Study Guide

Objective

Understanding of process systems is a central part of industrial automation. Dynamical systems are described through modeling and identification. The course aims at introducing different modeling techniques to the students to achieve a common platform of knowledge. The student will learn how to recognize, analyze, and describe different dynamic systems and to construct models, both model- and data driven ones, of systems and assess their quality and performance.

Knowledge and understanding
After completing the course, the student should be able to:
- recognize and describe common dynamic process systems
- explain the difference between various systems
- describe the practical usage of some process models

Skills and abilities
After completing the course, the student should be able to:
- create and simulate process models
- experiment with different process models
- perform basic identification of processes

Evaluation ability and approach
After completing the course, the student should be able to:
- justify the choice of a process model
- evaluate and report on the choice of a model

Content

The contents of the course are concept and principles of dynamic systems, system modeling and simulation, techniques for system identification and optimization.

Materials

The study material will be provided by the lecturer.

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

Grade 1: Satisfactory skills in systems thinking, modeling, identification, and optimization.

Assessment criteria, good (3)

Grade 3: Good skills in systems thinking, modeling, identification, and optimization.

Assessment criteria, excellent (5)

Grade 5: Excellent skills in systems thinking, modeling identification, and optimization.

Qualifications

No prerequisites.

Objective

The students will be introduced to intelligent systems in the industrial context. The student will learn what defines an intelligent system and the basic principles of intelligent systems. The student will gain knowledge of the parts that constitute an intelligent system and how they interact.

After completing the course, the student should be able to:
Knowledge and understanding
- explain the basic parts and functionality of an intelligent system
- describe the challenges, risks, and opportunities with intelligent systems
- understand the working principles of intelligent systems

Skills and abilities
- analyze the needs and requirements for an intelligent system
- practice with different methods for realizing intelligent systems

Evaluation ability and approach
- plan the development of an intelligent system
- propose and evaluate solutions for intelligent systems

Content

Content
The course gives an overview of intelligent systems in the industrial automation context. The course serves as a common platform of knowledge for the studies in the program. Content:
• Fundamentals of industrial automation systems
• Data-driven and model-based design
• Automated and autonomous decision making
• Digital twins
• Sensors and IoT devices
• Data collection, storage, and flow
• Cyber security

Materials

The study material will be provided by the lecturer.

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

Grade 1: Satisfactory skills in understanding and development of intelligent systems.

Assessment criteria, good (3)

Grade 3: Good skills in understanding and development of intelligent systems.

Assessment criteria, excellent (5)

Grade 5: Excellent skills in understanding and development of intelligent systems.

Qualifications

No prerequisites.

Objective

The course focuses on different machine learning and artificial intelligence-based techniques that can be used for system identification, process optimization, classification, and predictive purposes.

After completing the course, the student:
- has knowledge of what AI and ML is, where it is used and how it has development
- can identify and recognize industrial problems that are solvable through machine learning
- can plan and apply the machine learning workflow for classification and regression problems
- understands and can explain the difference between different machine learning tasks and techniques

- can recognize different inputs used in AI and machine learning
- is able to develop and build machine learning models for different tasks
- can validate and test the performance of a model

- knows how to interpret the result of a machine learning experiment
- report on the result of a machine learning experiment
- can assess the outcome of a machine learning experiment

Content

The availability of big amounts of data from various systems makes it possible to apply both linear and nonlinear models. The course focuses on different techniques that can be used for identification, classification, and regression in industrial automation. The course also gives knowledge of feature selection and pre-processing techniques.

Materials

The study material will be provided by the lecturer.

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

Grade 1: Satisfactory skills in understanding and applying ML techniques for classification, prediction, and identification.

Assessment criteria, good (3)

Grade 3: Good skills in understanding and using ML techniques for classification, prediction, and identification.

Assessment criteria, excellent (5)

Grade 5: Excellent skills in understanding and using ML techniques for classification, prediction, and identification. 

Qualifications

No prerequisites.

Objective

The student
- has identified a relevant task to explore
- has written a description of the research problem following the principles in scientific writing (the research plan)
- has chosen a suitable method for the project and has access to relevant data sources
- has presented the thesis project (the start-up seminar)
- is able to revise the project after receiving feedback.

Content

Master's thesis - part 1

Evaluation scale

Approved/Rejected

Qualifications

No prerequisites.

Objective

During the second stage the thesis process continues by gathering information and combining the theoretical framework and empirical work/data collection.

The student
- is able to critically evaluate the used sources and methods
- can select applicable sources and uses them systematically
- is able to use the methods chosen and theory required for the project
- is able to discuss work in progress

Content

Master's thesis work - part 2

Evaluation scale

Approved/Rejected

Qualifications

Master's thesis - part 1

Objective

The student:
- masters the methods and practices used in the area of intelligent systems and industrial automation and is able to complete a thesis
- is able to document the final results and report the findings according to good scientific and ethical principles
- is capable to give a final presentation as well as to publish the thesis
- the thesis writer follows all thesis process related steps and rules.

Content

Master's thesis work - part 3

Evaluation scale

Approved/Rejected

Qualifications

Master's thesis - part 2

Objective

The course focuses on different machine learning and artificial intelligence-based techniques that can be used for system identification, process optimization, classification, and predictive purposes.

After completing the course, the student:
- has knowledge of what AI and ML is, where it is used and how it has development
- can identify and recognize industrial problems that are solvable through machine learning
- can plan and apply the machine learning workflow for classification and regression problems
- understands and can explain the difference between different machine learning tasks and techniques

- can recognize different inputs used in AI and machine learning
- is able to develop and build machine learning models for different tasks
- can validate and test the performance of a model

- knows how to interpret the result of a machine learning experiment
- report on the result of a machine learning experiment
- can assess the outcome of a machine learning experiment

Content

The availability of big amounts of data from various systems makes it possible to apply both linear and nonlinear models. The course focuses on different techniques that can be used for identification, classification, and regression in industrial automation. The course also gives knowledge of feature selection and pre-processing techniques.

Materials

The study material will be provided by the lecturer.

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

Grade 1: Satisfactory skills in understanding and applying ML techniques for classification, prediction, and identification.

Assessment criteria, good (3)

Grade 3: Good skills in understanding and using ML techniques for classification, prediction, and identification.

Assessment criteria, excellent (5)

Grade 5: Excellent skills in understanding and using ML techniques for classification, prediction, and identification. 

Qualifications

No prerequisites.

Objective

Understanding of process systems is a central part of industrial automation. Dynamical systems are described through modeling and identification. The course aims at introducing different modeling techniques to the students to achieve a common platform of knowledge. The student will learn how to recognize, analyze, and describe different dynamic systems and to construct models, both model- and data driven ones, of systems and assess their quality and performance.

Knowledge and understanding
After completing the course, the student should be able to:
- recognize and describe common dynamic process systems
- explain the difference between various systems
- describe the practical usage of some process models

Skills and abilities
After completing the course, the student should be able to:
- create and simulate process models
- experiment with different process models
- perform basic identification of processes

Evaluation ability and approach
After completing the course, the student should be able to:
- justify the choice of a process model
- evaluate and report on the choice of a model

Content

The contents of the course are concept and principles of dynamic systems, system modeling and simulation, techniques for system identification and optimization.

Materials

The study material will be provided by the lecturer.

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

Grade 1: Satisfactory skills in systems thinking, modeling, identification, and optimization.

Assessment criteria, good (3)

Grade 3: Good skills in systems thinking, modeling, identification, and optimization.

Assessment criteria, excellent (5)

Grade 5: Excellent skills in systems thinking, modeling identification, and optimization.

Qualifications

No prerequisites.

Objective

The student
- has identified a relevant task to explore
- has written a description of the research problem following the principles in scientific writing (the research plan)
- has chosen a suitable method for the project and has access to relevant data sources
- has presented the thesis project (the start-up seminar)
- is able to revise the project after receiving feedback.

Content

Master's thesis - part 1

Evaluation scale

Approved/Rejected

Qualifications

No prerequisites.

Objective

During the second stage the thesis process continues by gathering information and combining the theoretical framework and empirical work/data collection.

The student
- is able to critically evaluate the used sources and methods
- can select applicable sources and uses them systematically
- is able to use the methods chosen and theory required for the project
- is able to discuss work in progress

Content

Master's thesis work - part 2

Evaluation scale

Approved/Rejected

Qualifications

Master's thesis - part 1

Objective

The student:
- masters the methods and practices used in the area of intelligent systems and industrial automation and is able to complete a thesis
- is able to document the final results and report the findings according to good scientific and ethical principles
- is capable to give a final presentation as well as to publish the thesis
- the thesis writer follows all thesis process related steps and rules.

Content

Master's thesis work - part 3

Evaluation scale

Approved/Rejected

Qualifications

Master's thesis - part 2

Objective

The students will be introduced to intelligent systems in the industrial context. The student will learn what defines an intelligent system and the basic principles of intelligent systems. The student will gain knowledge of the parts that constitute an intelligent system and how they interact.

After completing the course, the student should be able to:
Knowledge and understanding
- explain the basic parts and functionality of an intelligent system
- describe the challenges, risks, and opportunities with intelligent systems
- understand the working principles of intelligent systems

Skills and abilities
- analyze the needs and requirements for an intelligent system
- practice with different methods for realizing intelligent systems

Evaluation ability and approach
- plan the development of an intelligent system
- propose and evaluate solutions for intelligent systems

Content

Content
The course gives an overview of intelligent systems in the industrial automation context. The course serves as a common platform of knowledge for the studies in the program. Content:
• Fundamentals of industrial automation systems
• Data-driven and model-based design
• Automated and autonomous decision making
• Digital twins
• Sensors and IoT devices
• Data collection, storage, and flow
• Cyber security

Materials

The study material will be provided by the lecturer.

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

Grade 1: Satisfactory skills in understanding and development of intelligent systems.

Assessment criteria, good (3)

Grade 3: Good skills in understanding and development of intelligent systems.

Assessment criteria, excellent (5)

Grade 5: Excellent skills in understanding and development of intelligent systems.

Qualifications

No prerequisites.