IMT ATLANTIQUE - Deep learning of dynamical anchoring models [postdoc]

Post-doctoral position (18 months) in deep learning of dynamical anchoring models

 

Context

IMT-Atlantique, an engineering school under the supervision of the Ministry of Industry, is looking for a post-doc for 18 months, to start at the earliest from September 2020. The position is based on the Brest campus of the school. The candidate will join the Signal and Communications department, within the TOMS team of the Lab-STICC (signal and image processing from natural signals), whose research activities include signal and image processing for remote sensing, and learning dynamical models using artificial intelligence.

The open position is part of the SUBSEE4D project co-sponsored by Cervval, a company specializing in digital simulation and decision support in complex systems, France Energies Marines, an institute for marine renewable energies (MRE), and IMT Atlantique. Installed or floating wind turbines and tidal turbines are major infrastructure projects that are costly in terms of investment and also, due to the restrictive marine environment, in terms of operation and maintenance, particularly for the submerged part: inspection of anodes, corrosion detection, monitoring of organic aggregates (bio-colonization), monitoring of their structural condition, particularly of underwater cables and anchor lines. MRE eet managers will face unprecedented operating and maintenance challenges, even greater than those faced by offshore oil and gas companies, due in particular to the shallow waters that characterize MRE facilities: currents, waves, water turbidity and the proliferation of living organisms on the infrastructure make it diffcult for divers and ROVs (Remote Operated Vehicles) to operate and maintain the facilities, and degrade and damage the infrastructure.

In this context, the objective of the position is to learn from observation and simulation data a dynamical model of the behaviour of the anchor line. Initially, a limited list of characteristic variables will be determined. In particular the strains and possibly the accelerations (identification of structural damage for example) may be sufficient for the need of fatigue monitoring. On the other hand, the maintenance assistance and training system rather requires knowledge of the movement amplitudes and velocity of these points. An initial sensitivity analysis will be carried out on the variables already known to be influential. The deep-learning model that will be developed will initially assume a very large list of influential parameters. A reflection will be carried out on the basis of the reference model and knowledge of the physics of these systems to identify parameter interdependencies and to integrate these constraints into the models in order to limit it and to prevent the degradation of learning performance (e.g. taking into account non-physical events related to measurement or numerical problems, etc.). This will also lead to an optimized learning model by achieving the required performance from a smaller volume of data. The notion of uncertainty will also be considered as it represents an essential reliability criterion for improving life time predictions.

 

Candidate

The candidate must have a PhD in image or signal processing, machine learning or related _elds, or equivalent experience. Qualifications required:

  • Machine Learning, Signal and Image Processing, Applied Mathematics, Dynamical Systems
  • Programming in Python
  • Experience in deep learning methods and associated libraries in Python (Keras, Tensorow, Pytorch)

 

Contact

Lucas Drumetz, Associate Professor, IMT-Atlantique, Signal and Communications Department, and UMR LabSTICC, TOMS team. Please send a resume and cover letter to Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser..

© 2020 BreTel