期刊文献+

基于最小二乘支持向量机的生物质发电气化过程建模 被引量:1

Study on the Gasification Process Model of Biomass Power Generation Based on Least Square Support Vector Machine
下载PDF
导出
摘要 采用动力学方法进行生物质发电的气化过程建模需要许多物性参数,而这些参数往往难以获得。针对机理建模的这些缺陷,考虑直接基于实验数据进行气化建模,提出了基于最小二乘支持向量机的建模方法,给出了相应的系统结构和算法,用实验数据进行验证取得了很好的预测效果。通过和实际数据的比较,仿真结果证明该方法具有很好的性能指标,能为现场生物质发电气化过程的控制与优化提供一定的参考依据。 The gasification process modeling of biomass power generation based on dynamic method needs a lot of parameters, but these parameters are usually not easy to get. One modeling method based on least square support vector machine (LS-SVM) which directly using the experimental data was presented to overcome the weaknesses of mechanism modeling, the system structure and algorithm were given, the experimental results prove the precision of this model. Compared with the experimental data, the simulation results showed that this method has good performance, it can provide controling and optimization reference to the gasification process of biomass power generation.
出处 《电力科学与工程》 2009年第12期1-4,共4页 Electric Power Science and Engineering
基金 国家自然科学基金资助项目(50776030)
关键词 生物质发电 最小二乘支持向量机 气化过程 建模 biomass power generation LS-SVM gasification process modeling
  • 相关文献

参考文献5

  • 1Sakoda A, Sadakata M, Koya T, et al. Gasification of biomass in a fluidized bed [J]. The Chemical Engineering Journal, 1981, 22 (3): 221-227.
  • 2Mansaray K G, Al-Taweel A M, Ghaly A E, et al. Mathematical Modeling of a Fluidized Bed Rice Husk Gasifier: PartⅠ-Model Development [J]. Energy Sources, 2000,22: 83-98.
  • 3Bing Guo, Dingkai Li. Congming Cheng et al Simulation of biomass gasification with a hybrid neural network model [J]. Bioresource Technology, 2001,76 (2): 77-83.
  • 4李学军,桂卫华,张艳存,王凌云.基于LS-SVM的软测量模型及其工业应用[J].计算机测量与控制,2008,16(3):294-296. 被引量:7
  • 5相征,张太镒,孙建成.基于最小二乘支持向量机的非线性系统建模[J].系统仿真学报,2006,18(9):2684-2687. 被引量:27

二级参考文献21

  • 1桂卫华,李勇刚,阳春华,陈志盛.基于改进聚类算法的分布式SVM及其应用[J].控制与决策,2004,19(8):852-856. 被引量:13
  • 2李勇刚,桂卫华,胡燕瑜.基于PCA的多神经网络软测量模型及其在工业中的应用[J].小型微型计算机系统,2004,25(10):1781-1784. 被引量:9
  • 3吴德会.一种基于LS-SVM的特征提取新方法及其在智能质量控制中的应用[J].计算机应用,2006,26(10):2446-2449. 被引量:1
  • 4Brillinger D R. Time series, Data Analysis and Theory[M]. New York:McGraw-hill, 1981.
  • 5Han M, Xi J, Xu S. Prediction of chaotic time series based on the recurrent predictor neural network[J]. IEEE Trans. Signal Processing(S1053-587X), 2004, 52(2): 3409-3416.
  • 6Wang L P, Teo K K, Lin Z. Predicting time series using wavelet packet neural networks[C]//Proc. IJCNN 200L 2001: 1593-1597.
  • 7Castillo O, Melin P. Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic, and fractal theory[J].IEEE Trans. Neural Networks(S1045-9227), 2002, 13(1): 1395-1408.
  • 8Vapnik V. The Nature of Statistical Learning Theory[M]. Translated by Zhang Xuegong. Beijing: Tsinghua University Press, 2000:91-108.
  • 9Wang L P(Ed.). Support Vector Machines: Theory and Application[M].New York: Springer, Berlin Heidelberg, 2005: 51-123.
  • 10Suykens J A K, Vandewalle J. Least Squares Support Vector Machines [J]. Neurel Processing Letters(S1370-4621), 1999, 9(3):293-300.

共引文献32

同被引文献15

引证文献1

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部