In the last years, the automotive engineering industry has been deeply influenced by the use of «machine learning» techniques for new design and innovation purposes. However, some specific engineering aspects like numerical optimization study still require the development of suitable high-performance machine learning approaches involving parametrized Finite Elements (FE) structural dynamics simulation data. Weight reduction on a car body is a crucial matter that improves the environmental impact and the cost of the product. The actual optimization process at Renault SA uses numerical Design of Experiments (DOE) to find the right thicknesses and materials for each part of the vehicle that guarantees a reduced weight while keeping a good behavior of the car body, identified by criteria or sensors on the body (maximum displacements, upper bounds of instantaneous acceleration …). The usual DOE methodology generally uses between 3 and 10 times the numbers of parameters of the study (which means, for a 30-parameters study, at least 90 simulations, with typically 10 h per run on a 140-core computer). During the last 2 years, Renault's teams strived to develop a disruptive methodology to conduct optimization study. By 'disruptive' , we mean to find a methodology that cuts the cost of computational effort by several orders of magnitude. It is acknowledged that standard DoEs need a number of simulations which is at least proportional to the dimension of the parameter space, leading generally to hundreds of fine simulations for real applications. Comparatively, a disruptive method should require about 10 fine evaluations only. This can be achieved by means of a combination of massive data knowledge extraction of FE crash simulation results and the help of parallel high-performance computing (HPC). For instance, in the recent study presented by Assou et al. (A car crash reduced order model with random forest. In: 4th International workshop on reduced basis, POD and PGD Model Reduction Techniques-MORTech 2017. 2017), it took 10 runs to find a solution of a 34-parameter problem that fulfils the specifications. In order to improve this method, we must extract more knowledge from the simulation results (correlations, spatio-temporal features, explanatory variables) and process them in order to find efficient ways to describe the car crash dynamics and link criteria/quantities of interest with some explanatory variables. One of the improvements made in the last months is the use of the so-called Empirical Interpolation Method (EIM, [Barrault et al.]) to identify the few time instants and spatial nodes of the FE-mesh (referred to as magic points) that "explain" the behavior of the body during the crash, within a dimensionality reduction approach. The EIM

No abstract

There are several simulators for medical ultrasound (US) applications that can fully compute the nonlinear propagation on the transmitted pulse and the corresponding radio-frequency (RF) images. Creanuis is one recent model used to generate nonlinear RF images; however, the time requirements are long compared with linear models using a convolution strategy. In this paper, we describe an approach using convolution coupled with nonlinear information to create a pseudoacoustic tool that is able to quickly generate realistic US images. Several point-spread functions (PSFs) are computed with Creanuis. These PSFs are extracted at different depths in order to take into account variation in the resolution and apparition of harmonics during propagation. One convolution is then conducted for each PSF to generate a set of nonlinear raw RF images. The final image is obtained by merging these raw images using a PSF-weighting function. This hybrid Creanuis strategy was extended to 2-D, 2-D +t , 3-D, and 3-D +t images for both linear and phased-array geometries. We validated h-Creanuis using the mean deviation between the proposed images and those created using Creanuis and examined their statistical distributions. The mean deviations of Creanuis and h-Creanuis are below 2.5% for fundamental and second-harmonic images. The 3-D +t images obtained demonstrate the correct motion characteristics for speckle in sequences of both fundamental and second-harmonic images.