冷凝器污垢的智能预测方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
冷凝器电力、化工、机械等行业的大型换热设备,是火力发电厂的主要辅助设备之一,它在汽轮机装置的热力循环中起冷源的作用。因此,冷凝器工作性能的好坏对整个汽轮机运行过程中的经济性以及安全性会产生直接的影响。然而,冷凝器一旦投入运行,冷凝管的内部总会产生一些对运行有害的污垢。为了解决这方面的问题并为清洗提供理论依据,近年来不少国内外学者提出了预测污垢的新技术。本文以冷凝器内的结垢为研究对象,主要研究了冷凝器污垢的软测量建模和预测方法:
     论文首先对冷凝器污垢产生的原因及污垢是怎样影响冷凝器工作效率的情况做了一定的阐述,指出了对冷凝器污垢预测的重要意义,介绍了冷凝器的工作原理以及污垢预测的研究现状。
     其次,根据冷凝器污垢的形成机理、分类以及形成的各个阶段,对冷凝器污垢预测模型给出了详细的说明。然后,将污垢分解为软垢和硬垢两部分,而软垢又分阶段进行预测,硬垢则由数理统计模型得到,最后叠加得到总的污垢系数值。常规的污垢测量方法虽然应用广泛,但从经济性与准确性的角度上来说,都有各自的弊端。针对该问题,本文设计了一种基于K均值算法及切比雪夫神经网络的在线污垢预测方法。传统的切比雪夫神经网络是动态的单输入单输出模型,为适应冷凝器污垢受多种工况参数影响的情况,本文对算法进行了改进,用多输入单输出模型取而代之。在冷凝器污垢系数的预测过程中,污垢系数受工况突变或大扰动的影响很大,为保持污垢预测的连续性,对采样进来的数据进行了预处理,在预先设定的门槛值的限定下,预测值能够在预设精度范围内与实际值逼近一致。灰色模型与人工神经网络各具特点,本文在最后介绍了一种以灰色模型为主,以人工神经网络为辅的灰色神经网络的污垢预测方法。仿真对比结果表明,灰色神经网络预测模型在不同工况下预测精度比其它常规预测模型在短期预测中的精确度要高。
     最后,将各算法用MATLAB进行仿真,以检测算法的有效性和可行性。结果表明算法是有效且可行的。
Condenser a large transfer auxiliary equipment in the powers, chemical,machinery and other fields plays an essential part in thermal power plants for itsproviding the cold source for the thermodynamic cycle in the large steam turbine.Therefore, the performance of its work has direct influence on the economy andsecurity in the entire steam turbine operation process. However, once the condenser isput into operation, there will be some fouling inside the condenser, which will do harmto the operation of condensers. In recent years many scholars from home and broadhave proposed a lot of new technologies of predicting fouling in order to solve theproblems discussed above and offer the basis for washing. The paper chooses thecondenser scaling as the main research object, its modeling and predicting method insoft measurement has been studied.
     Firstly, this paper explained the cause of fouling accumulation, the reason why itinfluences the performance of condenser, the important significance of its prediction,working principle and the status of prediction for it.
     Secondly, the prediction model of fouling in condenser is instructed thoroughlyaccording to its formation mechanism, classification and each phase when it is forming.Then, the overall fouling is separated into two parts soft fouling and hard fouling,which can be respectively got by phased prediction and mathematical statistics model,and the final fouling factor can be attained by adding up them together. Though, theconventional measurement methods of fouling are widely used, they have their ownshortcoming from the point of view of economics and accuracy. This paper designs anonline fouling prediction strategy based on K-means algorithm and Chebyshev neuralnetwork to conquer the problem discussed above, and introduces the multiple inputsingle output (MISO) models instead of the traditional dynamic single input singleoutput (SISO) Chebyshev neural network to adapt to the condenser fouling which isaffected by various of condition parameters. The fouling factor is largely influenced byworking conditions and big disturbance in the process of prediction, so sampling datapretreatment, which controls the data under the limit of the threshold to maintain thecontinuity of fouling data, is given to keep the prediction value in the default precisionand equal the actual value. At last the gray neural networks based on gray models andneural networks is proposed for fouling prediction because of Grey models and neuralnetworks has their own characteristics. In this model, gray models play a main role rather than neural network. By contrast, the simulation results show that gray modelscan achieve more accurate fouling prediction than traditional fouling models underdifferent work conditions in the short-term prediction process.
     Finally, we simulate the proposed algorithms to verify the validity and feasibilityof the algorithms. The results show that the algorithms are effective and feasible.
引文
[1]徐婷婷,郭洋.火电厂空冷技术探讨.应用能源技术,2011,(9):41-44
    [2]凌武,王韬.冷却水与冷冻水对制冷系统的影响.机械制造与自动化,2012,(1): 85-105
    [3]鲁兆伟.凝汽器污垢监测的发展和现状.广东电力,2011,(6):23-27
    [4]刘乾.节能技术.石油和化工节能,2009,(6):12-22
    [5]刘磊,王振业,吴彬.油田集输系统换热器中污垢热阻预测研究.北京石油化工学院学报,2010,(4):51-54
    [6]徐志明,刘艳,文孝强.基于灰色理论模型的交叉缩放椭圆管污垢特性预测.华北电力大学学报(自然科学版),2011,(4):96-100
    [7] Witrant Emmanuel,Bremond Sylvain.Shape identification for distributedparameter systems and temperature profiles in tokamaks.Decision and Controland European Control Conference,2011:2626-2631
    [8] Fernandez-Perdomo E.,Hernandez-Sosa D.,Prieto-Maranon V.Single andmultiple glider path planning using an optimization-based approach. OCEANS,2011:1-10
    [9] Markowski P.,Dziedzic A.,Prociow E.Mixed thick-/thin film thermoelectricmicrogenerators.Electronics System-Integration Technology Conference,2008:601-606
    [10] Smith D.,Timms G.,de Souza P.A quality control framework for marine sensingusing statistical,causal inference.OCEANS,2011:1-7
    [11] Berteaux H.,Prindle B.,May D.,The Deep Sea Moorings FishbiteProblem.OCEANS,1987:661-673
    [12] Welch D.W.,Melnychuk M.C.,O'Dor,R.Applications of the Pacific OceanShelf Tracking System (POST): A Permanent Continental-Scale AcousticTracking Array for Fisheries Research & Ocean Observation.OCEANS,2006:1-5
    [13] Ludovice P.,n L.,Catrambone R.Special session—Improvisation methods tocatalyze engineering creativity.Frontiers in Education Conference (FIE),2010,(F1A):1-2
    [14] Cary J.R.,Hakim A.,Hong Zhang.A Framework for Parallel Coupling of FusionComponents.2010 18th Euromicro International Conference,2010: 435-442
    [15] Liang Yuming,Wen Ruchun,Zhang Zhenli.Dynamic coverage path planningand obstacle avoidance for cleaning robot based on behavior.ElectricInformation and Control Engineering (ICEICE),2011: 4952-4956
    [16] Ji Shi-feng,Gao Chun-mei,Wang Chun-feng. Influence of Iron Content onActivated Sludge Performance in Membrane Bioreactor.Bioinformatics andBiomedical Engineering (iCBBE),2010,(4): 1-5
    [17] ShaoFeng Zhu,HongYuan Liu.Research advances of ultrafiltration technologyin drinking water treatment.Mechanic Automa- tion and Control Engineering(MACE),2010:4350-4353
    [18] Gambier A.,Badreddin E.Dynamic modeling of a single-stage MSF plant foradvanced control purposes.Control Applications,2005:681-686
    [19] Sun Lingfang,Zhang Yingying,Rina S.Research on the fouling prediction ofheat exchanger based on Support Vector Machine optimized by Particle SwarmOptimization algorithm.Mechatronics and Automation,2009:2002- 2007
    [20] Siobhan F.E.Boerlage,Control Applications.CCA,2005:21-29
    [21] Sun Lingfang,Zhang Yingying,Rina S.Research on the fouling prediction ofheat exchanger based on Support Vector Machine optimized by Particle SwarmOptimization algorithm.Mechatronics and Automation,2009:2002- 2007
    [22] Abdelsalam H.S.,Maly K.,Kaminsky D.Analysis of Energy Efficiency inClouds.COMPUTATION WORLD,2009: 416 - 421
    [23]陈晓文,张早校,陈二锋.换热设备污垢检测及预测研究进展.化工机械,2005,(1):60-64
    [24]杨善让.基于模拟循环冷却装置的微生物污垢形成的影响因素.化工学报,2011,(12):3503-3510
    [25]徐志明,郭淑清,杨善让.基于概率分析的污垢模型.工程热物理学报,2003,(2):322-324
    [26]柴海棣,王维航,张连生.基于径向基神经网络的污垢预测方法研究.Journalof Northeast Dianli University,2006,(4):46-49
    [27]郝战焱.小型容器或工件全封闭全自动清洗设备设计.清洗世界,2012,(1):36-41
    [28]赵宇,王勤韧,陈江平.电化学腐蚀对翅片管换热器性能的影响.化工学报,2010,(1):22-26
    [29]钱剑峰,谭延坤,张吉礼.污水源热泵系统声空化除污与强化换热技术.建筑热能通风空调,2011,(6):24-29
    [30]彭珍,张充,吴立锋.基于RBF神经网络的换热管污垢热阻预测.煤气与热力,2008,28(6):25-28.
    [31]季小民.冷却水动态模拟试验数据的回归分析.金山油化纤,1997,(3):19-25
    [32]徐志明,张进朝,张仲彬等.圆管内CaSO4析晶污垢模型与数值模拟.化学工程,2009,37(7):14-16
    [33]孙卓辉.换热面上结垢过程数值模拟:[硕士学位论文].北京:中国石油大学,2008:27-45
    [34]冷学礼,田茂诚,潘继红.渐近型污垢生长过程的特性分析.热能动力工程,2008,23(3):278-279
    [35]徐志明,张仲彬等.微粒和析晶混合污垢模型.工程热物理学报,2006,27(2):81-84
    [36]吴学慧,孙德兴.污水换热器污垢生长特性试验研究.节能技术,2008,26(4):300-304
    [37]常公鹏,支国军.电厂锅炉结渣预测模型研究.电力学报,2004,19(1):15-17.
    [38]王雷等.基于支持向量回归的冷凝器清洁系数时间序列预测.中国电机工程学报,2007,27(4):62-66
    [39]徐志明,文孝强.基于最小二乘支持向量回归机的光管污垢特性预测.化工学报,2009,60(7):1618-1621
    [40]张颖颖.基于支持向量机的换热设备污垢预测研究:[硕士学位论文].吉林省吉林市:东北电力大学,2009:23-50
    [41]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机:北京:科学出版社,2004
    [42]韩冬梅,牛文清,于长锐.组合预测建模中单项预测模型筛选研究.系统工程与电子技术,2009,(6):1381-1385
    [43]李章平,陈玉成,罗林坤.图书馆读者满意度测评中的3种定性因子赋权方法.西南师范大学学报(自然科学版),2010(2):242-246
    [44]孙建安.概率模型与应用.潍坊学院学报,2010,(4):83-85
    [45]杨志霞.用时间序列模型预测深层地下水位.水资源研究,2010,(4):16-18
    [46]崔智超,王青建.数理统计学源流及应用.大连教育学院学报,2005,(2):53-55
    [47]朱光兆,何伟.基于支持向量机的混沌时间序列预测分析.自动化与仪器仪表,2012,(1):145-147
    [48]赵琪.高速公路收费站收费预测研究.长安大学,2010:3-5
    [49]王先成,严晓峰.贝叶斯网络模型在软件可靠性预测模型中的应用.科技致富向导,2011,(36):19-20
    [50]周孙锋,张文广.西安市公交客运量的回归分析预测研究.广东交通职业技术学院学报,2011,(4): 29-32
    [51]钱宝源,刘干斌,陈忠.宁波地区单桩极限承载力GM(1,1)灰色模型预测.宁波工程学院学报,2011,(4):83-89
    [52]徐盈.基于不同预测模型的舟山市客运量预测.浙江国际海运职业技术学院学报,2009,(1):9-12
    [53]美国联邦铁路局研究结果.轨温预测模型的开发.西铁科技,2009,(2):2-4
    [54]陈晋音,杨东勇,卢瑾.基于惩罚机制的自适应交叉粒子群算法.计算机科学,2010,(4):249-255
    [55]涂序彦.协同智能建模与协同智能仿真.计算机仿真,2011,(9):145-147
    [56]蔡义.板式换热器失效原因分析及处理.热电技术,2011,(2):52-54
    [57]张吉礼,马良栋,曹达君等.热阻法管内反冲洗除污特性试验研究.暖通空调,2010,(1):106-109
    [58]张莹,王耀南,文益民.基于清洁度的冷凝器污垢监测方法研究.湖南大学学报(自然科学版),2011,(4):36-40
    [59]刘义达.换热器金属表面行为对其析晶污垢生成特性的影响研究.山东大学,2011:56-70
    [60]窦丹,邢晓凯.换热器中析晶垢结垢过程的预测模型.管道技术与设备,2009,(3):32-34
    [61]张莹.大型冷凝器清洗机器人视觉控制方法研究.湖南大学,2010,(1):112-113
    [62]郑水明,缪卫东,曾心传.砂土液化全概率分析方法探讨.地下空间与工程学报,2010,(4):23-28
    [63]王文远.基于控制函数估计图像噪音的标准方差.计算机科学,2009,(9):290-292
    [64] Howarth J H,Glen N F,Jenkins A M.The use of fouling monitoringtechniques.New York:Begell house Inc.,1999:309-314
    [65] Chandy R,Scully D J.A optical fiber sensor for bio-film measurement usingintensity modulation and image analysis.IEEE Journal on selected topics inquantum electronics,2000,6(5):762-764
    [66] Flenmming H C,Tamachkiarows A,Klahre J,et al.Monitoring of fouling andbiofouling in technical systems.Water science and technology,1998,38(8):291-298
    [67] Glen F,Howarth J H,Jenkin A M.Understanding heat exchanger fouling and itsmitigation.New York: Begell house Inc.,1999:256-264
    [68] Temu A K,Naess E,Sonju O K.Development and testing of a probe to monitorgas-side fouling in cross flow. Heat Transfer Engineering,2004,23(3):50-59
    [69]曹新功.探测管道结垢的先进仪器-闭塞解析仪.化学清洗,1993,9,(4):36-38
    [70]许婷,程伟良.基于网络热力学的能量转换最优效率研究.电力科学与工程,2009,(4):50-53
    [71]李小武,邵剑飞,廖秀玲.一种基于K-means的分布式聚类算法.桂林电子科技大学学报.2011,(6):461-463
    [72] Kaur.Responses of two cultivars of Trifolium repens L. to ethylene diurea in re-lation to ambient ozone.Journal of Environmental Sciences,2010,(7):1096-1103
    [73] Lai Yi ZHU,Ying Ying ZHAO.On Newman-Type Rational Interpolation to |x| atthe Adjusted Chebyshev Nodes of the Second Kind.数学研究与评论,2011,(2):202-207
    [74]卢庆龄,白盟亮,彭艳丽.基于灰色神经网络的装甲器材需求量预测. Journalof Academy of Armored Force Engineering,2011,(6):19-22
    [75]陈相东,王彬.多因素灰色预测模型及其应用.数学的实践与认识,2012,(1):80-82
    [76]陈顺立.基于人工神经网络的动态系统仿真模型和算法研究.煤炭技术,2012,(1):219-220
    [77]宋双,李巨才,武志云.基于人工神经网络的粗纺羊绒纱线质量预报模型.河北纺织,2009,(9):54-60

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700