[1]马 莉,潘少波,代新冠,等.基于PSO-Adam-GRU的煤矿瓦斯浓度预测模型[J].西安科技大学学报,2020,(02):363-368.
 MA Li,PAN Shao-bo,DAI Xin-guan,et al.Gas concentration prediction model of working face based on PSO-Adam-GRU[J].Journal of Xi'an University of Science and Technology,2020,(02):363-368.
点击复制

基于PSO-Adam-GRU的煤矿瓦斯浓度预测模型(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2020年02期
页码:
363-368
栏目:
出版日期:
2020-03-30

文章信息/Info

Title:
Gas concentration prediction model of working face based on PSO-Adam-GRU
文章编号:
1672-9315(2020)02-0363-06
作者:
马 莉1潘少波1代新冠1宋 爽2石新莉1
(1.西安科技大学 通信与信息工程学院,陕西 西安 710054; 2.西安科技大学 能源学院,陕西 西安 710054)
Author(s):
MA Li1PAN Shao-bo 1DAI Xin-guan1SONG Shuang 2SHI Xin-li 1
(1.College of Communication and Information Engineering,Xi'an University of Science and Technology,Xi'an 710054,China; 2.College of Energy Science and Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)
关键词:
煤矿安全 瓦斯浓度预测 门控循环单元 粒子群算法
Keywords:
coal mine safety gas concentration prediction GRU PSO
分类号:
TD 713
文献标志码:
A
摘要:
煤矿瓦斯浓度的精准预测是矿井瓦斯防治的关键。为了准确可靠地预测工作面瓦斯浓度,提出了一种基于门控循环单元方法的工作面瓦斯浓度预测模型。采用邻近均值法对数据缺失值和异常值进行补全,采用MinMaxScaler方法对实验数据进行归一化处理,为了提高模型精度和稳定性,采用粒子群算法和Adam算法对GRU超参数进行优化,从而构建了基于PSO-Adam-GRU的工作面瓦斯浓度预测模型。以崔家沟煤矿生产监测数据为样本数据进行模型训练,采用平均绝对误差、均方根误差、运行时间3种评价指标对预测模型性能进行评估,并将预测结果与BPNN和LSTM进行对比。结果表明:PSO-Adam-GRU较BPNN和LSTM具有更高的精度和稳定性,在预测过程中MAE可降低到0.058,RMSE可降低到0.005.结果表明,基于PSO-Adam-GRU的瓦斯浓度预测模型和参数优选方法可有效预测出瓦斯浓度,该模型在瓦斯浓度时间序列预测方面具有更高的准确性和鲁棒性,可为矿井瓦斯治理提供一定指导意见。
Abstract:
The accurate prediction of coal mine gas concentration is the key to mine gas prevention and control.To predict the gas concentration of the working faceaccurately and reliably,a gas concentration prediction model based on gate recurrent unit was proposed,the data missing value and outlier value were complemented by the neighboring mean method,and the experimental data was normalized by MinMaxScaler method.In order to improve the accuracy and stability of the model,the PSO and Adam algorithm are used to calculate the GRU hyperparameter Optimization,so as to construct a PSO-Adam-GRU gas concentration prediction model of working surface.It takes Cuijiagou coal mine monitoring data as sample data for model training,and the performance of the prediction model was evaluated by the Mean Absolute Error,Root Mean Square Error and running time,Then the prediction results were compared with BPNN and LSTM methods.The experimental results show that GRU has higher precision and stability than BPNN and LSTM method,the MAE can be reduced to 0.058 during the prediction process,and the RMSE can be reduced to 0.005.The results indicate that the gas concentration prediction model and parameter optimization method based on PSO-Adam-GRU can effectively predict the gas concentration,the model has higher accuracy and robustness in gas concentration time series prediction,which can be provide some guidance for gas control in mine.

参考文献/References:

[1] 付 华,代 巍.基于ACPSO的PSR-MK-LSSVM瓦斯浓度动态预测方法[J].传感技术学报,2016,29(6):903-908. FU Hua,DAI Wei.A dynamic prediction method of gas concentration in PSR-MK-LSSVM based on ACPSO[J].Journal of Transduction Technology,2016,29(6):903-908. [2]钱建生.深度学习耦合粒子群优化SVM的瓦斯浓度预测[J].煤矿安全,2016,47(11):173-176. QIAN Jian-sheng.Gas concentration prediction of deep learning coupled particle swarm optimization SVM[J].Safety in Coal Mines,2016,47(11):173-176. [3]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 Guang-lu.Research on multi-sensor prediction model of coal mine gas concentration based on information fusion and GA-SVM[J].Chinese Journal of Safety Science,2013,23(9):33-38. [4]刘奕君,赵 强,郝文利.基于遗传算法优化BP神经网络的瓦斯浓度预测研究[J].矿业安全与环保,2015,42(2):56-60. LIU Yi-jun,ZHAO Qiang,HAO Wen-li.Study on gas concentration prediction based on genetic algorithm optimized BP neural network[J].Mining Safety & Environmental Protection,2015,42(2):56-60. [5]姜 雷.基于BP神经网络的煤矿瓦斯浓度预测模型构建及仿真[J].矿业安全与环保,2010,37(4):37-39. JIANG Lei.Construction and simulation of coal mine gas concentration prediction model based on BP neural network[J].Mining Safety & Environmental Protection,2010,37(4):37-39. [6]韩婷婷,吴世跃,王鹏军.基于马尔科夫残差修正的瓦斯浓度预测[J].工矿自动化,2014,40(3):28-31. HAN Ting-ting,WU Shi-yue,WANG Peng-jun.Prediction of gas concentration based on markov residual correction[J].Industrial and Mining Automation,2014,40(3):28-31. [7]杨 丽,刘 晖,毛善君,等.基于多元分布滞后模型的瓦斯浓度动态预测[J].中国矿业大学学报,2016,45(3):455-461. YANG Li,LIU Hui,MAO Shan-jun,et al.Dynamic prediction of gas concentration based on multivariate distributed lag model[J].Journal of China University of Mining & Technology,2016,45(3):455-461. [8]吴兆法,吴 响,钱建生.基于插值梯形模糊信息粒化的瓦斯浓度趋势预测[J].工矿自动化,2014,40(12):31-36. WU Zhao-fa,WU Xiang,QIAN Jian-sheng.Trend prediction of gas concentration based on interpolation trapezoidal fuzzy information granulation[J].Industrial Automation,2014,40(12):31-36. [9]桑海峰,陈紫珍.基于双向门控循环单元3D人体运动预测[J].电子与信息学报,2019,41(9):2256-2263. SANG Hai-feng,CHEN Zi-zhen.3D Human motion prediction based on two-way gated cyclic unit[J].Journal of Electronics & Information Technology,2019,41(9):2256-2263. [10]桑海峰,陈紫珍,何大阔.基于双向GRU和注意力机制模型的人体动作预测[J].计算机辅助设计与图形学学报,2019,31(7):1166-1174. SANG Hai-feng,CHEN Zi-zhen,HE Da-kuo.Human motion prediction based on two-way GRU and attention mechanism model[J].Journal of Computer-Aided Design & Computer Graphics,2019,31(7):1166-1174. [11]王增平,赵 兵.基于GRU-NN模型短期负荷预测方法[J].电力系统自动化,2019,43(5):53-62. WANG Zeng-ping,ZHAO Bing.Short term load forecasting method based on GRU-NN model[J].Automation of Electric Power Systems,2019,43(5):53-62. [12]牛哲文,余泽远,李 波,等.基于深度门控循环单元神经网络的短期风功率预测模型[J].电力自动化设备,2018,38(5):36-42. NIU Zhe-wen,YU Ze-yuan,LI Bo,et al.A short-term wind power prediction model based on neural network with deep gated loop unit[J].Electric Power Automation Equipment,2018,38(5):36-42. [13]WANG Jin-jiang,YAN Jian-xing,CHEN,et al.Deep heterogeneous GRU model for predictive analytics in smart manufacturing:Application to tool wear prediction[J].Computers in Industry,2019,111:1-14. [14]Bert Dijk,Bruno F Santos,Joao P Pita.The recoverable robust stand allocation problem:a GRU airport case study[J].OR Spectrum,2019,41(3):615-639. [15]Mehdi Poorabdollah,Arezoo Kamran.Optimising cure cycle of unsaturated polyester nanocomposites using directed grid search method[J].Polymers & AMP,Polymer Composites,2019,27(5):253-261. [16]Hatem A,Fayed,Amir F Atiya.Speed up grid-search for parameter selection of support vector machines[J].Applied Soft Computing Journal,2019,80:202-210. [17]Boukhalfa Ghoulemallah,Belkacem Sebti,Chikhi Abdesselem,et al.Application of fuzzy PID controller based on genetic algorithm and particle swarm optimization in direct torque control of double star induction motor[J].Journal of Central South University,2019,26(7):1886-1896. [18]CHANG Zi-han,ZHANG Yang,CHEN Wen-bo.Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform[J].Energy,2019:1-12. [19]WANG Liang,WANG Guang-wei,NING Xiao-jun,et al.Application of BP neural network to the prediction of coal ash melting characteristic temperature[J].Fuel,2020:1-8. [20]GENG Zhi-qiang,CHEN Guo-fei,HAN Yong-ming,et al.Semantic relation extraction using sequential and tree-structured LSTM with attention[J].Information Sciences,2020,509:182-192. [21]Fan H B,Liu W F,Wu J P et al.Ecosystem carbon pools in mixed stands of hardwood species and masson pine/Takungan karbon ekosistem dirian campur spesies kayu keras dan pain Masson[J].Journal of Tropical Forest Science,2013,25(2):154-165.

相似文献/References:

[1]冀汶莉,马 晴,贾 东.井下移动目标定位跟踪关键技术[J].西安科技大学学报,2016,(01):132.
 JI Wen-li,MA Qing,JIA Dong.Key technology of locating and tracking mobile object in underground mines[J].Journal of Xi'an University of Science and Technology,2016,(02):132.
[2]李占利,陈佳迎,李洪安,等.安全时间模型下的井下运动目标防撞预警方法[J].西安科技大学学报,2016,(06):875.[doi:10.13800/j.cnki.xakjdxxb.2016.0619]
 LI Zhan-li,CHEN Jia-ying,LI Hong-an,et al.An anti-collision early-warning method of coal mine underground moving objects based on security time model[J].Journal of Xi'an University of Science and Technology,2016,(02):875.[doi:10.13800/j.cnki.xakjdxxb.2016.0619]
[3]谭章禄,单 斐,陈孝慈.国内煤矿安全研究领域的知识图谱分析[J].西安科技大学学报,2017,(06):837.[doi:10.13800/j.cnki.xakjdxxb.2017.0611 ]
 TAN Zhang-lu,SHAN Fei,CHEN Xiao-ci.Analysis of knowledge map in domestic coal mine safety research field[J].Journal of Xi'an University of Science and Technology,2017,(02):837.[doi:10.13800/j.cnki.xakjdxxb.2017.0611 ]
[4]徐杨,周延.煤自然发火预报的人工神经网络模型[J].西安科技大学学报,2009,(04):410.[doi:10.13800/j.cnki.xakjdxxb.2009.04.014]
[5]袁晓翔,屈永利,许满贵,等.煤矿安全质量标准化建设原理[J].西安科技大学学报,2011,(06):786.
 YUAN Xiao-xiang,QU Yong-li,XU Man-gui,et al.Principle of standardization construction ofcoal mines safety quality[J].Journal of Xi'an University of Science and Technology,2011,(02):786.

备注/Memo

备注/Memo:
收稿日期:2020-01-11 责任编辑:刘 洁
基金项目:国家自然科学基金(51734007,51804248); 西安科技大学博士启动金(6310115032)
通信作者:马 莉(1979-),女,甘肃兰州人,博士,副教授,E-mail:mary@xust.edu.cn
更新日期/Last Update: 2020-03-30