Conference
Towards On-Board Implementation of ML-Based Helicopter Weight Estimator
| Title: | Towards On-Board Implementation of ML-Based Helicopter Weight Estimator |
|---|---|
| Authors: | Valot, Nicolas, Mechouche, Ammar, Lesage, Benjamin, Pagetti, Claire, Fabre, Louis |
| Contributors: | Airbus Helicopters, Aeroport International de Marseille-Provence, DTIS, ONERA, Université de Toulouse Toulouse, ONERA-Communauté d'universités et établissements de Toulouse (Comue de Toulouse), PATO DGAC, The Future of Vertical Flight (VFS), ANR-23-IACL-0002,ANITI IA Cluster,Artificial and Natural Intelligence Toulouse Institute(2023) |
| Source: | The 2026 Annual Forum and Technology Display (Forum 82) ; https://hal.science/hal-05655153 ; The 2026 Annual Forum and Technology Display (Forum 82), The Future of Vertical Flight (VFS), May 2026, Palm Beach Florida, USA, United States |
| Publisher Information: | CCSD |
| Publication Year: | 2026 |
| Collection: | ONERA: HAL (Centre français de recherche aérospatiale / French Aerospace Lab) |
| Subject Terms: | Certification, Implementation, Semantic preservation, Embedded AI, ACM: C.: Computer Systems Organization/C.5: COMPUTER SYSTEM IMPLEMENTATION, [INFO.INFO-ES]Computer Science [cs]/Embedded Systems, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
| Subject Geographic: | Palm Beach Florida, USA, United States |
| Description: | International audience ; This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopterweight during takeoff, utilizing extensive datasets from Airbus’s global in-service fleet. The study details a learningassurance process aligned with the EASA concept paper for machine learning application, and with the on-goingEurocae ED-324. We propose a set of Machine Learning Requirements, a Machine Learning Model Description, andits implementation for a long short-term memory recurrent neural network. Finally, we verify the requirements on theimplementation. Demonstrated on legacy avionics computers, the implementation is suitable for the deployment ofthe developed Machine Learning Model weight estimator on airborne targets for critical functions such as on-boardalerting. |
| Document Type: | conference object |
| Language: | English |
| Availability: | https://hal.science/hal-05655153 https://hal.science/hal-05655153v1/document https://hal.science/hal-05655153v1/file/main.pdf |
| Rights: | https://creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: | edsbas.D1AF5A46 |
| Database: | BASE |
| Description not available. |