal Society,2008,33(6):665-669.
[12]付华,王馨蕊,王志军,等.基于PCA和PSO-ELM的煤与瓦斯突出软测量研究[J].传感技术学报,2014,27(12):1 710-1 715.FU Hua,WANG Xinrui,WANG Zhijun,et al.Research on the soft sensor of coal and gas outburst based on PCA and PSO-ELM[J].Chinese Journal of Sensors and Actuators,2014,27(12):1 710-1 715.
[13]兰明,刘志祥,冯凡.在线极限学习机在岩爆预测中的应用[J].安全与环境学报,2014,14(2):90-93.LAN Ming,LIU Zhixiang,FENG Fan.Attempt to study the applicability of the on-line sequential extreme learning machine to the rock burst forecast[J].Journal of Safety and Environment,2014,14(2):90-93.
[14]欧阳喆,周永权.自适应步长萤火虫优化算法[J].计算机应用,2011,31(7):1 804-1 807.OUYANG Zhe,ZHOU Yongquan.Self-adaptive step glowworm swarm optimization algorithm[J].Journal of Computer Applications,2011,31(7):1 804-1 807.
[2]张宝燕,李茹,穆文瑜.基于混沌时间序列的瓦斯浓度预测研究[J].计算机工程与应用,2011,47(10):244-248.ZHANG Baoyan,LI Ru,MU Wenyu.Study on gas concentration prediction based on chaotic time series[J].Computer Engineering and Applications,2011,47(10):244-248.
[3]程健,白静宜,钱建生,等.基于混沌时间序列的煤矿瓦斯浓度短期预测[J].中国矿业大学学报,2008,37(2):231-235.CHENG Jian,BAI Jingyi,QIAN Jiansheng,et al.Short-term forecasting method of coalmine gas concentration based on chaotic time series[J].Journal of China University of Mining&Technology,2008,37(2):231-235.
[4]李刚.瓦斯浓度的分形分析与混沌预测模型研究[D].北京:中国矿业大学(北京),2009.
[5]董丁稳,李树刚,常心坦,等.瓦斯浓度区间预测的灰色聚类与高斯过程模型[J].中国安全科学学报,2011,21(5):40-45.DONG Dingwen,LI Shugang,CHANG Xintan,et al.Grey clustering and gaussian process model for gas concentration interval prediction[J].China Safety Science Journal,2011,21(5):40-45.
[6]李晋文.采煤工作面瓦斯浓度的LMD-SVM预测[J].煤矿开采,2012,17(6):17-20.LI Jinwen.Methane concentration prediction with LMD-SVM model in mining face[J].Coal Mining Technology,2012,17(6):17-20.
[7]刘俊娥,杨晓帆,郭章林.基于FIG-SVM的煤矿瓦斯浓度预测[J].中国安全科学学报,2013,23(2):80-84.LIU June,YANG Xiaofan,GUO Zhanglin.Prediction of coal mine gas concentration based on FIG-SVM[J].China Safety Science Journal,2013,23(2):80-84.
[8]郭瑞,徐广璐.基于信息融合与GA-SVM的煤矿瓦斯浓度多传感器预测模型研究[J].中国安全科学学报,2013,23(9):33-38.GUO Rui,XU Guanglu.Research on coal mine gas concentration multi-sensor prediction model based on information fusion and GA-SVM[J].China Safety Science Journal,2013,23(9):33-38.
[9]付华,李文娟,孟祥云,等.IGA-DFNN在瓦斯浓度预测中的应用[J].传感技术学报,2014,27(2):262-266.FU Hua,LI Wenjuan,MENG Xiagyun,et al.Application of IGA-DFNNfor predicting coal mine gas concentration[J].Chinese Journal of Sensors and Actuators,2014,27(2):262-266.
[10]付华,刘雨竹,李海霞,等.煤矿瓦斯浓度的CAPSO-ENN短期预测模型[J].传感技术学报,2015,28(5):717-722.FU Hua,LIU Yuzhu,LI Haixia,et al.Short term forecasting model of gas concentration in coal mine using the CAPAO-ENN[J].Chinese Journal of Sensors and Actuators,2015,28(5):717-722.
[11]WANG Q,CHENG J.Forecast of coalmine gas concentration based on the immune neural network model[J].Journal of the China Coal Society,2008,33(6):665-669.
[12]付华,王馨蕊,王志军,等.基于PCA和PSO-ELM的煤与瓦斯突出软测量研究[J].传感技术学报,2014,27(12):1 710-1 715.FU Hua,WANG Xinrui,WANG Zhijun,et al.Research on the soft sensor of coal and gas outburst based on PCA and PSO-ELM[J].Chinese Journal of Sensors and Actuators,2014,27(12):1 710-1 715.
[13]兰明,刘志祥,冯凡.在线极限学习机在岩爆预测中的应用[J].安全与环境学报,2014,14(2):90-93.LAN Ming,LIU Zhixiang,FENG Fan.Attempt to study the applicability of the on-line sequential extreme learning machine to the rock burst forecast[J].Journal of Safety and Environment,2014,14(2):90-93.
[14]欧阳喆,周永权.自适应步长萤火虫优化算法[J].计算机应用,2011,31(7):1 804-1 807.OUYANG Zhe,ZHOU Yongquan.Self-adaptive step glowworm swarm optimization algorithm[J].Journal of Computer Applications,2011,31(7):1 804-1 807.