Valid from: Autumn 2019
Decided by: Margareta Sandahl
Date of establishment: 2019-08-27
Division: Chemical Engineering
Course type: Third-cycle course
Teaching language: English
Give insight into how mathematical models of process systems can be calibrated and validated against experimental data and how experiments should be planned for good model calibration.
Knowledge and Understanding
For a passing grade the doctoral student must know the basic methods for linear and nonlinear regression as well as corresponding regression analysis.
Competences and Skills
For a passing grade the doctoral student must use the basic methods in parameter estimation, model calibration and machine learning.
Judgement and Approach
For a passing grade the doctoral student must understand how the quality of data and design of experiments affect model calibration and evaluate properties of methods for parameter estimation and how these influence model calibration.
The course presents methods and their properties for parameter estimation and model calibration. The first part focuses on basic methods for linear and nonlinear regression along with model calibration. The second introduces experimental planning (DoE) and multivariate statistics, and machine learning. Some assignments and a model calibration project are also included in the course.
Englezos, P. & Kalogerakis, N.: Applied Parameter Estimation for Chemical Engineers.. Dekker media, 2001.
Types of instruction: Lectures, exercises, project
Examination formats: Written report, written assignments, seminars given by participants
Grading scale: Failed, pass
Examiner:
Admission requirements: Basic courses in transport phenomena, reaction engineering and separtion engineering or equivalent courses
Course coordinators:
Web page: https://staff.chemeng.lth.se/~BerntN/Courses/ModCal.html