期刊文献+

基于T-S模糊模型的船舶柴油机动态辨识

Dynamic Identification of Ship Diesel Engine Based on T-S Fuzzy Model
下载PDF
导出
摘要 考虑到船舶柴油机模型的非线性和负载的不确定性,用T-S(Takagi-Sugeno)模糊辨识方法建立了船舶柴油机的动态模型。采用模糊聚类简化了T-S模糊规则数的确定和前提中隶属度函数参数的生成,用加权最小二乘算法得出辨识结论中的线性参数。对船舶柴油机在稳态运行工况下作小偏差工况扰动实验,得到在油门尺度和负载变化下柴油机转速、涡轮增压器转速等输出数据,利用该数据建立了描述柴油机动态性能的T-S模糊模型。仿真结果表明,利用该算法能有效地辨识出柴油机转速、涡轮增压器转速、增压压力、空冷器压力等输出在小工况扰动下的变化模型。 Considering the nonlinear of ship diesel engine model and the uncertainty of its loads, the paper investigated a T-S fuzzy identification algorithm to build ship diesel engine dynamic model. The number of fuzzy rules and the parameters of membership functions in the antecedent of T-S model were generated by fuzzy clustering method, the linear parameters of identification consequent in each rule were separately identified by weighted least square method. The output data of diesel speeds and turbocharger speeds under different throttle scales and loads were gained from some experimentations, when diesel engine was disturbed by a small deviation signal in its steady running state, the data were used to build a T-S fuzzy model of ship diesel engine, which could express the dynamic characteristic of diesel engine. Simulation result shows that the method is effective to identify the models of diesel engine speed, turbocharger speed, turbocharger pressure and air condenser pressure under small deviations. 2 tabs, 6 figs, 10 refs
出处 《交通运输工程学报》 EI CSCD 北大核心 2006年第1期80-83,共4页 Journal of Traffic and Transportation Engineering
基金 上海市教育委员会科研重点项目(04FA02) 上海市重点学科建设项目(T0602)
关键词 轮机工程 柴油机 系统辨识 T-S模糊模型 模糊聚类 marine engineering diesel engine system identification T-S fuzzy model fuzzy clustering
  • 相关文献

参考文献8

二级参考文献23

  • 1赵振宇.模糊理论和神经网络的基础和应用[M].北京:清华大学出版社,1993..
  • 2徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1993..
  • 3[1]Gamo S, Ouenou R A, Ouladsine M. GMDH Method Applied to Nonlinear Identification of a Turbocharged Diesel Engine [J]. Systems Analysis Modelling Simulation, 2000, 37(4): 501~512.
  • 4[2]Hafner M, Schuler M, Nelles O. Dynamical Identification and Control of Combustion Engine Exhaust [C]. Pro of ACC, 1999. 222~226.
  • 5[3]Park J, Sandberg I W. Approximation and Radial-Basis-Function Network[J]. Neural Computation, 1993,5(3): 305~316.
  • 6[4]Chen T P, Chen H. Approximation Theory Capability to Functions of Several Variables, Nonlinear Functional, and Operators by Radial Basis Functions Neural Network [J]. IEEE Trans. on Neural Network, 1995,6: 904~910.
  • 7[5]Kohonen T. Self-Organization Maps(3rd edition) [M]. Berlin: Springer-Verlag, 2001. 105~176.
  • 8[6]Roy S, Malik O P, Hope G S. A Least-Squares Based Model-Fitting Identification Technique for Diesel Prime-Movers with Unknown Dead-Time [J]. IEEE Trans. on Energy Conversion, 1991, 6(2): 251~256.
  • 9[7]Hovakimyan H, Lee H, Calise A. On Approximate NN Realization of an Unknown Dynamic System from its Input-Output History [C]. Pro. of ACC, 2000. 919~923.
  • 10[8]Langari R, Wang L. A Modified RBF Network with Application to System Identification [C]. Pro. of IEEE Conference on Control Application, 1995. 649~654.

共引文献35

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