Optimisation des niveaux de stock de pièces de rechange

La STM vient d’incorporer un progiciel de gestion d’entreprise (ERP) et souhaite valoriser les données des stocks de pièces afin de réduire ses coûts d’entreposage. Ce projet est la phase initiale d’un projet d’envergure et il vise à développer un outil d’aide à la décision du processus de stockage et de transit des pièces de rechange dans les centres de contrôle. Il s’agit concrètement de mettre en place un processus efficace d’identification des stocks et de voir s’il est possible d’automatiser les modèles descriptifs des inventaires avec les données de l’ERP.

Self-Sustainable Wireless Sensors and Base-Stations Powered by Leaky-Energy Recycling and Harvesting from High Voltage Power Lines

The increasing complexity of large power distribution networks (PDN) has suggested that real-time monitoring systems (CMS) become crucial for both daily operation and emerging research. Future smart grids are expected to be assisted by but also operate for a vast number of sensor and actuator nodes. Such sensor/actuator nodes will demand a more consistent and reliable power supply in order to perform operation-monitoring tasks as well as collaborative edge computing and wireless communication functions such as 5G or even smart in-situ autonomous repairs of the power grids.

Indicateurs d’accessibilité de la population aux espaces verts – Développement d’un outil misant sur les données ouvertes

Les indicateurs d’accessibilité aux destinations permettent de mesurer la performance conjointe des systèmes de transport et d’aménagement du territoire. Bien que leur apport à une meilleure planification des transports ait été largement démontré, ils sont encore peu utilisés en pratique, étant donné les défis liés à leur opérationnalisation. Le projet proposé vise donc à développer une méthodologie utilisant les données ouvertes afin de générer et de visualiser les indicateurs d’accessibilité sur plateforme de données de Jalon MTL.

Pursuing innovative non-rare earth amplified fibered DFB lasers: Ultra-long fiber Bragg gratings non-linear induced temperature control

Recent years have seen significant leaps towards perfecting the fabrication of ultra-long fiber Bragg gratings (FBGs) for application in non-linear optics, including fibered DFB lasers. Previous work from the laboratory was able to successfully identify and mitigate some of the intrinsic defects causing non-uniformity in multiple type of fibers leading to their compensation attaining high quality reproducible ultra-long FBGs.

Hardware/Software Codesign Methodology for High Performance On-Board Processing applied on the Artificial Intelligence of Space

The result of this project (which will be demonstrated by a use case) can make health equipments to be used outside of hospitals. This is achieved by reducing the computation cost of running Deep Learning models by 3rd party tools and use our accelerator solution to run the size reduced and optimized model. This greatly helps to lower the barrier for using costly equipments and make them more affordable and reachable to people in need of these equipments.

Seq2Hypergraph: Link prediction on knowledge graphs using relation conditioned Transformer Networks

Learning from relational data is crucial for modeling the processes found in many application domains ranging from computational biology to social networks. In this project, we propose to work on developing new modeling techniques that combine the advantages of the approaches found in two fields of study: Machine Learning (through graph neural networks and transformer networks) and Statistical Learning (through statistical relational learning methods).

Système aéroporté sans pilote de détection de cibles humaines dans l’eau

Le projet de détection et de reconnaissance de personnes sur une étendue d’eau permettra de minimiser les pertes humaines en intervenant le plus rapidement possible lors d’une situation d’urgence. Le temps de survie d’une personne à l’eau est très limité, sous certaines conditions quelques minutes et il varie en fonction du port de ceinture ou costume de flottaison, de la température de l’eau et de la condition physique de la personne. Il est donc crucial de retrouver rapidement les personnes dans une telle situation.

A scalable data science platform to support intelligent freight services and logistics

ShipHaul Logistics aims at developing an Intelligent Freight Services platform towards the digitization, integration and optimization of freight management. The proposed project is the first step to provide the foundations and infrastructure and kickstart the development of the envisioned platform. To this end, we will emphasize evaluation, testing and comparative studies concerning the efficiency and capabilities of various software solutions for the constituent modules of the proposed platform.

Novel approaches for longitudinal control laws of commercial aircraft

The A220 aircraft, former CSeries, is the first commercial aircraft certified by Bombardier with fully augmented Fly-by-Wire Control Laws. The longitudinal controller gains are usually scheduled across the flight envelope according to relevant aerodynamic variables. Their tuning can be a lengthy and, sometimes, sub-optimal process. Hence, it is key for Airbus Canada to continue developing state-of-the-art design methodologies based on recent academic research. During this Master’s thesis, the student will evaluate the benefits and applicability to A220 of two ways of addressing this topic.

CBCT dose planning for adaptive radiotherapy solutions

Adaptive radiotherapy (ART) consists of adjusting irradiation at each treatment phase in response to changes in the patient’s body (such as weight loss) or from the patient’s change in position. Indeed, since initial dose plans are determined from standard CT, the initial dose distribution may vary and yield sub-optimal dose delivery. Intra-procedural imaging such as cone-beam CT (CBCT) can be used to adapt plans on a daily basis, but requires real-time performance with the patient on the table.