Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
机械与能源工程     
循环流化床入炉垃圾热值软测量
尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军
1.浙江大学 能源清洁利用国家重点实验室,浙江 杭州 310027； 
2. 杭州萧山锦江绿色能源有限公司,浙江 杭州 311203
Soft measurement of heating value of burning municipal solid waste for circulating fluidized bed
YOU Hai-hui, MA Zeng-yi, TANG Yi-jun, WANG Yue-lan, ZHENG Lin, YU Zhong, JI Cheng-jun
1. State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China;
2. Hangzhou Xiaoshan Green Energy Co. Ltd, Hangzhou 311203, China
 全文: PDF(1247 KB)   HTML
摘要：

面对城市生活垃圾（MSW）的热值（HVs)难以实时测量的现状,构建基于减法聚类的自适应模糊神经网络(ANFIS)的入炉垃圾热值软测量模型.针对循环流化床（CFB）生活垃圾焚烧炉的工艺特点,选择模型的输入变量；依据专家经验对样本的热值进行模糊分类；利用减法聚类(SC)算法对训练样本进行分析,自适应地确定初始模糊规则和模糊神经网络的初始结构参数；结合最小二乘估计法和误差反向传播算法对模糊神经网络的参数进行学习,构建自适应神经模糊推理系统,完成CFB生活垃圾焚烧锅炉入炉垃圾热值的软测量建模.对比研究BP神经网络、RBF神经网络和支持向量机模型在垃圾热值预测方面的表现,结果表明：基于减法聚类的模糊神经网络模型具有最高的预测精度.预测值和实际垃圾热值的比较结果证明：模糊神经网络模型能够表征垃圾热值的整体变化趋势,可以对循环流化床垃圾焚烧锅炉的运行、控制和管理起到指导作用,并且能够为循环流化床生活垃圾焚烧锅炉的燃烧自动控制（ACC）系统提供可靠的热值反馈信号.
Abstract:

A soft sensor was developed to estimate the heating values (HVs) of burning municipal solid waste (MSW) based on adaptive neuro-fuzzy inference system in order to overcome the difficulty that there is no reliable real time instrument to measure HVs. The input variables of the model were selected by analyzing the operational mechanism of the circulating fluidized bed incinerator (CFBI); the HV of burning MSW was classified into one of nine fuzzy expressions with the aid of expert experience; the subtractive clustering (SC) algorithm was adopted to determine the initial membership functions (MFs) by partitioning the training samples and extracting a set of fuzzy rules; the adptive neuro-fuzzy inference system (ANFIS) model was trained with gradient decent method and least square method. Moreover, the performance of SC-ANFIS model was compared with other different HV forecasting models, including multilayer perceptron (MLP) neural network, radial basis function (RBF) neural network, and support vector machine (SVM). Results indicate that the SC-ANFIS based HV forecasting model has the best performance. The predictive HVs of SC-ANFS model were compared with measured HVs likewise, which demonstrates that the SC-ANFIS HVs soft sensor can reflect the overall trend of HVs accurately; such a model will contribute to the control of CFBIs operation and provide reliable HV signals for automatic combustion control (ACC) system.
出版日期: 2017-06-11
CLC:  TK 229.91  
基金资助:

国家环境保护公益项目（201503013）.
通讯作者: 马增益，男，教授. ORCID: 0000-0002-4504-6198.     E-mail: mazy@zju.edu.cn
作者简介: 尤海辉（1989—），男，博士生，从事循环流化床生活垃圾焚烧系统建模与控制研究. ORCID: 0000-0002-8892-4747. E-mail：hsyouhaihui@126.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　

引用本文:

尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2017.06.014.

YOU Hai-hui, MA Zeng-yi, TANG Yi-jun, WANG Yue-lan, ZHENG Lin, YU Zhong, JI Cheng-jun. Soft measurement of heating value of burning municipal solid waste for circulating fluidized bed. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2017.06.014.

参考文献(References)：
［1］  马攀，马增益，陈继华，等. 循环流化床垃圾焚烧炉混烧羊毛脂废料试验研究［J］. 中国电机工程学报，2012，32(8): 6-11.
MA Pan, MA Zeng-yi, CHEN Ji-hua, et al. Experimental study on co-firing of lanolin waste and municipal solid waste in a circulating fluidized bed incinerator ［J］. Proceedings of the CSEE, 2012, 32(8): 6-11.
［2］ 曹玉林，严建华，李晓东，等. 垃圾与煤流化床混烧及其排放特性［J］. 热力发电，2005, 34(11): 57-63.
CAO Yu-lin, YAN Jian-hua, LI Xiao-dong, et al. Study on co-firing of coal and MSW and emission performance in a circulating fluidized bed incinerator ［J］. Thermal Power Generation, 2005, 34(11): 57-63.
［3］ 中国环境保护产业协会城市生活垃圾处理专业委员会. 城市生活垃圾处理行业2014年发展综述［J］. 中国环保产业，2015, 11：17-24.
Specialized Committee of Urban Domestic Refuse of CAEPI. Development report on China treatment industry of urban domestic refuse in 2013 ［J］. China Environmental Protection Industry, 2015, 11: 17-24.
［4］ ZHOU H, MENGA, LONG Y, et al. An overview of characteristics of municipal solid waste fuel in China: physical, chemical composition and heating value ［J］. Renewable and Sustainable Energy Reviews, 2014, 36: 107-122.
［5］ LIUKKONEN M, HILTUNEN T, HLIKK E, et al. Modeling of the fluidized bed combustion process and NOx emissions using selforganizing maps: an application to the diagnosis of process states ［J］. Environmental Modelling and Software, 2011, 26(5): 605-614.
［6］ 沈凯. 垃圾焚烧炉自适应控制策略及热值监测模型研究［D］.武汉：华中科技大学，2005： 77-79.
SHEN Kai. Study on the adaptive control strategy of incinerators and the monitoring model of heating values ［D］. Wuhan: Huazhong University of Science and Technology, 2005: 77-79.
［7］ 谢承利，陆继东，沈凯，等.基于焚烧运行参数的垃圾热值软测量模型［J］.燃烧科学与技术，2007, 13（1）： 81-85.
XIE Cheng-li, LU Ji-dong, SHEN Kai, et al. Indirect measurement model for waste heating value based on incineration operational parameters ［J］. Journal of Combustion Science and Technology, 2007, 13(1): 81-85.
［8］ MCCAULEY B, REINHART D, SEIR H, et al. Municipal solid waste composition studies ［J］. ASCE Practice Periodical of Hazardous and Radioactive Waste, 1997, 1(4): 158-163.
［9］ DAVID C, BRAINK K, JOHN M. Estimating the lower heating values of hazardous and solid wastes ［J］. Air and Waste Manage Association, 1999, 49(4): 471-476.
［10］ LIN X, WANG F, CHI Y, et al. A simple method for predicting the lower heating value of municipal solid waste in China based on wet physical composition ［J］. Waste Management, 2105, 36: 24-32.
［11］ Moh’d A, Hani A, Abu Q. Energy content of municipal solid waste in Jordan and its potential utilization ［J］. Energy Conversation and Management, 2000, 41: 983-991.
［12］ CHANG Y, LIN C, CHAN J, et al. Multiple regression models for the lower heating value of municipal solid waste in Taiwan ［J］. Journal of Environmental Management, 2007, 85: 891-899.
［13］ EBRU A, AHMET D. Energy content estimation of municipal solid waste by multiple regression analysis ［C］ ∥ 5th International Advanced Technologies Symposium. Turkery: ［s. n.］ 2009.
［14］ DONG C, JIN B, LI D. Predicting the heating value of MSW with a feed forward neural network ［J］. Waste Management, 2003, 23: 103-106.
［15］ HEIKKINEN M, HILTUNEN T, LIUKKONEN M, et al. A modelling and optimization and optimization system for fluidized bed power plants ［J］. Expert Systems with Applications, 2009, 36(7): 10247-10279.
［16］ YILMAZ I, KAYNAR O. Multiple regression, ANNRBF, MLP and ANFIS models for prediction of swell potential of clay soils ［J］. Expert Systems with Applications, 2011, 38(5): 5958-5966.
［17］ MOGHADDAMNIA A, REMESAN R, HASSANPOUR M., et al. Comparison of LLR, MLP, Elman, NNARX and ANFIS Models-with a case study in solar radiation estimation ［J］. Journal of Atmospheric and SolarTerrestrial Physics, 2009, 71(8): 975-982.
［18］ ROOLHOLLAH N, GHOLAMALI H, KHOSRO A, et al. Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration ［J］. Atmospheric Environment, 2010, 444): 476-482.
［19］ ZHANG Y, ZHOU Q, SUN C, et al. RBF neural network and ANFIS-based short-term load forecasting approach in real-time price environment ［J］. IEEE Transactions on Power Systems, 2008, 23(3): 853-858.
［20］ YANG S, Ross S. Comparison of support vector machine, neural network and CART algorithms for the land-cover classification using limited training data points ［J］. ISPRS Journal of Photogrammetry andremote sensing, 2012, 70: 78-87.
［21］ YILMAZ I. Comparison of landslide susceptibility mapping methodologies for Kouyulhisar, Turkey: conditional probability, logistic regression, artificial neural networks and support vector machine ［J］. Environmental Earth Sciences, 2010, 614): 821-836.
［22］ 潘海鹏，吕勇松. 时滞系统的模糊神经网络补偿控制［J］. 浙江大学学报：工学版，2010，44（7）: 1343-1347.
Pan Hai-peng, LV Yong-song. Fuzzy neural network control method with compensation for timedelay system ［J］. Journal of Zhejiang University：Engineering Science, 2010, 44(7): 1343-1347.
［23］ CHEN M. A hybrid ANFIS model for business failure prediction utilizing particle swarm optimization and subtractive clustering ［J］. Information Science, 2013, 220, 180-195.
［24］ 李培强，李欣然，陈辉华，等. 基于减法聚类的模糊神经网络负荷建模［J］. 电工技术学报，2006，21（9）： 2-6.
LI Pei-qiang, LI Xin-ran, CHEN Hui-hua, et al. Fuzzy neural network load modeling based on subtractive clustering ［J］. Transactions of China Electrotechnical Society, 2006, 2(19): 2-6.
［25］ HOSSEIN A, TAGHANNSKI S, MASOUND K, et al. Implementing ANFIS for prediction of reservoir oil solution gas-oil ratio ［J］. Journal of Natural Gas Science and Engineering, 2015, 15: 325-334.
［26］ CHIU S. Fuzzy model identification based on cluster estimation ［J］. Journal of Intelligent and Fuzzy Systems, 1994, 2: 267-278.
［27］ JANG J. ANFIS: adaptive-network-based fuzzy inference system ［J］. IEEE Transactions on Systems, Man and Cybernetics, 1993, 2(33): 665-685.
［28］ 闫涛. 循环流化床焚烧炉中生活垃圾燃烧特性研究［D］.北京：清华大学，2004: 44-49.
YAN Tao. Research on combustion characteristics of municipal solid waste in circulating fluidized bed incinerator ［D］.Beijing: Tsinghua University, 2004: 44-49.
［29］ 刘青，于海洋，张守玉，等. 循环流化床垃圾焚烧锅炉炉膛设计分析［J］. 锅炉技术，2007,38（6）： 20-25.
LIU Qing, YU Hai-yang, ZHANG Shou-yu, et al.Analysis for the design of circulating fluidized bed incinerator furnace ［J］. Boiler Technology, 2007, 38(6):20-25.
［30］ 徐旭常，周力行. 燃烧技术手册［M］. 北京：化学工业出版社，2008: 578581.
［31］ 江爱鹏. 城市生活垃圾典型组分的燃烧特性和排放特性研究［D］. 杭州：浙江大学，2002： 43-58.
JIANG Ai-peng. Research on combustion characteristics and emission performance of typical municipal solid waste components in circulating fluidized bed incinerator ［D］. Hangzhou: Zhejiang University, 2002: 43-58.
［32］ 张衍国，李海明，李海清，等. 垃圾焚烧炉内传热计算［J］.清华大学学报： 自然科学版，2001，41（21）： 95-98.
ZHANG Yan-guo, LI Hai-ming, LI Hai-qing, et al. Heat transfer in a municipal solid waste incinerator ［J］. Journal of Tsinghua University: Natural ScienceEdition, 2001, 41(21): 95-98.
［33］ 张轩. 大型循环流化床床温动态模型与优化控制的研究［D］.北京：华北电力大学，2013:15-16.
ZHANG Xuan. Research on dynamic modeling and optimization control on the bed temperature of circulating fluidized bed Boiler ［D］. Beijing: North China Electric Power University, 2013: 15-16.
［34］ CJJ/T 1372010. 生活垃圾焚烧厂评价标准［S］. 北京：中华人民共和国住房和城乡建设部，2010.
［35］ SAITO M, AMGAI K, OGIWARA G., et al. Combustion characteristics of waste material containing high moisture ［J］. Fuel, 2001, 8(9): 1201-1209.
［36］ 董长青，金保升，仲兆平，等. 循环流化床掺烧生活垃圾实验研究［J］. 东南大学学报：自然科学版，2002,3(21)：  95-99.
DONG Chang-qing, JIN Bao-sheng, ZHONG Z-ping, et al. Experimental study on the co-firing of municipal refuse in a circulating fluidized bed ［J］. Journal of Southeast University：Natural Science Edition, 2002,3(21): 95-99.
［37］ LIUKKONEN M, HLIKK E, HILTUNNEN T, et al. Dynamic soft sensors for NOx emissions in a circulating fluidized bed boiler ［J］. Applied Energy, 2012, 97: 483-490.
［38］ BUYUKDA M. Co-combustion of peanut hull and coal blends: artificial neural networks modelling, particle swarm optimization and Monte Carlo simulation［J］. Bioresource Technology, 2016, 216: 280-286.
［39］ 李清毅，周昊，林阿平，等.基于网格搜索和支持向量机的灰熔点预测［J］. 浙江大学学报：工学版，2011,54（12）： 2181-2187.
LI Qing-yi, ZHOU Hao, LIN A-ping, et al. Prediction of ash fusion temperature based on grid search and support vector machine ［J］. Journal of Zhejiang University：Engineering Science, 2011,45(2): 2181-2187.
［40］ 赵志刚，张纯杰，苟向锋，等. 基于粒子群优化支持向量机的太阳电池温度预测［J］. 物理学报，2015，64（8）：1-7.
ZHAO Zhi-gang, ZHANG Chun-jie, GOU Xiang-feng, et al. Solar cell temperature prediction model of support vector machine optimized by particle swarm optimization algorithm ［J］. Acta Physica Sinica, 2015,64(8):1-7.
［41］ 王德明，王莉，张广明. 基于遗传BP神经网络的短期风速预测模型［J］. 浙江大学学报：工学版，2012,46（5）： 837-841.
WANG De-ming, WANG Li, ZHANG Guang-ming. Short-term wind speed forecast model for wind farms based on genetic BP neural network ［J］. Journal of Zhejiang University：Engineering Science, 2012， 46(5): 837-841.
No related articles found!