

浏览全部资源
扫码关注微信
新疆大学 电气工程学院,新疆 乌鲁木齐 830017
Received:05 December 2025,
Revised:2026-01-19,
Accepted:28 January 2026,
Published:25 March 2026
移动端阅览
张启帆,胡丽娜,曾浩,刘威,杨灿.基于MEVMD与GA-CNN+LSTM的NOx浓度动态预测模型研究[J].新疆大学学报(自然科学版中英文),2026,43(2):169-182.
Zhang Qifan,Hu Lina,Zeng Hao,Liu Wei,Yang Can.A dynamic prediction model for NOx concentration based on MEVMD and GA-CNN+LSTM[J].Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(2):169-182.
张启帆,胡丽娜,曾浩,刘威,杨灿.基于MEVMD与GA-CNN+LSTM的NOx浓度动态预测模型研究[J].新疆大学学报(自然科学版中英文),2026,43(2):169-182. DOI: 10.13568/j.cnki.651094.651316.2025.12.05.0001.
Zhang Qifan,Hu Lina,Zeng Hao,Liu Wei,Yang Can.A dynamic prediction model for NOx concentration based on MEVMD and GA-CNN+LSTM[J].Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(2):169-182. DOI: 10.13568/j.cnki.651094.651316.2025.12.05.0001.
燃煤电厂作为主要NO
x
排放源,其SCR脱硝系统的高效运行对降低污染物排放至关重要,但在预测NO
x
过程中,数据的剧烈动态变化会制约模型的预测精度.本文提出一种基于模态能量差和样本熵的变分模态分解(MEVMD)耦合遗传算法(GA)优化卷积神经网络(CNN)和长短期记忆网络(LSTM)的混合预测模型.首先,通过3σ准则修正异常值,再采用皮尔逊相关系数筛选20个关键输入变量,利用最大信息系数(MIC)确定各变量延迟时间,实现特征与目标变量的时序对齐.其次,通过自适应变分模态分解(VMD),精准剥离NO
x
时序信号中的多频率特征;通过GA优化超参数,实现多子模态的适配性建模.最后,通过VMD逆分解将各子模态融合输出预测结果.实验结果表明,本文所提模型的均方根误差(
RMSE
)为0.949 2,平均绝对误差(
MAE
)为0.496 9,决定系数(
R
2
)为0.976 7,优于对比模型.
Coal-fired power plants serve as primary sources of NO
x
emissions
and the efficient operation of SCR denitrification systems is crucial for reducing pollutant emissions. However
the highly dynamic changes of data during NO
x
prediction processes limit the accuracy of predictive models. Therefore
a hybrid prediction framework based on modal energy diffe‑rence and sample entropy
which combining variational mode decomposition (MEVMD) with genetic algorithm (GA) to optimize convolutional neural network (CNN) and long short-term memory network (LSTM)
is proposed. Firstly
abnormal data are corrected using the 3σ criterion; 20 key auxiliary variables are selected via Pearson correlation coefficients. The maximum information coefficient (MIC) is employed to determine the delay time for each variable
achieving temporal alignment between features and target variables. Secondly
adaptive variational mode decomposition (VMD) precisely extracts multi-frequency features from NO
x
time-series signals. Hyperparameters are optimized via GA to achieve adaptive modeling of multiple sub-modes. Finally
prediction results are generated through data reconstruction. Experimental results demonstrate that the proposed model achieves
RMSE
of 0.949 2
MAE
of 0.496 9
and
R
2
of 0.976 7
outperforming comparison models.
Jin Y , Scherer L , Sutanudjaja E H , et al . Climate change and CCS increase the water vulnerability of China’s thermoelectric power fleet [J]. Energy , 2022 , 245 : 123339 .
Chang S Y , Zhuo J K , Meng S , et al . Clean coal technologies in China:Current status and future perspectives [J]. Enginee‑ring , 2016 , 2 ( 4 ): 447 - 459 .
Faghihi E M , Shamekhi A H . Development of a neural network model for selective catalytic reduction(SCR)catalytic converter and ammonia dosing optimization using multi objective genetic algorithm [J]. Chemical Engineering Journal , 2010 , 165 ( 2 ): 508 - 516 .
Liu G F , Bao W Y , Zhang W , et al . An intelligent control of NH 3 injection for optimizing the NO x /NH 3 ratio in SCR system [J]. Journal of the Energy Institute , 2019 , 92 ( 5 ): 1262 - 1269 .
Huang D W , Tang S H , Zhou D J , et al . NO x emission estimation in gas turbines via interpretable neural network observer with adjustable intermediate layer considering ambient and boundary conditions [J]. Measurement , 2022 , 189 : 110429 .
Yang T T , Ma K F , Lyu Y , et al . Real-time dynamic prediction model of NO x emission of coal-fired boilers under variable load conditions [J]. Fuel , 2020 , 274 : 117811 .
Wang Z , Pen X Y , Cao S X , et al . NO x emission prediction using a lightweight convolutional neural network for cleaner production in a down-fired boiler [J]. Journal of Cleaner Production , 2023 , 389 : 136060 .
Rao H D , Shi X Z , Rodrigue A K , et al . Feature selection based on artificial bee colony and gradient boosting decision tree [J]. Applied Soft Computing , 2019 , 74 : 634 - 642 .
Wang F , Ma S X , Wang H , et al . Prediction of NO x emission for coal-fired boilers based on deep belief network [J]. Control Engineering Practice , 2018 , 80 : 26 - 35 .
李影 , 卓建坤 , 吴逸凡 , 等 . 可解释的变负荷下燃煤机组SCR反应器入口NO x 质量浓度预测模型 [J]. 热力发电 , 2024 , 53 ( 7 ): 119 - 128 .
Li Y , Zhuo J K , Wu Y F , et al . Interpretable prediction model for NO x mass concentration at SCR reactor inlet in coal-fired power plants under flexible operating conditions [J]. Thermal Power Generation , 2024 , 53 ( 7 ): 119 - 128 . (in Chinese)
吴康洛 , 黄俊 , 李峥辉 , 等 . 基于MIC-CFS-LSTM的SCR出口NO x 浓度动态预测 [J]. 洁净煤技术 , 2023 , 29 ( 6 ): 142 - 150 .
Wu K L , Huang J , Li Z H , et al . Dynamic prediction of the NO x concentration at SCR system outlet based on MIC-CFS-LSTM model [J]. Clean Coal Technology , 2023 , 29 ( 6 ): 142 - 150 . (in Chinese)
张鹏新 , 高明明 , 郭炯楠 , 等 . 基于混合建模方法循环流化床锅炉深度调峰NO x 排放预测 [J]. 洁净煤技术 , 2024 , 30 ( 9 ): 85 - 94 .
Zhang P X , Gao M M , Guo J N , et al . Prediction of NO x emissions from deep peaking circulating fluidized bed boilers based on a hybrid modelling approach [J]. Clean Coal Technology , 2024 , 30 ( 9 ): 85 - 94 . (in Chinese)
Wang X W , Liu W J , Wang Y N , et al . A hybrid NO x emission prediction model based on CEEMDAN and AM-LSTM [J]. Fuel , 2022 , 310 : 122486 .
Tang Z H , Wang S K , Chai X Y , et al . Auto-encoder-extreme learning machine model for boiler NO x emission concentration prediction [J]. Energy , 2022 , 256 : 124552 .
张珑慧 , 林德海 , 王颖 , 等 . 机器学习在火电厂NO x 减排中的应用综述 [J]. 热力发电 , 2023 , 52 ( 1 ): 7 - 17 .
Zhang L H , Lin D H , Wang Y , et al . Review of applications of machine learning in nitrogen oxides reduction in thermal power plants [J]. Thermal Power Generation , 2023 , 52 ( 1 ): 7 - 17 . (in Chinese)
Bokde N , Feijóo A , Villanueva D , et al . A review on hybrid empirical mode decomposition models for wind speed and wind power prediction [J]. Energies , 2019 , 12 : 254 .
Yao X J , Yi T H , Qu C X . Autoregressive spectrum-guided variational mode decomposition for time-varying modal identification under nonstationary conditions [J]. Engineering Structures , 2022 , 251 : 113543 .
Sun Z X , Zhao M Y , Zhao G H . Hybrid model based on VMD decomposition,clustering analysis,long short memory network,ensemble learning and error complementation for short-term wind speed forecasting assisted by Flink platform [J]. Energy , 2022 , 261 : 125248 .
Wu Z , Zhang Y , Dong Z . Prediction of NO x emission concentration from coal-fired power plant based on joint knowledge and data driven [J]. Energy , 2023 , 271 : 127044 .
Salcedo-Sanz S , Cornejo-Bueno L , Prieto L , et al . Feature selection in machine learning prediction systems for renewable ener‑gy applications [J]. Renewable and Sustainable Energy Reviews , 2018 , 90 : 728 - 741 .
Reshef D N , Reshef Y A , Finucane H K , et al . Detecting novel associations in large data sets [J]. Science , 2011 , 334 ( 6062 ): 1518 - 1524 .
Cao Y H , Tung W W , Gao J B , et al . Detecting dynamical changes in time series using the permutation entropy [J]. Physical Review E , 2004 , 70 ( 4 ): 046217 .
Lian J J , Liu Z , Wang H J , et al . Adaptive variational mode decomposition method for signal processing based on mode characteristic [J]. Mechanical Systems and Signal Processing , 2018 , 107 : 53 - 77 .
Li N , Hu Y . The deep convolutional neural network for NO x emission prediction of a coal-fired boiler [J]. IEEE Access , 2020 , 8 : 85912 - 85922 .
0
Views
2
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621