Olga Fink: Catalogue data in Spring Semester 2021

Name Dr. Olga Fink
FieldIntelligent Maintenance Systems
Address
EPFL ENAC IIC IMOS
Station 18
GC G1 494 (Bâtiment GC)
1015 Lausanne
SWITZERLAND
Telephone0041216936629
E-mailofink@ethz.ch
DepartmentCivil, Environmental and Geomatic Engineering
RelationshipLecturer

NumberTitleECTSHoursLecturers
101-0521-10LMachine Learning for Predictive Maintenance Applications Restricted registration - show details
The number of participants in the course is limited to 25 students.

Students interested in attending the lecture are requested to upload their transcript and a short motivation responding the following two questions (max. 200 words):
-How does this course fit to the other courses you have attended so far?
-How does the course support you in achieving your goal?
The following link can be used to upload the documents.
Link
8 credits4GO. Fink
AbstractThe course aims at developing machine learning algorithms that are able to use condition monitoring data efficiently and detect occurring faults in complex industrial assets, isolate their root cause and ultimately predict the remaining useful lifetime.
ObjectiveStudents will
- be able to understand the main challenges faced by predictive maintenance systems
- learn to extract relevant features from condition monitoring data
-learn to select appropriate machine learning algorithms for fault detection, diagnostics and prognostics
-learn to define the learning problem in way that allows its solution based on existing constrains such as lack of fault samples.
- learn to design end-to-end machine learning algorithms for fault detection and diagnostics
-be able to evaluate the performance of the applied algorithms.

At the end of the course, the students will be able to design data-driven predictive maintenance applications for complex engineered systems from raw condition monitoring data.
ContentEarly and reliable detection, isolation and prediction of faulty system conditions enables the operators to take recovery actions to prevent critical system failures and ensure a high level of availability and safety. This is particularly crucial for complex systems such as infrastructures, power plants and aircraft engines. Therefore, their system condition is increasingly tightly monitored by a large number of diverse condition monitoring sensors. With the increased availability of data on system condition on the one hand, and the increased complexity of explicit system physics-based models on the other hand, the application of data-driven approaches for predictive maintenance has been recently increasing.
This course provides insights and hands-on experience in selecting, designing, optimizing and evaluating machine learning algorithms to tackle the challenges faced by maintenance systems of complex engineered systems.

Specific topics include:

-Introduction to condition monitoring and predictive maintenance systems
-Feature extraction and selection methodology
-Machine learning algorithms for fault detection and fault isolation
-End-to-end learning architectures (including feature learning) for fault detection and fault isolation
-Unsupervised and semi-supervised learning algorithms for predictive maintenance
-Machine learning algorithms for prediction of the remaining useful life
-Performance evaluation
-Predictive maintenance systems at fleet level
-Domain adaptation for fault diagnostics
-Introduction to decision support systems for maintenance applications
Lecture notesSlides and other materials will be available online.
LiteratureRelevant scientific papers will be discussed in the course.
Prerequisites / NoticeStrong analytical skills.
Programming skills in python are strongly recommended.
101-0522-10LDoctoral Seminar Data Science and Machine Learning in Civil, Env. and Geospatial Engineering Restricted registration - show details
Number of participants limited to 21.
1 credit2SB. Soja, E. Chatzi, F. Corman, O. Fink, I. Hajnsek, M. A. Kraus, M. Lukovic, K. Schindler, M. J. Van Strien
AbstractCurrent research in machine learning and data science within the research fields of the department. The goal is to learn about current research projects at our department, to strengthen our expertise and collaboration with respect to data-driven models and methods, to provide a platform where research challenges can be discussed, and also to practice scientific presentations.
Objective- learn about discipline-specific methods and applications of data science in neighbouring fields
- network people and methodological expertise across disciplines
- establish links and discuss connections, common challenges and disciplinespecific differences
- practice presentation and discussion of technical content to a broader, less specialised scientific audience
ContentCurrent research at D-BAUG will be presented and discussed.
Prerequisites / NoticeThis doctoral seminar is intended for doctoral students affiliated with the Department of Civil, Environmental and Geomatic Engineering. Other students who work on related topics need approval by at least one of the organisers to register for the seminar.

Participants are expected to possess elementary skills in statistics, data
science and machine learning, including both theory and practical modelling and implementation. The seminar targets students who are actively working on related research projects.
101-0523-11LFrontiers in Machine Learning Applied to Civil, Env. and Geospatial Engineering (FS21) Restricted registration - show details
Number of participants limited to 21.
1 credit2SM. Lukovic, E. Chatzi, F. Corman, O. Fink, I. Hajnsek, M. A. Kraus, K. Schindler, B. Soja, M. J. Van Strien
AbstractThis doctoral seminar organised by the D-BAUG platform on data science and machine learning aims at discussing recent research papers in the field of machine learning and analyzing the transferability/adaptability of the proposed approaches to applications in the field of civil and environmental engineering (if possible and applicable, also implementing the adapted algorithms).
ObjectiveStudents will
• Critically read scientific papers on the recent developments in machine learning
• Put the research in context
• Present the contributions
• Discuss the validity of the scientific approach
• Evaluate the underlying assumptions
• Evaluate the transferability/adpatability of the proposed approaches to own research
• (Optionally) implement the proposed approaches.
ContentWith the increasing amount of data collected in various domains, the importance of data science in many disciplines, such as infrastructure monitoring and management, transportation, spatial planning, structural and environmental engineering, has been increasing. The field is constantly developing further with numerous advances, extensions and modifications.
The course aims at discussing recent research papers in the field of machine learning and analyzing the transferability/adaptability of the proposed approaches to applications in the field of civil and environmental engineering (if possible and applicable, also implementing the adapted algorithms).
Each student will select a paper that is relevant for his/her research and present its content in the seminar, putting it into context, analyzing the assumptions, the transferability and generalizability of the proposed approaches. The students will also link the research content of the selected paper to the own research, evaluating the potential of transferring or adapting it. If possible and applicable, the students will also implement the adapted algorithms The students will work in groups of three students, where each of the three students will be reading each other’s selected papers and providing feedback to each other.
Prerequisites / NoticeThis doctoral seminar is intended for doctoral students affiliated with the Department of Civil, Environmental and Geomatic Engineering. Other students who work on related topics need approval by at least one of the organisers to register for the seminar.

Participants are expected to possess elementary skills in statistics, data science and machine learning, including both theory and practical modelling and implementation. The seminar targets students who are actively working on related research projects.