Dynamic Modeling of SNCR Denitrification System for Waste Incinerators Based on BKA-Transformer-BiGRU

ZHAO Zheng; LIANG Lei

doi:10.19805/j.cnki.jcspe.2026.250251

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Dynamic Modeling of SNCR Denitrification System for Waste Incinerators Based on BKA-Transformer-BiGRU

更新时间：2026-09-15

- Dynamic Modeling of SNCR Denitrification System for Waste Incinerators Based on BKA-Transformer-BiGRU
- Chinese Journal of Power Engineering Vol. 46, Issue 9, Pages: 180-191(2026)
- 作者机构：
  
  1. 华北电力大学自动化系,河北,保定,071003
  2. 保定市综合能源系统状态检测与优化调控重点实验室,河北,保定,071003
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2026.250251
  CLC： TM619
- Published：2026
- 稿件说明：
移动端阅览
赵征, 梁磊. 基于BKA-Transformer-BiGRU的垃圾焚烧炉SNCR脱硝系统动态建模[J]. 动力工程学报, 2026, 46(9): 180-191.
赵征, 梁磊. 基于BKA-Transformer-BiGRU的垃圾焚烧炉SNCR脱硝系统动态建模[J]. 动力工程学报, 2026, 46(9): 180-191. DOI： 10.19805/j.cnki.jcspe.2026.250251.

DOI： 10.19805/j.cnki.jcspe.2026.250251

摘要

针对垃圾焚烧炉选择性非催化还原（SNCR）脱硝系统影响因素多、非线性强、响应滞后，导致NOx排放难以准确测量等问题，提出了一种融合Transformer与双向门控循环单元（BiGRU）的动态建模方法，并利用黑翅鸢算法（BKA）优化模型相关参数。首先通过机理分析识别脱硝的主要影响因素，初选特征变量；随后利用组合特征提取算法——MRX-SynFilter算法进一步选取相关性高的变量，去除冗余变量；然后利用数据趋势分析法结合最大信息系数对变量迟延时间进行估计；接着利用BKA搜寻最优变量阶次组合，完成数据动态重构，增强模型对系统时序特性的感知能力；最后基于Transformer-BiGRU网络构建SNCR脱硝系统动态模型，并通过BKA同步优化网络超参数。实验结果表明：变量筛选、迟延估计和阶次选择均会提升建模准确性，且BKA-Transformer-BiGRU模型在拟合精度与误差控制方面均优于其他对比模型，能够更有效地捕捉SNCR脱硝系统复杂的非线性动态特征。

Abstract

The selective non-catalytic reduction (SNCR) denitrification system in waste incinerators involves multiple influencing factors

strong nonlinearity

and response delays

posing challenges to the accurate measurement of NOx emissions. A dynamic modeling method integrating Transformer with bidirectional gated recurrent unit (BiGRU) was proposed

with model parameters optimized using the black-winged kite algorithm (BKA). First

mechanism analysis was conducted to identify primary denitrification factors for preliminary feature selection. Then

the combined feature extraction algorithm—MRX-SynFilter algorithm was employed to select highly correlated variables and remove redundant ones. Subsequently

variable delay times were estimated by data trend analysis combined with the maximal information coefficient (MIC). Next

the BKA was used to search for optimal variable order combinations to complete dynamic data reconstruction

enhancing the model's ability to capture temporal characteristics. Finally

the dynamic model was built on the Transformer-BiGRU network

with network hyperparameters simultaneously optimized by BKA. Experimental results demonstrate that variable selection

delay estimation

and order selection all improve modeling accuracy. The BKA-Transformer-BiGRU model outperforms other comparative models in fitting accuracy and error control

effectively capturing the complex nonlinear dynamic characteristics of the SNCR denitrification system.

关键词

Keywords

references

XIA Zihong, LI Jian, WU Tingting, et al. CFD simulation of MSW combustion and SNCR in a commercial incinerator[J]. Waste Management, 2014, 34(9): 1609-1618.

LI Zhenghui, YAO Shunchun, CHEN Da, et al. Multi-parameter co-optimization for NOx emissions control from waste incinerators based on data-driven model and improved particle swarm optimization[J]. Energy, 2024, 306: 132477.

赵征, 梁磊, 刘赛恒. 基于变量选择和POA-NARX的SNCR脱硝系统出口NOx浓度动态软测量模型[J]. 动力工程学报, 2025, 45(4): 592-601. ZHAO Zheng, LIANG Lei, LIU Saiheng. Dynamic soft measurement model of NOx concentration at the outlet of SNCR denitrification system based on variable selection and POA-NARX[J]. Journal of Chinese Society of Power Engineering, 2025, 45(4): 592-601.

刘定平, 吴泽豪. 水泥分解炉SNCR脱硝系统的深度强化学习多目标优化控制研究[J]. 中国电机工程学报, 2024, 44(12): 4815-4825. LIU Dingping, WU Zehao. Research on deep reinforcement learning multi-objective optimization control of SNCR denitration system of cement calciner[J]. Proceedings of the CSEE, 2024, 44(12): 4815-4825.

XU Qingquan, HAO Xiaochen, SHI Xin, et al. Control of denitration system in cement calcination process: a novel method of deep neural network model predictive control[J]. Journal of Cleaner Production, 2022, 332: 129970.

杨国田, 刘凯, 王英男. 基于门控循环单元神经网络的NOx排放量预测[J]. 控制工程, 2022, 29(7): 1204-1209. YANG Guotian, LIU Kai, WANG Yingnan. Prediction of NOx emissions prediction based on gated recurrent unit neural network[J]. Control Engineering of China, 2022, 29(7): 1204-1209.

BAO Gengyi, LIU Xinhua, ZOU Bosong, et al. Collaborative framework of Transformer and LSTM for enhanced state-of-charge estimation in lithium-ion batteries[J]. Energy, 2025, 322: 135548.

SUN Rongli, CHEN Junsheng, LI Benchuan, et al. State of health estimation for Lithium-ion batteries based on novel feature extraction and BiGRU-Attention model[J]. Energy, 2025, 319: 134756.

赵征, 周孜钰, 卢叶, 等. 炉排式垃圾焚烧炉燃烧过程动态建模方法研究[J]. 中国电机工程学报, 2025, 45(11): 4360-4371. ZHAO Zheng, ZHOU Ziyu, LU Ye, et al. Research on dynamic modeling method of waste incinerator combustion process[J]. Proceedings of the CSEE, 2025, 45(11): 4360-4371.

金秀章, 刘岳, 赵文杰, 等. 基于mRMR和MA-RELM的火电厂出口SO2质量浓度预测[J]. 动力工程学报, 2022, 42(7): 664-670, 676. JIN Xiuzhang, LIU Yue, ZHAO Wenjie, et al. Prediction of SO2 mass concentration at outlet of the thermal power plant based on mRMR and MA-RELM[J]. Journal of Chinese Society of Power Engineering, 2022, 42(7): 664-670, 676.

姚宁, 金秀章, 李阳峰. 基于改进鲸鱼算法优化Bi-LSTM的脱硝系统NOx建模[J]. 华北电力大学学报, 2022, 49(6): 76-83. YAO Ning, JIN Xiuzhang, LI Yangfeng. NOx modeling of denitrification system based on Bi-LSTM optimized by improved whale algorithm[J]. Journal of North China Electric Power University, 2022, 49(6): 76-83.

金秀章, 史德金, 乔鹏. 基于平衡优化算法-径向基神经网络的燃煤机组SO2浓度动态软测量模型[J]. 华北电力大学学报, 2025, 52(6): 123-132. JIN Xiuzhang, SHI Dejin, QIAO Peng. Dynamic soft measurement model for SO2 concentration in coal-fired units based on equilibrium optimizer algorithm-radial basis function neural network[J]. Journal of North China Electric Power University, 2025, 52(6): 123-132.

HU Zhifeng, JIANG Enchen, MA Xiaoqian. Numerical simulation on operating parameters of SNCR process in a municipal solid waste incinerator[J]. Fuel, 2019, 245: 160-173.

王琦, 黄璐瑶, 胡万平, 等. 基于IPSO算法的SNCR脱硝系统建模[J]. 山西大学学报(自然科学版), 2023, 46(6): 1322-1330. WANG Qi, HUANG Luyao, HU Wanping, et al. Modeling of SNCR denitration system based on IPSO algorithm[J]. Journal of Shanxi University (Natural Science Edition), 2023, 46(6): 1322-1330.

洪新, 张晓斌, 何骏. 基于支持向量机的垃圾焚烧炉SNCR系统优化控制[J]. 能源研究与信息, 2022, 38(3): 155-160. HONG Xin, ZHANG Xiaobin, HE Jun. Optimized control of selective non-catalytic reduction system in a waste incinerator based on support vector machine[J]. Energy Research and Information, 2022, 38(3): 155-160.

张媛媛, 曲江源, 苏欣欣, 等. 循环流化床燃煤机组SNCR脱硝过程气液传质和反应特性[J]. 化工学报, 2023, 74(6): 2404-2415.ZHANG Yuanyuan, QU Jiangyuan, SU Xinxin, et al. Gas-liquid mass transfer and reaction characteristics of SNCR denitration in CFB coal-fired unit[J]. CIESC Journal, 2023, 74(6): 2404-2415.

FAN Yuchen, LIU Xin, ZHANG Chaoqun, et al. Dynamic prediction of boiler NOx emission with graph convolutional gated recurrent unit model optimized by genetic algorithm[J]. Energy, 2024, 294: 130957.

WANG Zhi, ZHOU Huaichun, PENG Xianyong, et al. A predictive model with time-varying delays employing channel equalization convolutional neural network for NOx emissions in flexible power generation[J]. Energy, 2024, 306: 132495.

LIN Yuhao, YAN Wei, ZHANG Yi, et al. Emergency drug demand forecasting in earthquakes with XGBoost and AFT-LSTM[J]. Sustainability, 2025, 17(5): 1910.

MA Shuaiyin, LIU Yuyang, LIU Yang, et al. Artificial intelligence-enabled predictive energy saving planning of liquid cooling system for data centers[J]. Advanced Engineering Informatics, 2025, 65: 103283.

REN Dongfeng, HU Qian, ZHANG Tengda. EKLT: Kolmogorov-Arnold attention-driven LSTM with Transformer model for river water level prediction[J]. Journal of Hydrology, 2025, 649: 132430.

JIANG Zheyong, TAN Qingmei, LI Nan, et al. A novel BiGRU multi-step wind power forecasting approach based on multi-label integration random forest feature selection and neural network clustering[J]. Energy Conversion and Management, 2024, 319: 118904.

WANG Jun, WANG Wenchuan, HU Xiaoxue, et al. Black-winged kite algorithm: a nature-inspired meta-heuristic for solving benchmark functions and engineering problems[J]. Artificial Intelligence Review, 2024, 57(4): 98.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dynamic Soft Measurement Model of NOx Concentration at the Outlet of SNCR Denitrification System Based on Variable Selection and POA-NARX

Short-term Prediction of PV Power Based on BSimilar Optimized PTransformer

VMD-Transformer Prediction Model of SO2 Emission Concentration Based on WOA in Circulating Fluidized Bed Boiler

Main Steam Temperature Prediction for Waste Incinerator Based on IGRA and CNN-LSTM

Research on the Application of Singular Value Decomposition in Early Friction Fault Diagnosis

Related Author

ZHAO Zheng

LIANG Lei

LIU Saiheng

张文广

蔡浩

刘科

孙盼荣

PENG Tongchao

Related Institution

华北电力大学新能源电力系统全国重点实验室

华北电力大学控制与计算机工程学院

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources(North China Electric Power University)

Key Laboratory for Thermal Science and Power Engineering of Ministry of Education(Department of Energy and Power Engineering, Tsinghua University)

Baoding Key Laboratory of State Detection and Optimization Regulation for Integrated Energy System

AI问答

⁰