火电厂汽轮机运行初压优化方法研究与应用
|
摘要
随着电网容量的增大和用电结构的变化，电网峰谷差日益增加，火电机组不得不参与变负荷甚至启停调峰运行。汽轮机长期处于变工况运行状态，热经济性明显下降。要确保汽轮机变工况运行时仍能保持最佳状态，就必须对汽轮机的运行初压进行优化，将得到的最优运行初压作为汽轮机自动运行时主蒸汽压力的设定值，能有效地降低汽轮机的热耗率，节约发电成本。本文在对基本万有引力搜索算法和最小二乘支持向量回归算法改进的基础上，建立了汽轮机主蒸汽流量和热耗率的动态预测模型并根据实际运行工况给出了优化的滑压运行曲线。主要研究内容如下：
首先，提出了一种改进的万有引力搜索算法。通过引入反向学习策略、精英策略以及边界变异策略，使基本的万有引力搜索算法具有了更高的优化精度及运行稳定性，通过13个基准函数的测试，验证了改进的万有引力搜索算法具有较好的优化性能。接着，提出了一种自适应最小二乘支持向量回归算法，依据“两步走策略”和“删除最小拉格朗日乘子绝对值对应的支持向量”这两个原则，通过递推公式更新模型参数，既避免了复杂逆矩阵的求解，又考虑了不同训练样本对预测结果的影响，数值实验验证了该算法在线建模时的有效性。
然后，研究了反向建模方法在主蒸汽流量预测中的应用，重点讨论了基于粗糙集理论的最小二乘支持向量回归算法在主蒸汽流量离线建模中的优异表现，同时还利用自适应最小二乘支持向量回归算法建立了主蒸汽流量的在线预测模型。预测得到的主蒸汽流量作为热耗率建模的输入参数之一，进一步研究了改进的万有引力搜索算法和最小二乘支持向量回归算法相结合的混合建模方法在汽轮机热耗率预测中的应用，改进的万有引力搜索算法用于优化最小二乘支持向量机的超参数进而提高其热耗率建模的预测精度及泛化能力。此外还讨论了不同适应度值的计算方法对汽轮机热耗率预测精度的影响。
最后，利用自适应最小二乘支持向量回归算法建立汽轮机热耗率的在线预测模型，实时预测的热耗率值作为改进万有引力搜索算法寻优时的适应度值，在可行的运行初压范围内，以热耗率最低为优化目标来在线确定汽轮机变工况运行时的最优运行初压并据此给出优化后的滑压运行曲线。得出的实时最优滑压运行曲线能够更好地指导汽轮机变工况时优化运行。
Along with the increase of electric power plant capacity and the change of powerconsumption, the peak-valley difference of electrical network increases day by day. Thesteam turbine units have to take part in changing the load and even to startup-halt foradjusting the peak output. Steam turbine is in the state of long-term variable loadoperation deviating from its design conditions, so thermal economy decreases greatly. Theinitial steam pressure of turbine must be optimized to ensure the steam turbine maintainthe best runing state under the variable working condition. The optimal initial pressure istaken as the setting value of main steam pressure, which can effectively reduce the heatrate of steam turbine and save the generating cost. This paper establishes the dynamicprediction models of main steam flow and heat rate and gives the optimal sliding pressureoperation curve according to the actual running state of turbine based on the improvingGravitation Search Algorithm (GSA) and Least Squares Support Vector Regression(LSSVR) algorithm. The main research results of this paper can be summarized asfollows:
Firstly, this paper proposes an Improved Gravitation Search Algorithm (IGSA). Itsignificantly improves the optimization precision and the operation stability of standardGSA by introducing opposite learning strategy, elite strategy and boundary mutationstrategy. This paper verifies that the improved algorithm has better optimizationperformance than standard GSA through13benchmark functions. Also, this paperproposes an Adaptive Least Squares Support Vector Regression (ALSSVR) algorithm.This algorithm updates the model parameters by a recursion formula. It adopts a "two-stepstrategy" which avoids the complex calculation of the inverse matrix, and simultaneouslydeletes the corresponding support vector of minimum Lagrange multiplier absolute value,which is considered to influence the prediction precision for different samples. Thenumerical simulation experiment verifies that the ALSSVR applies to the online modeling.
Secondly, a reverse modeling method is applyed to forecast the main steam flow. Thepredicted performance of LSSVR based on rough sets is better than that those of LSSVR, SVR and BP without attribute reduction. At the same time, as a new reverse modelingalgorithm, ALSSVR can be applied to the online modelling of main steam flow. Thepredicted value of main steam flow is taken as one of the input parameters of heat ratemodelling. Then, a hybrid modeling method based on IGSA-LSSVR is applied to forecastthe heat rate of steam turbine, in which IGSA is used to optimize the super parameters ofleast squares support vector machine, and effectively improve the prediction precision ofheat rate modeling. In addition, this paper still discusses the influence of differentcalculation fitness methods on the prediction precision.
Finally, this paper establishs the online prediction model for steam turbine heat rateby ALSSVR algorithm. IGSA searches the optimal operation initial pressure within thefeasible operation initial pressure range according to the rule of minimizing the heat rateunder the variable working conditions of steam turbine. Therefore, the real-time predictionvalue of heat rate is taken as the IGSA’s fitness function. The real-time optimal operationinitial pressure curve can better guide the optimizing operation of steam turbine andeffectively save energy and reduce consumption.
首先，提出了一种改进的万有引力搜索算法。通过引入反向学习策略、精英策略以及边界变异策略，使基本的万有引力搜索算法具有了更高的优化精度及运行稳定性，通过13个基准函数的测试，验证了改进的万有引力搜索算法具有较好的优化性能。接着，提出了一种自适应最小二乘支持向量回归算法，依据“两步走策略”和“删除最小拉格朗日乘子绝对值对应的支持向量”这两个原则，通过递推公式更新模型参数，既避免了复杂逆矩阵的求解，又考虑了不同训练样本对预测结果的影响，数值实验验证了该算法在线建模时的有效性。
然后，研究了反向建模方法在主蒸汽流量预测中的应用，重点讨论了基于粗糙集理论的最小二乘支持向量回归算法在主蒸汽流量离线建模中的优异表现，同时还利用自适应最小二乘支持向量回归算法建立了主蒸汽流量的在线预测模型。预测得到的主蒸汽流量作为热耗率建模的输入参数之一，进一步研究了改进的万有引力搜索算法和最小二乘支持向量回归算法相结合的混合建模方法在汽轮机热耗率预测中的应用，改进的万有引力搜索算法用于优化最小二乘支持向量机的超参数进而提高其热耗率建模的预测精度及泛化能力。此外还讨论了不同适应度值的计算方法对汽轮机热耗率预测精度的影响。
最后，利用自适应最小二乘支持向量回归算法建立汽轮机热耗率的在线预测模型，实时预测的热耗率值作为改进万有引力搜索算法寻优时的适应度值，在可行的运行初压范围内，以热耗率最低为优化目标来在线确定汽轮机变工况运行时的最优运行初压并据此给出优化后的滑压运行曲线。得出的实时最优滑压运行曲线能够更好地指导汽轮机变工况时优化运行。
Along with the increase of electric power plant capacity and the change of powerconsumption, the peak-valley difference of electrical network increases day by day. Thesteam turbine units have to take part in changing the load and even to startup-halt foradjusting the peak output. Steam turbine is in the state of long-term variable loadoperation deviating from its design conditions, so thermal economy decreases greatly. Theinitial steam pressure of turbine must be optimized to ensure the steam turbine maintainthe best runing state under the variable working condition. The optimal initial pressure istaken as the setting value of main steam pressure, which can effectively reduce the heatrate of steam turbine and save the generating cost. This paper establishes the dynamicprediction models of main steam flow and heat rate and gives the optimal sliding pressureoperation curve according to the actual running state of turbine based on the improvingGravitation Search Algorithm (GSA) and Least Squares Support Vector Regression(LSSVR) algorithm. The main research results of this paper can be summarized asfollows:
Firstly, this paper proposes an Improved Gravitation Search Algorithm (IGSA). Itsignificantly improves the optimization precision and the operation stability of standardGSA by introducing opposite learning strategy, elite strategy and boundary mutationstrategy. This paper verifies that the improved algorithm has better optimizationperformance than standard GSA through13benchmark functions. Also, this paperproposes an Adaptive Least Squares Support Vector Regression (ALSSVR) algorithm.This algorithm updates the model parameters by a recursion formula. It adopts a "two-stepstrategy" which avoids the complex calculation of the inverse matrix, and simultaneouslydeletes the corresponding support vector of minimum Lagrange multiplier absolute value,which is considered to influence the prediction precision for different samples. Thenumerical simulation experiment verifies that the ALSSVR applies to the online modeling.
Secondly, a reverse modeling method is applyed to forecast the main steam flow. Thepredicted performance of LSSVR based on rough sets is better than that those of LSSVR, SVR and BP without attribute reduction. At the same time, as a new reverse modelingalgorithm, ALSSVR can be applied to the online modelling of main steam flow. Thepredicted value of main steam flow is taken as one of the input parameters of heat ratemodelling. Then, a hybrid modeling method based on IGSA-LSSVR is applied to forecastthe heat rate of steam turbine, in which IGSA is used to optimize the super parameters ofleast squares support vector machine, and effectively improve the prediction precision ofheat rate modeling. In addition, this paper still discusses the influence of differentcalculation fitness methods on the prediction precision.
Finally, this paper establishs the online prediction model for steam turbine heat rateby ALSSVR algorithm. IGSA searches the optimal operation initial pressure within thefeasible operation initial pressure range according to the rule of minimizing the heat rateunder the variable working conditions of steam turbine. Therefore, the real-time predictionvalue of heat rate is taken as the IGSA’s fitness function. The real-time optimal operationinitial pressure curve can better guide the optimizing operation of steam turbine andeffectively save energy and reduce consumption.
引文
[1]全国电力工业统计快报[R].北京:中国电力企业联合会统计信息部,2012.
[2]我国供电煤耗率降至325克/千瓦时降速超预期[N/OL].新闻晚报,2011-04-15.http://finance.sina.com.cn/roll/20110415/13029696865.shtml
[3]崔民选.中国能源发展报告[M].北京：社会科学文献出版社,2009:136-139.
[4]西安热工所译.现行火电厂降低热耗率工作导则：50家美国电力公司降低电厂机组热耗率的经验总结,1993.
[5]李明,黄丕维,焦庆丰,等.大型汽轮机组运行方式优化试验研究及经济性分析[J].湖南电力,2008,28(1):27-30,49.
[6]雷如意,李新民,陈吉荣.125MW汽轮机组低负荷运行及经济性分析[J].热力发电,2002,31(6):59-63.
[7] M. Dentice D’Accadia. Optimal operation of a complex thermal system: a case study[J].International Journal of Refrigeration,2001,4(24):290-301.
[8]王晓龙.大型汽轮机组滑压运行参数优化及试验研究[M].北京：华北电力大学,2010.
[9]刘乃龙,刘永霞.300MW机组定滑定运行方式经济性分析[J].河北电力技术,2000,19(1):12-14.
[10] S. Makkonen, R. Lahdelma. Non-convex power plant modelling in energy optimisation[J].European Journal of Operational Research,2006,3(171):1113-1126.
[11]浙江省电力试验研究院.大型汽轮机滑压优化策略研究及应用[R/OL].2011-10-26.http://wenku.baidu.com/view/1f756bc0d5bbfd0a795673b2.html
[12] O. S. Naimanov. Features of the Selection of Initial Steam Pressure of Geothermal PowerStations with One and Two Evaporation Stages[J]. Thermal Engineering,1986,2(33):79-82.
[13] M. A. Rosen, I. Dincer. Exergoeconomic analysis of power plants operating on various fuels[J].Applied Thermal Engineering,2003,6(23):643-658.
[14] L. Bayón, J. M Grau, M. M. Ruiz. New development son equivalent thermal in hydrothermaloptimization: an algorithm of approximation[J]. Journal of Computational and AppliedMathematics,2005,175(1):63-75.
[15]魏铁征,王军.锅炉运行[M].天津:天津科学技术出版社,2000.
[16]任浩仁,李蔚,盛德仁,等.火电机组变工况下运行应达值的分析[J].中国电机工程学报.1999,19(9):50-52.
[17]崔映红,王惠杰,马晓芳.汽轮机变负荷运行时经济运行方式的探讨[J].研究与探讨.2002(4):4-8.
[18]吕太,吴海波,胡乔良.汽轮机最佳运行工况的经济性试验分析[J].东北电力大学学报,2010,30(1):1-4.
[19]闫顺林,刘帅,李玉辉.汽轮机变工况优化运行模型的研究[J].陕西电力,2009(7):24-27.
[20]胡冰,张仲民,武永运,等.应用BP神经网络确定汽轮机组滑压运行的最优初压[J].热力发电,2003(7):24-30.
[21]江永.基于遗传算法的调峰时最优运行初压的确定[J].现代电力,2008,25(2):61-63.
[22] X. Luo, B. Zhang, Y. Chen, et al. Modeling and optimization of a utility system containingmultiple extractions steam turbines[J]. Energy,2011,36(5):3501-3512.
[23]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[24] C.J.C. Burges. A tutorial on support vector machines for pattern recognition[J]. Data Mining andKnowledge Discovery,1998,2(2):121-167.
[25] C. Cortes, V. Vapnik. Support vector networks[J]. Machine Learning,1995,20(3):273-297.
[26]张勇,巩敦卫,张婉秋.一种基于单纯形法的改进微粒群优化算法及其收敛性分析[J].自动化学报,2009,35(3):289-298.
[27]李海燕,井元伟,马明旭.基于动态罚函数的协调优化算法[J].控制与决策,2009,24(6):911-914,920.
[28] A. J. Smola, B. Sch61kopf, K-R Mfiller. The connection between regularization operators andsupport vector kenerls[J]. Neural Networks,1998,11(4):637-649.
[29] E. Osuna, R. Freund, F. Girosi. An improved training algorithm for support vector machines[C].The Proceedings of IEEE Workshop on Neural Networks for Signal Processing, Amelea Island,1997,276-285.
[30] E. Osuna, R. Freund, F. Girosi. Training support vector machines: an application to facedetection[C]. The Proceedings of CVPR’97, NewYork,1997,130-136.
[31] T. Joachims. Transductive inference for text classification using support vector machine[C]. TheProceedings of the Sixteenth International Conference on Machine Learning, Morgan Kaufmann,1999,148-l56
[32] C. W. Hsu, C. J. Lin. A comparison of methods for multi-class support vector machines[J]. IEEETrans on Neural Networks,2002,13(2):415-425.
[33] P. Laskov. Feasible direction decomposition algorithms for training support vector machines[J].Machine Learning,2002,46(1):315-349.
[34] S. S. Keerthi, E. G. Gilbert. Convergence of a generalized SMO algorithm for SVM ClassifierDesign[J]. Machine Learning,2002,46(1):351-360.
[35] S. N. Ahmed. Incremental learning with support vector machines[C]. The Proceedings ofWorkshop on Support Vector Machines. Stockholm, Sweden,1999,208-307.
[36] M. Carozza, S. Rampone. Towards an incremental SVM for regression[C]. The Proceedings ofthe IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy,2000,405-410.
[37] R. Xiao, J. C. Wang, F. Y. Zhang. An approach to incremental SVM learning algorithm[C]. TheProceedings of12th IEEE International Conference on Tools with Artificial Intelligence Accouter,BC, Canada,2000,268-273.
[38] X. G. Zhang. Using class-center vectors to build support vector machines[C]. The Proceedings ofNeural Networks for Signal Processing IX-Proc of the1999IEEE Workshop, Wisconsin,1999,33-37.
[39] S. S. Keerthi, S. K. Shavade. A fast interactive nearest point algorithm for support vectormachine classifier design[J]. IEEE Trans on Neural Networks,2000,11(1):124-136.
[40] D. Bastos, D. Campos. A fast training algorithm for unbiased proximal SVM[C]. TheProceedings of International Conference on Acoustics Speech and Signal Processing,Philadelphia,2005,245-248.
[41] C. F. Lin, S. D Wang. Fuzzy support vector machines[J]. IEEE Transaction on Neural Networks,2002,13(2):464-471.
[42] C. J. Lin. On the convergence of the decomposition method for support vector machines[J].IEEE Transaction on Neural Networks,200l,12(6):1288-1298.
[43] M. L. Kuna, C. J. Lin. A Study on Reduced Support Vector Machines[J]. IEEE Transaction onNeural Networks,2003,14(6):1449-1459.
[44]林继鹏,刘君华.基于小波的支持向量机算法研究[J].西安交通大学学报,2005,39(8):816-819.
[45] D. H. Li, H. X. Du, T. J. Wu. A weighted support vector machine method and its application[C].The proceedings of the5“World Congress on Intelligent Control and Automation, Hangzhou,China,2004,1834-1837.
[46]宋杰,庸焕文.基于线性规划的v-支持向量机分类器[J].大连理工大学学报,2005,45(2):303-307.
[47] C. F. Chuang, F. Y. Shih. Recognizing facial action units using independent coinponent analysisand support vector machine[J]. Pattern Recognition,2006,39(9):1795-1798.
[48] R. Brunelli. Identity verification through finger matching: A comparison of support vectormachines and Gaussian basis functions classifiers[J]. Pattern Recognition Letters,2006,27(16):1905-1915.
[49] W. M. Apbell, J. P. Campbell, D.A. Reynolds et a1.Support vector machines for speaker andlanguage recognition[J].Computer Speech＆Language,2006,20(2):229.
[50] J. Cervantes, X. O. Li, W. Yu, et a1. Support vector machine classification for large data sets viaminimum enclosing ball clustering[J]. Neurocomputing,2008,71(46):611-619.
[51] F. Lauer, G. Bloch. Incorporating prior knowledge in support vector machines for classification:A review[J]. Neurocomputing,2008,71(7):1578-1594.
[52] U. Thissen, R. V. Brakel, A. P. Weijer, et a1. Using support vector machines for time seriesprediction[J]. Chemometrics and Intelligent Laboratory Systems,2003,69(1):35-49.
[53] H. Dong, H. L. Fu, W. M. Leng. Support vector machines for time series regression andprediction[J]. Journal of System Simulation,2006,18(7):1785-1788.
[54]王革丽,杨培才,毛字清.基于支持向量机方法对非平稳时间序列的预测[J].物理学报,2008,57(2):714-719.
[55] J. B. Gao, S. R. Gunn, C. J. Harris. Mean field method for the support vector machineregression[J]. Neurocomputing,2003,50:391-405.
[56] C. Hwang, D. H. Hong, K. H. Seok. Support vector interval regression machine for crisp inputand output data[J]. Fuzzy Sets and Systems,2006,157(8):1114-1125.
[57] Y. W. Kang, J. LI, G. Y. Cao, et a1. Dynamic temperature modeling of an SOFC using leastsquares support vector machines[J]. Journal of Power Sources,2008,179(2):683-692.
[58] H. J. Shin, D. H. Eom, S. S. Kim. One-class support vector machines an application in machinefault detection and classification[J]. Computers＆Industrial Engineering,2005,48(2):395-408.
[59] I. Ylamos, G. Escudero, M. Graells, et a1. Simultaneous fault diagnosis in chemical plants usingsupport vector machines[J]. Computer Aided Chemical Engineering,2007,24:1253-1258.
[60] J. Liang, R. Du. Model-based fault detection and diagnosis of HVAC systems using supportvector machine method[J]. International Journal of Refrigeration,2007,30(6):1104-1114.
[61] J. A. K. Sunken, J. Vandewalle. Least squares support vector machine classifiers[J]. NeuralProcessing Letters,1999,9(3):293-300.
[62] J. A. K. Sunkens. Nonlinear modeling and support vector machines[C]//IEEE Instrumentationand Measurement Technology Conference. Budapest, Hungary：Institute of Electrical andElectronics Engineers Inc.,2001:287-295.
[63] J. A. K. Sunkens, J. Vandewalle. Weighted least squares support vector maelaines：robustnessand sparse approximation[J]. Neuroeomputing,2002,(48):85-105.
[64] C. F. Lin, S. D. Wang. Fuzzy support vector machines[J]. IEEE Transaction on Neural Networks,2002,13(2):46-47.
[65] H. P. Huang, Y. h. Liu. Fuzzy support vector machines for pattern recognition and datamining[J]. International Jotmal of Fuzzy Systems,2002,4(3):826-835.
[66] H. M. Chi, O. K Ersoy. Recursive update Algorithm for Least Squares Support VectorMachines[J]. Neural Processing Letters,2003,2(17):165-173.
[67] K. S. Chua. Efficient Computations for Large Least Square Support Vector MachineClassifiers[J]. Pattern Recognition Letters,2003,24(1):75-80.
[68] J. A. K. Sunken, L. Lukas, V. Doreen, et a1. Least squares support vector machine classifiers: alarge scale algorithm[C]. The Proceeding of European Conference on Circuit Theory and Design:Institute of Electrical and Electronics Engineers Computer Society, Stresa, Italy,1999,839-842.
[69] W. Chu, C. J. Ong, S. S. Keerthi. An improved conjugate gradient scheme to the solution of leastsquares SVM[J]. IEEE Transaction on Neural Networks,2005,16(2):498-501.
[70] J. A. K. Sunkens, L. Lukas, J. Vandewalle. Sparse approximation using least squares supportvector machines[C], The Proceeding of IEEE Intemational Symposium on Circuits and Systems:Institute of Electrical and Electronics Engineers Inc, Geneva, Switzerland,2000,757-760.
[71] X. Y. Zeng, X. W. Chen. SMO-based pruning methods for sparse least squares support vectormachines[J]. IEEE Transaction on Neural Networks,2005,16(6):1541-1546.
[72]刘毅,王海清,李平.局部最小二乘支持向量机回归在线建模方法及其在间歇过程的应用[J].化工学报,2007(11):2846-2851.
[73] I. Goethals, K. Pelckmans, J. A. K. Suykens, et al. Identification of MIMO Hammerstein modelsusing least squares support vector machines[J]. Automatic,2005,41(7):1263-1272.
[74] I. Goethals, K. Pelckmans, J. A. K. Suykens, et a1. Subspace identificationof hammersteinsystems using least squares support vector machines[J]. IEEE Transtraction on AutomaticControl,2005,50(10):1509-1519.
[75]阎威武,朱宏栋,邵惠鹤.基于最小二乘支持向量机的软测量建模[J].系统仿真学报,2003,15(10):1494-1496.
[76]张英,苏宏业,褚健.基于模糊最小二乘支持向量机的软测量建模[J].控制与决策,2005,20(6):621-624.
[77]贾嵘,王小宇,蔡振华,等.最小二乘支持向量机回归的HHT在水轮发电机组故障诊断中的应用[J].中国电机工程学报,2006,26(22):128-133.
[78]杨奎河,单甘霖,赵玲玲.最小二乘支持向量机在故障诊断中的应用[J].计算机科学,2007,34(1):289-291.
[79]杨奎河,单甘霖,赵玲玲.基于最小二乘支持向量机的汽轮机故障诊断[J].控制与决策,2007,22(7):778-782.
[80]叶美盈.基于最小二乘支持向量机建模的混沌系统控制[J].物理学报,2005,54(1):30-34.
[81]刘斌,苏宏业,褚健.一种基于最小二乘支持向量机的预测控制算法[J].控制与决策,2004,19(12):1439-1402.
[82] J. A. K. Sunkens, L. Lukas, V. Doreen. Optimal control by least squares support vectormachines[J]. Neural Networks,2001,14(1):23-35.
[83]桑海峰,王福利,何大阔.基于最小二乘支持向量机的发酵过程混合建模[J].仪器仪表学报,2006,27(6):629-633.
[84] X. Lin, G. Y. Cao, X. J. Zhu. Modeling and control of PEMFC based on least squares supportvector machines[J]. Energy Conversion and Management,2006,47(7):1032-1050.
[85] H. B. Huo, X. J. Zhu, G. Y. Cao. Nonlinear modeling of a SOFC stack based on a least squaressupport vector machine[J]. Journal of Power Sources,2006,162(2):1220-1225.
[86] K. Polat, B. Akdemir, S. Günes. Computer aided diagnosis of ECG data on the least squaresupport vector machine[J]. Digital Signal Processing,2008,18(1):25-32.
[87] D. Hanbay. An expert system based on least square support vector machines for diagnosis of thevalvular heart disease[J]. Expert Systems with Applications,2008,36(3):4232-4238.
[88]张德富.启发式算法研究及应用[D].华中科技大学.2002,6.
[89] K.S. Tang, K.F. Man, S. Kwong, et al. Genetic algorithms and their applications[J]. IEEE SignalProcessing Magazine,1996,13(6):22-37.
[90] K. Scott. Optimization by simulated annealing: Quantitative studies[J]. Journal of StatisticalPhysics,1984,34(5-6):975-986.
[91] J.D. Farmer, N.H. Packard. The immune system, adaptation and machine learning[J], Physica D:Nonlinear Phenomena,1986,22(1-3):187-204.
[92] M Dorigo, V. Maniezzo A. Colorni. The ant system: optimization by a colony of cooperatingagents[J]. IEEE Transactions on Systems, Man, and Cybernetics-part B,1996,26(1):29-41.
[93] T. Jon, N. Mark, H, John. An artificial immune system for data analysis[J]. Biosystems,2000,55(1-3):143-150.
[94] J. Kennedy, R. Eberhart. Particle swarm optimization[C]. The proceedings of IEEE internationalconference on Neural Networks,1995,1942-1948.
[95] D. KARABOGA. An idea based on honey bee swarm for numerical optimization[R]. Kayseri:Erciyes University, Engineering Faculty, Computer Engineering Department,2005.
[96] M. Dorigo, V. Maniezzo, A. Colorni. The ant system: optimization by a colony of cooperatingagents[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part B,1996,26(1):29-41.
[97] V. Gazi, K.M. Passino. Stability analysis of social foraging swarms[J]. IEEE Transactions onSystems, Man, and Cybernetics-Part B,2004,34(1):539-557.
[98] T. Peter, Tarasewich, M. Patrick R. Swarm intelligence: power in numbers, Communications ofthe ACM-Evolving data mining into solutions for insights[J]. Communications of the ACM,2002,45(8):62-67.
[99] R. Esmat, N. Hossein, S. Saeid. BGSA: binary gravitational search algorithm[J]. NaturalComputing,2010,9(3):727-745.
[100] W. Du, B. Li. Multi-strategy ensemble particle swarm optimization for dynamic optimization[J].Information Sciences,2008,(178):3096-3109.
[101] E. Rashedi, H. Nezamabadi-pour, S. Saryazdi. GSA: A Gravitational Search Algorithm[J].Information Sciences,2009,179(13):2232-2248.
[102]徐遥,王士同.引力搜索算法的改进[J].计算机工程与应用,2011(35):1-5.
[103]谷文祥,李向涛,朱磊,等.求解流水线调度问题的万有引力搜索算法[J].智能系统学报,2010,5(5):411-418.
[104]谷文祥,郭丽萍,殷明浩.模糊c-均值算法和万有引力算法求解模糊聚类问题[J].智能系统学报,2011,6(6):520-525.
[105] D. Karaboga, B. Akay. A comparative study of Artificial Bee Colony algorithm[J]. AppliedMathematics and Computation,2009,214(1):108-132.
[106] D. Holliday, R. Resnick, J. Walker. Fundamentals of physics[M]. John Wiley and Sons,1993.
[107] R. M. Wald. General Relativity [M]. The University of Chicago Press,1984:11-23.
[108] R. Mansouri, F. Nasseri, M. Khorrami. Effective time variation of G in a model universe withvariable space dimension[J]. Physics Letters,1999,259(3-4):194-200.
[109] S. Rahnamayan. Opposition-based differential evolution[J]. Evolutionary Computation,2008,12(1):64-79.
[110] D. Karaboga, B Basturk. A powerful and efficient algorithm for numerical function optimization:artificial bee colony(ABC) algorithm[J]. Journal of Global Optimization,2007,39(3):459-471.
[111] D. Karaboga, B Basturk. On the performance of artificial bee colony(abc) algorithm[J]. AppliedSoft Computing,2008,8(1):687-697.
[112] D. Basak, S. Paland, D. C. Patranabis. Support Vector Regression[J]. Neural InformationProcessing,2007,11(10):203-225.
[113] Q. H. LI, Y. G. Zhang, M. Q. Chen, et al.Study on drying and combustion process in grate-CFBincinerator[J]. Science in China Series E: Technological Sciences,2009,52(5):1153-1160.
[114] S. S. Keerthi, C. J. Lin. Asymptotic behaviors of support vector machines with Gaussiankernel[J]. Neural Computation,2003,15(7):1667-1689.
[115] J. A. K. Suykens, L. Lukas, J.Vandewalle. Sparse approximation using least squares supportvector machines[C]. The Proceeding of IEEE Intemational Symposium on Circuits and Systems:Institute of Electrical and Electronics Engineers Inc, Geneva, Switzerland,2000,757-760.
[116]王春林,周昊,周樟华.基于支持向量机的大型电厂锅炉飞灰含炭量建模[J].中国电机工程学报,2005,25(20):72-77.
[117]王雷,王洪跃,张瑞青.基于支持向量机回归的凝汽器真空应达值确定方法的研究[J].汽轮机技术,2007,49(1):43-47.
[118]吴海姬,王雷,司风琪,等.基于BP神经网络的主蒸汽流量计算模型[J].汽轮机技术,2007,49(4):269-273.
[119]王雷,张瑞青,肖增弘,等.基于SVM的主蒸汽流量回归估计[J].华东电力,2008,36(12):89-92.
[120]周建新,王雷,吴海姬,等.基于支持向量回归的大容量机组主蒸汽流量建模[J].热能动力工程,2008,23(2):122-126.
[121]付忠广,靳涛,周丽君,等.复杂系统反向建模方法及偏最小二乘法建模应用研究[J].中国电机工程学报,2009,29(2):25-29.
[122]孙永平,朱芳梅,王敏.北仑电厂2号机组DAS系统主蒸汽流量计算模型的修改[J].浙江电力,2000,19(3):14-16.
[123]毕政益,黄欣.引进型300MW机组的主蒸汽流量计算模型[J].华东电力,1998(9):21-22.
[124]何军民,李明.湘潭电厂300MW机组主蒸汽流量计算模型的修改[J].湖南电力,2005,25(5):17-19.
[125]张文琴.反向建模方法的一般规律及其应用[M].华北电力大学,2009:3-10.
[126]杨苹,吴捷.火电厂锅炉常见故障的数据挖掘诊断方法[J].仪器仪表学报,2005,26(7):696-701.
[127]盛德仁,李蔚,刘长东,等.火电厂运行优化系统运行状况的调研与展望[J].浙江电力,2003,9(11):15-22.
[128] Z. H. Zou, T. L. Tseng, H. Sohn, et al. A rough set based approach to distributor selection insupply chain management[J]. Expert Systems with Applications,2011,38(1):106-115.
[129]雷绍兰,孙才新,周兰,等.属性约简在空间负荷预测中的应用[J].重庆大学学报,2004,27(3):85-88.
[130]黄锦涛,武学素.应用多元线性回归原理建立300MW抽汽凝汽式汽轮机组的特性方程[J].动力工程,1993,13(4):16-20.
[131] J. M. Liu. Analysis by regression for the operational performance of typical600MW turbine[J].Journal of Genus Sciences,1993,5(1):18-23.
[132]张文琴,付忠广,靳涛,等.基于偏最小二乘算法的热耗率回归分析[J].现代电力,2009,26(5):56-58.
[133]朱誉,冯利法,徐治皋.基于BP神经网络的热经济性在线计算模型[J].热力发电,2008,37(12):17-19.
[134] Z. H. Guo, J. Wu, H. Y. Hai. A case study on a hybrid wind speed forecasting method using BPneural network[J]. Knowledge-Based Systems,2011,24(7):1048-1056.
[135]王雷,张欣刚,王洪跃,等.基于支持向量回归算法的汽轮机热耗率模型[J].动力工程,2007,27(1):19-23.
[136] W. P. Zhang, P. F. Niu. LS-SVM based on chaotic particle swarm optimization with simulatedannealing and application[C]. The Proceedings of the2ndinternational conference on IntelligentControl and Information Processing, Harbin, China,2011,(2):931-934.
[137]盛德仁,李蔚,陈坚红,等.汽轮机组热耗率分析及实时计算[J].热力发电,2003,32(5):16-19.
[138]廖开太.自密封系统经济性运行[J].汽轮机技术,2005,47(5):18-24.
[139]吕太,吴海波,胡乔良.汽轮机最佳运行工况的经济性试验分析[J].东北电力大学学报,2010,30(1):1-4.
[140] V. Vapnik. Statistical Learning Theory[M]. New York: Wiley Interscience,1998.
[141] N. E. Ayat, M. Cheriet, C. Y. Suen. Automatic model selection for the optimization of SVMkernels[J]. Pattern Recognition,2005,38(10):1733-1745.
[142] K. B. Ismael, S. H. Salleh, J. M. Najeb, et al. Efficient parameter selection of support vectormachines[C]. The proceeding of the4thKuala Lumpur International Conference on BiomedicalEngineering,2008,183-186.
[143] L. G. Zhou, K. Kin, L. Yu. Credit scoring using support vector machines with direct search forparameters selection[J]. Soft Computing,2009,13(2):149-155
[144] L. Yu, X. Yao, S. Y. Wang, et al. Credit risk evaluation using a weighted least squares SVMclassifier with design of experiment for parameter selection[J]. Expert system With Application,2011,38(12):15392-15399.
[145] R. kohavi. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and ModelSection[C]. The Proceedings of the International Joint Conference on Artificial Intelligence,1995.
[146]任浩仁,李蔚,盛德仁,等.火电机组变工况下运行指标应达值的分析[J].中国电机工程学报,1999,19(9):50-53.
[147]童小忠,孙永平,樊印龙.汽轮发电机组滑压运行寻优方法的试验研究[J].浙江电力,2008(5):24-26.
[148]范鑫,秦建明,付晨鹏,等.超临界600MW汽轮机滑压优化运行的试验研究[J].汽轮机技术,2011,53(2):143-146.
[149]吕太,李耀德,胡乔良.汽轮机滑压运行方式的经济性实验分析[J].汽轮机技术,2010,52(2):127-129.
[150]杨海娅,谷俊杰.调峰运行时汽轮机组蒸汽初压的优化确定[J].应用能源技术,2010(7):39-43.
[151]姜巍,曹孟杰,张红,等.基于综合热效分析的汽轮机组运行优化研究[J].热力发电,2007(11):16-20.
[152]吴生辉.滑压运行经济性分析系统在火电厂的应用[J].自动化应用,2011(3):71-74.
[153]李秀云,严俊杰,林万超.滑压机组背压变化对经济性影响的两种新计算方法[J].中国电机工程学报,1999,19(9):22-26.
[154] R. Z. Aminov, A. M. Chertykov. Choice of optimal stage of initial steam pressure inheat-generating power units[J]. Tyazheloe Mashinostroenie,1992(8):18-19.
[2]我国供电煤耗率降至325克/千瓦时降速超预期[N/OL].新闻晚报,2011-04-15.http://finance.sina.com.cn/roll/20110415/13029696865.shtml
[3]崔民选.中国能源发展报告[M].北京：社会科学文献出版社,2009:136-139.
[4]西安热工所译.现行火电厂降低热耗率工作导则：50家美国电力公司降低电厂机组热耗率的经验总结,1993.
[5]李明,黄丕维,焦庆丰,等.大型汽轮机组运行方式优化试验研究及经济性分析[J].湖南电力,2008,28(1):27-30,49.
[6]雷如意,李新民,陈吉荣.125MW汽轮机组低负荷运行及经济性分析[J].热力发电,2002,31(6):59-63.
[7] M. Dentice D’Accadia. Optimal operation of a complex thermal system: a case study[J].International Journal of Refrigeration,2001,4(24):290-301.
[8]王晓龙.大型汽轮机组滑压运行参数优化及试验研究[M].北京：华北电力大学,2010.
[9]刘乃龙,刘永霞.300MW机组定滑定运行方式经济性分析[J].河北电力技术,2000,19(1):12-14.
[10] S. Makkonen, R. Lahdelma. Non-convex power plant modelling in energy optimisation[J].European Journal of Operational Research,2006,3(171):1113-1126.
[11]浙江省电力试验研究院.大型汽轮机滑压优化策略研究及应用[R/OL].2011-10-26.http://wenku.baidu.com/view/1f756bc0d5bbfd0a795673b2.html
[12] O. S. Naimanov. Features of the Selection of Initial Steam Pressure of Geothermal PowerStations with One and Two Evaporation Stages[J]. Thermal Engineering,1986,2(33):79-82.
[13] M. A. Rosen, I. Dincer. Exergoeconomic analysis of power plants operating on various fuels[J].Applied Thermal Engineering,2003,6(23):643-658.
[14] L. Bayón, J. M Grau, M. M. Ruiz. New development son equivalent thermal in hydrothermaloptimization: an algorithm of approximation[J]. Journal of Computational and AppliedMathematics,2005,175(1):63-75.
[15]魏铁征,王军.锅炉运行[M].天津:天津科学技术出版社,2000.
[16]任浩仁,李蔚,盛德仁,等.火电机组变工况下运行应达值的分析[J].中国电机工程学报.1999,19(9):50-52.
[17]崔映红,王惠杰,马晓芳.汽轮机变负荷运行时经济运行方式的探讨[J].研究与探讨.2002(4):4-8.
[18]吕太,吴海波,胡乔良.汽轮机最佳运行工况的经济性试验分析[J].东北电力大学学报,2010,30(1):1-4.
[19]闫顺林,刘帅,李玉辉.汽轮机变工况优化运行模型的研究[J].陕西电力,2009(7):24-27.
[20]胡冰,张仲民,武永运,等.应用BP神经网络确定汽轮机组滑压运行的最优初压[J].热力发电,2003(7):24-30.
[21]江永.基于遗传算法的调峰时最优运行初压的确定[J].现代电力,2008,25(2):61-63.
[22] X. Luo, B. Zhang, Y. Chen, et al. Modeling and optimization of a utility system containingmultiple extractions steam turbines[J]. Energy,2011,36(5):3501-3512.
[23]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[24] C.J.C. Burges. A tutorial on support vector machines for pattern recognition[J]. Data Mining andKnowledge Discovery,1998,2(2):121-167.
[25] C. Cortes, V. Vapnik. Support vector networks[J]. Machine Learning,1995,20(3):273-297.
[26]张勇,巩敦卫,张婉秋.一种基于单纯形法的改进微粒群优化算法及其收敛性分析[J].自动化学报,2009,35(3):289-298.
[27]李海燕,井元伟,马明旭.基于动态罚函数的协调优化算法[J].控制与决策,2009,24(6):911-914,920.
[28] A. J. Smola, B. Sch61kopf, K-R Mfiller. The connection between regularization operators andsupport vector kenerls[J]. Neural Networks,1998,11(4):637-649.
[29] E. Osuna, R. Freund, F. Girosi. An improved training algorithm for support vector machines[C].The Proceedings of IEEE Workshop on Neural Networks for Signal Processing, Amelea Island,1997,276-285.
[30] E. Osuna, R. Freund, F. Girosi. Training support vector machines: an application to facedetection[C]. The Proceedings of CVPR’97, NewYork,1997,130-136.
[31] T. Joachims. Transductive inference for text classification using support vector machine[C]. TheProceedings of the Sixteenth International Conference on Machine Learning, Morgan Kaufmann,1999,148-l56
[32] C. W. Hsu, C. J. Lin. A comparison of methods for multi-class support vector machines[J]. IEEETrans on Neural Networks,2002,13(2):415-425.
[33] P. Laskov. Feasible direction decomposition algorithms for training support vector machines[J].Machine Learning,2002,46(1):315-349.
[34] S. S. Keerthi, E. G. Gilbert. Convergence of a generalized SMO algorithm for SVM ClassifierDesign[J]. Machine Learning,2002,46(1):351-360.
[35] S. N. Ahmed. Incremental learning with support vector machines[C]. The Proceedings ofWorkshop on Support Vector Machines. Stockholm, Sweden,1999,208-307.
[36] M. Carozza, S. Rampone. Towards an incremental SVM for regression[C]. The Proceedings ofthe IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy,2000,405-410.
[37] R. Xiao, J. C. Wang, F. Y. Zhang. An approach to incremental SVM learning algorithm[C]. TheProceedings of12th IEEE International Conference on Tools with Artificial Intelligence Accouter,BC, Canada,2000,268-273.
[38] X. G. Zhang. Using class-center vectors to build support vector machines[C]. The Proceedings ofNeural Networks for Signal Processing IX-Proc of the1999IEEE Workshop, Wisconsin,1999,33-37.
[39] S. S. Keerthi, S. K. Shavade. A fast interactive nearest point algorithm for support vectormachine classifier design[J]. IEEE Trans on Neural Networks,2000,11(1):124-136.
[40] D. Bastos, D. Campos. A fast training algorithm for unbiased proximal SVM[C]. TheProceedings of International Conference on Acoustics Speech and Signal Processing,Philadelphia,2005,245-248.
[41] C. F. Lin, S. D Wang. Fuzzy support vector machines[J]. IEEE Transaction on Neural Networks,2002,13(2):464-471.
[42] C. J. Lin. On the convergence of the decomposition method for support vector machines[J].IEEE Transaction on Neural Networks,200l,12(6):1288-1298.
[43] M. L. Kuna, C. J. Lin. A Study on Reduced Support Vector Machines[J]. IEEE Transaction onNeural Networks,2003,14(6):1449-1459.
[44]林继鹏,刘君华.基于小波的支持向量机算法研究[J].西安交通大学学报,2005,39(8):816-819.
[45] D. H. Li, H. X. Du, T. J. Wu. A weighted support vector machine method and its application[C].The proceedings of the5“World Congress on Intelligent Control and Automation, Hangzhou,China,2004,1834-1837.
[46]宋杰,庸焕文.基于线性规划的v-支持向量机分类器[J].大连理工大学学报,2005,45(2):303-307.
[47] C. F. Chuang, F. Y. Shih. Recognizing facial action units using independent coinponent analysisand support vector machine[J]. Pattern Recognition,2006,39(9):1795-1798.
[48] R. Brunelli. Identity verification through finger matching: A comparison of support vectormachines and Gaussian basis functions classifiers[J]. Pattern Recognition Letters,2006,27(16):1905-1915.
[49] W. M. Apbell, J. P. Campbell, D.A. Reynolds et a1.Support vector machines for speaker andlanguage recognition[J].Computer Speech＆Language,2006,20(2):229.
[50] J. Cervantes, X. O. Li, W. Yu, et a1. Support vector machine classification for large data sets viaminimum enclosing ball clustering[J]. Neurocomputing,2008,71(46):611-619.
[51] F. Lauer, G. Bloch. Incorporating prior knowledge in support vector machines for classification:A review[J]. Neurocomputing,2008,71(7):1578-1594.
[52] U. Thissen, R. V. Brakel, A. P. Weijer, et a1. Using support vector machines for time seriesprediction[J]. Chemometrics and Intelligent Laboratory Systems,2003,69(1):35-49.
[53] H. Dong, H. L. Fu, W. M. Leng. Support vector machines for time series regression andprediction[J]. Journal of System Simulation,2006,18(7):1785-1788.
[54]王革丽,杨培才,毛字清.基于支持向量机方法对非平稳时间序列的预测[J].物理学报,2008,57(2):714-719.
[55] J. B. Gao, S. R. Gunn, C. J. Harris. Mean field method for the support vector machineregression[J]. Neurocomputing,2003,50:391-405.
[56] C. Hwang, D. H. Hong, K. H. Seok. Support vector interval regression machine for crisp inputand output data[J]. Fuzzy Sets and Systems,2006,157(8):1114-1125.
[57] Y. W. Kang, J. LI, G. Y. Cao, et a1. Dynamic temperature modeling of an SOFC using leastsquares support vector machines[J]. Journal of Power Sources,2008,179(2):683-692.
[58] H. J. Shin, D. H. Eom, S. S. Kim. One-class support vector machines an application in machinefault detection and classification[J]. Computers＆Industrial Engineering,2005,48(2):395-408.
[59] I. Ylamos, G. Escudero, M. Graells, et a1. Simultaneous fault diagnosis in chemical plants usingsupport vector machines[J]. Computer Aided Chemical Engineering,2007,24:1253-1258.
[60] J. Liang, R. Du. Model-based fault detection and diagnosis of HVAC systems using supportvector machine method[J]. International Journal of Refrigeration,2007,30(6):1104-1114.
[61] J. A. K. Sunken, J. Vandewalle. Least squares support vector machine classifiers[J]. NeuralProcessing Letters,1999,9(3):293-300.
[62] J. A. K. Sunkens. Nonlinear modeling and support vector machines[C]//IEEE Instrumentationand Measurement Technology Conference. Budapest, Hungary：Institute of Electrical andElectronics Engineers Inc.,2001:287-295.
[63] J. A. K. Sunkens, J. Vandewalle. Weighted least squares support vector maelaines：robustnessand sparse approximation[J]. Neuroeomputing,2002,(48):85-105.
[64] C. F. Lin, S. D. Wang. Fuzzy support vector machines[J]. IEEE Transaction on Neural Networks,2002,13(2):46-47.
[65] H. P. Huang, Y. h. Liu. Fuzzy support vector machines for pattern recognition and datamining[J]. International Jotmal of Fuzzy Systems,2002,4(3):826-835.
[66] H. M. Chi, O. K Ersoy. Recursive update Algorithm for Least Squares Support VectorMachines[J]. Neural Processing Letters,2003,2(17):165-173.
[67] K. S. Chua. Efficient Computations for Large Least Square Support Vector MachineClassifiers[J]. Pattern Recognition Letters,2003,24(1):75-80.
[68] J. A. K. Sunken, L. Lukas, V. Doreen, et a1. Least squares support vector machine classifiers: alarge scale algorithm[C]. The Proceeding of European Conference on Circuit Theory and Design:Institute of Electrical and Electronics Engineers Computer Society, Stresa, Italy,1999,839-842.
[69] W. Chu, C. J. Ong, S. S. Keerthi. An improved conjugate gradient scheme to the solution of leastsquares SVM[J]. IEEE Transaction on Neural Networks,2005,16(2):498-501.
[70] J. A. K. Sunkens, L. Lukas, J. Vandewalle. Sparse approximation using least squares supportvector machines[C], The Proceeding of IEEE Intemational Symposium on Circuits and Systems:Institute of Electrical and Electronics Engineers Inc, Geneva, Switzerland,2000,757-760.
[71] X. Y. Zeng, X. W. Chen. SMO-based pruning methods for sparse least squares support vectormachines[J]. IEEE Transaction on Neural Networks,2005,16(6):1541-1546.
[72]刘毅,王海清,李平.局部最小二乘支持向量机回归在线建模方法及其在间歇过程的应用[J].化工学报,2007(11):2846-2851.
[73] I. Goethals, K. Pelckmans, J. A. K. Suykens, et al. Identification of MIMO Hammerstein modelsusing least squares support vector machines[J]. Automatic,2005,41(7):1263-1272.
[74] I. Goethals, K. Pelckmans, J. A. K. Suykens, et a1. Subspace identificationof hammersteinsystems using least squares support vector machines[J]. IEEE Transtraction on AutomaticControl,2005,50(10):1509-1519.
[75]阎威武,朱宏栋,邵惠鹤.基于最小二乘支持向量机的软测量建模[J].系统仿真学报,2003,15(10):1494-1496.
[76]张英,苏宏业,褚健.基于模糊最小二乘支持向量机的软测量建模[J].控制与决策,2005,20(6):621-624.
[77]贾嵘,王小宇,蔡振华,等.最小二乘支持向量机回归的HHT在水轮发电机组故障诊断中的应用[J].中国电机工程学报,2006,26(22):128-133.
[78]杨奎河,单甘霖,赵玲玲.最小二乘支持向量机在故障诊断中的应用[J].计算机科学,2007,34(1):289-291.
[79]杨奎河,单甘霖,赵玲玲.基于最小二乘支持向量机的汽轮机故障诊断[J].控制与决策,2007,22(7):778-782.
[80]叶美盈.基于最小二乘支持向量机建模的混沌系统控制[J].物理学报,2005,54(1):30-34.
[81]刘斌,苏宏业,褚健.一种基于最小二乘支持向量机的预测控制算法[J].控制与决策,2004,19(12):1439-1402.
[82] J. A. K. Sunkens, L. Lukas, V. Doreen. Optimal control by least squares support vectormachines[J]. Neural Networks,2001,14(1):23-35.
[83]桑海峰,王福利,何大阔.基于最小二乘支持向量机的发酵过程混合建模[J].仪器仪表学报,2006,27(6):629-633.
[84] X. Lin, G. Y. Cao, X. J. Zhu. Modeling and control of PEMFC based on least squares supportvector machines[J]. Energy Conversion and Management,2006,47(7):1032-1050.
[85] H. B. Huo, X. J. Zhu, G. Y. Cao. Nonlinear modeling of a SOFC stack based on a least squaressupport vector machine[J]. Journal of Power Sources,2006,162(2):1220-1225.
[86] K. Polat, B. Akdemir, S. Günes. Computer aided diagnosis of ECG data on the least squaresupport vector machine[J]. Digital Signal Processing,2008,18(1):25-32.
[87] D. Hanbay. An expert system based on least square support vector machines for diagnosis of thevalvular heart disease[J]. Expert Systems with Applications,2008,36(3):4232-4238.
[88]张德富.启发式算法研究及应用[D].华中科技大学.2002,6.
[89] K.S. Tang, K.F. Man, S. Kwong, et al. Genetic algorithms and their applications[J]. IEEE SignalProcessing Magazine,1996,13(6):22-37.
[90] K. Scott. Optimization by simulated annealing: Quantitative studies[J]. Journal of StatisticalPhysics,1984,34(5-6):975-986.
[91] J.D. Farmer, N.H. Packard. The immune system, adaptation and machine learning[J], Physica D:Nonlinear Phenomena,1986,22(1-3):187-204.
[92] M Dorigo, V. Maniezzo A. Colorni. The ant system: optimization by a colony of cooperatingagents[J]. IEEE Transactions on Systems, Man, and Cybernetics-part B,1996,26(1):29-41.
[93] T. Jon, N. Mark, H, John. An artificial immune system for data analysis[J]. Biosystems,2000,55(1-3):143-150.
[94] J. Kennedy, R. Eberhart. Particle swarm optimization[C]. The proceedings of IEEE internationalconference on Neural Networks,1995,1942-1948.
[95] D. KARABOGA. An idea based on honey bee swarm for numerical optimization[R]. Kayseri:Erciyes University, Engineering Faculty, Computer Engineering Department,2005.
[96] M. Dorigo, V. Maniezzo, A. Colorni. The ant system: optimization by a colony of cooperatingagents[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part B,1996,26(1):29-41.
[97] V. Gazi, K.M. Passino. Stability analysis of social foraging swarms[J]. IEEE Transactions onSystems, Man, and Cybernetics-Part B,2004,34(1):539-557.
[98] T. Peter, Tarasewich, M. Patrick R. Swarm intelligence: power in numbers, Communications ofthe ACM-Evolving data mining into solutions for insights[J]. Communications of the ACM,2002,45(8):62-67.
[99] R. Esmat, N. Hossein, S. Saeid. BGSA: binary gravitational search algorithm[J]. NaturalComputing,2010,9(3):727-745.
[100] W. Du, B. Li. Multi-strategy ensemble particle swarm optimization for dynamic optimization[J].Information Sciences,2008,(178):3096-3109.
[101] E. Rashedi, H. Nezamabadi-pour, S. Saryazdi. GSA: A Gravitational Search Algorithm[J].Information Sciences,2009,179(13):2232-2248.
[102]徐遥,王士同.引力搜索算法的改进[J].计算机工程与应用,2011(35):1-5.
[103]谷文祥,李向涛,朱磊,等.求解流水线调度问题的万有引力搜索算法[J].智能系统学报,2010,5(5):411-418.
[104]谷文祥,郭丽萍,殷明浩.模糊c-均值算法和万有引力算法求解模糊聚类问题[J].智能系统学报,2011,6(6):520-525.
[105] D. Karaboga, B. Akay. A comparative study of Artificial Bee Colony algorithm[J]. AppliedMathematics and Computation,2009,214(1):108-132.
[106] D. Holliday, R. Resnick, J. Walker. Fundamentals of physics[M]. John Wiley and Sons,1993.
[107] R. M. Wald. General Relativity [M]. The University of Chicago Press,1984:11-23.
[108] R. Mansouri, F. Nasseri, M. Khorrami. Effective time variation of G in a model universe withvariable space dimension[J]. Physics Letters,1999,259(3-4):194-200.
[109] S. Rahnamayan. Opposition-based differential evolution[J]. Evolutionary Computation,2008,12(1):64-79.
[110] D. Karaboga, B Basturk. A powerful and efficient algorithm for numerical function optimization:artificial bee colony(ABC) algorithm[J]. Journal of Global Optimization,2007,39(3):459-471.
[111] D. Karaboga, B Basturk. On the performance of artificial bee colony(abc) algorithm[J]. AppliedSoft Computing,2008,8(1):687-697.
[112] D. Basak, S. Paland, D. C. Patranabis. Support Vector Regression[J]. Neural InformationProcessing,2007,11(10):203-225.
[113] Q. H. LI, Y. G. Zhang, M. Q. Chen, et al.Study on drying and combustion process in grate-CFBincinerator[J]. Science in China Series E: Technological Sciences,2009,52(5):1153-1160.
[114] S. S. Keerthi, C. J. Lin. Asymptotic behaviors of support vector machines with Gaussiankernel[J]. Neural Computation,2003,15(7):1667-1689.
[115] J. A. K. Suykens, L. Lukas, J.Vandewalle. Sparse approximation using least squares supportvector machines[C]. The Proceeding of IEEE Intemational Symposium on Circuits and Systems:Institute of Electrical and Electronics Engineers Inc, Geneva, Switzerland,2000,757-760.
[116]王春林,周昊,周樟华.基于支持向量机的大型电厂锅炉飞灰含炭量建模[J].中国电机工程学报,2005,25(20):72-77.
[117]王雷,王洪跃,张瑞青.基于支持向量机回归的凝汽器真空应达值确定方法的研究[J].汽轮机技术,2007,49(1):43-47.
[118]吴海姬,王雷,司风琪,等.基于BP神经网络的主蒸汽流量计算模型[J].汽轮机技术,2007,49(4):269-273.
[119]王雷,张瑞青,肖增弘,等.基于SVM的主蒸汽流量回归估计[J].华东电力,2008,36(12):89-92.
[120]周建新,王雷,吴海姬,等.基于支持向量回归的大容量机组主蒸汽流量建模[J].热能动力工程,2008,23(2):122-126.
[121]付忠广,靳涛,周丽君,等.复杂系统反向建模方法及偏最小二乘法建模应用研究[J].中国电机工程学报,2009,29(2):25-29.
[122]孙永平,朱芳梅,王敏.北仑电厂2号机组DAS系统主蒸汽流量计算模型的修改[J].浙江电力,2000,19(3):14-16.
[123]毕政益,黄欣.引进型300MW机组的主蒸汽流量计算模型[J].华东电力,1998(9):21-22.
[124]何军民,李明.湘潭电厂300MW机组主蒸汽流量计算模型的修改[J].湖南电力,2005,25(5):17-19.
[125]张文琴.反向建模方法的一般规律及其应用[M].华北电力大学,2009:3-10.
[126]杨苹,吴捷.火电厂锅炉常见故障的数据挖掘诊断方法[J].仪器仪表学报,2005,26(7):696-701.
[127]盛德仁,李蔚,刘长东,等.火电厂运行优化系统运行状况的调研与展望[J].浙江电力,2003,9(11):15-22.
[128] Z. H. Zou, T. L. Tseng, H. Sohn, et al. A rough set based approach to distributor selection insupply chain management[J]. Expert Systems with Applications,2011,38(1):106-115.
[129]雷绍兰,孙才新,周兰,等.属性约简在空间负荷预测中的应用[J].重庆大学学报,2004,27(3):85-88.
[130]黄锦涛,武学素.应用多元线性回归原理建立300MW抽汽凝汽式汽轮机组的特性方程[J].动力工程,1993,13(4):16-20.
[131] J. M. Liu. Analysis by regression for the operational performance of typical600MW turbine[J].Journal of Genus Sciences,1993,5(1):18-23.
[132]张文琴,付忠广,靳涛,等.基于偏最小二乘算法的热耗率回归分析[J].现代电力,2009,26(5):56-58.
[133]朱誉,冯利法,徐治皋.基于BP神经网络的热经济性在线计算模型[J].热力发电,2008,37(12):17-19.
[134] Z. H. Guo, J. Wu, H. Y. Hai. A case study on a hybrid wind speed forecasting method using BPneural network[J]. Knowledge-Based Systems,2011,24(7):1048-1056.
[135]王雷,张欣刚,王洪跃,等.基于支持向量回归算法的汽轮机热耗率模型[J].动力工程,2007,27(1):19-23.
[136] W. P. Zhang, P. F. Niu. LS-SVM based on chaotic particle swarm optimization with simulatedannealing and application[C]. The Proceedings of the2ndinternational conference on IntelligentControl and Information Processing, Harbin, China,2011,(2):931-934.
[137]盛德仁,李蔚,陈坚红,等.汽轮机组热耗率分析及实时计算[J].热力发电,2003,32(5):16-19.
[138]廖开太.自密封系统经济性运行[J].汽轮机技术,2005,47(5):18-24.
[139]吕太,吴海波,胡乔良.汽轮机最佳运行工况的经济性试验分析[J].东北电力大学学报,2010,30(1):1-4.
[140] V. Vapnik. Statistical Learning Theory[M]. New York: Wiley Interscience,1998.
[141] N. E. Ayat, M. Cheriet, C. Y. Suen. Automatic model selection for the optimization of SVMkernels[J]. Pattern Recognition,2005,38(10):1733-1745.
[142] K. B. Ismael, S. H. Salleh, J. M. Najeb, et al. Efficient parameter selection of support vectormachines[C]. The proceeding of the4thKuala Lumpur International Conference on BiomedicalEngineering,2008,183-186.
[143] L. G. Zhou, K. Kin, L. Yu. Credit scoring using support vector machines with direct search forparameters selection[J]. Soft Computing,2009,13(2):149-155
[144] L. Yu, X. Yao, S. Y. Wang, et al. Credit risk evaluation using a weighted least squares SVMclassifier with design of experiment for parameter selection[J]. Expert system With Application,2011,38(12):15392-15399.
[145] R. kohavi. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and ModelSection[C]. The Proceedings of the International Joint Conference on Artificial Intelligence,1995.
[146]任浩仁,李蔚,盛德仁,等.火电机组变工况下运行指标应达值的分析[J].中国电机工程学报,1999,19(9):50-53.
[147]童小忠,孙永平,樊印龙.汽轮发电机组滑压运行寻优方法的试验研究[J].浙江电力,2008(5):24-26.
[148]范鑫,秦建明,付晨鹏,等.超临界600MW汽轮机滑压优化运行的试验研究[J].汽轮机技术,2011,53(2):143-146.
[149]吕太,李耀德,胡乔良.汽轮机滑压运行方式的经济性实验分析[J].汽轮机技术,2010,52(2):127-129.
[150]杨海娅,谷俊杰.调峰运行时汽轮机组蒸汽初压的优化确定[J].应用能源技术,2010(7):39-43.
[151]姜巍,曹孟杰,张红,等.基于综合热效分析的汽轮机组运行优化研究[J].热力发电,2007(11):16-20.
[152]吴生辉.滑压运行经济性分析系统在火电厂的应用[J].自动化应用,2011(3):71-74.
[153]李秀云,严俊杰,林万超.滑压机组背压变化对经济性影响的两种新计算方法[J].中国电机工程学报,1999,19(9):22-26.
[154] R. Z. Aminov, A. M. Chertykov. Choice of optimal stage of initial steam pressure inheat-generating power units[J]. Tyazheloe Mashinostroenie,1992(8):18-19.