Portail HAL Ensta
Not a member yet
11080 research outputs found
Sort by
A Deep Neural Network Model for Hybrid Spectrum Sensing in Cognitive Radio
No full textInternational audienceSpectrum sensing (SS) is an essential task of the secondary user (SU) in a cognitive radio system. SS monitors the primary user (PU) activity in order to avoid any collision with SU, as the latter should be silent when PU is active on a given channel. Hybrid SS (HSS) is one of the powerful methods used to monitor PU activity. It consists of using different detectors together to make a final decision on the PU status. In this manuscript, artificial neural networks (ANN) are used to perform HSS. Since our data is composed from the test statistics (TSs) of several detectors, thus it can be modeled as tabular. Fully connected neural networks become the most suitable ANN model. We applied cutting-edge techniques in the field of deep learning in order to get the best possible accurate neural network model in our application. These techniques boil down to: embedding, regularization, batch normalization and smart learning rate selection. With the help TSs related to several detectors, ANN is trained to distinguish between two hypotheses, H-0: PU is absent and H-1: PU is active. Numerical results show the effectiveness of our proposed ANN-based HSS, as it outperforms the classical ANN-based energy detector and proves its capability to detect PU signal at very low SNR
Iterative Learning for Model Reactive Control: Application to autonomous multi-agent control
No full textInternational audienceIn this paper, a decentralized autonomous controller aimed to control a fleet of quadrotors is designed, based on the iterative generation and exploitation of logged traces. The presented approach, inspired by model predictive control, aims to maintain the geometrical configuration for a set of quadrotors led by remotely controlled leaders. The novelty of this approach is to rely on inexpensive commercial off-the-shelf sensors (as opposed to positioning systems and/or cameras) that only measure the distance among quadrotors. In the first phase (trace generation) quadrotors are operated using randomized controllers based on domain knowledge, and their trajectories are registered. In the exploitation phase, a policy is learned from the traces generated in the previous phase, and the policy is iteratively refined, to achieve a robust reactive control of each quadrotor agent. Extensive experiments using RotorS, a Software In the Loop (SITL) framework in Gazebo simulator demonstrates the efficiency of the approach, and its ability to preserve the flocking structure of the quadrotors, following the (remotely and independently controlled) leaders
Grounding Language to Autonomously-Acquired Skills via Goal Generation
No full textInternational audienceWe are interested in the autonomous acquisition of repertoires of skills. Language-conditioned reinforcement learning (LC-RL) approaches are great tools in this quest, as they allow to express abstract goals as sets of constraints on the states. However, most LC-RL agents are not autonomous and cannot learn without external instructions and feedback. Besides, their direct language condition cannot account for the goal-directed behavior of pre-verbal infants and strongly limits the expression of behavioral diversity for a given language input. To resolve these issues, we propose a new conceptual approach to language-conditioned RL: the Language-Goal-Behavior architecture (LGB). LGB decouples skill learning and language grounding via an intermediate semantic representation of the world. To showcase the properties of LGB, we present a specific implementation called DECSTR. DECSTR is an intrinsically motivated learning agent endowed with an innate semantic representation describing spatial relations between physical objects. In a first stage (G -> B), it freely explores its environment and targets self-generated semantic configurations. In a second stage (L -> G), it trains a language-conditioned goal generator to generate semantic goals that match the constraints expressed in language-based inputs. We showcase the additional properties of LGB w.r.t. both an end-to-end LC-RL approach and a similar approach leveraging non-semantic, continuous intermediate representations. Intermediate semantic representations help satisfy language commands in a diversity of ways, enable strategy switching after a failure and facilitate language grounding
Influence of bed roughness and megatidal current (inertial regime) on saltation
No full textInternational audienc
Structural design of offshore wind turbine blade spars
No full textInternational audienceThe structural design of spars for horizontal axis wind turbine blades to achieve satisfactory levels of performance starts with the knowledge of aerodynamic forces acting on the blades. The present paper proposes a comparative study of the geometries of three spars designed for a 48 m long composite blade. The spars are evaluated under compression, bending loads as well as on free vibration. Different Subroutines have been developed and coupled with Finite Element Analysis (FEA) software to analyze the mechanical performances and the qualities of each one of the three designed spars. In other words, it seeks not only to define the behavior and response of each one of the spars and the effect of composite materials on the improvement of the structure stiffness and weight, but also to determine the suitable spars type for the wind turbine blade and the results shows that the Box spars offers a compromise of the main parameters
PVDF Based Pressure Sensor for the Characterisation of the Mechanical Loading during High Explosive Hydro Forming of Metal Plates
No full textInternational audienceHigh explosive hydro forming (HEHF) is a suitable technique for large metal plate forming. Manufacturing stages of such a part requires an adapted design of explosive charge configurations to define the mechanical loading exerted on the part. This mechanical loading remains challenging to be experimentally determined but necessary for predictive numerical simulation in the design of parts to form. Providing that the actual mechanical impulse would allow the neglecting of the modelling of the detonation stage, this considerably increases the computational time. The present work proposes an experimental method for obtaining the exerted mechanical loading by HEHF on the part to form. It relies on the development of low-cost sensor based on a polyvinyliden fluorid (PVDF) gauge. In addition to it, an analytical approach based on shock physics is proposed for the sensor signal interpretation. The method considers the multi-layer aspect of the sensor and its intrusiveness with respect to waves propagation. Measurements were repeated to assess their relevance and the reproducibility by using steel and aluminium anvils in HEHF. Numerical modelling in 2D plane geometry of the experiments was performed with two commercial hydrocodes. The comparison of mechanical impulses shows an agreement in terms of chronology but a noticeable difference in terms of amplitude, explained by mesh size and numerical diffusion
Multiaxial Variable Amplitude Loading for Automotive Parts Fatigue Life Assessment: A Loading Classification-based Approach Proposal
No full textInternational audienceThis work reports the different steps of a frequency decomposition method applied for fatigue lifetime assessment. The studied loadings are multiaxial time series measured at the vehicle wheel. The proposed decomposition presupposes that the loading results from both dynamic vehicle effects at low frequencies (Driven Road loadings) and random loads at high frequencies (Random Road loadings). This signal partition has two assets for fatigue purposes. First, the spectral methods can be applied to the Random effects. Two spectral damage formulations are tested in this paper. Then, the Driven Road loadings, related to the vehicle manoeuvre, enables to implement the Rainflow counting method on only one time series instead of the initial set of six per wheel, or twelve per axle. The implemented approach illustrated on a braking manoeuvre is validated, comparing the damage summation of the Random and Driven Road loadings with the one based on the usual Rainflow counting method applied to the overall time series
Micromechanical characterization of Carbon Black reinforced adhesive nanocomposite using micro indentation
No full textInternational audienceCarbon black (CB) reinforced adhesive are structurally complex materials with unique characteristics at various length scales. They have enormous potential applications in a variety of industries, automotive, aerospace, and marine. Microindentation with a VICKERS indenter was used to measure the micromechanical properties of carbon black CB reinforced adhesive composites with varying mass fractions (0, 1, 2, and 5 wt%). The micro-indentation deformation was studied by in-situ imaging of the impression using light microscopy analysis KEYENCE. Micromechanical properties, such as hardness, elastic modulus, and stiffness, gradually increase as the mass fraction of nanofiller (CB) continuously increases. This progress depends on various parameters, such as dispersion of nanofiller belong the adhesive matrix, interfacial bonding, and load transfer. These findings emphasize the possibility of achieving a diverse set of mechanical properties through a deeper understanding of the microindentation response of CB reinforced adhesive, which can be effective for the choice of materials and product developments in a variety of functional uses
On Weyl's type theorems and genericity of projective rigidity in sub-Riemannian Geometry
No full text18 pagesInternational audienceH. Weyl in 1921 demonstrated that for a connected manifold of dimension greater than , if two Riemannian metrics are conformal and have the same geodesics up to a reparametrization, then one metric is a constant scaling of the other one. In the present paper, we investigate the analogous property for sub-Riemannian metrics. In particular, we prove that the analogous statement, called the Weyl projective rigidity, holds either in real analytic category for all sub-Riemannian metrics on distributions with a specific property of their complex abnormal extremals, called minimal order, or in smooth category for all distributions such that all complex abnormal extremals of their nilpotent approximations are of minimal order. This also shows, in real analytic category, the genericity of distributions for which all sub-Riemannian metrics are Weyl projectively rigid and genericity of Weyl projectively rigid sub-Riemannian metrics on a given bracket generating distributions. Finally, this allows us to get analogous genericity results for projective rigidity of sub-Riemannian metrics, i.e.when the only sub-Riemannian metric having the same sub-Riemannian geodesics, up to a reparametrization, with a given one, is a constant scaling of this given one. This is the improvement of our results on the genericity of weaker rigidity properties proved in recent paper arXiv:1801.04257[math.DG]