Autonomous and intelligent embedded solutions are mainly designed as cognitive systems composed of a three step process: perception, decision and action, periodically invoked in a closed-loop manner in order to detect changes in the environment and appropriately choose the actions to be performed according to the mission to be achieved. In an autonomous agent such as a robot, a drone or a vehicle, these 3 stages are quite naturally instantiated in the form of i) the fusion of information from different sensors, ii) then the scene analysis typically performed by artificial neural networks, and iii) finally the selection of an action to be operated on actuators such as engines, mechanical arms or any mean to interact with the environment. In that context, the growing maturity of the complementary technologies of Event-Based Sensors (EBS) and Spiking Neural Networks (SNN) is proven by recent results. The nature of these sensors questions the very way in which autonomous systems interact with their environment. Indeed, an Event-Based Sensor reverses the perception paradigm currently adopted by Frame-Based Sensors (FBS) from systematic and periodical sampling (whether an event has happened or not) to an approach reflecting the true causal relationship where the event triggers the sampling of the information. We propose to study the disruptive change of the perception stage and how event-based processing can cooperate with the current frame-based approach to make the system more reactive and robust. Hence, SNN models have been studied for several years as an interesting alternative to Formal Neural Networks (FNN) both for their reduction of computational complexity in deep network topology, but also for their natural ability to support unsupervised and bio-inspired learning rules. The most recent results show that these methods are becoming more and more mature and are almost catching up with the performance of formal networks, even though most of the learning is done without data labels. But should we compare the two approaches when the very nature of their input-data is different? In the context of interest of image processing, one (FNN) deals with whole frames and categorizes objects, the other (SNN) is particularly suitable for event-based sensors and is therefore more suited to capture spatio-temporal regularities in a constant flow of events. The approach we propose to follow in the DeepSee project is to associate spiking networks with formal networks rather than putting them in competition.

"Nowadays, the forming process steps and the design phases of real parts are most of the time unrelated. The mechanical design of these components under service conditions does not account for the thermomechanical and microstructural history of the materials used. This leads sometimes to approximate estimations of their mechanical strengths and to too high safety coefficients. Recently, some numerical simulation forming process codes allow to estimate the mechanical properties of a component after the forming process. They also give information on the microstructure with regard to the thermomechanical conditions used during the process. The damage fatigue models (low cycle and high cycle fatigue regimes, uniaxial and multiaxial loading conditions) and the related design codes, do not yet use these informations as input data. It is now important to identify the principal mechanical and microstructural characteristics induced by the forming process and playing a role in the fatigue strength. This knowledge will make possible the increase of the fatigue model predictivity and will lead to consider the process phase as the previous step of the fatigue design approach. The DEFISURF project main objective is to carefully study the effects of the surface defects and microstructural heterogeneities on the fatigue damage mechanisms of forged components in order to give better predictions of their mechanical properties and conduct the best possible design. It is more exactly planed to analyze and model the influence of the surface state (microgeometry, gradient of microstructure, residual stresses intensity and distribution) on the fatigue behavior of forged parts generally highly loaded. This project is composed of several tasks dealing with: 1. The assessment of the principal defects (geometrical and metallurgical) occurring in forged parts together with their origins 2. The estimation by relevant techniques (that can be used in the industrial framework) of the defects distribution in a component 3. The use of advanced experimental devices (tomography, EBSD 3D, nanoindentation …) to characterize surface geometrical and metallurgical defects 4. The fatigue testing under different loading modes and path of three steels showing different defect contents and shot-peening conditions (residual stresses distribution, surface hardening …) 5. The numerical modeling, at the microscopic and the macroscopic scales, of the nucleation and growth of different defects along the forming process steps 6. The numerical modeling, at the microscopic and the macroscopic scales, of the fatigue response of different steels showing several defect and microstructural heterogeneities content. Different loading conditions will be applied like very high compressive loading for the rod."

In SCALABLE, eminent industrials and academic partners will team up to achieve the scaling to unprecedented performance, scalability, and energy efficiency of an industrial LBM-based computational fluid dynamics (CFD) software. Lattice Boltzmann methods (LBM) have already evolved to become trustworthy alternatives to conventional CFD. In several engineering applications they are shown to be roughly an order of magnitude faster than Navier-Stokes approaches in a fair comparison and in comparable scenarios. LBM methods are also flexible so that they can be extended to handle complex, dynamically changing geometries, multiphase flows, and wide range of other multiphysics applications that are of high industrial relevance. In the context of EuroHPC, the distinguishing critical features of the LBM is the algorithmic locality stemming from an explicit time step. This makes the LBM especially well-suited to exploit advanced supercomputer architectures through vectorization, accelerators, and massive parallelization. In the public domain research code waLBerla, superb performance and unlimited scalability has been demonstrated, reaching more than a trillion (10^12) lattice cells already on Petascale systems. This becomes possible through systematic performance engineering and the development of an innovative computer science technology. WaLBerla performance excels because of its uncompromising unique, architecture-specific automatic generation of optimized compute kernels, together with carefully designed parallel data structures. waLBerla, however, is not compliant with industrial applications due to lack of a geometry engine and user friendliness for non-HPC experts. On the other hand, the industrial CFD software LaBS already has such industrial capabilities at a proven high level of maturity, but it still has performance worthy of improvement. Therefore, SCALABLE will transfer the leading edge performance technology from waLBerla to LaBS, thus breaking the silos between the scientific computing world and physical flow modelling world. The collaboration will deliver improved efficiency and scalability for LaBS to be prepared for the upcoming European Exascale systems. The project outcomes will be disseminated through the LaBS software and will directly benefit to the european industry as confirmed by the active involvement of Renault & Airbus in the project, and by the additional numerous letters of support from a wide aeronautics and automotive industrial community. Additionally, SCALABLE will also contribute to fundamental research. This will include energy efficient computing, GPU accelerated kernels, and a novel memory efficient sparse data structure available as open source software within the waLBerla framework.

BioInspired Oleophobic Self-Cleaning surfaces for Automotive indoor environment The fast development of new types of mobility based on car sharing, with frequent change of drivers and occupants of the vehicle, reinforces the need for the development of innovative automotive interior materials surfaces with anti-fouling and self-cleaning properties, especially against oily deposits. Based on bioinspired models of superoleophobic surface texture and composition, from natural species such as springtails, the BIOSCA project gathers two research laboratories specialized in bio-inspired surface functionalization, and two major actors of the automotive industry. It combines 1) the preparation and structuration at the nano and micro levels of polymer surfaces, 2) their chemical functionalization to achieve low surface energy, 3) the evaluation of performances on automotive interior materials samples and process industrialization. This applied research project relies on complementary scientific expertises of the academic partners. One research laboratory has developed an expertise to create polymer films exhibiting topographical features such as hierarchical organization and re-entrant roughness or porosity relevant for superoleophobicity. This topography can be achieved by the “breath figure” (BF) process leading to honeycomb films in close-packed hexagonal arrays after fast drying of a polymer solution under a humid air-flow. It can also combine nanoscale self-assembly of diblock copolymers. Another research laboratory, coordinator of the project, is one of the world leaders in the preparation of bioinspired superhydrophobic/suoeroleophobic surfaces thanks to a molecular conception developed from the deposition of polymers to their nanostructural and chemical surface functionalization using electrochemical and plasma-assisted treatments. The industrial partners will select car interior parts of interest for anti-fouling and self-cleaning treatment, and will prepare samples of car interior materials, possibly painted or film-coated. After their surface treatment by the academic partners theses samples will undergo a series of standardized tests to validate and quantify the performance of the process, including its durability after ageing. They will also analyze the technical and economical feasibility of industrializing the process, with environment compliance criteria and cost targets. Possible extension to other car parts and to other industrial sectors will also be examined.