Process Models

Low-order transfer function models with static gain, time constant, and input/output delay

Process models are popular for describing system dynamics in many industries and apply to various production environments. The advantages of these models are that they are simple, they support transport delay estimation, and the model coefficients have easy interpretations as poles and zeros.

A simple SISO process model has a gain, a time constant, and a transport delay.

$s y s = \frac{K_{p}}{1 + T_{p 1} s} e^{- T_{d} s} .$

Here, K_p is the proportional gain, T_p₁ is the time constant of the real pole, and T_d is the transport delay (dead time).

In System Identification Toolbox™, the idproc model provides the process model structure and can represent process models with up to three poles and a zero.

For more information, see What Is a Process Model?

Apps

System Identification

Identify models of dynamic systems from measured data

Live Editor Tasks

Estimate Process Model

Estimate continuous-time process model for single-input, single-output (SISO) system in either time or frequency domain in the Live Editor

Functions

expand all

Create Process Model

`idproc`	Continuous-time process model with identifiable parameters
`procest`	Estimate process model using time-domain or frequency-domain data

Model Initialization and Structure Parameters

`pem`	Prediction error minimization for refining linear and nonlinear models
`idpar`	Create parameter for initial states and input level estimation
`delayest`	Estimate time delay (dead time) from data
`init`	Set or randomize initial parameter values

Extract or Set Model Parameters

`getpvec`	Obtain model parameters and associated uncertainty data
`setpvec`	Modify values of model parameters
`getpar`	Obtain attributes such as values and bounds of linear model parameters
`setpar`	Set attributes such as values and bounds of linear model parameters

Estimation Options

procestOptions Options set for procest

Topics

Process Model Basics

What Is a Process Model?
A process model is a simple continuous-time transfer function that describes linear system dynamics in terms of static gain, time constants, and input-output delay.
Data Supported by Process Models
Use regularly sampled time-domain and frequency-domain data, and continuous-time frequency-domain data.

Estimate Process Models

Estimate Process Models Using the App
Specify model parameters and estimation options to use for estimating a process model.
Identify Low-Order Transfer Functions (Process Models) Using System Identification App
Identify continuous-time transfer functions from single-input/single-output (SISO) data using the app.
Estimate Process Models at the Command Line
Estimate first-order process models with fully free parameters and with a combination of fixed and free parameters.
Estimating Multiple-Input, Multi-Output Process Models
Specify whether to estimate the same transfer function for all input-output pairs, or a different transfer function for each pair.

Set Process Model Options

Process Model Structure Specification
Configure the model structure by specifying the number of real or complex poles, and whether to include a zero, delay, and integrator.
Disturbance Model Structure for Process Models
Specify a noise model.
Specifying Initial Conditions for Iterative Estimation Algorithms
Specify how the algorithm treats initial conditions for estimation of model parameters.

Featured Examples

Building and Estimating Process Models Using System Identification Toolbox

Build simple process models using System Identification Toolbox.

Open Script