Syllabus for |
|
IMS065 - Data science in product realization
|
Data science inom produktframtagning |
|
Syllabus adopted 2020-02-10 by Head of Programme (or corresponding) |
Owner: MPPEN |
|
7,5 Credits
|
Grading: TH - Pass with distinction (5), Pass with credit (4), Pass (3), Fail |
Education cycle: Second-cycle |
Major subject: Automation and Mechatronics Engineering, Mechanical Engineering
|
Department: 40 - INDUSTRIAL AND MATERIALS SCIENCE
|
Teaching language: English
Application code: 34125
Open for exchange students: Yes
Block schedule:
B
Maximum participants: 50
Module |
|
Credit distribution |
|
Examination dates |
Sp1 |
Sp2 |
Sp3 |
Sp4 |
Summer course |
No Sp |
0120 |
Project |
7,5 c |
Grading: TH |
|
|
7,5 c
|
|
|
|
|
|
|
In programs
MPPDE PRODUCT DEVELOPMENT, MSC PROGR, Year 2 (elective)
MPPEN PRODUCTION ENGINEERING, MSC PROGR, Year 2 (elective)
MPPEN PRODUCTION ENGINEERING, MSC PROGR, Year 1 (elective)
Examiner:
Anders Skoogh
Go to Course Homepage
Eligibility
General entry requirements for Master's level (second cycle)
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.
Specific entry requirements
English 6 (or by other approved means with the equivalent proficiency level)
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.
Course specific prerequisites
Programming, statistics, fundamentals of product and/or production development.
Aim
The purpose is to enable data-driven and facts-based decisions in mechanical engineering,
specifically in the industrial product realization process. Therefore, the course aims to provide the students with fundamental knowledge about data science (including elements of Artificial Intelligence and Machine Learning) and abilities to apply data science techniques for improving production systems and product development.
Learning outcomes (after completion of the course the student should be able to)
On successful completion of the course, the student will be able to:
LO1. Describe the fundamentals of data science, its applications (AI/ML), data-driven modelling and big data analytics.
LO2. Apply the basics of well-known libraries of the toolboxes for data scientists.
LO3. Describe steps of the data mining process.
LO4. Describe and apply visualization techniques with respect to the data mining process.
LO5. Perform data pre-processing methods to ensure multi-dimensional measure of data quality.
LO6. Explain fundamental meaning and interpret applicability AI/ML algorithms for improving production systems and product development.
LO7. Interpret and discuss state-of-the-art knowledge from scientific papers related with data science in mechanical engineering.
LO8. Implement commonly used AI/ML algorithms, analyze their performance, and discuss their application using industrial applications from product realization life cycle.
LO9. Critically analyze and argue key ethical principles and potential impacts of AI on people and society and evaluate social and human requirements of systems and scenarios.
Content
The course is divided five modules and each module covers the following topics:
Module 1: Introduction to Data Science
• Fundamentals of data science (AI/ML)
• An overview of data-driven modelling and big data analytics
• Introducing toolboxes for data scientists
Module 2: Data Mining & Visualization
• Introduction to the data mining process
• Exploratory Data Analysis (EDA) & Statistics
• An overview of data quality dimensions
• Methods for data pre-processing
Module 3: AI and ML
• A general introduction to AI and ML
• Examples of ML algorithms to understand in what situations they can be used
• Examples of Deep Learning: Neural Networks (NNs)
• Analysis of different industrial applications from product realization life cycle using AL/ML
Module 4: The Ethics of AI
• Ethical, regulatory and social aspects of AI
• Understanding of how to work together with AI technologies
Module 5: How to drive AI in the product realization process
• Practicing with group work project for understanding AI/ML systems through the appropriate formulation of the selected industrial cases from product realization life cycle
Organisation
The course applies active learning methods including problem-based learning activities and flipped classroom techniques to be able to engage with students and support their learning in a creative way. Different learning activities will be used in the modules:
• Lectures
• Laboratory lectures including introductive programming tutorial
• Modelling exercises for training different visualization, data pre-processing techniques, and AI/ML applications
• Project work with laboratory exercises
• Presentation and discussion of scientific papers related to applications in the product realization process
Literature
- Scientific papers
- Lecture materials
Examination including compulsory elements
Grading is based on a project work, summarizing the laboratory exercises throughout the course and discussing the results in relation to state-of-the-art knowledge within the field. The project outcome includes a technical report, with lab reports and discussions, and an individual mandatory knowledge test. Grades are individual and the scale is 5, 4, 3, Fail.