基于复合加权人类学习网络的超超临界机组建模与仿真

doi:10.16182/j.issn1004731x.joss.22-0259

系统仿真学报 ›› 2022, Vol. 34 ›› Issue (7): 1430-1438.doi: 10.16182/j.issn1004731x.joss.22-0259

• 专栏：电力和能源自动化仿真 • 上一篇下一篇

基于复合加权人类学习网络的超超临界机组建模与仿真

程传良¹(), 彭晨¹(), 曾德良², 张腾飞³

^1.上海大学机电工程与自动化学院, 上海 200444
^2.华北电力大学控制与计算机工程学院, 北京 102206
^3.南京邮电大学自动化学院和人工智能学院, 江苏南京 210023

收稿日期:2022-03-25 修回日期:2022-04-27 出版日期:2022-07-30 发布日期:2022-07-20
通讯作者: 彭晨 E-mail:chengch1017@163.com;c.peng@shu.edu.cn
作者简介:程传良（1989-），男，博士生，研究方向为燃煤发电系统建模与优化控制。E-mail：chengch1017@163.com
基金资助:
国家自然科学基金(61833011)

Modeling and Simulation of Ultra Supercritical Unit Using A Composite Weighted Human Learning Network

Chuanliang Cheng¹(), Chen Peng¹(), Deliang Zeng², Tengfei Zhang³

^1.School of Mechanical and Electrical Engineering and Automation, Shanghai University, Shanghai 200444, China
^2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
^3.College of Automation and College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing 210023, China

Received:2022-03-25 Revised:2022-04-27 Online:2022-07-30 Published:2022-07-20
Contact: Chen Peng E-mail:chengch1017@163.com;c.peng@shu.edu.cn

摘要/Abstract

摘要：

中间点温度是超超临界（ultra supercritical， USC）机组的一个重要参数，其系统具有强非线性，常规方法很难对其进行建模。为了解决非线性问题，并获得良好的建模效果，提出了一种基于复合加权人类学习优化网络（composite weighted human learning optimization network， CWHLON）的建模方法，以动态线性模型的形式来模拟对象的非线性动态过程。在仿真实验部分，将CWHLON模型与传统的递推最小二乘法和其他三种元启发式方法得到的模型进行综合比较，数据显示本文提出的方法在模型精度方面平均提高了77.93%，最大提高了78.65%，实现了辨识精度的有效提升。

关键词: 中间点温度, 强非线性, 建模, 复合加权人类学习优化网络, 超超临界机组

Abstract:

Intermediate point temperature is an important parameter in ultra supercritical (USC) unit. However, due to strong nonlinearity, it is difficult to determine the form and coefficients of the corresponding model by using traditional methods. In order to get a better control effect, a novel composite weighted human learning optimization network (CWHLON) is proposed to tackle the above-mentioned problems. Though the real-time dynamic linear model, the characteristics of the object are accurately simulated. In the simulation experiment, CWHLON is compared with the traditional recursive least squares and other three meta heuristic methods. The data show that the proposed method improves the model accuracy by 77.93% on average and 78.65% on maximum, effectively improving the identification accuracy.

Key words: intermediate point temperature, strong nonlinearity, modeling, CWHLON, USC

中图分类号:

TP391.9

程传良, 彭晨, 曾德良, 张腾飞. 基于复合加权人类学习网络的超超临界机组建模与仿真[J]. 系统仿真学报, 2022, 34(7): 1430-1438.

Chuanliang Cheng, Chen Peng, Deliang Zeng, Tengfei Zhang. Modeling and Simulation of Ultra Supercritical Unit Using A Composite Weighted Human Learning Network[J]. Journal of System Simulation, 2022, 34(7): 1430-1438.

图/表 10

图1

图2

图3

图4

图5

表1

图6

表2

图7

表3

参考文献 23

1	王建录, 张晓东, 侯明军. 超超临界二次再热机组汽轮机应用现状与展望[J]. 热力发电, 2017, 46(8): 11-15.
	Wang Jianlu, Zhang Xiaodong, Hou Mingjun. Development and Expectation of Application of Ultra-supercritical Double-reheat Steam Turbines. Thermal Power Generation, 2017, 46(8): 11-15.
2	孙宇贞, 唐毅伟, 李帅. 基于改进粒子群算法的超超临界燃煤机组负荷系统建模[J]. 系统仿真学报, 2021, 33(4): 875-882.
	Sun Yuzhen, Tang Yiwei, Li Shuai. Load System Modeling of Ultra-Supercritical Coal-Fired Power Unit Based on Improved Particle Swarm Optimization [J]. Journal of System Simulation, 2021, 33(4): 875-882.
3	孙燕平, 常永亮, 李振林. 基于SIS的火电机组热工对象数学模型辨识[J]. 仪器仪表用户, 2022, 29(1): 97-99.
	Sun Yanping, Chang Yongliang, Li Zhenlin. Identification of Mathematical Model of Thermal Power Plant's Thermal Object Based on SIS[J]. Instrumentation, 2022, 29(1):97-99.
4	陈琛, 潘蕾, Y Lee Kwang. 超超临界机组机炉协调系统的min-max模糊模型预测跟踪控制[J]. 东南大学学报: 英文版, 2021, 37(1): 42-51.
	Chen Chen, Pan Lei, Y Lee Kwang. Min-max Fuzzy Model Predictive Tracking Control of Boiler-Turbine System for Ultra-Supercritical Units[J]. Journal of Southeast University: English Edition, 2021, 37(1): 42-51.
5	闫姝. 超超临界机组非线性控制模型研究[D]. 北京: 华北电力大学, 2013.
	Yan Shu. A Non-linear Control Model of Ultra-supercritical Unit[D]. Beijing: North China Electric Power University, 2013.
6	熊小伏, 陈康, 郑伟, 等. 基于最小二乘法的光伏逆变器模型辨识[J]. 电力系统保护与控制, 2012, 40(22): 52-57.
	Xiong Xiaofu, Chen Kang, Zheng Wei, et al. Photovoltaic Inverter Model Identification Based on Least Squares Method[J]. Power System Protection and Control, 2012, 40(22): 52-57.
7	吴刘仓, 马婷, 戴琳. 基于StN分布下联合位置与尺度模型的极大似然估计[J]. 应用数学, 2013, 26(3):671-676.
	Wu Liucang, Ma Ting, Dai Lin. Maximum Likelihood Estimation for Joint Location and Scale Models of the Skew-t-normal Distribution[J]. Applied Mathematics, 2013, 26(3): 671-676.
8	李太福,熊隽迪. 基于梯度下降法的自适应模糊控制系统研究[J]. 系统仿真学报, 2007, 19(6): 1265-1268.
	Li Taifu, Xiong Jundi. Time Series Modeling Method based on Boosting Gradient Descent Theory[J]. Journal of System Simulation, 2007, 19(6): 1265-1268.
9	梁庆姣, 刘吉臻, 薛彦广, 等. 超超临界直流炉核心模型的建立与仿真分析[J]. 计算机仿真, 2012, 29(3): 338-343.
	Liang Qingjiao, Liu Jizhen, Xue Yanguang, et al. Establishment and Simulation Analysis of Core Modelfor Ultra-supercritical Once-through boiler[J]. Computer Simulation, 2012, 29(3): 338-343.
10	Cheng Chuanliang, Peng Chen, Zhang Tengfei. Fuzzy K-means Cluster Based Generalized Predictive Control of Ultra Supercritical Power Plant[J]. IEEE Transactions on Industrial Informatics (S1941-0050), 2021, 17(7): 4575-4583.
11	Wang L, Ni H, Yang. A Simple Human Learning Optimization Algorithm [J]. Communications in Computer and Information Science (S1865-0937), 2014, 462: 56-65.
12	Wang L, Yang R X. A Human Learning Optimization Algorithm and Its Application to Multi-dimensional Knapsack Problems[J]. Applied Soft Computing (S2666-2221), 2015, 34: 736-743.
13	Cao J, Yan Z, Xu X, et al. Optimal Power Flow Calculation in AC/DC Hybrid Power System Based on Adaptive Simplified Human Learning Optimization Algorithm [J]. Journal of Modern Power Systems & Clean Energy (S2196-5625), 2016, 4(4): 690-701.
14	Wang L, An L, Pi J, et al. A Diverse Human Learning Optimization Algorithm[J]. Journal of Global Optimization (S1573-2916), 2017, 67(1/2): 1-41.
15	杨硕, 张悦. 基于改进广义预测控制的过热蒸汽温度优化[J]. 电力科学与工程, 2021, 37(12):47-56.
	Yang Shuo, Zhang Yue. Optimal Temperature Control of Superheated Steam in Boiler Based on Improved GPC[J]. Electric Power Science and Engineering, 2021, 37(12):47-56.
16	唐飞, 董斌, 赵敏. 超超临界机组在我国的发展及应用[J]. 电力建设, 2010, 3(1): 80-82.
	Tang Fei, Dong Bin, Zhao Min. USC Unit Development and Application in China[J]. Electric Power Construction, 2010, 3(1): 80-82.
17	杨敏, 牟文彪, 陆陆, 等. 一种RB工况下超临界机组主蒸汽温度控制策略[J]. 电力科学与工程, 2020, 36(7):61-67.
	Yang Min, Mou Wenbiao, Lu Lu, et al. A Main Steam Temperature Control Strategy of Supercritical Unit Under RB Condition[J]. Power science and Engineering, 2020, 36(7): 61-67.
18	梁伟平, 鲍鹏凯. 基于PCA-RF直流炉中间点温度预测控制[J]. 仪器仪表用户, 2021, 28(7): 86-89.
	Liang Weiping, Bao Pengkai. Based on PCA-RF DC Furnace Temperature Prediction Control[J]. Instrumentation, 2021, 28(7): 86-89.
19	梁伟平, 王文成, 张旭. 基于中间点温度前馈的主汽温模糊PID控制系统[J]. 电力科学与工程, 2019, 35(1):71-77.
	Liang Weiping, Wang Wencheng, Zhang Xu. Fuzzy-PID Control System of Main Steam Temperature Based on Intermediate Point Temperature Feedforward[J]. Electric Power Science and Eingineering, 2019, 35(1): 71-77.
20	杨启文, 阳外玲, 薛云灿, 等. 基于Maclaurin展开的时间绝对误差积分次优时滞系统设计[J]. 控制理论与应用, 2011, 28(12): 1831-1836.
	Yang Qiwen, Yang Wailing, Xue Yuncan, et al. Design of Integral Time Absolute Error Suboptimal Time-Delay System Based on Maclaurin Expansion[J]. Control Theory and Application, 2011, 28(12): 1831-1836.
21	Vb A, Ag A, Mr B, et al. Identification of Fractional Water Transport Model With Caputo Derivatives Using Particle Swarm Optimization Algorithm[J]. Applied Mathematics and Computation (S0096-3003), 2021, 390(1): 125665.
22	Hu W K, Fang Y J. Multimodel Parameters Identification for Main Steam Temperature of Ultra-Supercritical Units Using an Improved Genetic Algorithm[J]. Journal of Energy Engineering (S0733-9402), 2013, 139: 290-298.
23	Zheng T, Liu J, Luo W, et al. Structural Damage Identification Using Cloud Model Based Fruit Fly Optimization Algorithm[J]. Structural Engineering and Mechanics (S1225-4568), 2018, 67(3): 245-254.

算法	区域
算法		1	2	3	4	5	6	7
HLO	平均值	2 115.12	9 796.88	8 626.31	2 844.95	3 372.69	15 180.81	9 456.23
HLO	最优值	2 092.03	9 652.79	8 227.71	2 754.01	3 299.48	14 820.49	8 901.65
GA	平均值	2 183.91	11 151.97	10 507.71	2 952.17	3 507.09	17 059.41	10 104.06
	最优值	2 168.95	10 160.47	9 319.92	2 831.99	3 420.46	15 506.13	9 976.25
	与HLO的对比/%	-3.54	-4.99	-11.71	-2.75	-3.53	-6.66	-10.44
FOA	平均值	2 159.90	10 563.81	10 028.80	3 080.06	3 483.02	16 109.71	9 858.62
	最优值	2 132.61	10 059.84	8 595.51	2 929.17	3 401.07	15 507.88	9 559.49
	与HLO的对比/%	-1.90	-4.04	-4.27	-5.97	-2.98	-6.68	-6.39
PSO	平均值	2 210.42	13 244.72	13 356.23	3 447.11	3 623.23	18 425.82	10 145.52
	最优值	2 159.55	13 169.40	12 265.53	3 438.49	3 612.51	17 318.87	9 995.49
	与HLO的对比/%	-3.12	-26.7	-32.92	-19.90	-8.66	-24.28	-10.63
RLS	平均/最优	2 212.00	13 302.77	17 131.33	3 916.18	4 292.47	20 560.36	10 306.90
RLS	与HLO的对比/%	-5.42	-27.43	-51.97	-29.67	-23.13	-55.79	-13.66

算法	平均值	最优值
CWHLON	28 589.04	28 589.04
HLO	127 332.19	126 686.65
GA	128 905.70	128 187.74
FOA	127 796.35	126 798.73
PSO	129 830.12	127 881.61
RLS	133 919.77	133 919.77

算法	平均值	最优值
CWHLON	7 961.99	7 961.99
HLO	15 482.03	15 360.01
GA	15 666.85	15 391.30
FOA	15 769.38	15 447.75
PSO	16 232.63	15 666.78
RLS	17 975.07	17 975.07

[1]	罗俊仁, 张万鹏, 袁唯淋, 胡振震, 陈少飞, 陈璟. 面向多智能体博弈对抗的对手建模框架[J]. 系统仿真学报, 2022, 34(9): 1941-1955.
[2]	杨正, 向智敏, 马世文. 一种基于可变规则的松耦合实体建模方法[J]. 系统仿真学报, 2022, 34(7): 1506-1511.
[3]	陆承, 靳学胜. 基于Steam VR的交互仿真水枪灭火训练系统设计[J]. 系统仿真学报, 2022, 34(6): 1312-1319.
[4]	倪娜, 何坤金, 朱新成, 陈正鸣. 一种人体肌肉的参数化建模及变形方法研究[J]. 系统仿真学报, 2022, 34(5): 1109-1117.
[5]	古鹏飞, 张霖, 陈真, 叶俊杰. 基于X语言的起飞场景民机协同设计与仿真一体化方法[J]. 系统仿真学报, 2022, 34(5): 929-943.
[6]	刘文正, 张和明. 面向复杂系统运动仿真的信息物理融合建模[J]. 系统仿真学报, 2022, 34(5): 954-963.
[7]	林清泉, 杨佳然, 张和明. 一种基于离散事件系统规范的复杂产品行为模型描述方法[J]. 系统仿真学报, 2022, 34(4): 661-669.
[8]	李伯虎, 柴旭东, 张霖, 卿杜政, 施国强, 林廷宇, 郭丽琴, 杨晨, 谷牧, 贾政轩, 公慧, 唐震. 面向智慧物联网的新型嵌入式仿真技术研究[J]. 系统仿真学报, 2022, 34(3): 419-441.
[9]	施国强, 刘泽伟, 林廷宇, 徐钊, 杨星熠, 郭丽琴, 贾政轩. 面向复杂产品建模与仿真系统的开放式云架构设计[J]. 系统仿真学报, 2022, 34(3): 442-451.
[10]	孙晓安, 栾小丽, 刘飞. 基于智能优化灰色模型的电子固废预测[J]. 系统仿真学报, 2022, 34(3): 536-542.
[11]	张霖, 王昆玉, 赖李媛君, 任磊. 基于建模仿真的体系工程[J]. 系统仿真学报, 2022, 34(2): 179-190.
[12]	李锋, 魏莹. 社会学习和参照点效应对企业产品决策的影响[J]. 系统仿真学报, 2022, 34(2): 234-246.
[13]	王永志, 李振朝, 刘鹏彧, 王慧. 基于能量算子的三维空间实体LOD建模方法[J]. 系统仿真学报, 2022, 34(2): 247-257.
[14]	聂凯, 曾科军, 孟庆海. 基于深度贝叶斯网络学习的不确定性建模方法[J]. 系统仿真学报, 2022, 34(1): 79-85.
[15]	樊长佳, 杜炎秋, 梁笛, 胡凯, 黄葭燕. COVID-19期间上海市应急医疗资源配置建模与仿真[J]. 系统仿真学报, 2022, 34(1): 93-103.

基于复合加权人类学习网络的超超临界机组建模与仿真

Modeling and Simulation of Ultra Supercritical Unit Using A Composite Weighted Human Learning Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 23

相关文章 15

编辑推荐

Metrics

本文评价