Publisher
source

Daniel StraubDaniel Straub

1 year ago

Engineering Risk Analysis Technical University of Munich in Germany

Degree Level

PhD

Field of study

Computer Science

Funding

Funded by the European Commission’s Horizon 2023 Marie Sklodowska-Curie programme

Deadline

Expired

Country flag

Country

Germany

University

Technical University of Munich (TUM)

Social connections

How do Korean students apply for this?

Sign in for free to reveal details, requirements, and source links.

Where to contact

Official Email

No info

Keywords

Computer Science
Data Science
Environmental Science
Systems Engineering
Mechanical Engineering
Electrical Engineering
Decision Making
Predictive Modeling
Risk Assessment
Artificial Intelligence
Renewable Energy
Risk Analysis
Reinforcement Learning
Maintenance Engineering
Wind Energy Engineering
Autonomous Vehicle Technology
Predictive Maintenance
Maintenance Planning
Autonomous Systems Engineering
Intelligent Systems
Data-driven Framework
Autonomous Operations
Imperfect Deterioration Models
Self-learning Algorithms
Sequential Decision-making

About this position

PhD position ?? We are hiring!The Engineering Risk Analysis Group (www.cee.ed.tum.de/era) at Technical University of Munich is looking for 2 PhD students to work on AI-Based Maintenance Planning for Wind Energy Structures. These PhD positions are part of the hashtag#IntelliWind Doctoral Network. They offer an exciting opportunity to work with leading experts and a larger group of 16 PhD students across Europe to develop Intelligent systems for autonomous wind power plant operations via the IntelliWind MSCA Doctoral Network funded by the European Commission’s Horizon 2023 Marie Sklodowska-Curie programme. Intelliwind is coordinated by DTU - Technical University of Denmark, Nikolay Dimitrov. The PhD students at TUM will work towards intelligent maintenance, combining data with physics- and expert models to find optimal solutions to this sequential decision making problem under uncertainty. One student will focus on optimal maintenance decision processes with transfer learning. The project develops a data-driven framework to optimize maintenance actions directly from records of monitoring data and past maintenance activities at the wind farm level, leveraging recent developments in reinforcement learning in partially observable environments. The project will employ real-life data from wind farms. This PhD student will have secondments at Fraunhofer Institute for Wind Energy Systems IWES with Julia Walgern and at ETH Zürich with Prof. Eleni Chatzi.The second student will work towards obust predictive maintenance planning under imperfect deterioration models: The project develops and investigates strategies for handling the sim2reality gap, i.e., the bias between state-of-the-art models and the real world. You will explore algorithms that apply self-learning and can correct biases as data becomes available and develop robust approaches to sequential decision-making under the sim2reality gap. This PhD student will have secondments at Ramboll with Moritz Häckell and at TU Delft with Prof. Dimitrios Zarouchas.More details on the position and the application process are given in the PDF:…more

Funding details

Funded by the European Commission’s Horizon 2023 Marie Sklodowska-Curie programme

How to apply

More details in the PDF

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?

Professors