Learning outcome

On successful completion of the module, students will have learning outcomes in the form of acquired knowledge, skills, and general competence, as described below.

Knowledge
On successful completion of the module the students will be able to:
understand multivariate analysis and calibration techniques
understand basic experimental design approaches
understand the theory and practice of sampling
explain what soft sensors (SS) are
identify strategies for SS based on multi sensor data fusion, fuzzy logic, neural networks,
discuss possibilities of implementing SS for a given application
describe the underlying SS principle for a SS solution

Skills
On successful completion of the module, the candidate will be able to:
use experimental design approaches
analyse multivariate data
calibrate multivariate models for prediction
apply theory of sampling in practice
appraise the key issues related to SS for a concrete application
compare different SS solutions for various case studies
design SS using fuzzy logic or neural network

General competence
On successful completion of the module, the candidate will be able to:
communicate acquired knowledge in specific subtopics involving concrete practical assignments in the form of technical reports and oral presentations to peers and staff.
[1] Codes given in parentheses correspond to the codes given in the programme description.

Course Description

Multivariate Data Analysis: Experimental design, significant testing, factorial design, fractional factorial design, regression, MLR, PCA (principal component analysis) multivariate calibration: PCR (principal component regression), PLS-R (partial least squares regression), validation of multivariate prediction models, overview of multivariate data analysis methods, applications/ examples and computer assignments.

Soft sensors: Wherever several (even hundreds or thousands of) measurements are processed together, the soft sensor approach is a viable approach. Fusion of such measurement signals can be used for estimating new quantities without actually measuring them. Soft sensors are data-centric and data-driven and evolve out of multi sensor data fusion (MSDF), where measurements of diverse characteristics and dynamics are fused to get an overall view of the system under study. Key topics are:

Multi Sensor Data Fusion (MSDF), Soft sensor. Steps in soft sensor technology: data collection, data pre-processing, variable and time delay selection, calibration, and validation.

Assessment Methods

A set of mandatory assignments count 40% and an individual written final test counts 60% of the final grade.
No study aids are permitted during the final written exam.
The assignments and the final test are used to assess knowledge and skills. The assignments are also used to assess general competence.

Minor adjustments may occur during the academic year, subject to the decision of the Dean