Course detail

Machine Learning in Engineering Calculations

FSI-QAI Acad. year: 2027/2028 Summer semester

The course outlines possible ways of applying machine learning in the context of engineering calculations. Students will get to know the basic principles of machine learning and artificial intelligence, with an emphasis on Reinforcement learning. The course includes an introduction to the Python programming language and its use for implementing suitable libraries for linking dynamic computational models and artificial intelligence tools.

Language of instruction

Czech

Number of ECTS credits

2

Learning outcomes of the course unit

Upon successful completion of the course, students will be able to:

  • Distinguish between supervised, unsupervised and reinforcement learning and assess their suitability for selected engineering problems.
  • Develop and modify simple Python programs, process numerical data and use NumPy, Pandas and Matplotlib.
  • Explain the fundamentals of neural networks and prepare data, train and evaluate a simple supervised learning model using PyTorch.
  • Explain the FMI/FMU standard and demonstrate the exchange or coupling of a simulation model with another computational or control environment.
  • Design a basic reinforcement learning environment, specify observations, actions, reward and termination conditions, and train an agent.
  • Compare selected RL algorithms and hyperparameter settings in terms of training performance, learned behaviour and limitations of sim-to-real transfer.

Entry knowledge

Basic knowledge of mathematics, physics, kinematics and dynamics of mechanical systems, and familiarity with engineering computations are expected. Previous programming experience is an advantage but is not essential; the fundamentals of Python are included in the course.

Rules for evaluation and completion of the course

The course is completed by obtaining a course credit. To obtain the course credit, students must actively participate in practical classes, during which their progress in completing individual assignments is continuously monitored.

Attendance at practical classes is compulsory and monitored by the instructor. Arrangements for making up missed classes are determined individually in consultation with the instructor or the course guarantor.

The use of artificial intelligence tools is permitted during independent study and practical classes. However, students are fully responsible for the correctness of their solutions and are expected to be able to explain the methods and procedures used.

Aims

The aim of the subject is to familiarize students with the basic approaches of the application of machine learning, specifically Reinforcement Learning in engineering calculations.

The graduate of the course will gain basic knowledge of algorithms and data structures, useful for effective implementation of Reinforcement Learning algorithms through the Python programming language.

The graduate will also gain practical experience in tasks in the field of connecting machine learning and selected engineering calculations, which can serve as inspiration for further development in this area.

Study aids

Study resources include materials for computer-assisted practical classes, sample source code and datasets, software instructions and recommended specialist literature. Teaching materials and assignments are provided via the course’s electronic learning environment.

The study programmes with the given course

Programme N-ADI-P: Automotive and Material Handling Engineering, Master's, elective

Programme N-AAE-P: Advanced Automotive Engineering, Master's, elective

Type of course unit

 

Computer-assisted exercise

26 hours, compulsory

Syllabus


  1. Classification of Machine Learning and Artificial Intelligence

  2. Introduction to Python Programming 1

  3. Introduction to Python Programming 2

  4. Fundamentals of Neural Network Theory 1

  5. Fundamentals of Neural Network Theory 2

  6. Supervised Learning in Python 1

  7. Supervised Learning in Python 2

  8. FMI Standard

  9. Fundamentals of Control Theory

  10. Reinforcement Learning Environments

  11. Reinforcement Learning Algorithms

  12. Reward Functions

  13. Hyperparameters