PhD: Deep Learning for FSI of Modular Floating Structures

Norges teknisk-naturvitenskapelige universitet (NTNU); Trondheim; On-site; NOK 496,000 - 606,000; Full time

Benefits offered by this job

Open and inclusive working environment

Pension fund (SPK)

Job summary

NTNU seeks a PhD Candidate in Deep Learning enhanced FSI modelling of Multi-modular Floating Structures. The project sits in AIMOS, advancing AI methods for offshore structures and digital twins. You will work with high-fidelity CFD-FEA data to develop physics-informed surrogates and predictive models.

The role involves coupling CFD–FEM, developing data-driven predictions, and collaborating with peers. Strong English and a solid master’s background are required, with admission to NTNU’s PhD

Qualifications

• Master's degree with 120 credits at master's level as required.
• Strong academic record with grade equal to B or better on NTNU scale.
• Eligibility for admission to the faculty's doctoral program.

Responsibilities

• Take courses totaling at least 30 ECTS.
• Run coupled CFD–FEM simulations for waves, mooring, and deformation.
• Develop deep learning surrogate models for fast predictions.
• Validate models with simulations, experiments and field data.
• Analyze dynamic behavior of modular floating structures under varying sea states.
• Collaborate with AIMOS colleagues in intelligent control and smart materials.
• Publish in high-quality journals and present at conferences.

Skills

Python

MATLAB

English proficiency

Education

Master's degree in marine technology, civil engineering, mechanical engineering, applied mathematics or equivalent

Tools

STAR-CCM-ABAQUS

PyTorch

TensorFlow

CFD/FEM software

Job description

NTNU seeks a PhD Candidate in Deep Learning enhanced FSI modelling of Multi-modular Floating Structures. The project sits in AIMOS, advancing AI methods for offshore structures and digital twins. You will work with high-fidelity CFD-FEA data to develop physics-informed surrogates and predictive models.

The role involves coupling CFD–FEM, developing data-driven predictions, and collaborating with peers. Strong English and a solid master’s background are required, with admission to NTNU’s PhD