https://luck.synhera.be/handle/123456789/150 2026-04-15T09:45:08Z https://luck.synhera.be/handle/123456789/1637 Contribution à l’autoconsommation de l’électricité produite par deux installations photovoltaïques via batteries, contrôle de la production d’eau chaude sanitaire et prises intelligentes HANUS, Vincent Le projet Gaume Energies a, entre autres, comme objectif de mettre en place des solutions de stockage décentralisé d’énergie afin d’augmenter au-delà de 60% le taux d’autoconsommation d’énergie d’origine photovoltaïque. Le placement de batteries, de contrôleurs de puissance sur la production d’eau chaude sanitaire et de prises intelligentes pendant deux ans sur deux installations a permis de constater, via un monitoring, un taux d’autoconsommation entre 71 et 84%, selon les installations et les années considérées, à comparer avec un taux compris entre 20 et 31 % sans système 2022-01-01T00:00:00Z https://luck.synhera.be/handle/123456789/1636 Analyse de la résistance d’un caisson de vidage horizontal (approche par éléments finis - SPH) VAISSAUD, Yoko Afin d'estimer la résistance du caisson d'un nouveau système horizontal de déchargement d’une semi-remorque, deux étapes de simulation ont été réalisées. Tout d'abord, la méthode SPH (Smoothed Particle Hydrodynamic) a simulé le phénomène de décharge et la distribution de la pression de la terre écrasée contre la benne a été récupérée. Ensuite, on a appliqué la distribution de pression extraite de la simulation SPH comme condition de chargement dans la simulation FEM (Finite Element Method) du caisson de la semi-remorque : la résistance mécanique de ce dernier a été constatée comme suffisante. 2022-01-01T00:00:00Z https://luck.synhera.be/handle/123456789/1613 Head Pitch Angular Velocity Discriminates (Sub-)Acute Neck Pain Patients and Controls Assessed with the DidRen Laser Test BUISSERET, Fabien; HOURY, Martin; Hage, R.; DIERICK, Frédéric Understanding neck pain is an important societal issue. Kinematic data from sensors may help to gain insight into the pathophysiological mechanisms associated with neck pain through a quantitative sensorimotor assessment of one patient. The objective of this study was to evaluate the potential usefulness of artificial intelligence with several machine learning (ML) algorithms in assessing neck sensorimotor performance. Angular velocity and acceleration measured by an inertial sensor placed on the forehead during the DidRen laser test in thirty-eight acute and subacute non-specific neck pain (ANSP) patients were compared to forty-two healthy control participants (HCP). Seven supervised ML algorithms were chosen for the predictions. The most informative kinematic features were computed using Sequential Feature Selection methods. The best performing algorithm is the Linear Support Vector Machine with an accuracy of 82% and Area Under Curve of 84%. The best discriminative kinematic feature between ANSP patients and HCP is the first quartile of head pitch angular velocity. This study has shown that supervised ML algorithms could be used to classify ANSP patients and identify discriminatory kinematic features potentially useful for clinicians in the assessment and monitoring of the neck sensorimotor performance in ANSP patients. 2022-01-01T00:00:00Z https://luck.synhera.be/handle/123456789/1607 Real Time Hand Gesture Recognition in Industry Dumoulin, W.; Thiry, N.; Slama, R. With the 4th industrial revolution and the increased use of cobots in the industries comes many opportunities for new generation control panels. In this article, we proposed to develop a deep learning model to recognize in real time 10 different gestures that can be used to interact with a cobot. We proposed a new dataset containing gestures that can be used in an industrial context. The videos were taken from a computer webcam and then processed to remove the noise created by the background by isolating the movement of the gray scale images. We proposed to extract the spatio-temporal features by the combination of 3D convolution and LSTM layers. We also proposed a real time method to recognize our gestures, the frames are captured continuously and fed to the model to get a prediction every 2.4 seconds. Our experimental results show for 8 out of 10 gestures, a recognition rate of more than 90%. Furthermore, an interface was created to test our method in real time and to add new classes of gestures to be recognized by our model. 2021-01-01T00:00:00Z