Postdoc in Data Driven Modeling for Monitoring Wind Turbine Bering Operation
Postdoc in Data Driven Modeling for Monitoring Wind Turbine Bering Operation
Aalborg University
Aalborg, Denmark
We are is seeking a Post Doc candidate for a project in collaboration with Siemens-Gamesa; focused on the development and application of data driven modeling techniques for monitoring the health of the main bearing in wind turbines. This innovative research aims to enhance the operation of next-generation offshore wind turbines through the development of a novel condition monitoring system. The project is founded by Innovation Found Denmark.
Responsibilities:
In the project two main approaches are compared. One based on black/gray box machine learning methods and another one on gray/white box data driven methods. The Post Doc will be working with the latter.
The model structure will be founded on first principles models with parameters that ideally possess physical significance. Parameters that are less known or unknown will need to be estimated using Maximum Likelihood or similar estimation techniques. A well-defined model will primarily be characterized by specific turbine and wind condition parameters. The model is used for condition monitoring and fault detection using methods focusing on statistical methods using residual generation and Kalman filtering.
Qualifications:
Phd and master's degree in, Engineering, Data Science, Computer Science or a related field with a strong foundation in physical and data driven modeling, statistics and stochastic processes. Experience in control engineering, signal processing, data analysis, or related areas. Proficiency in programming languages commonly used in data driven modeling and statistical detection methods, such as Matlab, Python or R. Excellent analytical and problem-solving skills. Ability to work independently as well as collaboratively in a team-oriented environment. Strong communication skills, both written and oral, are essential.
The project will be conducted under the auspices of the Learning and Decisions research group. This group specializes in developing control and decision-making strategies for autonomous systems and infrastructures, integrating physical models with pervasive data. It combines three key areas of research: optimization(encompassing multi-objective optimization, dynamic programming, and reinforcement learning), safety and resilience evaluation, and the secure, privacy-preserving implementation of control algorithms.
© EuroJobsites 2024
