Sort by
Refine Your Search
-
Listed
-
Category
-
Employer
- NTNU - Norwegian University of Science and Technology
- NTNU Norwegian University of Science and Technology
- University of Oslo
- Norwegian University of Life Sciences (NMBU)
- University of Bergen
- Western Norway University of Applied Sciences
- NORCE Norwegian Research Centre
- UNIS
- UiT The Arctic University of Norway
- University of South-Eastern Norway
-
Field
-
relevant if there is a strong focus on data-driven modeling, machine learning, and control. In any case, a documented background or experience in control is required. Your education must correspond to a five
-
. You will become part of a dynamic, collaborative working environment with expertise in drilling engineering, geomechanics, machine learning, and energy systems. The project will integrate real‑time
-
optimization (WOB, RPM, flow rate, etc.) using machine learning techniques Anomaly detection for downhole vibrations, bit failure, and circulation losses Integrating physical modeling, digital twins, and data
-
complementary and synergic methods at the intersection of Artificial intelligence, Machine learning, Numerical simulation, Formal verification. Such methods include, among the others: AI-guided simulation
-
-state model will be approximated using machine-learning surrogates and will be used for a real-time optimization, such that the plant operates optimally despite disturbances. The candidate will be part of
-
Computer science » Computer systems Computer science » Programming Technology » Communication technology Technology » Telecommunications technology Researcher Profile First Stage Researcher (R1) Positions PhD
-
research or project activities involving machine learning or data-driven modelling you demonstrate knowledge of energy systems, smart grids, or cyber-physical systems Personal characteristics To complete a
-
Experience with AI / probabilistic AI / Machine Learning Experience with numerical optimization and MPC Strong programming skills (Python, C) Experience with predictive maintenance, fatigue, fault detection
-
shelf lives, and additionally may change colour, texture, and stiffness rapidly. Further, the lack of standardised 3D models for the wide variety of products makes offline learning challenging. As a
-
areas: Developing and training robust machine learning surrogates to replace computationally expensive high-fidelity simulations, enabling exploration of vast design spaces. Formulating optimization