过程辨识Lec1课件.pptVIP

系 统 辨 识System Identification 上海交通大学自动化系 袁景淇 jqyuan@ Tel:Fall 2010 What is system identification ? 系统辨识： 根据动态系统在输入作用下的响应, 或根据系统在正常运行时的输入输出记录数据，通过数据处理得出系统模型的学问。System identification focuses on the modeling of dynamical systems from experimental data （D.E. Rivera/Arizona State University）; System Identification is the experimental approach to process modeling (V.M. Becerra/Uni Reading). 它默认：系统的动态特性“必然”表现在其变化着的输入输出数据中，而辨识就是用数学的方法从数据序列中提炼出动态对象的模型。 系统辨识也叫过程辨识 System identification includes usually the following steps: (1) Experiment design The purpose is to obtain good experimental data, including the choice of the measured variables and of the character of the input signals. (2) Selection of model structure A suitable model structure is chosen using prior knowledge and trial and error. (3) Choice of the criterion to fit A suitable cost function is chosen, which reflects how well the model fits the experimental data. (4) Parameter estimation An optimization problem is solved to obtain the numerical values of the model parameters. (5) Model validation The model is tested in order to reveal any inadequacies. The flow chart of system identification: Choose model structure Experiment design Data Choose cri-terion to fit Parameter identification Validate model OK If not OK Then revise Use of system identification in adaptive control Plant Output Control signal Controller Parameter adjustment Set point Process re-identification parameter adjustment of the controller Adjusted parameters Two key factors for using adaptive control are ? Variations in process dynamics ? Variations in the character of the disturbances On-line determination of process parameters is a key element in adaptive control Outline of the course Discrete description of dynamical processes Modeling in general; First principle modeling ARMA model, RWLS, Runge-Kutta, Simplex Nonlinear system identification with ANN - modeling for a bioprocess as an e