Embedded Control System for Calibrating Gas Analysers
More Info
expand_more
Abstract
This Thesis report will discuss the development of embedded control systems for process control (in this case for the calibration of a gas analyser). The main research question being: Which control algorithm will be able to achieve the most optimal calibration procedure? A calibration bench which will be used to create a specific condition (gas concentration, gas pressure, gas flow) for a gas analyser, so that it can be calibrated accurately.
Embedded Systems usually suffer from low computation power and do not have a lot of resources available, so designing a control system for an embedded system will require some special attention.
Designing a good controller is never an easy task, every single component needs to be chosen in a way to meet the requirements and ensure best performance. Controller design both programming/simulations and hardware development: both are important to get a good regulation, direct/linear and predictable actuation is needed. Therefore hardware design should make sure that reading sensors and actuating actuators do not suffer from big non linearities or delays.
Software will make a big difference in the sense of: how efficient is the algorithm? Is it robust (what happens to the system when an error occurs, will it show unexpected behaviour or will it stay stable)?
This report has been cut in 5 big pieces: hardware design,
embedded software design, interface software design, model identification and
controller design.
Hardware design will elaborate on the electronic circuit design and the mechanical design of the pneumatics.
Embedded software design will elaborate on the software written for the control
board (which is responsible for regulating gas pressure and gas flow).
Interface software design will show the development of the GUI (Graphical User
Interface), so the user can interact with the calibration bench by simply clicking on buttons instead of working with a command line tool.
Model identification will explain how to get a prediction model of the process
out of the data of a set of carefully selected tests.
Controller design will elaborate more on the control algorithms designed and
how to use the prediction model found in model identification.