Romain Brault

  • Citations Per Year
Learn More
The complex mechanical behaviour of composite materials, due to internal heterogeneity and multi-layered composition impose deeper studies. This paper presents an experimental investigation technique to perform volume kinematic measurements in composite materials. The association of X-ray micro-computed tomography acquisitions and Digital Volume Correlation(More)
The present study analyses an aircraft composite fuselage structure manufactured by the Liquid Resin Infusion (LRI) process and subjected to a compressive load. LRI is based on the moulding of high performance composite parts by infusing liquid resin on dry fibres instead of prepreg fabrics or Resin Transfer Moulding (RTM). Actual industrial projects face(More)
The aim of this study is to gain knowledge concerning the process and its physics, as well as to become able to optimize the fabrication of large and complex composite parts in aeronautics applications. Composite materials have many advantages and the use of this technology is increasing in the aeronautic industry. In the L.R.I. process, dry textile(More)
Random Forests (RFs) are strong machine learning tools for classification and regression. However, they remain supervised algorithms, and no extension of RFs to the one-class setting has been proposed, except for techniques based on second-class sampling. This work fills this gap by proposing a natural methodology to extend standard splitting criteria to(More)
The aim of this study is to gain knowledge concerning the process and its physics, as well as to become able to optimize the fabrication of large and complex composite parts in aeronautics applications. Composite materials have many advantages and the use of this technology is increasing in the aeronautic industry. In the L.R.I. process, dry textile(More)
A nonparametric approach to Vector Autoregressive Modeling consists in working in vector-valued Reproducing Kernel Hilbert Spaces. The main idea is to build vector-valued models (OKVAR) using operator-valued kernels. Similar to scalar-valued kernels, operator-valued kernels enjoy representer theorems and learning algorithms that heavily depends on training(More)
Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces. To scale up these methods, we extend the celebrated Random Fourier Feature methodology to get an approximation of operatorvalued kernels. We propose a general(More)
Although the Dalkon shield has been one of the most popular IUDs in past years, manufacturing standards followed in its production were very poor. Its insertion was rather dangerous and the uterine perforation rate was quite high. The authors examined it by scanning an electron microscope before and after insertion. It is concluded that, if the shape of(More)