基于遗传算法的汽轮机数字电液调节系统的参数辨识研究

调节系统性能的退化和故障的发生，首先表现在系统各个组成环节的参数的变化上，因此通过参数辨识可以这现汽轮机调筇系统的性能预测，状态监测和故障诊断，文中在简要介绍遗传算法的基础上将其应用于汽轮机数字电液调节系统的参数辨识，给出了参数辨识的基本原理和数据处理方法，辨识结果表明，这种辨识算法具有计算速度快，精度高，程序通用性强等优点，通过合理选择误差函数，相对误差可以控制在1％以上，为汽轮机调节系统的参数辨识提供了一种有效的新方法，具有重要的工程使用价值。

STUDY ON PARAMETER IDENTIFICATION FOR STEAM TURBINE DHE GOVERNING SYSTEM BASED ON GENETIC ALGORITHM

System performance degeneration and fault occurrences will cause the time constant variations and parameter alterations of each element. Therefore, it is possible to realize the performance prediction and condition monitor as well as fault diagnosis for steam turbine governing system, using the parameter identification method. In this paper, Genetic Algorithm (GA) is used for parameter identification of steam turbine Digital Electrical Hydraulic (DEH) governing system, and the basic theory of parameter identification and data processing method with GA are studied. The identification results show that such parameter identification method with GA has the advantages of fast computation, high parameter identification precision, and better program generality. The relative error of parameter identification can be limited within 1% by reasonable selection of error function. It provides a new way for parameter identification of steam turbine governing system.