VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Abstract
The course aims to introduce machine learning methods applied in industrial applications and to create an understanding how to define the problems in a way that would allow their solutions in the context of industrial applications where labeled data remains scarce, the variability of the operating conditions and diversity of the systems poses a significant challenge on the developed ML models.
Objective
Students will - be able to understand the main challenges faced by intelligent maintenance and operations systems -learn to select appropriate tools for the specific problem -learn to evaluate the performance of the applied algorithms -learn to identify the requirements for the deployment of the algorithms -learn identify potential misconceptions and fields of improvement -learn how to define the problem is a way that allows its solution
Content
While application fields such as computer vision and natural language processing have been flourishing, machine learning applications for industrial systems have still not realized their potential. While condition monitoring and operational data have been increasingly collected, many applications have still not overcome the level of proofs of concepts. The challenges faced by industrial applications include lack of correctly labeled datasets, high diversity of the systems, their configurations and operating conditions, diverse environmental conditions and data collection setups, noisy labels, diverse types of collected data. The developed solutions are often not scalable and fail to generalize. This course provides insights in selecting, designing, optimizing and evaluating machine learning algorithms to overcome the challenges faced by intelligent maintenance and operations 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 and generalization for fault detection and diagnostics -Introduction to decision support systems for maintenance applications -Benefits and costs of predictive maintenance Small case studies will be elaborated and discussed in groups.
General Information
- Language
- English
- Levels
- NDS
- Frequency
- Yearly recurring
Examination
- Type
- ungraded semester performance
Registration & Places
- Max Places
- 40
- Signup End
- 08.02.2026
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| seminar |
Machine Learning for Industrial Applications
Does not take place this semester.
|
No time listed | 32 h semesterly |