BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//6.6.4.4//EN TZID:Asia/Jerusalem X-WR-TIMEZONE:Asia/Jerusalem BEGIN:VEVENT UID:0-1173@aerospace.technion.ac.il DTSTART;TZID=Asia/Jerusalem:20250730T133000 DTEND;TZID=Asia/Jerusalem:20250730T143000 DTSTAMP:20250730T095448Z URL:https://aerospace.technion.ac.il/events/ml-based-wing-shape-loads-and- aoa-sensing-from-measured-strain-from-ground-test-to-flight-ready-integrat ion/ SUMMARY:ML-Based Wing Shape\, Loads\, and AoA Sensing from measured strain: From Ground Test to Flight-Ready Integration DESCRIPTION:Lecturer:Ido Hauzer \n Faculty:Department of Aerospace Engineer ing\n Institute:Technion – Israel Institute of Technology\n Location:Cla ssroom 165\, ground floor\, Library\, Aerospace Eng.\n Zoom: https://techn ion.zoom.us/j/93549691766\n Abstract: \n\n\nThis thesis presents a machine learning (ML) based method for sensing both the shape and applied distrib uted loads of a highly flexible wing (the Pazy wing) using measured strain data. The predicted shape and load distribution are then integrated with an aerodynamic model to estimate the rigid angle of attack (RAoA).\n\nThe research employs a practical approach\, utilizing relatively simple static ground tests with a few concentrated loads to train the ML model\, which subsequently predicts aerodynamic distributed loads and wing deformation d uring wind tunnel tests.\nA comprehensive workflow for designing training experiments and evaluating results is detailed\, complemented by a well-st ructured data processing and training pipeline. The concept is validated u sing ML models initially trained on a finite element (FE) structural model of the wing\, simulating loads that produce geometrically nonlinear defle ctions up to 50% (275mm) of the wing's 550mm span.\nThe performance of the load and shape prediction models is then evaluated using actual wind tunn el test data with deflections up to 100mm\, achieving maximum errors below 9.1%. The generalization and extrapolation capabilities of the models are assessed and demonstrate robust performance beyond the training domain.\n Finally\, the ML models are employed to determine the wing's aerodynamic c haracteristics and estimate the rigid AoA in wind tunnel tests ranging fro m -10° to 10°\, with a maximum error of 5.2% (0.6°) within the model's training range.\nThis study successfully establishes a comprehensive metho dology for predicting in-flight shape and loads using ground-test-trained ML models\, providing an effective approach for estimating RAoA for highly flexible structures.\n\n \;\n\nIdo is a master's student at the Facul ty of Aerospace Engineering at the Technion\, under the supervision of Pro f. Daniela Raveh. He holds a bachelor's degree in Mechanical Engineering f rom the Technion and has over a decade of experience in the aerospace indu stry. His areas of expertise include finite element analysis (FEA)\, multi body dynamics\, experimental testing\, and machine learning. Ido focuses o n integrating simulation\, experimentation\, and advanced algorithms to br idge the gap between physics-based modeling and artificial intelligence\, with the goal of enhancing engineering and validation processes for advanc ed airborne structures.\n\n\n\n Details: \n CATEGORIES:Seminars,סמינרים LOCATION:Classroom 165\, ground floor\, Library\, Aerospace Eng. END:VEVENT BEGIN:VTIMEZONE TZID:Asia/Jerusalem X-LIC-LOCATION:Asia/Jerusalem BEGIN:DAYLIGHT DTSTART:20250328T030000 TZOFFSETFROM:+0200 TZOFFSETTO:+0300 TZNAME:IDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR