Engineering Systems Design Analytics and AI, 6.0 ECTS
March 1 @ 08:00 - May 31 @ 17:00
CREDITS |
6.0 (ECTS) credits |
COURSE LEVEL |
Post graduate level (Science Master, and PhD students) |
EXAMINER |
Petter Krus, Linköping University (LiU) |
CONTACT |
Petter Krus, Linköping University (LiU) petter.krus@liu.se |
TARGET GROUP |
PhD student interested in model-based system engineering and design analytics and the application of artificial intelligence. |
PREREQUISITES |
Basic background in engineering. Some experience in Python is advantageous but not required. |
AIM |
The course aims to provide doctoral students with advanced analytical methods for evaluation and design of complex engineering systems. Emphasis is placed on statistical modelling, machine learning, sensitivity analysis, functional modelling, system complexity, and information-theoretic measures. The course prepares participants to critically and productively integrate modern machine learning techniques and large language models into engineering research and industrial development projects.
|
LEARNING OUTCOMES |
After successful completion of the course, the student shall be able to: Apply functional modelling, decomposition, and systematic methods for engineering system concept generation. Develop data-driven models capturing relationships between system requirements and component or system characteristics. Perform sensitivity and robustness analyses and interpret system coupling effects. Estimate and analyse system complexity, including computational complexity aspects. Use Generative AI tools to generate, evaluate, and refine analysis-oriented software code for system design, modelling, and design analytics, with critical assessment of correctness and applicability. |
CONTENTS |
Design analytics (8 hours)
• Axiomatic design • Sensitivity analysis • Robustness • Functional correlation Machine learning and design space generation (8 hours)
• Introduction to machine learning in design contexts • Multiple regression analysis • Principal component analysis (PCA) using singular value decomposition (SVD) • Neural networks • Design space representation and parametrization System structures and modelling (4 hours)
• Use of large language models (LLMs) for analysis, modelling, and simulation • Requirement and functional modelling (UML/SysML) • Dependency structure matrices • System concept generation supported by LLMs Information entropy in engineering design (4 hours)
• Shannon’s information theory • Information entropy as a measure of system complexity • Design space quantification • Axiomatic design and complexity • System optimisation and information entropy Throughout the course, large language models are treated as design-support and analysis tools, with emphasis on critical evaluation, validation, and integration into engineering workflows.
|
TEACHING AND LEARNING ACTIVITIES |
The course is delivered online and consists of lectures, supervised exercises, project work, and an examination presentation meeting. Each scheduled teaching occasion typically includes approximately two hours of lectures and two hours of supervised exercises. The main project is conducted individually or in small groups and is closely aligned with each participant’s doctoral research topic. |
LITERATURE |
Course compendium and selected scientific journal and conference papers.
|
EXAMINATION |
The primary examination component is a written project report. The report shall demonstrate the application of course methods to a well-defined engineering system problem relevant to the student’s doctoral research. Additional compulsory assignments, including oral presentations, are included during the course. Grading scale: Pass / Fail. |
COURSE OFFERING |
The course is offered as an online doctoral-level course. It is normally scheduled to start in March and run over two months. Exact dates and times are announced well in advance. |
SCHEDULE |
March 2. 13-17 (CET). Design analytics I, Axiomatic design, Machine learning in design. March 10. 13-17 (CET). Design analytics II. Sensitivity Analysis, Robustness and functional correlation. March 17. 13-17 (CET). Machine learning and design space generation I: Subsystem modelling. Regression analysis and Principal Component Analysis March 31. 13-17 (CET). Machine learning and design space generation II. Principal Component Analysis and Neural Networks. System structures and modelling April 7. 13-17 (CET). Invited talks (TBD). April 14. 13-17 (CET). Information entropy in Design and Optimization. April 28 13-17 (CET). Project presentation. Schedule is preliminary and may be subject to change. |
Download course syllabus here.
Registeration
PhD course in Engineering Systems Design Analytics and AI