Dirk Mohr: Catalogue data in Spring Semester 2021

Name Prof. Dr. Dirk Mohr
FieldArtificial Intelligence in Mechanics and Manufacturing
KI in Mechanik und Fertigung
ETH Zürich, CLA F 9
Tannenstrasse 3
8092 Zürich
Telephone+41 44 632 26 12
DepartmentMechanical and Process Engineering
RelationshipFull Professor

151-0075-21LFormula Student Electric Restricted registration - show details
Prerequisite: Enrollment for 151-0075-20L Formula Student Electric in HS20.
14 credits15AD. Mohr
AbstractStudents develop and build a product from A-Z! They work in teams and independently, learn to structure problems, to identify solutions, system analysis and simulations, as well as presentation and documentation techniques. They build the product with access to a machine shop and state of the art engineering tools (Matlab, Simulink, etc).
ObjectiveThe various objectives of the Focus Project are:
- Synthesizing and deepening the theoretical knowledge from the basic courses of the 1. - 4. semester
- Team organization, work in teams, increase of interpersonal skills
- Independence, initiative, independent learning of new topic contents
- Problem structuring, solution identification in indistinct problem definitions, searches of information
- System description and simulation
- Presentation methods, writing of a document
- Ability to make decisions, implementation skills
- Workshop and industrial contacts
- Learning and recess of special knowledge
- Control of most modern engineering tools (Matlab, Simulink, CAD, CAE, PDM)
151-0502-00LMechanics 2: Deformable Solids and Structures
Prerequisite: 151-0501-00L Mechanics 1: Kinematics and Statics

This course is only for students of Mechanical Engineering, Civil Engineering and Human Movement Sciences.

Students in Human Movement Sciences and Sport must enrol in "Mechanics 1" and "Mechanics 2" as a two-semester course.
6 credits4V + 2UD. Mohr
AbstractStress tensor, deformations, linear elastic solids, bending of prismatic beams, numerical methods, bending, torsion, plastic work and deformation energy, energy methods, buckling.
ObjectiveFor the mechanical design of systems, knowledge about basic concepts of continuum mechanics are indispensable. These include mechanical stress, deformations, etc. which are demonstrated on simple examples resulting in an understanding which is both mathematically correct and intuitive. In this course students learn the basic concepts of the mechanics of deformable media that they will later apply in other courses such as Dimensioning which are closer to real engineering applications.
ContentSpannungstensor, Verzerrungen, linearelastische Körper, spezielle Biegung prismatischer Balken, numerische Methoden, allgemeinere Biegeprobleme, Torsion, Arbeit und Deformationsenergie, Energiesätze und -verfahren, Knickung.
LiteratureMahir B. Sayir, Jürg Dual, Stephan Kaufmann
Ingenieurmechanik 2: Deformierbare Körper, Teubner Verlag
151-0840-00LOptimization and Machine Learning
Note: previous course title until FS20 "Principles of FEM-Based Optimization and Robustness Analysis".
4 credits2V + 2UB. Berisha, D. Mohr
AbstractThe course teaches the basics of nonlinear optimization and concepts of machine learning. An introduction to the finite element method allows an extension of the application area to real engineering problems such as structural optimization and modeling of material behavior on different length scales.
ObjectiveStudents will learn mathematical optimization methods including gradient based and gradient free methods as well as established algorithms in the context of machine learning to solve real engineering problems, which are generally non-linear in nature. Strategies to ensure efficient training of machine learning models based on large data sets define another teaching goal of the course.

Optimization tools (MATLAB, LS-Opt, Python) and the finite element program ABAQUS are presented to solve both general and real engineering problems.
Content- Introduction into Nonlinear Optimization
- Design of Experiments DoE
- Introduction into Nonlinear Finite Element Analysis
- Optimization based on Meta Modeling Techniques
- Shape and Topology Optimization
- Robustness and Sensitivity Analysis
- Fundamentals of Machine Learning
- Generalized methods for regression and classification, Neural Networks, Support Vector machines
- Supervised and unsupervised learning
Lecture notesLecture slides and literature