Neural Network-based Improved Active Disturbance Rejection Control Strategy for Superheated Steam Temperature

CHANG Yaohua; WEI Genyuan; ZHAO Shen; CHEN Liang

doi:10.19805/j.cnki.jcspe.2025.240256

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Neural Network-based Improved Active Disturbance Rejection Control Strategy for Superheated Steam Temperature

更新时间：2026-10-10

- Neural Network-based Improved Active Disturbance Rejection Control Strategy for Superheated Steam Temperature
- Chinese Journal of Power Engineering Vol. 45, Issue 6, Pages: 887-894(2025)
- 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.2025.240256
  CLC：
- Online First：16 June 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
常耀华,韦根原,赵深,陈亮. 基于神经网络的过热汽温改进自抗扰控制策略动力工程学报, 2025, 45(6): 887-894 https://doi.

org/10.19805/j.cnki.jcspe.2025.240256
常耀华,韦根原,赵深,陈亮. 基于神经网络的过热汽温改进自抗扰控制策略动力工程学报, 2025, 45(6): 887-894 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240256.

org/10.19805/j.cnki.jcspe.2025.240256 DOI：

摘要

针对过热汽温系统高阶大惯性、多扰动的问题

提出了一种基于BP神经网络的超前补偿模型辅助线性自抗扰控制(BP-LMLADRC) 。在二阶线性自抗扰控制的基础上

在前馈通路和反馈通路分别串联前馈补偿器和超前补偿器

从而解决低阶线性扩张状态观测器前馈信号和反馈信号不同步以及扰动响应滞后的问题;在此基础上

根据闭环系统传递函数表达式

分析系统稳态性能和闭环参数稳定域

推导出参数调节区间

简化参数整定过程

进一步采用BP神经网络得出最优带宽;最后

将所提出的控制策略应用于过热汽温控制系统

并与多种控制器性能进行对比。结果表明:对于过热汽温系统这类高阶大惯性系统

所提出的控制策略在定值跟踪、抗干扰和鲁棒性上具有明显优势。

Abstract

Concerning the problem of high-order large inertia and multiple disturbance in superheated steam temperature system

a linear active disturbance rejection control based on BP neural network assisted by lead compensation model was proposed. Based on second-order linear active disturbance rejection control

a feedforward compensator and a lead compensator were connected in series in the feedforward and feedback paths

respectively

to solve the problems of asynchrony of feedforward and feedback signals and delay of disturbance response in low order linear extended state observers. On this basis

according to the expression of closed-loop system transfer function

the steady-state system performance and the stable domain of closed-loop parameters were analyzed

the parameter adjustment interval was derived

the parameter tuning process was simplified

and BP neural network was further used to obtain the optimal bandwidth. Finally

the proposed control strategy was applied to superheated steam temperature control system and compared the performance with various controllers. Results show that the proposed control strategy has significant advantages in fixed value tracking

disturbance resistance

and robustness for high-order large inertia systems such as superheated steam temperature system.

关键词

Keywords

references

HUANG Congzhi, SHENG Xinxin. Data-driven model identification of boiler-turbine coupled process in 1000 MW ultra-supercritical unit by improved bird swarm algorithm[J]. Energy, 2020, 205: 118009.

MAZALAN N A, MALEK A A, WAHID M A, et al. Review of control strategies employing neural network for main steam temperature control in thermal power plant[J]. Jurnal Teknologi, 2014, 66(2): 73-76.

王天堃. 火电厂主蒸汽温度UMDA整定模糊PID控制算法[J]. 动力工程学报, 2017, 37(7): 546-551, 557. WANG Tiankun. Fuzzy self-tuning PID control of main steam temperature in thermal power boilers based on UMDA[J]. Journal of Chinese Society of Power Engineering, 2017, 37(7): 546-551, 557.

WU Zhenlong, LI Donghai, WANG Lingmei. Control of the superheated steam temperature: a comparison study between PID and fractional order PID controller[C]//2016 35th Chinese Control Conference. Chengdu: IEEE, 2016: 10521-10526.

WU Xiao, SHEN Jiong, LI Yiguo, et al. Fuzzy modeling and predictive control of superheater steam temperature for power plant[J]. ISA Transactions, 2015, 56: 241-251.

TONG Zheming, CHEN Xin, TONG Shuiguang, et al. Dense residual LSTM-attention network for boiler steam temperature prediction with uncertainty analysis[J]. ACS Omega, 2022, 7(13): 11422-11429.

陈祎璠, 曹越, 司风琪. 燃煤机组过热汽温宽负荷模型前馈控制[J]. 动力工程学报, 2024, 44(1):76-83. CHEN Yifan, CAO Yue, SI Fengqi. Feedforward control of superheated steam temperature with wide load model for coal-fired units[J]. Journal of Chinese Society of Power Engineering, 2024, 44(1):76-83.

韩京清. 自抗扰控制器及其应用[J]. 控制与决策, 1998(1): 19-23. HAN Jingqing. Auto-disturbances-rejection controller and its applications[J]. Control and Decision, 1998(1): 19-23.

郭伟, 石波, 张益林. 加速器驱动次临界系统堆芯功率的自抗扰控制[J]. 动力工程学报, 2022, 42(3): 242-248. GUO Wei, SHI Bo, ZHANG Yilin. Active disturbance rejection control of core power for accelerator driven subcritical systems[J]. Journal of Chinese Society of Power Engineering, 2022, 42(3): 242-248.

GAO Zhiqiang. Scaling and bandwidth-parameterization based controller tuning[C]//Proceedings of the American Control Conference. Denver, CO, USA: IEEE, 2003: 4989-4996.

高强, 刘新鹏, 刘春平, 等. 四旋翼无人机串级自抗扰姿态控制及轨迹跟踪[J]. 电光与控制, 2023, 30(3): 90-95. GAO Qiang, LIU Xinpeng, LIU Chunping, et al. Cascaded active disturbance rejection attitude control and trajectory tracking of quadrotor UAV[J]. Electronics Optics & Control, 2023, 30(3): 90-95.

MADONSKI R, SHAO S, ZHANG H, et al. General error-based active disturbance rejection control for swift industrial implementations[J]. Control Engineering Practice, 2019, 84: 218-229.

SUN Li, XUE Wenchao, LI Donghai, et al. Quantitative tuning of active disturbance rejection controller for FOPTD model with application to power plant control[J]. IEEE Transactions on Industrial Electronics, 2022, 69(1): 805-815.

ZHENG Qinling, GAO Zhiqiang. Predictive active disturbance rejection control for processes with time delay[J]. ISA Transactions, 2014, 53(4): 873-881.

王佑, 吴振龙, 薛亚丽, 等. 高阶大惯性系统的线性自抗扰控制器设计[J]. 控制与决策, 2023, 38(4): 999-1007. WANG You, WU Zhenlong, XUE Yali, et al. Design of linear active disturbance rejection controller for high-order large inertia system[J]. Control and Decision, 2023, 38(4): 999-1007.

CHEN Zhuo, HAO Yongsheng, SUN Li, et al. Phase compensation based active disturbance rejection control for high order superheated steam temperature system[J]. Control Engineering Practice, 2022, 126: 105200.

CONG Mengxin, ZHAO Tong. Active disturbance rejection trajectory tracking control of manipulator based on neural network[C]//2020 Chinese Control and Decision Conference (CCDC). Hefei: IEE, 2020: 1732-1737.

牛海明, 于佼, 丁常富, 等. 基于多目标粒子群算法的过热汽温自抗扰控制[J]. 中国电力, 2020, 53(3): 126-133. NIU Haiming, YU Jiao, DING Changfu, et al. Active disturbance rejection control over superheated steam temperature based on multi-objective particle swarm optimization[J]. Electric Power, 2020, 53(3): 126-133.

HE Ting, WU Zhenlong, LI Donghai, et al. A tuning method of active disturbance rejection control for a class of high-order processes[J]. IEEE Transactions on Industrial Electronics, 2020, 67(4): 3191-3201.

SKOGESTAD S, GRIMHOLT C. The SIMC method for smooth PID controller tuning[M]//VILANOVA R, VISIOLI A. PID Control in the Third Millennium. London: Springer, 2012: 147-175.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Optimal Scheduling Method for Source-Grid- Load-Storage Systems Considering Electro-Thermal Load Demands in Industrial Parks

Research on Key Technologies of Medium and High Temperature Thermochemical Heat Storage

Optimized Scheduling of Virtual Power Plant Considering Coal-biomass Co-firing Carbon Capture and Low Carbon Incentive Mechanism

Reduced-order Model for Solution of Cascade Flow Field Based on Physical Model and Machine Learning

Double-layer Coordination Economic and Real-time Dispatching Strategy for Large-scale Energy Base

Related Author

WANG Yan

GAO Jianqiang

LI Zheng

XUE Yali

WANG You

ZHANG Yong

BAO Zhe

WANG Xu

Related Institution

School of Energy, Power and Mechanical Engineering, North China Electric Power University

Guoneng Bengbu Power Generation Co., Ltd.

State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment,Department of Energy and Power Engineering, Tsinghua University

Shanxi Research Institute For Clean Energy, Tsinghua University

College of Environmental Science and Engineering, North China Electric Power University

AI问答

⁰