Prediction method and application of gas emission from mining workface based on STL-EEMD-GA-SVR
-
摘要: 瓦斯涌出量准确预测可为矿井通风及瓦斯灾害防治措施提供重要依据。为提高采煤工作面瓦斯涌出量预测精度，根据陕西黄陵某矿采煤工作面绝对瓦斯涌出量监测数据，应用基于局部加权回归的周期趋势分解(Seasonal-Trend decomposition procedure based on Loess, STL)，将监测数据分解成趋势项、周期项和不规则波动项；利用集成经验模态分解(Ensemble Empirical Mode Decomposition, EEMD)，将不规则波动项分解得到不同特征尺度的IMFs(Intrinsic Mode Functions, IMFs)分量以及残差余量；通过遗传算法(Genetic Algorithms, GA)参数寻优后的支持向量回归机(Support Vector Regression, SVR)，对各项分解数据进行预测；叠加各分量模型预测结果，得到最终瓦斯涌出量预测结果。结果表明：在预测集为247、147和70组3种情景下，对比分析了STL-EEMD-GA-SVR模型(简称SEGS)、EEMD-GA-SVR模型、GA-SVR模型和高斯过程回归(Gaussian Process Regression, GPR)模型的评价指标精度，其中，SEGS模型最优，拟合度R2分别为0.81、0.92、0.99，峰值点平均相对误差最低，分别为3.15%、2.33%、1.04%。所构建的SEGS模型可以准确预测采煤工作面的瓦斯涌出量。Abstract: Accurate prediction of gas emission can provide important basis for mine ventilation and the prevention and measures of gas disasters. In order to improve the prediction accuracy of gas emission in the mining workface, the monitoring data of gas emission were decomposed into the trend term, periodic term and irregular fluctuation term by the Seasonal-Trend decomposition procedure based on Loess (STL) based on the monitoring data of gas emission from the mining workface of Huangling Mine in Shaanxi. Besides, the irregular fluctuation term was further broken down into the Intrinsic Mode Functions (IMFs) components with different characteristics and the residual margins by the Ensemble Empirical Mode Decomposition (EEMD). Then, each decomposed data was predicted by the Support Vector Regression (SVR) through parameter optimization by Genetic Algorithms (GA). Moreover, the prediction result of each component model was superposed to obtain the final prediction result of gas emission. In addition, the evaluation indicators for precision of STL-EEMD-GA-SVR model (hereinafter referred to as SEGS), EEMD-GA-SVR model, GA-SVR model and Gaussian Process Regression (GPR) model were analyzed comparatively in the 3 scenarios with 247, 147 and 70 groups of prediction set. According to the results, SEGS model is the best, of which the fitting degree R2 was 0.81, 0.92 and 0.99 respectively, and the average relative error at the peak point was 3.15%, 2.33% and 1.04% respectively. In general, the constructed SEGS model could accurately predict the gas emission of mining workface.
-
图 3 STL分解后采煤工作面瓦斯涌出量
Fig. 3 Gas emission data of mining workface after STL decomposition
图 5 不规则波动项与EEMD分解分量叠加值对比
Fig. 5 Comparison of irregular fluctuation term with superposed value of decomposition components by EEMD
图 6 时序分解各分量模型预测结果
Fig. 6 Prediction results of each component model in time series decomposition
图 8 不同情景下模型预测结果对比
注：图中添加符号处表示峰值点。
Fig. 8 Comparison of model prediction results under different scenarios
表 1 瓦斯涌出量数据
Table 1 Gas emission data
序号 时间 瓦斯风排量/ (m3·min−1) 瓦斯抽采量/
(m3·min−1)绝对瓦斯涌出量/
(m3·min−1)1 2020-05-16 7.37 29.96 37.33 2 2020-05-17 5.94 30.92 36.86 3 2020-05-18 7.78 31.00 38.78 4 2020-05-19 6.14 31.62 37.76 5 2020-05-20 6.55 31.96 38.52 $ \vdots $ $\vdots $ $\vdots $ $\vdots $ $\vdots $ 343 2021-04-23 4.54 41.98 46.52 344 2021-04-24 5.45 41.45 46.89 345 2021-04-25 5.63 41.83 47.46 346 2021-04-26 5.45 42.09 47.53 347 2021-04-27 5.45 NA 5.45 注：NA表示此处为缺失值。 
下载: 导出CSV
表 2 瓦斯涌出量缺失数据
Table 2 Missing data of gas emission
序号 时间 瓦斯风排
量/(m3·min−1)瓦斯抽采
量/
(m3·min−1)绝对瓦斯涌出量/
(m3·min−1)200 2020-12-01 6.64 NA 6.64 209 2020-12-10 5.91 NA 5.91 241 2021-01-11 9.19 NA 9.19 275 2021-02-14 4.33 NA 4.33 281 2021-02-20 6.57 NA 6.57 347 2021-04-27 5.45 NA 5.45 注：NA表示此处为缺失值。
下载: 导出CSV
表 3 随机缺失插补误差对比
Table 3 Comparison of interpolation error for random missing values
不同插补方法下的均方误差 缺失率/% 二重
插补三重
插补四重
插补五重插补 均值插补 线性插补 5 4.29 21.26 8.40 7.24 2.31 0.12 10 12.77 25.45 21.50 12.71 14.38 0.13 15 20.51 14.46 10.43 13.88 7.04 0.37 20 13.46 9.21 17.11 24.98 11.10 0.24 25 14.87 16.52 17.28 14.04 13.26 0.43 30 15.05 11.87 9.52 14.64 9.06 0.39
下载: 导出CSV
表 4 线性插补填补数据
Table 4 Linear interpolation fill data values
序号 时间 瓦斯风排
量/
(m3·min−1)瓦斯抽采
量/
(m3·min−1)绝对瓦斯涌出
量/
(m3·min−1)200 2020-12-01 6.64 45.87 52.51 209 2020-12-10 5.91 45.65 51.56 241 2021-01-11 9.19 41.45 50.64 275 2021-02-14 4.33 45.85 50.18 281 2021-02-20 6.57 41.75 48.32 347 2021-04-27 5.45 43.14 48.59
下载: 导出CSV
表 5 分解损失量
Table 5 Decomposition loss
序号 时间 不规则波动
项/(m3·min−1)分解分量叠加
值/(m3·min−1)分解损失量/
(m3·min−1)1 2020-05-16 −1.440 4 −1.423 1 −0.017 3 2 2020-05-17 −1.151 0 −1.189 6 0.038 6 3 2020-05-18 1.073 0 1.054 0 0.019 0 4 2020-05-19 0.360 0 0.337 9 0.022 1 5 2020-05-20 1.922 6 1.903 0 0.019 5 $\vdots $ $\vdots $ $\vdots $ $\vdots $ $\vdots $ 343 2021-04-23 −0.693 5 −0.664 0 −0.029 5 344 2021-04-24 −0.313 8 −0.305 1 −0.008 6 345 2021-04-25 0.023 9 0.081 1 −0.057 2 346 2021-04-26 −0.221 4 −0.236 6 0.015 2 347 2021-04-27 0.649 1 0.634 8 0.014 3 注：为避免保留2位小数出现多处零值，此处保留小数点后4位。其中分解损失量为不规则波动项与分解分量叠加值的差值。
下载: 导出CSV
表 6 GA各分量SVR模型超参数寻优值
Table 6 Optimal value of hyperparameters for each SVR component model of GA
分解分量 情景一寻优值 情景二寻优值 情景三寻优值 bestc bestg bestc bestg bestc bestg IMF1 9.78 0.03 5.23 0.56 9.63 0.01 IMF2 9.61 0.32 8.31 0.02 9.47 0.02 IMF3 6.44 2.39 3.89 2.25 7.96 0.02 IMF4 3.67 2.10 3.10 4.93 30.1 5.05 IMF5 7.00 0.02 7.76 0.02 9.83 0.01 IMF6 5.89 0.52 6.92 0.53 5.11 4.93 IMF7 7.51 0.02 3.70 4.89 4.39 2.33 RES 7.87 2.34 6.47 0.02 5.22 4.92 趋势项 6.77 0.02 6.63 0.02 3.11 2.41 周期项 6.44 0.58 1.82 2.38 3.86 5.00 注：bestc、bestg分别为GA寻优的最佳惩罚因子C和核函数gamma。
下载: 导出CSV
表 7 各分量模型预测绝对误差
Table 7 Absolute error of each component model
分量预测模型 绝对误差/(m3·min−1) 最小值 最大值 平均值 IMF1 0.000 3 0.412 5 0.051 8 IMF2 0.000 2 0.291 1 0.032 8 IMF3 0.000 4 0.218 8 0.044 2 IMF4 0 0.030 9 0.017 4 IMF5 0 0.016 2 0.007 9 IMF6 0.000 1 0.009 3 0.005 8 IMF7 0.000 1 0.009 4 0.005 2 RES 0 0.001 5 0.000 7 趋势项 0.083 0 3.158 5 0.724 7 周期项 0.001 6 0.014 9 0.010 1 注：为避免保留2位小数出现多处零值，此处保留小数点后4位。
下载: 导出CSV
表 8 各预测模型评价指标对比
Table 8 Comparison of evaluation indicators for each prediction model
评价指标 SEGS EEMD-GA-SVR GA-SVR GPR 情景一 EMA 1.58 2.32 2.09 2.28 EMAP/% 2.93 4.35 3.88 4.25 ERMS 1.87 2.63 2.33 2.56 R2 0.81 0.67 0.73 0.69 情景二 EMA 0.90 1.29 1.22 1.45 EMAP/% 1.67 2.37 2.25 2.65 ERMS 1.27 1.41 1.54 1.60 R2 0.92 0.91 0.88 0.88 情景三 EMA 0.39 0.59 1.03 0.74 EMAP/% 0.73 1.17 2.05 1.46 ERMS 0.47 0.70 1.10 0.83 R2 0.99 0.98 0.94 0.97 注：EMA、EMAP、ERMS值愈小模型愈优；R2值愈高，模型愈优。
下载: 导出CSV
表 9 各模型峰值点预测误差对比
Table 9 Comparison of prediction errors at peak points for each model
平均值 SEGS EEMD-GA-SVR GA-SVR GPR 情景一 绝对误差/
(m3·min−1)1.77 2.39 2.60 2.85 相对误差/% 3.15 4.29 4.68 5.13 情景二 绝对误差/
(m3·min−1)1.37 1.70 2.16 2.09 相对误差/% 2.33 2.95 3.72 3.62 情景三 绝对误差/
(m3·min−1)0.58 0.75 1.29 0.91 相对误差/% 1.04 1.35 2.40 1.65
下载: 导出CSV
-
[1] 程远平,周德永,俞启香,等. 保护层卸压瓦斯抽采及涌出规律研究[J]. 采矿与安全工程学报,2006,23(1):12−18.. doi: 10.3969/j.issn.1673-3363.2006.01.003CHENG Yuanping,ZHOU Deyong,YU Qixiang,et al. Research on extraction and emission laws of gas for pressure–relief in protecting coal seams[J]. Journal of Mining & Safety Engineering,2006,23(1):12−18.. doi: 10.3969/j.issn.1673-3363.2006.01.003 [2] 樊保龙,白春华,李建平. 基于LMD–SVM的采煤工作面瓦斯涌出量预测[J]. 采矿与安全工程学报,2013,30(6):946−952.FAN Baolong,BAI Chunhua,LI Jianping. Forecasting model of coalface gas emission based on LMD–SVM method[J]. Journal of Mining & Safety Engineering,2013,30(6):946−952. [3] 张超林,王恩元,王奕博,等. 近20年我国煤与瓦斯突出事故时空分布及防控建议[J]. 煤田地质与勘探,2021,49(4):134−141.. doi: 10.3969/j.issn.1001-1986.2021.04.016ZHANG Chaolin,WANG Enyuan,WANG Yibo,et al. Spatial–temporal distribution of outburst accidents from 2001 to 2020 in China and suggestions for prevention and control[J]. Coal Geology & Exploration,2021,49(4):134−141.. doi: 10.3969/j.issn.1001-1986.2021.04.016 [4] 桂祥友,郁钟铭,孟絮屹. 贵州煤矿瓦斯涌出量灰色预测的应用[J]. 采矿与安全工程学报,2007,24(4):449−452.. doi: 10.3969/j.issn.1673-3363.2007.04.015GUI Xiangyou,YU Zhongming,MENG Xuyi. Application of grey forecast for coal bed methane emission from coal mines in Guizhou Province[J]. Journal of Mining & Safety Engineering,2007,24(4):449−452.. doi: 10.3969/j.issn.1673-3363.2007.04.015 [5] 付华,于翔,卢万杰. 基于蚁群粒子群混合算法与LS–SVM瓦斯涌出量预测[J]. 传感技术学报,2016,29(3):373−377.. doi: 10.3969/j.issn.1004-1699.2016.03.012FU Hua,YU Xiang,LU Wanjie. Prediction of gas emission based on hybrid algorithm of Ant Colony Particle Swarm optimization and LS–SVM[J]. Chinese Journal of Sensors and Actuators,2016,29(3):373−377.. doi: 10.3969/j.issn.1004-1699.2016.03.012 [6] 章立清,秦玉金,姜文忠,等. 我国矿井瓦斯涌出量预测方法研究现状及展望[J]. 煤矿安全,2007,38(8):58−60.. doi: 10.3969/j.issn.1003-496X.2007.08.020ZHANG Liqing,QIN Yujin,JIANG Wenzhong,et al. Research status and prospects of mine gas emission prediction methods in my country[J]. Safety in Coal Mines,2007,38(8):58−60.. doi: 10.3969/j.issn.1003-496X.2007.08.020 [7] 姜文忠,霍中刚,秦玉金. 矿井瓦斯涌出量预测技术[J]. 煤炭科学技术,2008,36(6):1−4.. doi: 10.13199/j.cst.2008.06.6.jiangwzh.018JIANG Wenzhong,HUO Zhonggang,QIN Yujin. Predicted technology of mine gas emission[J]. Coal Science and Technology,2008,36(6):1−4.. doi: 10.13199/j.cst.2008.06.6.jiangwzh.018 [8] 刘俊娥,安凤平,林大超,等. 采煤工作面瓦斯涌出量的固有模态SVM建模预测[J]. 系统工程理论与实践,2013,33(2):505−511.. doi: 10.3969/j.issn.1000-6788.2013.02.028LIU Jun’e,AN Fengping,LIN Dachao,et al. Prediction of gas emission from coalface by intrinsic mode SVM modeling[J]. Systems Engineering–Theory & Practice,2013,33(2):505−511.. doi: 10.3969/j.issn.1000-6788.2013.02.028 [9] 付华,谢森,徐耀松,等. 基于MPSO–WLS–SVM的矿井瓦斯涌出量预测模型研究[J]. 中国安全科学学报,2013,23(5):56−61.FU Hua,XIE Sen,XU Yaosong,et al. Study on MPSO−WLS–SVM based mine gas emission prediction model[J]. China Safety Science Journal,2013,23(5):56−61. [10] 付华,谢森,徐耀松,等. 基于ACC–ENN算法的煤矿瓦斯涌出量动态预测模型研究[J]. 煤炭学报,2014,39(7):1296−1301.FU Hua,XIE Sen,XU Yaosong,et al. Gas emission dynamic prediction model of coal mine based on ACC–ENN algorithm[J]. Journal of China Coal Society,2014,39(7):1296−1301. [11] 董晓雷,贾进章,白洋,等. 基于SVM耦合遗传算法的回采工作面瓦斯涌出量预测[J]. 安全与环境学报,2016,16(2):114−118.DONG Xiaolei,JIA Jinzhang,BAI Yang,et al. Prediction for gas–gushing amount from the working face of stope based on the SVM coupling genetic algorithm[J]. Journal of Safety and Environment,2016,16(2):114−118. [12] 温廷新,孙雪,孔祥博,等. 基于PSOBP–AdaBoost模型的瓦斯涌出量分源预测研究[J]. 中国安全科学学报,2016,26(5):94−98.WEN Tingxin,SUN Xue,KONG Xiangbo,et al. Research on prediction of gas emission quantity with sub sources basing on PSOBP–AdaBoost[J]. China Safety Science Journal,2016,26(5):94−98. [13] 周鑫隆,章光,吕辰,等. 深部煤层瓦斯含量的差值GM–RBF预测模型及其应用[J]. 安全与环境学报,2017,17(6):2050−2055.ZHOU Xinlong,ZHANG Guang,LYU Chen,et al. A grey model for predicting the gas content in the deep coal seam and its application via the neural network of the difference radial basis function[J]. Journal of Safety and Environment,2017,17(6):2050−2055. [14] 林海飞,高帆,严敏,等. 煤层瓦斯含量PSO–BP神经网络预测模型及其应用[J]. 中国安全科学学报,2020,30(9):80−87.LIN Haifei,GAO Fan,YAN Min,et al. Study on PSO–BP neural network prediction method of coal seam gas content and its application[J]. China Safety Science Journal,2020,30(9):80−87. [15] 马文涛. 基于WT与GALSSVM的瓦斯涌出量预测[J]. 采矿与安全工程学报,2009,26(4):524−528.. doi: 10.3969/j.issn.1673-3363.2009.04.028MA Wentao. Gas emission forecast based on WT and GALSSVM[J]. Journal of Mining & Safety Engineering,2009,26(4):524−528.. doi: 10.3969/j.issn.1673-3363.2009.04.028 [16] 任海峰,严由吉,吴青海. 基于SAPSO–ELM的瓦斯涌出量分源预测及应用[J]. 煤田地质与勘探,2021,49(2):102−109.. doi: 10.3969/j.issn.1001-1986.2021.02.013REN Haifeng,YAN Youji,WU Qinghai. Different–source prediction of gas emission based on SAPSO–ELM and its application[J]. Coal Geology & Exploration,2021,49(2):102−109.. doi: 10.3969/j.issn.1001-1986.2021.02.013 [17] 陶云奇,许江,李树春. 改进的灰色马尔柯夫模型预测采煤工作面瓦斯涌出量[J]. 煤炭学报,2007,32(4):391−395.. doi: 10.3321/j.issn:0253-9993.2007.04.012TAO Yunqi,XU Jiang,LI Shuchun. Predict gas emissing quantity of mining coal face with improved grey Markov model[J]. Journal of China Coal Society,2007,32(4):391−395.. doi: 10.3321/j.issn:0253-9993.2007.04.012 [18] 高莉,胡延军,于洪珍. 基于W–RBF的瓦斯时间序列预测方法[J]. 煤炭学报,2008,33(1):67−70.. doi: 10.3321/j.issn:0253-9993.2008.01.015GAO Li,HU Yanjun,YU Hongzhen. Prediction of gas emission time series based on W–RBF[J]. Journal of China Coal Society,2008,33(1):67−70.. doi: 10.3321/j.issn:0253-9993.2008.01.015 [19] 单亚锋,侯福营,付华,等. 基于改进极端学习机的混沌时间序列瓦斯涌出量预测[J]. 中国安全科学学报,2012,22(12):58−63.SHAN Yafeng,HOU Fuying,FU Hua,et al. Prediction of chaotic time series of gas emission based on improved extreme learning machine[J]. China Safety Science Journal,2012,22(12):58−63. [20] 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.. doi: 10.3321/j.issn:1000-1964.2008.02.018CHENG Jian,BAI Jingyi,QIAN Jiansheng,et al. Short–term forecasting method of coal mine gas concentration based on chaotic time series[J]. Journal of China University of Mining & Technology,2008,37(2):231−235.. doi: 10.3321/j.issn:1000-1964.2008.02.018 [21] 施式亮,李润求,罗文柯. 基于EMD–PSO–SVM的煤矿瓦斯涌出量预测方法及应用[J]. 中国安全科学学报,2014,24(7):43−49.SHI Shiliang,LI Runqiu,LUO Wenke. Method for predicting coal mine gas emission based on EMD–PSO–SVM and its application[J]. China Safety Science Journal,2014,24(7):43−49. [22] 李润求,施式亮,伍爱友,等. 采煤工作面瓦斯涌出预测的EMD–Elman方法及应用[J]. 中国安全科学学报,2014,24(6):51−56.LI Runqiu,SHI Shiliang,WU Aiyou,et al. Research on coal mining workface gas emission prediction method based on EMD–Elman and its application[J]. China Safety Science Journal,2014,24(6):51−56. [23] 撒占友,刘岩,刘杰. 基于EMD–ARMA的矿井瓦斯涌出量预测[J]. 煤矿安全,2016,47(7):174−176.SA Zhanyou,LIU Yan,LIU Jie. Mine gas emission prediction based on EMD–ARMA model[J]. Safety in Coal Mines,2016,47(7):174−176. [24] 卢国斌,李晓宇,祖秉辉,等. 基于EMD–MFOA–ELM的瓦斯涌出量时变序列预测研究[J]. 中国安全生产科学技术,2017,13(6):109−114.LU Guobin,LI Xiaoyu,ZU Binghui,et al. Research on time–varying series forecasting of gas emission quantity based on EMD–MFOA−ELM[J]. Journal of Safety Science and Technology,2017,13(6):109−114. [25] BANAS J,KOZUCH A. The application of time series decomposition for the identification and analysis of fluctuations in timber supply and price:A case study from Poland[J]. Forests,2019,10(11):990.. doi: 10.3390/f10110990 [26] 何清. 工作面瓦斯涌出量预测研究现状及发展趋势[J]. 矿业安全与环保,2016,43(4):98−101.. doi: 10.3969/j.issn.1008-4495.2016.04.026HE Qing. Present research situation on gas emission prediction of working face and its developing trend[J]. Mining Safety & Environmental Protection,2016,43(4):98−101.. doi: 10.3969/j.issn.1008-4495.2016.04.026 [27] ROJO J,RIVERO R,ROMERO–MORTE J,et al. Modeling pollen time series using seasonal−trend decomposition procedure based on LOESS smoothing[J]. International Journal of Biometeorology,2017,61(2):335−348.. doi: 10.1007/s00484-016-1215-y [28] XIONG Tao,LI Chongguang,BAO Yukun. Seasonal forecasting of agricultural commodity price using a hybrid STL and ELM method:Evidence from the vegetable market in China[J]. Neurocomputing,2018,275:2831−2844.. doi: 10.1016/j.neucom.2017.11.053 [29] SUN Tianhe,ZHANG Tieyan,TENG Yun,et al. Monthly electricity consumption forecasting method based on X12 and STL decomposition model in an integrated energy system[J]. Mathematical Problems in Engineering,2019,2019:9012543. [30] 胡爱军,孙敬敬,向玲. 经验模态分解中的模态混叠问题[J]. 振动、测试与诊断,2011,31(4):429−434.. doi: 10.3969/j.issn.1004-6801.2011.04.006HU Aijun,SUN Jingjing,XIANG Ling. Mode mixing in empirical mode decomposition[J]. Journal of Vibration,Measurement and Diagnosis,2011,31(4):429−434.. doi: 10.3969/j.issn.1004-6801.2011.04.006 [31] 易文华,刘连生,闫雷,等. 基于EMD改进算法的爆破振动信号去噪[J]. 爆炸与冲击,2020,40(9):095201.. doi: 10.11883/bzycj-2019-0471YI Wenhua,LIU Liansheng,YAN Lei,et al. Vibration signal de–noising based on improved EMD algorithm[J]. Explosion and Shock Waves,2020,40(9):095201.. doi: 10.11883/bzycj-2019-0471 [32] WU Zhaohua,HUANG N E. Ensemble empirical mode decomposition:A noise–assisted data analysis method[J]. Advances in Adaptive Data Analysis,2009,1(1):1−41.. doi: 10.1142/S1793536909000047 [33] 魏博文,柳波,徐富刚,等. 融合PSO–SVM的混凝土拱坝多测点变形监控混合模型[J]. 武汉大学学报(信息科学版),2021,46(11):1−14.WEI Bowen,LIU Bo,XU Fugang,et al. Multi−point hybrid model based on PSO–SVM for concrete arch dam deformation monitoring[J]. Geomatics and Information Science of Wuhan University,2021,46(11):1−14. [34] 边霞,米良. 遗传算法理论及其应用研究进展[J]. 计算机应用研究,2010,27(7):2425−2429.BIAN Xia,MI Liang. Development on genetic algorithm theory and its applications[J]. Application Research of Computers,2010,27(7):2425−2429. [35] 邓建新,单路宝,贺德强,等. 缺失数据的处理方法及其发展趋势[J]. 统计与决策,2019,35(23):28−34.. doi: 10.13546/j.cnki.tjyjc.2019.23.005DENG Jianxin,SHAN Lubao,HE Deqiang,et al. Processing method of missing data and its development tendency[J]. Statistics & Decision,2019,35(23):28−34.. doi: 10.13546/j.cnki.tjyjc.2019.23.005 [36] 赵厚翔,沈晓东,吕林,等. 基于GAN的负荷数据修复及其在EV短期负荷预测中的应用[J]. 电力系统自动化,2021,45(16):143−151.ZHAO Houxiang,SHEN Xiaodong,LYU Lin,et al. Load data restoration based on GAN and its application in short–term load forecasting of EV[J]. Automation of Electric Power Systems,2021,45(16):143−151. [37] LUO Yonghong, CAI Xiangrui, ZHANG Ying, et al. Multivariate time series imputation with generative adversarial networks[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal, 2018: 1603–1614. -
下载:
点击查看大图
图(9) / 表(9)
计量
- 文章访问数: 146
- HTML全文浏览量: 11
- PDF下载量: 21
- 被引次数: 0
