城市固废焚烧过程数据驱动建模与自组织控制

丁海旭; 汤健; 乔俊飞

doi:10.16383/j.aas.c220570

城市固废焚烧过程数据驱动建模与自组织控制

doi: 10.16383/j.aas.c220570

丁海旭^{1, 2,},
汤健^{1, 2,},
乔俊飞^{1, 2,}

1.
北京工业大学信息学部北京 100124
2.
智慧环保北京实验室北京 100124

基金项目: 科技创新2030 — “新一代人工智能”重大项目 (2021ZD0112300), 国家自然科学基金创新群体项目 (62021003), 国家科技重大专项 (61890930), 国家自然科学基金(62073006), 北京市自然科学基金(4212032, 4192009)资助

详细信息

作者简介:
丁海旭：北京工业大学信息学部博士研究生. 主要研究方向为城市固废焚烧过程特征建模与智能控制. E-mail: dinghaixu@emails.bjut.edu.cn

汤健：北京工业大学信息学部教授. 主要研究方向为小样本数据建模, 城市固废处理过程智能控制. E-mail: freeflytang@bjut.edu.cn

乔俊飞：北京工业大学信息学部教授. 主要研究方向为智能控制与智能信息处理, 环境感知和保护自动化技术. 本文通信作者. E-mail: adqiao@bjut.edu.cn

计量
- 文章访问数: 4112
- HTML全文浏览量: 303
- PDF下载量: 332
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-12
- 录用日期: 2022-09-01
- 网络出版日期: 2022-10-26
- 刊出日期: 2023-03-20

Data-driven Modeling and Self-organizing Control of Municipal Solid Waste Incineration Process

DING Hai-Xu^{1, 2
,},
TANG Jian^{1, 2
,},
QIAO Jun-Fei^{1, 2
,}

1.
Faculty of Information Technology, Beijing University of Technology, Beijing 100124
2.
Beijing Laboratory of Smart Environmental Protection, Beijing 100124

Funds: Supported by Science and Technology Innovation 2030 — “New Generation Artificial Intelligence” Major Project of China (2021ZD0112300), Innovative Research Group Project of the National Natural Science Foundation of China (62021003), National Science and Technology Major Project of China (61890930), National Natural Science Foundation of China (62073006), and Natural Science Foundation of Beijing (4212032, 4192009)

More Information

Author Bio:
DING Hai-Xu　Ph.D. candidate at the Faculty of Information Technology, Beijing University of Technology. His research interest covers feature modeling and intelligent control of municipal solid waste incineration process

TANG Jian　Professor at the Faculty of Information Technology, Beijing University of Technology. His research interest covers small sample data modeling and intelligent control of municipal solid waste treatment process

QIAO Jun-Fei　Professor at the Faculty of Information Technology, Beijing University of Technology. His research interest covers intelligent control and intelligent information processing, environmental awareness, and protection automation technology. Corresponding author of this paper

摘要

摘要: 城市固废焚烧(Municipal solid waste incineration, MSWI)是处置城市固废(Municipal solid waste, MSW) 的主要手段之一. 中国MSW来源范围广、组分复杂、热值波动大, 其焚烧过程通常依靠人工干预, 这导致MSWI过程智能化水平较低且难以满足日益提升的控制需求. MSWI具有多变量耦合、工况漂移等诸多不确定性特征, 因而难以建立其被控对象模型并设计在线控制器. 针对以上问题, 提出了一种面向MSWI过程的数据驱动建模与自组织控制方法. 首先, 构建了基于多输入多输出Takagi Sugeno 模糊神经网络(Multi-input multi-output Takagi Sugeno fuzzy neural network, MIMO-TSFNN) 的被控对象模型; 然后, 设计了基于多任务学习的自组织模糊神经网络控制器(Multi-task learning self-organizing fuzzy neural network controller, MTL-SOFNNC)用于同步控制炉膛温度与烟气含氧量, 其通过计算神经元的相似度与多任务学习(Multi-task learning, MTL)能力对控制器结构进行自组织调整; 接着, 通过Lyapunov定理对MTL-SOFNNC稳定性进行了证明; 最后, 通过北京市某MSWI厂的过程数据验证了模型与控制器的有效性.
- 城市固废焚烧 /
- 多任务学习 /
- 自组织控制 /
- 数据驱动建模 /
- 模糊神经网络
Abstract: Municipal solid waste incineration (MSWI) is one of the main means to dispose of municipal solid waste (MSW). MSW in China has a wide range of sources, complex components, and large fluctuations in calorific value. Its incineration process usually relies on manual intervention. This will lead to a low degree of intelligence in the MSWI process and it is difficult to meet the increasing control requirements. MSWI has many uncertain characteristics such as multivariable coupling and working condition drift, so it is difficult to build the model of controlled object and design the on-line controller. To solve the above problems, this paper proposes a data-driven modeling and self-organizing control method for MSWI process. Firstly, the model of controlled object based on multi-input multi-output Takagi Sugeno fuzzy neural network (MIMO-TSFNN) is constructed. Secondly, a multi-task learning self-organizing fuzzy neural network controller (MTL-SOFNNC) is designed to synchronously control the furnace temperature and flue gas oxygen content, which can self-organize the structural parameters of the controller by calculating the similarity of neurons and the ability of multi-task learning (MTL). Meanwhile, the stability of MTL-SOFNNC is proved by Lyapunov theorem. Finally, the effectiveness of the model and controller is verified by the process data of an MSWI plant in Beijing.
- Municipal solid waste incineration (MSWI) /
- multi-task learning (MTL) /
- self-organizing control /
- data-driven modeling /
- fuzzy neural network

HTML全文

图 1 MSWI的工艺流程

Fig. 1 MSWI process flow

下载: 全尺寸图片幻灯片

图 2 MIMO-TSFNN模型

Fig. 2 MIMO-TSFNN model

下载: 全尺寸图片幻灯片

图 3 基于MTL-SOFNNC的MSWI控制系统

Fig. 3 MSWI control system based on MTL-SOFNNC

下载: 全尺寸图片幻灯片

图 4 基于MTL-SOFNNC的控制框架

Fig. 4 Control structure based on MTL-SOFNNC

下载: 全尺寸图片幻灯片

图 5 MSWI执行机构和检测设备

Fig. 5 MSWI actuators and detection equipment

下载: 全尺寸图片幻灯片

图 6 模型训练过程的RMSE

Fig. 6 RMSE of the model training process

下载: 全尺寸图片幻灯片

图 7 测试样本拟合效果

Fig. 7 Testing samples fitting effect

下载: 全尺寸图片幻灯片

图 8 MTL-SOFNNC的结构自组织过程

Fig. 8 Self-organizing process of MTL-SOFNNC structure

下载: 全尺寸图片幻灯片

图 9 操作变量的自校正过程

Fig. 9 Self-tuning process of manipulated variables

下载: 全尺寸图片幻灯片

图 10 多变量跟踪控制结果

Fig. 10 Multi-variables control tracking results

下载: 全尺寸图片幻灯片

图 11 多变量跟踪控制误差

Fig. 11 Multi-variables control tracking errors

下载: 全尺寸图片幻灯片

表 1 实验对象的运行范围

Table 1 Operating range of experimental subjects

变量名	运行范围	单位
一次风总流量	40 ~ 100	km³N/h
干燥炉排速度百分比	0 ~ 100	%
二次风流量	0 ~ 30	km³N/h
炉膛温度	850 ~ 1050	℃
烟气含氧量	2 ~ 14	%
主蒸汽流量	65 ~ 85	t/h

下载: 导出CSV

表 2 被控对象建模效果评价

Table 2 Evaluation of modeling effect of controlled object model

被控模型	评价指标		炉膛温度模型	烟气含氧量模型	主蒸汽流量模型
MIMO-TSFNN	训练	RMSE	3.88 ℃	0.30%	0.43 t/h
	训练	APE	0.27%	3.16%	0.45%
	测试	RMSE	4.18 ℃	0.58%	0.49 t/h
	测试	APE	0.31%	6.97%	0.59%

下载: 导出CSV

表 3 MSWI过程多变量控制器性能比较

Table 3 Performance comparison of multi-variable controllers for MSWI process

控制器	神经元个数	炉膛温度				烟气含氧量
控制器	神经元个数	IAE	ISE	$ \bar{\sigma}{\text{%}} $	$\bar{t}_r \;({\rm{s} })$	IAE	ISE	$ \bar{\sigma} {\text{%}}$	$\bar{t}_r\; ({\rm{s} })$
MTL-SOFNNC	10	1.883	28.828	0.39%	23.93	0.151	0.124	3.12%	21.47
M-DSNNC	21	2.379	29.374	0.58%	25.68	0.188	0.150	3.14%	29.47
SOFC	20	2.464	30.229	0.46%	30.43	0.194	0.152	3.92%	29.37
SOTSFNNC	17	2.872	30.414	0.72%	23.38	0.214	0.136	4.13%	27.72
TSFNNC	20	2.854	30.728	0.75%	24.14	0.217	0.151	5.45%	34.77

下载: 导出CSV

参考文献(34)

[1]	《中国城市发展报告》委员会. 中国城市发展报告 2020/2021. 北京: 中国城市出版社, 2021. Editorial Board of China Urban Development Report. China Urban Development Report 2020/2021. Beijing: China City Press, 2021.
[2]	Kaza S, Yao L, Bhadatata P, Woerden F V. What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050. Washington: World Bank Publications, 2018.
[3]	Shah A V, Srivastava V K, Mohanty S S, Varjani S. Municipal solid waste as a sustainable resource for energy production: State-of-the-art review. Journal of Environmental Chemical Engineering, 2021, 9(4): Article No. 105717
[4]	Lu J W, Zhang S, Hai J, Lei M. Status and perspectives of municipal solid waste incineration in China: A comparison with developed regions. Waste Management, 2017, 69: 170-186 doi: 10.1016/j.wasman.2017.04.014
[5]	乔俊飞, 郭子豪, 汤健. 面向城市固废焚烧过程的二噁英排放浓度检测方法综述. 自动化学报, 2020, 46(6): 1063-1089 doi: 10.16383/j.aas.c190005 Qiao Jun-Fei, Guo Zi-Hao, Tang Jian. Dioxin emission concentration measurement approaches for municipal solid wastes incineration process: A survey. Acta Automatica Sinica, 2020, 46(6): 1063-1089 doi: 10.16383/j.aas.c190005
[6]	Korai M S, Mahar R B, Uqaili M A. The feasibility of municipal solid waste for energy generation and its existing management practices in Pakistan. Renewable and Sustainable Energy Reviews, 2017, 72: 338-353 doi: 10.1016/j.rser.2017.01.051
[7]	Bhatt M, Chakinala A G, Joshi J B, Sharma A, Sharma A. Valorization of solid waste using advanced thermo-chemical process: A review. Journal of Environmental Chemical Engineering, 2021, 9(4): Article No. 105434
[8]	Kalyani K A, Pandey K K. Waste to energy status in India: A short review. Renewable and Sustainable Energy Reviews, 2014, 31: 113-120 doi: 10.1016/j.rser.2013.11.020
[9]	Cheng H, Hu Y. Municipal solid waste (MSW) as a renewable source of energy: Current and future practices in China. Bioresource Technology, 2010, 101(11): 3816-3824 doi: 10.1016/j.biortech.2010.01.040
[10]	Chen D, Christensen T H. Life-cycle assessment (EASEWASTE) of two municipal solid waste incineration technologies in China. Waste Management & Research, 2010, 28(6): 508-519
[11]	国家发展改革委. “十四五”城镇生活垃圾分类和处理设施发展规划 [Online], 获取自: https://www.ndrc.gov.cn/xwdt/tzgg/202105/t20210513_1279764.html, May 13, 2021 National Development and Reform Commission. The 14th five-year plan for the development of urban domestic waste classification and treatment facilities [Online], available: https://www.ndrc.gov.cn/xwdt/tzgg/202105/t20210513_1279764.html, May 13, 2021
[12]	Ding H, Tang J, Qiao J. Control methods of municipal solid wastes incineration process: A survey. In: Proceedings of the 40th Chinese Control Conference. Shanghai, China: IEEE, 2021. 662−667
[13]	郭海涛, 汤健, 丁海旭, 乔俊飞. 基于混合数据增强的 MSWI 过程燃烧状态识别. 自动化学报, DOI: 10.16383/j.aas.c210843 Guo Hai-Tao, Tang Jian, Ding Hai-Xu, Qiao Jun-Fei. Combustion states recognition method of mswi process based on mixed data enhancement. Acta Automatica Sinica, DOI: 10.16383/j.aas.c210843
[14]	Pan X, Tang J, Ding H, Duan H, Qiao J. Air volume setting model of municipal solid waste incineration process based on color moment features of combustion flame. In: Proceedings of the China Automation Congress. Kunming, China: IEEE, 2021. 7984−7989
[15]	Meng X, Tang J, Qiao J. NOx emissions prediction with a brain-inspired modular neural network in municipal solid waste incineration processes. IEEE Transactions on Industrial Informatics, 2022, 18(7): 4622-4631 doi: 10.1109/TII.2021.3116528
[16]	柴天佑. 工业人工智能发展方向. 自动化学报, 2020, 46(10): 2005-2012 doi: 10.16383/j.aas.c200796 Chai Tian-You. Development directions of industrial artificial intelligence. Acta Automatica Sinica, 2020, 46(10): 2005-2012 doi: 10.16383/j.aas.c200796
[17]	周平, 赵向志. 面向建模误差PDF形状与趋势拟合优度的动态过程优化建模. 自动化学报, 2021, 47(10): 2402-2411 doi: 10.16383/j.aas.c200001 Zhou Ping, Zhao Xiang-Zhi. Optimized modeling of dynamic process oriented towards modeling error PDF shape and goodness of fit. Acta Automatica Sinica, 2021, 47(10): 2402-2411 doi: 10.16383/j.aas.c200001
[18]	丁进良, 杨翠娥, 陈远东, 柴天佑. 复杂工业过程智能优化决策系统的现状与展望. 自动化学报, 2018, 44(11): 1931-1943 Ding Jin-Liang, Yang Cui-E, Chen Yuan-Dong, Chai Tian-You. Research progress and prospects of intelligent optimization decision making in complex industrial process. Acta Automatica Sinica, 2018, 44(11): 1931-1943
[19]	Ding H, Tang J, Qiao J. MIMO modeling and multi-loop control based on neural network for municipal solid waste incineration. Control Engineering Practice, 2022, 127: Article No. 105280
[20]	Saab S S, Hauser M, Ray A. Multivariable nonadaptive controller design. IEEE Transactions on Industrial Electronics, 2020, 68(7): 6181-6191
[21]	Zhao D, Li F, Rui M A, Zhao G, Huangfu Y. An unknown input nonlinear observer based fractional order PID control of fuel cell air supply system. IEEE Transactions on Industry Applications, 2020, 56(5): 5523-5532 doi: 10.1109/TIA.2020.2999037
[22]	Wang Y, Wang Z, Zou L, Dong H. Multiloop decentralized H∞ fuzzy PID-like control for discrete time-delayed fuzzy systems under dynamical event-triggered schemes. IEEE Transactions on Cybernetics, 2020, 99: 1-13
[23]	Çetin G, Özkaraca O, Keçebaş A. Development of PID based control strategy in maximum exergy efficiency of a geothermal power plant. Renewable and Sustainable Energy Reviews, 2021, 137: Article No. 110623
[24]	Arruda L V R, Swiech M C S, Neves-Jr F, Delgado M R. Um método evolucionário para sintonia de controladores PI/PID em processos multivariáveis. Sba: Controle & Automação Sociedade Brasileira de Automatica, 2008, 19: 1-17
[25]	Han H, Zhang L, Liu H, Qiao J. Multiobjective design of fuzzy neural network controller for wastewater treatment process. Applied Soft Computing, 2018, 67: 467-478 doi: 10.1016/j.asoc.2018.03.020
[26]	Qiao J, Hou Y, Zhang L, Han H. Adaptive fuzzy neural network control of wastewater treatment process with multiobjective operation. Neurocomputing, 2018, 275(31): 383-393
[27]	Dai W, Chai T, Yang S X. Data-driven optimization control for safety operation of hematite grinding process. IEEE Transactions on Industrial Electronics, 2014, 62(5): 2930-2941
[28]	Wan J, Huang M, Ma Y, Guo W, Wang Y, Zhang H, et al. Prediction of effluent quality of a paper mill wastewater treatment using an adaptive network-based fuzzy inference system. Applied Soft Computing, 2011, 11(3): 3238-3246 doi: 10.1016/j.asoc.2010.12.026
[29]	Chen C S. Robust self-organizing neural-fuzzy control with uncertainty observer for MIMO nonlinear systems. IEEE Transactions on Fuzzy Systems, 2011, 19(4): 694-706 doi: 10.1109/TFUZZ.2011.2136349
[30]	Wu H, Qin S, Nie R, Cao J, Gorbachev S. Effective collaborative representation learning for multilabel text categorization. IEEE Transactions on Neural Networks and Learning Systems, 2021, 99: 1-15
[31]	Ku C C, Lee K Y. Diagonal recurrent neural networks for dynamic systems control. IEEE Transactions on Neural Networks, 1995, 6(1): 144-156 doi: 10.1109/72.363441
[32]	Zhang W, Qiao J. Multi-variable direct self-organizing fuzzy neural network control for wastewater treatment process. Asian Journal of Control, 2020, 22(2): 716-728 doi: 10.1002/asjc.1919
[33]	Qiao J, Zhang W, Han H. Self-organizing fuzzy control for dissolved oxygen concentration using fuzzy neural network 1. Journal of Intelligent & Fuzzy Systems, 2016, 30(6): 3411-3422
[34]	乔俊飞, 付文韬, 韩红桂. 基于SOTSFNN的溶解氧浓度控制方法. 化工学报, 2016, 67(3): 960-966 Qiao Jun-Fei, Fu Wen-Tao, Han Hong-Gui. Dissolved oxygen control method based on self-organizing T-S fuzzy neural network. CIESC Journal, 2016, 67(3): 960-966