具有调峰炉的热力站节能控制策略研究
|
摘要
能源问题是21世纪面临的重要挑战。我国作为一个能耗大国，降低能耗，实现低碳经济，是我国目前的一项基本国策。我国三北地区的采暖能耗，约占全社会能耗的27.2%。供热不仅能耗大，而且效率低，每单位面积供热能耗高出发达国家的2～3倍，供热节能潜力很大。因此，研究供热节能及其控制策略的意义重大。
调峰炉热力站作为供热系统调节的一种手段，在集中供热网末端加入调峰炉热力站，可以有效地解决供热高峰期负荷不足的问题，对于供热系统的稳定和良好运行起到了重要的作用。本文将研究调峰炉热力站的节能控制策略，需要从三个方面实现：一是通过供热负荷预报，准确地给出供热系统的负荷需求，防止过度供热情况的发生；二是通过优化调度，给出热力站供热系统中热负荷的最佳分配；三是通过先进的预测控制手段，保证供热系统的稳定运行，最终实现节能。
供热负荷预报是进行优化调度的前提。由于供热负荷数据存在着趋势性和周期性，本文首先采用乘积季节自回归滑动平均（Autoregressive IntegratedMoving Average，ARIMA）的方法进行供热负荷预报。但该方法不适于负荷存在较大突变的情况，因此采用Kalman在线递归预测乘积季节ARIMA模型参数，该方法提高了负荷突变阶段的预报精度。为了更好处理供热负荷数据中的非线性问题，引入最小最大概率机（Minimax Probability Machine，MPM），将相空间重构与最小最大概率回归相结合进行供热负荷预报。该方法同神经网络预报法、支持向量机（Support Vector Machine，SVM）预报法进行了比较，通过仿真分析各种预报方法的性能。
调峰炉热力站的优化调度是实现节能的关键。文中将供热负荷预报结果与国家供热标准相结合，给出准确的调峰炉热力站供热负荷需求，并以此负荷进行调度。调峰炉热力站的优化调度从能耗和经济性两个方面考虑，通过在供热高峰期和非高峰期对能耗和经济性不同侧重，实现优化调度的综合最佳。在寻优算法上先采用非线性规划等算法求解优化调度结果，但这些方法受到初值的选取的影响，用免疫粒子群（Immune Partile Swarm Optimization，IPSO）寻优的计算方法则避免这些方法上的缺陷。通过实例计算结果表明，免疫粒子群算法的优化调度计算更为方便和快速。
预测控制是实现调峰炉热力站优化调度结果的手段。优化调度给出节能监控信号，通过预测控制达到控制目标。在建模部分采用飞升曲线和最小二乘相结合的方法，建立调峰炉热力站供热过程中的质调通道模型，锅炉温度变化扰动模型和水量变化扰动模型。为了降低锅炉温度变化扰动和水量变化扰动带来的影响，文中采用加前馈补偿的三冲量预测控制方法。其中对质调通道进行神经网络预测控制，利用改进的差分进化法进行控制律的求解，对锅炉温度变化扰动和水量变化扰动进行前馈补偿。用仿真方法证明三冲量预测控制法的有效性。
最后，根据工程要求，开发调峰炉热力站监控装置。对该装置从硬件和软件两方面进行规划，给出基于PLC和GPRS无线通信的底层监控装置，并在监控中心开发优化调度软件。为了更好地满足优化调度和底层控制的需要，在MATLAB程序中实现智能算法的计算，并通过OPC技术实现与调度软件的数据交换。该监控装置样机在大庆让胡30号热力站稳定运行一年多，经过黑龙江省节能检测部门的技术检验，该装置的所有指标均达到设计要求，实现了节能。
Energy problem is an important issue in the twenty-first century. Consideringthe large Energy consumption in Chin, the reduction of energy consumption and lowcarbon economy is one of basic national policy of China. Building heating is a majordomain of energy-saving, and the heating energy consumption of China's northernregions had reached27.2%of total social energy consumption. The current problemof heating is high energy consumption but low efficiency, the heating energyconsumption in China per unit area is2and3times greater than that of thedeveloped countries, there is brilliant future in heating energy-saving. Therefore, itis significant to study the approach of heating energy-saving and control strategies.
Heating station with peak-shaving boiler is a heating pattern in heating system,this pattern can effectively solve the problem of insufficient in the heating load inthe peak period, and play an important role in stability and good operation ofheating system. Energy-saving of heating station with peak-shaving can be donefrom three aspects. First, the heating load forecasting provides accurate heat load ofthe system requirements. Second, optimal dispatch makes heating station in theoptimal heat load distribution. Third, advanced control strategy achieves the aims ofenergy-saving.
Heat load forecast is the premise of optimal dispatch. For the trend andperiodicity of heating load data, this thesis uses a multiple seasonal autoregressiveintegrated moving average (ARIMA) method in heating load forecasting. As thismethod is difficult to aquire accurate prediction results for where big mutations exist,so the Kalman recursive online is used to predict multiple seasonal ARIMA modelparameters in order to improve the prediction accurace of the load mutation. Tosolve nonlinear problem in heat load data, this paper introduces the minimaxprobability machine(MPM) theory and phase space reconstruction with acombination of MPM in order to forecast heating load, and compare this methodwith neural network and support vector machines(SVM) forecasting methods.Finally the thesis analyzes the performance of different forecasting methods withsimulation.
Optimal dispatch of heating station with peak-shaving boiler is the key toachieve heat energy saving. This paper utilizes heat load forecasting results to meetthe national heating standards, and provides accurate output heat load of heatingstation. Optimal dispatch of heating station with peak-shaving considers the heatenergy consumption and economy to achieve comprehensive best results. Nonlinearprogramming method is used to solve optimal dispatching problems, but this method depends on initial value. Immune particle swarm (IPSO) has better search ability.The simulation results show that the immune particle swarm optimization method ismore convenient and faster than traditional optimal computing.
Optimal dispatching results achieved through the control, this paper uses acombination of rising curves and least-squares method to establish quality-adjustmodel, quantity-adjust model, boiler temperature disturbance model and flowdisturbance model. In order to reduce the impact of boiler temperature disturbanceand flow disturbance, a three parameters predictive control based on feedforwardcompensation is proposed, and a neural network predictive control is used in thequality-adjust channel, and an improved differential evolution method is used tosolve the control law. Simulation results show the effectiveness of the threeparameters predictive control method.
Finally, based on the engineering requirements of heating station withpeak-shaving boiler, the thesis develops a heating station monitoring device whichincludes hardware and software, PLC and GPRS wireless communication. Theintelligent algorithm was programmed by MATLAB, data exchange was realiezedbetween the optimal sofeware and MATLAB through the OPC. Operating in Ranghudistrict of Daqing for more than a year, the monitoring device achieved the purposeof energy-saving, and pass the performance tests of national quality supervisiondepartment.
调峰炉热力站作为供热系统调节的一种手段，在集中供热网末端加入调峰炉热力站，可以有效地解决供热高峰期负荷不足的问题，对于供热系统的稳定和良好运行起到了重要的作用。本文将研究调峰炉热力站的节能控制策略，需要从三个方面实现：一是通过供热负荷预报，准确地给出供热系统的负荷需求，防止过度供热情况的发生；二是通过优化调度，给出热力站供热系统中热负荷的最佳分配；三是通过先进的预测控制手段，保证供热系统的稳定运行，最终实现节能。
供热负荷预报是进行优化调度的前提。由于供热负荷数据存在着趋势性和周期性，本文首先采用乘积季节自回归滑动平均（Autoregressive IntegratedMoving Average，ARIMA）的方法进行供热负荷预报。但该方法不适于负荷存在较大突变的情况，因此采用Kalman在线递归预测乘积季节ARIMA模型参数，该方法提高了负荷突变阶段的预报精度。为了更好处理供热负荷数据中的非线性问题，引入最小最大概率机（Minimax Probability Machine，MPM），将相空间重构与最小最大概率回归相结合进行供热负荷预报。该方法同神经网络预报法、支持向量机（Support Vector Machine，SVM）预报法进行了比较，通过仿真分析各种预报方法的性能。
调峰炉热力站的优化调度是实现节能的关键。文中将供热负荷预报结果与国家供热标准相结合，给出准确的调峰炉热力站供热负荷需求，并以此负荷进行调度。调峰炉热力站的优化调度从能耗和经济性两个方面考虑，通过在供热高峰期和非高峰期对能耗和经济性不同侧重，实现优化调度的综合最佳。在寻优算法上先采用非线性规划等算法求解优化调度结果，但这些方法受到初值的选取的影响，用免疫粒子群（Immune Partile Swarm Optimization，IPSO）寻优的计算方法则避免这些方法上的缺陷。通过实例计算结果表明，免疫粒子群算法的优化调度计算更为方便和快速。
预测控制是实现调峰炉热力站优化调度结果的手段。优化调度给出节能监控信号，通过预测控制达到控制目标。在建模部分采用飞升曲线和最小二乘相结合的方法，建立调峰炉热力站供热过程中的质调通道模型，锅炉温度变化扰动模型和水量变化扰动模型。为了降低锅炉温度变化扰动和水量变化扰动带来的影响，文中采用加前馈补偿的三冲量预测控制方法。其中对质调通道进行神经网络预测控制，利用改进的差分进化法进行控制律的求解，对锅炉温度变化扰动和水量变化扰动进行前馈补偿。用仿真方法证明三冲量预测控制法的有效性。
最后，根据工程要求，开发调峰炉热力站监控装置。对该装置从硬件和软件两方面进行规划，给出基于PLC和GPRS无线通信的底层监控装置，并在监控中心开发优化调度软件。为了更好地满足优化调度和底层控制的需要，在MATLAB程序中实现智能算法的计算，并通过OPC技术实现与调度软件的数据交换。该监控装置样机在大庆让胡30号热力站稳定运行一年多，经过黑龙江省节能检测部门的技术检验，该装置的所有指标均达到设计要求，实现了节能。
Energy problem is an important issue in the twenty-first century. Consideringthe large Energy consumption in Chin, the reduction of energy consumption and lowcarbon economy is one of basic national policy of China. Building heating is a majordomain of energy-saving, and the heating energy consumption of China's northernregions had reached27.2%of total social energy consumption. The current problemof heating is high energy consumption but low efficiency, the heating energyconsumption in China per unit area is2and3times greater than that of thedeveloped countries, there is brilliant future in heating energy-saving. Therefore, itis significant to study the approach of heating energy-saving and control strategies.
Heating station with peak-shaving boiler is a heating pattern in heating system,this pattern can effectively solve the problem of insufficient in the heating load inthe peak period, and play an important role in stability and good operation ofheating system. Energy-saving of heating station with peak-shaving can be donefrom three aspects. First, the heating load forecasting provides accurate heat load ofthe system requirements. Second, optimal dispatch makes heating station in theoptimal heat load distribution. Third, advanced control strategy achieves the aims ofenergy-saving.
Heat load forecast is the premise of optimal dispatch. For the trend andperiodicity of heating load data, this thesis uses a multiple seasonal autoregressiveintegrated moving average (ARIMA) method in heating load forecasting. As thismethod is difficult to aquire accurate prediction results for where big mutations exist,so the Kalman recursive online is used to predict multiple seasonal ARIMA modelparameters in order to improve the prediction accurace of the load mutation. Tosolve nonlinear problem in heat load data, this paper introduces the minimaxprobability machine(MPM) theory and phase space reconstruction with acombination of MPM in order to forecast heating load, and compare this methodwith neural network and support vector machines(SVM) forecasting methods.Finally the thesis analyzes the performance of different forecasting methods withsimulation.
Optimal dispatch of heating station with peak-shaving boiler is the key toachieve heat energy saving. This paper utilizes heat load forecasting results to meetthe national heating standards, and provides accurate output heat load of heatingstation. Optimal dispatch of heating station with peak-shaving considers the heatenergy consumption and economy to achieve comprehensive best results. Nonlinearprogramming method is used to solve optimal dispatching problems, but this method depends on initial value. Immune particle swarm (IPSO) has better search ability.The simulation results show that the immune particle swarm optimization method ismore convenient and faster than traditional optimal computing.
Optimal dispatching results achieved through the control, this paper uses acombination of rising curves and least-squares method to establish quality-adjustmodel, quantity-adjust model, boiler temperature disturbance model and flowdisturbance model. In order to reduce the impact of boiler temperature disturbanceand flow disturbance, a three parameters predictive control based on feedforwardcompensation is proposed, and a neural network predictive control is used in thequality-adjust channel, and an improved differential evolution method is used tosolve the control law. Simulation results show the effectiveness of the threeparameters predictive control method.
Finally, based on the engineering requirements of heating station withpeak-shaving boiler, the thesis develops a heating station monitoring device whichincludes hardware and software, PLC and GPRS wireless communication. Theintelligent algorithm was programmed by MATLAB, data exchange was realiezedbetween the optimal sofeware and MATLAB through the OPC. Operating in Ranghudistrict of Daqing for more than a year, the monitoring device achieved the purposeof energy-saving, and pass the performance tests of national quality supervisiondepartment.
引文
[1]江亿.我国供热节能中的问题和解决途径[J].暖通空调，2006（3）：37-41.
[2] Hong D H, Hwang C H. Interval Regression Analysis Using Quadratic LossSupport Vector Machine[J]. IEEE Transactions on Fuzzy Systems,2005,13（2）：229-237.
[3] Wojdyga K. An Influence of Weather Conditions on Heat Demand in DistrictHeating Systems[J]. Energy&Building,2004（11）：2009-2014.
[4] Werner S. The heat load in district heating system[M]. Swenden: ChalmersUniversity of Technology,1984：9-33.
[5] Krzysztof W. An influence of weather conditions on heat demand in districtheating systems[J]. Energy and Buildings,2008,40（11）：2009-2014.
[6]郝有志，李德英.热负荷预测方法评析[J].建筑热能通风空调，2003，22（1）：26-27.
[7] Madsen H, Sejling K, Sagard H T. On flow and supply temperature control indistrict heating system[J]. Heat Recovery Systems&CHP,1994,14（6）：613-620.
[8] Pedersen L, Stang J, Ulseth R. Load Prediction Method for Heat andElectricity Demand in Buildings for the Purpose of Planning for Mixed EnergyDistribution Systems[J]. Energy&Buildings,2008,40（7）：1124-1134.
[9] Rios M G, Trejo PM, Castaneda M R, et al. Modelling temperature inintelligent buildings by means of autoregressive models[J]. Automation inConstruction,2007,16（5）：713-724.
[10] Nielsen H A, Madse H. Modelling the Heat Consumption in District HeatingSystem Using a Grey-box Approach[J]. Energy and Buildings,2006,38（1）：63-71.
[11] Kreider J F. Operational data as the basis for neural network prediction ofhourly electrical demand[J]. ASHARE Transactions,1997,103（2）：927-934.
[12] Bradley P F. Generalized nonlinear regression with ensemble of neural nets: thegreat energy predictor shootout[J]. ASHARE Transactions,1994,100（2）：1075-1080.
[13] William J S. Using artificial neural nets to predict building energyparameters[J]. ASHRAE Transactions,1994,100（2）：1081-1087.
[14] Mattias O. Predicting System Loads with Artificial Neural Network-methodsfrom the Great Energy Predictor Shootout[J]. ASHARE Transactions,1994,100（2）：1063-1074.
[15] Soteris A K. Long-term performance prediction of forced circulation solardomestic water heating system using artificial neural networks[J]. AppliedEnergy,2000,66:63-74.
[16] Dodier R H, Henze G P. Statistical Analysis of Neural Network as Applied toBuilding Energy Prediction[J]. Journal of Solar Energy Engineering,2004（2）：19-27.
[17] Alberto H N, Flavio A S F. Comparison Between Detailed Model Simulationand Articial Neural Network for Forecasting Building Energy Consumption[J].Energy and Buildings,2008,40（12）：2169-2176.
[18] Daniela P, Florina U, Abel H G. Simulation Models for the Analysis of SpaceHeat Consumption of Buildings[J]. Energy,2009,34（10）：1447-1453.
[19] Ulien E, Stéphane G, Monique P. Wavelet-based Multi-resolution Analysis andArtificial Neural Networks for Forecasting Temperature and Thermal PowerConsumption[J]. Engineering Applications of Artificial Intelligence,2010（9）：157-172.
[20] Dong B, Cao C, Lee S E. Applying Support Vector Machines to PredictBuilding Energy Consumption in Tropical Region[J]. Energy and Building,2005,37:545-553.
[21] Pinson P, Nielsen T S, Nielsen H A, et al. Temperature Prediction at CriticalPoints in District Heating Systems[J]. European Journal of OperationalResearch,2009,194（1）：163-176.
[22]周恩泽，方修睦.供暖热水锅炉房的热负荷预测[J].哈尔滨建筑大学学报，2000，33（3）：56-60.
[23]马涛，徐向东.基于小波网模型的区域供热系统负荷预测[J].清华大学学报，2005，45（5）：708-710.
[24]胡文斌，华贲，杨昌智，孙一坚.灰色理论在城市供热负荷预测中的应用[J].煤气与热力，2002，22（1）：28-31.
[25]李玉云，王永骥.人工神经网络在暖通空调领域的应用研究发展[J].暖通空调，2001，31（1）：38-41.
[26]熊钧，姜永成，郭骏，逄秀锋.热网动态BP网络预测模型结构的研究[J].哈尔滨工业大学学报，2005，37（3）：391-393.
[27]林雨舒，李健，赵国材.一种粗糙广义回归神经网络在集中供热负荷预测中的应用[J].电气技术，2007（12）：17-19.
[28]朱栋华，黎展求.基于小波和神经网络的供热负荷预测[J].沈阳建筑大学学报(自然科学版)，2007，23（1）：157-160.
[29]刘剑，杨勇，邱庆刚.基于粒子群神经网络的热力站供热负荷预测[J].节能，2008（6）：27-30.
[30]黎展求，朱栋华.基于支持向量回归和小波包的供热负荷预测[J].暖通空调，2007，37（2）：1-5.
[31] Zhang Y M, Chen L, Qi W G. A New Probabilistic Prediction Approach Basedon Local v-Support Vector Regression[C]. Proceedings of the SeventhInternational Conference on Machine Learning and Cybernetics,2008:728-733.
[32]张永明，陈烈，齐维贵.基于支持向量区间回归的供热负荷概率预报方法[J].吉林大学学报(工学版)，2010，40（6）：1693-1697.
[33] Marecki J, Krajewski R, Renski A. Optimization Problems in a Large NuclearHeat-and-Power Plant Connected to a Developing District Heating System[J].Nuclear Technology,1978,38（1）：41-49.
[34] Laspisa R L, Stacy G, Sochan H M. Optimization Saves Energy at PolysarSteam and Power Plant[J]. Oil and Gas Journal,1978,76（25）：117-118,123-124.
[35] Couch R T, Stacy G D, Houston B.F, et al. Allocation of Plant EnergyResources[J]. Chemical Engineering Progress,1981,77（10）：37-41.
[36] Yee T F, Gro ssmann I E, Kravania Z. Simultaneous optimization models forheat integration. Process and heat exchanger network optimization[J]. ComputChem Eng,1990,14（11）：185-1200.
[37] Sonntag C, Su W J, Stursberg O. Optimized Start-up Control of anIndustrial-scale Evaporation System with Hybrid Dynamics[J]. ControlEngineering Practice,2008,16（8）：976-990.
[38] Rong A Y, Hakonen Hi, Lahdelma R. A Variant of the Dynamic ProgrammingAlgorithm for Unit Commitment of Combined Heat and Power Systems[J].European Journal of Operational Research,2008,190（3）：741-755.
[39] Shirakawa M, Kawai K, Arakawa M, et al. Intelligent Start-up ScheduleOptimization System for Athermal Power Plant[C]. Power Plants and PowerSystems Control2006,2007:189-194.
[40] Cai J J, Ma X Q, Li L X, et al. Chaotic Ant Swarm Optimization to EconomicDispatch[J]. Electric Power Systems Research,2007,77（10）：1373-1380.
[41] Wang L F, Singh C A. Stochastic Economic Emission Load dispatch through aModified Particle Swarm Optimization Algorithm[J]. Electric Power SystemsResearch,2008,78（8）：1466-1476.
[42]汝方济，赵士杭，华贲.石化企业热能动力系统的优化调度[J].石油炼制与化工，1993，24（7）：18-21.
[43]夏燕萍，吕泽华，赵士杭.热电厂锅炉-汽轮机的优化调度[J].清华大学学报，2000，40（11）：596-621.
[44]吕泽华，赵士杭，陈钢.抚顺石化热电厂热电联供系统的优化调度[J].石油炼制与化工，2002，33（10）：36-40.
[45]周康，吕泽华，赵士杭等.热力系统自适应优化调度应用[J].热力透平，2005，34（3）：174-179.
[46]李俊涛，冯霄.供热机组的热电负荷分配[J].西安交通大学学报，2006（3）：311-313.
[47]王培红，李琳，董益华.供热机组热电负荷优化算法研究[J].汽轮机技术，2004（1）：37-39.
[48]许红胜，杨莹莹，葛斌.蒸汽供热管网的优化方法研究和软件开发[J].建筑热能通风空调，2007，6（5）：55-59.
[49] Zmeureanu R, Rivard H. Optimization of a Geothermal Heating and CoolingSystem for a Large Commercial Building in Montreal[C]. World RenewableEnergy Congress VI,2000:322-325.
[50] Thorin E, Heike B. Christoph Weber Long-term Optimization of CogenerationSystems in a Competitive Market Environment[J]. Applied Energy,2005,81（2）：152-169.
[51] Karel M, Zdenek S, Petr S. Decision Support Tools for Advanced EnergyManagement[J]. Energy,2008,33（6）：858-873.
[52] Richalet J. Model Predictive Heuristic Control: Application to industrialProcesses[J]. Automatica,1978,14（5）：413-428.
[53] Rouhani R, Mehra R. Model Algorithmic Control Basic TheoreticalProperties[J]. Automatica,1982,18（4）：401~414.
[54] Cutler C, Ramaker B. Dynamic Matrix Control-A Computer ControlAlgorithm[C]. Proc JACC SanFranciso,1980：146-153.
[55] Clarke D, Mohtadi C, Tuffs P. Generalized Predictive Control Algorithm[J].Automatica,1987,23:137-160.
[56] Lelic M, Zarrop M. Generalized Pole Placement Self-tuning Controller[J].International Journal of Control，1987,46（2）：547-568.
[57] Garcia C, Morari M. Internal model control: Aunifying review and some newresults[C]. IEC Procees Des,1982,21（2）：308-323.
[58] KuntzE H, Jacubaseh A, Richalet J, et al. On the Predictive Functional Controlof an Elastic Industrial Robot[C]. Proc25thCDC,1986:1877-1881.
[59] Kawathekar R, Riggs J. Nonlinear Model Predictive Control of a ReactiveDistillation Column[J]. Control Engineering Practice,2007,15（2）：231-239.
[60] Dubay R, AbuAyyad M, Hernandez J. A Nonlinear Regression Model-basedPredictive Control Algorithm[J]. ISA transactions,2009,48（2）：180-189.
[61] delaParte M. Application of Predictive Sliding Model Controllers to a SolarPlant[J]. IEEE Transactions on Control Systems Technology,2008,16（4）：819-825.
[62] Prakash J, Senthil R. Design of Observer Based Nonlinear Model PredictiveController for a Continuous Stirredtank Reactor[J]. Journal of Process Control,2008,8（5）：504-514.
[63] Gareia C. Quadratic dynamic matrix control of nonlinear process[C]. AnApplication to a Batch Reactor Process, San Francisco,1984：538-561.
[64] Costas K, Chung C B. Nonlinear state feedback synthesis by globalinPut/outPut linearization[J]. AIChE Journal,1987,33（4）：592-603.
[65] Kurtz M, Henson M. InPut-OutPut Linearizing Control of ConstrainedNonlinear Proeesses[J]. Journal of Process control,1997,7（1）：3-17.
[66]张新民，荣冈.间歇反应过程的预测函数控制[J].信息与控制，1999，28（增刊）：102-106.
[67]孙浩，席裕庚，张钟俊.一类非线性系统的模型预测控制算法[J].上海交通大学学报，1994，28（4）：68-75.
[68] Todorov Y V, Tsvetkov T D. Volterra Model Predictive Control of a Lyophili-zation Plant[J].20084th International IEEE Conference Intelligent Systems,Varna,2008（2）：2013-2018.
[69] Xiang W, Sheng J, Chen Z H. Model Predictive Control Based on NeuralNetworks for Hammerstein Type Nonlinear Systems[J]. Journal of theGraduate School of the Chinese Academy of Sciences,2008,25（2）：224-232.
[70] Maciej L. Computationally Efficient Nonlinear Predictive Control Based onNeural Wiener Models[J]. Neurocomputing,2010,74:401-417.
[70] Maciej L. Suboptimal Nonlinear Predictive Control Based on Neural WienerModels[J]. Artificial Intelligence: Methodology, Systems, and Applications-13th International Conference,2008:410-414.
[72]都明宇，刘桂芝.一类双线性系统的广义预测控制研究[J].计算机仿真，2007，24（3）：173-176.
[73] Wang P L. Discrete Model Predietive Controller Design Using LaguerreFunctions [J]. Journal of Process Control,2005,14：131-142.
[74] Blazic. Design and Stability Analysis of Fuzzy Model-based PredictiveControl:a Case Study[J]. Journal of Intelligent and Robotic Systems:Theoryand Applications,2007,49（3）：279-292.
[75] Lei J, Lv H L, Cai W J. Model Predictive Control Based on Fuzzy Lineari-zation Technique for HVAC Systems Temperature Control[C].20061st IEEEConference on Industrial Electronics and Applications,2006:405-410.
[76] Duarte M, Suárez A, Bassi D. Multivariable Predictive Control of a PressurizedTank Using Neural Networks[J]. Neural Computing&Applications,2006,15（1）：18-25.
[77] Yuzgec U, Becerikli Y, Turker M. Dynamic Neural-network-based ModelPredictive Control of an Industrial Baker's Yeast Drying Process[J]. IEEETransactions on Neural Networks,2008,19（7）：1231-1242.
[78] Jalili M. Neural Networks as a Tool for Nonlinear Predictive Control:Application to Some Benchmark Systems[C]. International Journal of WaveletsMultiresolution and Information Processing,2007,5:69~99.
[79] Yoo S J, Choi Y H, Park J B. Generalized Predictive Control Based onSelf-recurrent Wavelet Neural Network for Stable Path Tracking of MobileRobots: Adaptive Learning Rates Approach[C]. IEEE Transactions on Circuitsand Systems I,2006,53（6）：1381-1394.
[80] Bao Z J, Zhong W M, Pi D Y. Robustly Stable Medel Predictive Control Basedon Parallel Support Vector Machines with Linear Kernal[J]. Journal of CentralSouth Uinversity of Technology,2007,14（5）：701-707.
[81] Ren Y, Cao G Y, Zhu X J. Predictive control of Proton Exchange MembraneFuel Eell Based on Support Vector Regression Machine[C]. Proceeding of theFourth International Conference on Machine Learning and Cybernetics,Guangzhou,2005:18-21.
[82]范剑青，姚琦伟.非线性时间序列[M].北京：高等教育出版社，2005：7-32.
[83]李晓武.用SAS识别ARIMA的简单季节模型与乘积季节模型[J].人工智能及识别技术，2007（02）：538-540.
[84]韩敏.混沌时间序列预测理论与方法[M].北京：中国水利水电出版社,2007：50-89，155-172.
[85]张永明，齐维贵.供热负荷时间序列混沌特性分析及预报模型研究[J].物理学报，2011，60（10）：1-10.
[86] Lanckriet G, Ghaoui L E, Bhattacharyya C, et al. Minimax Probability machine
[C]. Advances in Neural Information Processing Systems14Cambridge:MITPress,2002:75-99.
[87] Sun J C. Modelling of Chaotic Time Series Using Minimax ProbabilityMachine Regression[J]. Proceedings2009WRI International Conference onCommunications and Mobile Computing, Nanchang,2009:321-324.
[88] Mu X Y, Zhang T Y. A Novel Minimax Probability Machine[J]. InformationTechnology Journal,2009（8）：615-618.
[89]陈其松.智能优化支持向量机预测算法及应用研究[D].贵阳：贵州大学，2009：29-68.
[90]王晶，靳其兵，曹柳林.面向多输入输出系统的支持向量机回归[J].清华大学学报(自然科学版)，2007，47（S2）：1737-1741.
[91] Rebay M, Arfaoui A, Mebarki G, et al. Improvement of the Pulsed Photother-mal Technique for the Measurement of the Convective Heat TransferCoefficient[J]. Journal of Thermal Science,2010,19（4）：357-363.
[92]白江涛，朱惠人，张宗卫.流量比对气膜冷却叶片表面换热系数的影响[J].西安交通大学学报，2011，45（7）：95-99.
[93] Azevedo A, Oliveira A R L, Secundino S. Interior Point Method for Long-termGeneration Scheduling of Large-scale Hydrothermal Systems[J]. Annals ofOperations Research,2008（1）：55-80.
[94]苏孟龙，王建.同伦内点方法求解无界域上的非线性规划问题[J]，中国海洋大学数学科学学院，2011，41（1）：185-188.
[95]黄少荣.粒子群优化算法综述[J].计算机工程与设计，2009，30（8）：1977-1978.
[96]莫愿斌.粒子群优化算法的扩展与应用[D].杭州：浙江大学，2006：12-23.
[97]李宁.粒子群优化算法的理论分析与应用研究[D].武汉：华中科技大学.2006：2-15.
[98]张捍东，方玲，岑豫皖.三种混合粒子群算法比较[J].自动化与仪表，2011（7）：10-13.
[99]段富，苏同芬.免疫粒子群算法的改进及应用[J].计算机应用，2010,30（7）：1883-1888.
[100]QI W G, Chen L, Zhu X L. Study on Least Square Modeling of HeatEngineering Object Based on Typical Signal Response[J]. Journal of HarbinInstitute of Technology,2007,14（1）：1-4.
[101]陈烈.基于神经网络的热力站供热过程预测控制研究[D].哈尔滨：哈尔滨工业大学，2009：13-29.
[102]王毓栋，王京春.基于DE算法的非线性预测控制及其应用[J].控制工程，2008，15（1）：25-27.
[103]胡剑杭,陈冲.基于OPC技术的MATLAB实时过程控制系统[J].福州大学学报(自然科学版)，2009，36：105-109.
[104]迟猛.提供OPC数据接口的数据采集系统设计[J].工业控制计算机，2009，22（8）：35-38.
[105]Huang K Z, Yang H Q, Kin I, et al. Imbalanced Learning With a BiasedMinimax Probability Machine[J]. IEEE Transactions on Systems, Man, andCybernetics Part:Cybernetics,2006,36（4）：913-923.
[106]Mu T T, Nandi A K. Automatic Tuning of L2-SVM Parameters Employing theExtended Kalman Filter[J]. Expert Systems,2009,26（2）：160-175.
[107]Chang C C, Lin C J. LIBSVM:S Library for Support Vector Machines[J]. ACMTransactions on Intelligent Systems and Tech-nology,2010,2（3）：1-27.
[108]Kay C W, Alain A D, Andrew G H. RnaPredict-An Evolutionary Algorithm forRNA Secondary Structure Prediction[J]. Computational Biology andBioinformatics,2008,5（1）：25-40.
[109]王翼飞.生物信息学-智能计算算法及其应用[M].北京：化学工业出版社，2006：158-220.
[110]吴敏，丁雷，曹卫华.基于混合粒子群算法的烧结配料优化[J].信息与控制，2008（4）：242-246.
[111]刑杰，萧德云.混合粒子群优化算法及其应用[J].化工学报，2008，59（7）：1707-1710.
[112]Liu B, Wang L, Jin Y, et al. Improved Particle Swarm Optimization Combinedwith Chaos[J]. Chaos, Solitons and Fractals,2005,25:1261-1271.
[113]王辉，钱锋.基于拥挤度与变异的动态微粒群多目标优化算法[J].控制与决策，2008，23（11）：1238-1248.
[114]Xu Y F, Chen G C, Yu J S. Three Sub-Swarm Discrete Particle SwarmOptimization Algorithm[J].2006IEEE International Conference on Informa-tion Acquisition, shandong,2006:1224-1228.
[115]De F I, Della C A, Tarantino E. Facing Classification Problems with ParticleSwarm Optimization[J]. Applied Soft Computing,2007,7（3）：652-658.
[116]Kamalasadan S, Ghandakly A A. A Neural Network Parallel AdaptiveController for Dynamic System Control[J]. Transactions on Instrumentationand Measurement,2007,56（5）：1786-1796.
[117]Chang C H, Cheng N L, Xin P G. New Results on Stability Analysis of NeuralNetworks with Time-varying Delays[J]. Physics Letters A,2006,352（4）：335-340.
[118]张燕，王桂玲，杨立平等.锅炉温度系统的神经网络预测-PID串联控制[J].控制工程，2011，18（2）：175-177.
[119]Chen W B, Jin L. Exponential Stability for Neural Networks Systems withDiscrete and Distributed Time-varying Delays[J]. Control Engineering of China,2009,16（5）：566-574.
[120]李永富.基于Matlab的高级过程控制实时混合仿真平台[J].系统仿真学报，2007，19（18）：4150-4153.
[121]Long X M, Ping D. Stability Analysis of Uncertain Discrete Time-DelayControl Systems[J]. Journal of southwest Jiaotong University,2006,14（1）：41-46.
[122]肖本贤，王晓伟，朱志国等.基于改进PSO算法的过热汽温神经网络预测控制[J].控制理论与应用，2008，25（3）：569-573.
[123]许凌峰，徐大平，高峰等.基于神经网络的风力发电机组变桨距复合控制[J].华北电力大学学报(自然科学版)，2009，36（1）：28-34.
[124]Wang A X, Wu P, Li J J. A Real Time Tracking Algorithm Basing on MixedDifference Algorithm[J]. Advanced Materials Research,2010:291-296.
[125]Cai Z X, Wang Y. A Multiobjective Optimization Based EvolutionaryAlgorithm for Constrained Optimization[J]. IEEE Transactions on Evolutio-nary Computation,2006,10（6）：658-675.
[126]Noman N, Iba H. Accelerating Differential Evolution Using an Adaptive LocalSearch [J]. IEEE Trans Evolut Comput,2008,12:107-125.
[127]Qin A K, Huang V L, Suganthan P N. Differential Evolution Algorithm withStrategy Adaptation for Global Numerical Optimization[J]. IEEE Trans onEvolutionary Computation,2009,13（2）：398-417.
[128]Wang Y P, Dang C Y. An Evolutionary Algorithm for Global OptimizationBased on Level-set Evolution and Latin Squares[J]. IEEE Trans onEvolutionary Computation,2007,11（5）：579-595.
[129]刘忠.三冲量控制系统的设计及应用进[J].自动化与仪器仪表，2009（4）：18-20.
[130]李晓燕，孙建平，李伟.汽包锅炉给水串级三冲量控制系统[J].机械工程与自动化，2010（1）：155-160.
[131]刘林，刘丽娜，赵晓东.串级三冲量给水控制系统在实际应用中存在的问题及改进的措施[J].中国石油和化工标准与质量，2011（4）：33-34.
[2] Hong D H, Hwang C H. Interval Regression Analysis Using Quadratic LossSupport Vector Machine[J]. IEEE Transactions on Fuzzy Systems,2005,13（2）：229-237.
[3] Wojdyga K. An Influence of Weather Conditions on Heat Demand in DistrictHeating Systems[J]. Energy&Building,2004（11）：2009-2014.
[4] Werner S. The heat load in district heating system[M]. Swenden: ChalmersUniversity of Technology,1984：9-33.
[5] Krzysztof W. An influence of weather conditions on heat demand in districtheating systems[J]. Energy and Buildings,2008,40（11）：2009-2014.
[6]郝有志，李德英.热负荷预测方法评析[J].建筑热能通风空调，2003，22（1）：26-27.
[7] Madsen H, Sejling K, Sagard H T. On flow and supply temperature control indistrict heating system[J]. Heat Recovery Systems&CHP,1994,14（6）：613-620.
[8] Pedersen L, Stang J, Ulseth R. Load Prediction Method for Heat andElectricity Demand in Buildings for the Purpose of Planning for Mixed EnergyDistribution Systems[J]. Energy&Buildings,2008,40（7）：1124-1134.
[9] Rios M G, Trejo PM, Castaneda M R, et al. Modelling temperature inintelligent buildings by means of autoregressive models[J]. Automation inConstruction,2007,16（5）：713-724.
[10] Nielsen H A, Madse H. Modelling the Heat Consumption in District HeatingSystem Using a Grey-box Approach[J]. Energy and Buildings,2006,38（1）：63-71.
[11] Kreider J F. Operational data as the basis for neural network prediction ofhourly electrical demand[J]. ASHARE Transactions,1997,103（2）：927-934.
[12] Bradley P F. Generalized nonlinear regression with ensemble of neural nets: thegreat energy predictor shootout[J]. ASHARE Transactions,1994,100（2）：1075-1080.
[13] William J S. Using artificial neural nets to predict building energyparameters[J]. ASHRAE Transactions,1994,100（2）：1081-1087.
[14] Mattias O. Predicting System Loads with Artificial Neural Network-methodsfrom the Great Energy Predictor Shootout[J]. ASHARE Transactions,1994,100（2）：1063-1074.
[15] Soteris A K. Long-term performance prediction of forced circulation solardomestic water heating system using artificial neural networks[J]. AppliedEnergy,2000,66:63-74.
[16] Dodier R H, Henze G P. Statistical Analysis of Neural Network as Applied toBuilding Energy Prediction[J]. Journal of Solar Energy Engineering,2004（2）：19-27.
[17] Alberto H N, Flavio A S F. Comparison Between Detailed Model Simulationand Articial Neural Network for Forecasting Building Energy Consumption[J].Energy and Buildings,2008,40（12）：2169-2176.
[18] Daniela P, Florina U, Abel H G. Simulation Models for the Analysis of SpaceHeat Consumption of Buildings[J]. Energy,2009,34（10）：1447-1453.
[19] Ulien E, Stéphane G, Monique P. Wavelet-based Multi-resolution Analysis andArtificial Neural Networks for Forecasting Temperature and Thermal PowerConsumption[J]. Engineering Applications of Artificial Intelligence,2010（9）：157-172.
[20] Dong B, Cao C, Lee S E. Applying Support Vector Machines to PredictBuilding Energy Consumption in Tropical Region[J]. Energy and Building,2005,37:545-553.
[21] Pinson P, Nielsen T S, Nielsen H A, et al. Temperature Prediction at CriticalPoints in District Heating Systems[J]. European Journal of OperationalResearch,2009,194（1）：163-176.
[22]周恩泽，方修睦.供暖热水锅炉房的热负荷预测[J].哈尔滨建筑大学学报，2000，33（3）：56-60.
[23]马涛，徐向东.基于小波网模型的区域供热系统负荷预测[J].清华大学学报，2005，45（5）：708-710.
[24]胡文斌，华贲，杨昌智，孙一坚.灰色理论在城市供热负荷预测中的应用[J].煤气与热力，2002，22（1）：28-31.
[25]李玉云，王永骥.人工神经网络在暖通空调领域的应用研究发展[J].暖通空调，2001，31（1）：38-41.
[26]熊钧，姜永成，郭骏，逄秀锋.热网动态BP网络预测模型结构的研究[J].哈尔滨工业大学学报，2005，37（3）：391-393.
[27]林雨舒，李健，赵国材.一种粗糙广义回归神经网络在集中供热负荷预测中的应用[J].电气技术，2007（12）：17-19.
[28]朱栋华，黎展求.基于小波和神经网络的供热负荷预测[J].沈阳建筑大学学报(自然科学版)，2007，23（1）：157-160.
[29]刘剑，杨勇，邱庆刚.基于粒子群神经网络的热力站供热负荷预测[J].节能，2008（6）：27-30.
[30]黎展求，朱栋华.基于支持向量回归和小波包的供热负荷预测[J].暖通空调，2007，37（2）：1-5.
[31] Zhang Y M, Chen L, Qi W G. A New Probabilistic Prediction Approach Basedon Local v-Support Vector Regression[C]. Proceedings of the SeventhInternational Conference on Machine Learning and Cybernetics,2008:728-733.
[32]张永明，陈烈，齐维贵.基于支持向量区间回归的供热负荷概率预报方法[J].吉林大学学报(工学版)，2010，40（6）：1693-1697.
[33] Marecki J, Krajewski R, Renski A. Optimization Problems in a Large NuclearHeat-and-Power Plant Connected to a Developing District Heating System[J].Nuclear Technology,1978,38（1）：41-49.
[34] Laspisa R L, Stacy G, Sochan H M. Optimization Saves Energy at PolysarSteam and Power Plant[J]. Oil and Gas Journal,1978,76（25）：117-118,123-124.
[35] Couch R T, Stacy G D, Houston B.F, et al. Allocation of Plant EnergyResources[J]. Chemical Engineering Progress,1981,77（10）：37-41.
[36] Yee T F, Gro ssmann I E, Kravania Z. Simultaneous optimization models forheat integration. Process and heat exchanger network optimization[J]. ComputChem Eng,1990,14（11）：185-1200.
[37] Sonntag C, Su W J, Stursberg O. Optimized Start-up Control of anIndustrial-scale Evaporation System with Hybrid Dynamics[J]. ControlEngineering Practice,2008,16（8）：976-990.
[38] Rong A Y, Hakonen Hi, Lahdelma R. A Variant of the Dynamic ProgrammingAlgorithm for Unit Commitment of Combined Heat and Power Systems[J].European Journal of Operational Research,2008,190（3）：741-755.
[39] Shirakawa M, Kawai K, Arakawa M, et al. Intelligent Start-up ScheduleOptimization System for Athermal Power Plant[C]. Power Plants and PowerSystems Control2006,2007:189-194.
[40] Cai J J, Ma X Q, Li L X, et al. Chaotic Ant Swarm Optimization to EconomicDispatch[J]. Electric Power Systems Research,2007,77（10）：1373-1380.
[41] Wang L F, Singh C A. Stochastic Economic Emission Load dispatch through aModified Particle Swarm Optimization Algorithm[J]. Electric Power SystemsResearch,2008,78（8）：1466-1476.
[42]汝方济，赵士杭，华贲.石化企业热能动力系统的优化调度[J].石油炼制与化工，1993，24（7）：18-21.
[43]夏燕萍，吕泽华，赵士杭.热电厂锅炉-汽轮机的优化调度[J].清华大学学报，2000，40（11）：596-621.
[44]吕泽华，赵士杭，陈钢.抚顺石化热电厂热电联供系统的优化调度[J].石油炼制与化工，2002，33（10）：36-40.
[45]周康，吕泽华，赵士杭等.热力系统自适应优化调度应用[J].热力透平，2005，34（3）：174-179.
[46]李俊涛，冯霄.供热机组的热电负荷分配[J].西安交通大学学报，2006（3）：311-313.
[47]王培红，李琳，董益华.供热机组热电负荷优化算法研究[J].汽轮机技术，2004（1）：37-39.
[48]许红胜，杨莹莹，葛斌.蒸汽供热管网的优化方法研究和软件开发[J].建筑热能通风空调，2007，6（5）：55-59.
[49] Zmeureanu R, Rivard H. Optimization of a Geothermal Heating and CoolingSystem for a Large Commercial Building in Montreal[C]. World RenewableEnergy Congress VI,2000:322-325.
[50] Thorin E, Heike B. Christoph Weber Long-term Optimization of CogenerationSystems in a Competitive Market Environment[J]. Applied Energy,2005,81（2）：152-169.
[51] Karel M, Zdenek S, Petr S. Decision Support Tools for Advanced EnergyManagement[J]. Energy,2008,33（6）：858-873.
[52] Richalet J. Model Predictive Heuristic Control: Application to industrialProcesses[J]. Automatica,1978,14（5）：413-428.
[53] Rouhani R, Mehra R. Model Algorithmic Control Basic TheoreticalProperties[J]. Automatica,1982,18（4）：401~414.
[54] Cutler C, Ramaker B. Dynamic Matrix Control-A Computer ControlAlgorithm[C]. Proc JACC SanFranciso,1980：146-153.
[55] Clarke D, Mohtadi C, Tuffs P. Generalized Predictive Control Algorithm[J].Automatica,1987,23:137-160.
[56] Lelic M, Zarrop M. Generalized Pole Placement Self-tuning Controller[J].International Journal of Control，1987,46（2）：547-568.
[57] Garcia C, Morari M. Internal model control: Aunifying review and some newresults[C]. IEC Procees Des,1982,21（2）：308-323.
[58] KuntzE H, Jacubaseh A, Richalet J, et al. On the Predictive Functional Controlof an Elastic Industrial Robot[C]. Proc25thCDC,1986:1877-1881.
[59] Kawathekar R, Riggs J. Nonlinear Model Predictive Control of a ReactiveDistillation Column[J]. Control Engineering Practice,2007,15（2）：231-239.
[60] Dubay R, AbuAyyad M, Hernandez J. A Nonlinear Regression Model-basedPredictive Control Algorithm[J]. ISA transactions,2009,48（2）：180-189.
[61] delaParte M. Application of Predictive Sliding Model Controllers to a SolarPlant[J]. IEEE Transactions on Control Systems Technology,2008,16（4）：819-825.
[62] Prakash J, Senthil R. Design of Observer Based Nonlinear Model PredictiveController for a Continuous Stirredtank Reactor[J]. Journal of Process Control,2008,8（5）：504-514.
[63] Gareia C. Quadratic dynamic matrix control of nonlinear process[C]. AnApplication to a Batch Reactor Process, San Francisco,1984：538-561.
[64] Costas K, Chung C B. Nonlinear state feedback synthesis by globalinPut/outPut linearization[J]. AIChE Journal,1987,33（4）：592-603.
[65] Kurtz M, Henson M. InPut-OutPut Linearizing Control of ConstrainedNonlinear Proeesses[J]. Journal of Process control,1997,7（1）：3-17.
[66]张新民，荣冈.间歇反应过程的预测函数控制[J].信息与控制，1999，28（增刊）：102-106.
[67]孙浩，席裕庚，张钟俊.一类非线性系统的模型预测控制算法[J].上海交通大学学报，1994，28（4）：68-75.
[68] Todorov Y V, Tsvetkov T D. Volterra Model Predictive Control of a Lyophili-zation Plant[J].20084th International IEEE Conference Intelligent Systems,Varna,2008（2）：2013-2018.
[69] Xiang W, Sheng J, Chen Z H. Model Predictive Control Based on NeuralNetworks for Hammerstein Type Nonlinear Systems[J]. Journal of theGraduate School of the Chinese Academy of Sciences,2008,25（2）：224-232.
[70] Maciej L. Computationally Efficient Nonlinear Predictive Control Based onNeural Wiener Models[J]. Neurocomputing,2010,74:401-417.
[70] Maciej L. Suboptimal Nonlinear Predictive Control Based on Neural WienerModels[J]. Artificial Intelligence: Methodology, Systems, and Applications-13th International Conference,2008:410-414.
[72]都明宇，刘桂芝.一类双线性系统的广义预测控制研究[J].计算机仿真，2007，24（3）：173-176.
[73] Wang P L. Discrete Model Predietive Controller Design Using LaguerreFunctions [J]. Journal of Process Control,2005,14：131-142.
[74] Blazic. Design and Stability Analysis of Fuzzy Model-based PredictiveControl:a Case Study[J]. Journal of Intelligent and Robotic Systems:Theoryand Applications,2007,49（3）：279-292.
[75] Lei J, Lv H L, Cai W J. Model Predictive Control Based on Fuzzy Lineari-zation Technique for HVAC Systems Temperature Control[C].20061st IEEEConference on Industrial Electronics and Applications,2006:405-410.
[76] Duarte M, Suárez A, Bassi D. Multivariable Predictive Control of a PressurizedTank Using Neural Networks[J]. Neural Computing&Applications,2006,15（1）：18-25.
[77] Yuzgec U, Becerikli Y, Turker M. Dynamic Neural-network-based ModelPredictive Control of an Industrial Baker's Yeast Drying Process[J]. IEEETransactions on Neural Networks,2008,19（7）：1231-1242.
[78] Jalili M. Neural Networks as a Tool for Nonlinear Predictive Control:Application to Some Benchmark Systems[C]. International Journal of WaveletsMultiresolution and Information Processing,2007,5:69~99.
[79] Yoo S J, Choi Y H, Park J B. Generalized Predictive Control Based onSelf-recurrent Wavelet Neural Network for Stable Path Tracking of MobileRobots: Adaptive Learning Rates Approach[C]. IEEE Transactions on Circuitsand Systems I,2006,53（6）：1381-1394.
[80] Bao Z J, Zhong W M, Pi D Y. Robustly Stable Medel Predictive Control Basedon Parallel Support Vector Machines with Linear Kernal[J]. Journal of CentralSouth Uinversity of Technology,2007,14（5）：701-707.
[81] Ren Y, Cao G Y, Zhu X J. Predictive control of Proton Exchange MembraneFuel Eell Based on Support Vector Regression Machine[C]. Proceeding of theFourth International Conference on Machine Learning and Cybernetics,Guangzhou,2005:18-21.
[82]范剑青，姚琦伟.非线性时间序列[M].北京：高等教育出版社，2005：7-32.
[83]李晓武.用SAS识别ARIMA的简单季节模型与乘积季节模型[J].人工智能及识别技术，2007（02）：538-540.
[84]韩敏.混沌时间序列预测理论与方法[M].北京：中国水利水电出版社,2007：50-89，155-172.
[85]张永明，齐维贵.供热负荷时间序列混沌特性分析及预报模型研究[J].物理学报，2011，60（10）：1-10.
[86] Lanckriet G, Ghaoui L E, Bhattacharyya C, et al. Minimax Probability machine
[C]. Advances in Neural Information Processing Systems14Cambridge:MITPress,2002:75-99.
[87] Sun J C. Modelling of Chaotic Time Series Using Minimax ProbabilityMachine Regression[J]. Proceedings2009WRI International Conference onCommunications and Mobile Computing, Nanchang,2009:321-324.
[88] Mu X Y, Zhang T Y. A Novel Minimax Probability Machine[J]. InformationTechnology Journal,2009（8）：615-618.
[89]陈其松.智能优化支持向量机预测算法及应用研究[D].贵阳：贵州大学，2009：29-68.
[90]王晶，靳其兵，曹柳林.面向多输入输出系统的支持向量机回归[J].清华大学学报(自然科学版)，2007，47（S2）：1737-1741.
[91] Rebay M, Arfaoui A, Mebarki G, et al. Improvement of the Pulsed Photother-mal Technique for the Measurement of the Convective Heat TransferCoefficient[J]. Journal of Thermal Science,2010,19（4）：357-363.
[92]白江涛，朱惠人，张宗卫.流量比对气膜冷却叶片表面换热系数的影响[J].西安交通大学学报，2011，45（7）：95-99.
[93] Azevedo A, Oliveira A R L, Secundino S. Interior Point Method for Long-termGeneration Scheduling of Large-scale Hydrothermal Systems[J]. Annals ofOperations Research,2008（1）：55-80.
[94]苏孟龙，王建.同伦内点方法求解无界域上的非线性规划问题[J]，中国海洋大学数学科学学院，2011，41（1）：185-188.
[95]黄少荣.粒子群优化算法综述[J].计算机工程与设计，2009，30（8）：1977-1978.
[96]莫愿斌.粒子群优化算法的扩展与应用[D].杭州：浙江大学，2006：12-23.
[97]李宁.粒子群优化算法的理论分析与应用研究[D].武汉：华中科技大学.2006：2-15.
[98]张捍东，方玲，岑豫皖.三种混合粒子群算法比较[J].自动化与仪表，2011（7）：10-13.
[99]段富，苏同芬.免疫粒子群算法的改进及应用[J].计算机应用，2010,30（7）：1883-1888.
[100]QI W G, Chen L, Zhu X L. Study on Least Square Modeling of HeatEngineering Object Based on Typical Signal Response[J]. Journal of HarbinInstitute of Technology,2007,14（1）：1-4.
[101]陈烈.基于神经网络的热力站供热过程预测控制研究[D].哈尔滨：哈尔滨工业大学，2009：13-29.
[102]王毓栋，王京春.基于DE算法的非线性预测控制及其应用[J].控制工程，2008，15（1）：25-27.
[103]胡剑杭,陈冲.基于OPC技术的MATLAB实时过程控制系统[J].福州大学学报(自然科学版)，2009，36：105-109.
[104]迟猛.提供OPC数据接口的数据采集系统设计[J].工业控制计算机，2009，22（8）：35-38.
[105]Huang K Z, Yang H Q, Kin I, et al. Imbalanced Learning With a BiasedMinimax Probability Machine[J]. IEEE Transactions on Systems, Man, andCybernetics Part:Cybernetics,2006,36（4）：913-923.
[106]Mu T T, Nandi A K. Automatic Tuning of L2-SVM Parameters Employing theExtended Kalman Filter[J]. Expert Systems,2009,26（2）：160-175.
[107]Chang C C, Lin C J. LIBSVM:S Library for Support Vector Machines[J]. ACMTransactions on Intelligent Systems and Tech-nology,2010,2（3）：1-27.
[108]Kay C W, Alain A D, Andrew G H. RnaPredict-An Evolutionary Algorithm forRNA Secondary Structure Prediction[J]. Computational Biology andBioinformatics,2008,5（1）：25-40.
[109]王翼飞.生物信息学-智能计算算法及其应用[M].北京：化学工业出版社，2006：158-220.
[110]吴敏，丁雷，曹卫华.基于混合粒子群算法的烧结配料优化[J].信息与控制，2008（4）：242-246.
[111]刑杰，萧德云.混合粒子群优化算法及其应用[J].化工学报，2008，59（7）：1707-1710.
[112]Liu B, Wang L, Jin Y, et al. Improved Particle Swarm Optimization Combinedwith Chaos[J]. Chaos, Solitons and Fractals,2005,25:1261-1271.
[113]王辉，钱锋.基于拥挤度与变异的动态微粒群多目标优化算法[J].控制与决策，2008，23（11）：1238-1248.
[114]Xu Y F, Chen G C, Yu J S. Three Sub-Swarm Discrete Particle SwarmOptimization Algorithm[J].2006IEEE International Conference on Informa-tion Acquisition, shandong,2006:1224-1228.
[115]De F I, Della C A, Tarantino E. Facing Classification Problems with ParticleSwarm Optimization[J]. Applied Soft Computing,2007,7（3）：652-658.
[116]Kamalasadan S, Ghandakly A A. A Neural Network Parallel AdaptiveController for Dynamic System Control[J]. Transactions on Instrumentationand Measurement,2007,56（5）：1786-1796.
[117]Chang C H, Cheng N L, Xin P G. New Results on Stability Analysis of NeuralNetworks with Time-varying Delays[J]. Physics Letters A,2006,352（4）：335-340.
[118]张燕，王桂玲，杨立平等.锅炉温度系统的神经网络预测-PID串联控制[J].控制工程，2011，18（2）：175-177.
[119]Chen W B, Jin L. Exponential Stability for Neural Networks Systems withDiscrete and Distributed Time-varying Delays[J]. Control Engineering of China,2009,16（5）：566-574.
[120]李永富.基于Matlab的高级过程控制实时混合仿真平台[J].系统仿真学报，2007，19（18）：4150-4153.
[121]Long X M, Ping D. Stability Analysis of Uncertain Discrete Time-DelayControl Systems[J]. Journal of southwest Jiaotong University,2006,14（1）：41-46.
[122]肖本贤，王晓伟，朱志国等.基于改进PSO算法的过热汽温神经网络预测控制[J].控制理论与应用，2008，25（3）：569-573.
[123]许凌峰，徐大平，高峰等.基于神经网络的风力发电机组变桨距复合控制[J].华北电力大学学报(自然科学版)，2009，36（1）：28-34.
[124]Wang A X, Wu P, Li J J. A Real Time Tracking Algorithm Basing on MixedDifference Algorithm[J]. Advanced Materials Research,2010:291-296.
[125]Cai Z X, Wang Y. A Multiobjective Optimization Based EvolutionaryAlgorithm for Constrained Optimization[J]. IEEE Transactions on Evolutio-nary Computation,2006,10（6）：658-675.
[126]Noman N, Iba H. Accelerating Differential Evolution Using an Adaptive LocalSearch [J]. IEEE Trans Evolut Comput,2008,12:107-125.
[127]Qin A K, Huang V L, Suganthan P N. Differential Evolution Algorithm withStrategy Adaptation for Global Numerical Optimization[J]. IEEE Trans onEvolutionary Computation,2009,13（2）：398-417.
[128]Wang Y P, Dang C Y. An Evolutionary Algorithm for Global OptimizationBased on Level-set Evolution and Latin Squares[J]. IEEE Trans onEvolutionary Computation,2007,11（5）：579-595.
[129]刘忠.三冲量控制系统的设计及应用进[J].自动化与仪器仪表，2009（4）：18-20.
[130]李晓燕，孙建平，李伟.汽包锅炉给水串级三冲量控制系统[J].机械工程与自动化，2010（1）：155-160.
[131]刘林，刘丽娜，赵晓东.串级三冲量给水控制系统在实际应用中存在的问题及改进的措施[J].中国石油和化工标准与质量，2011（4）：33-34.