When a previously trained machine learning model is put into production, the production phase begins where said model makes predictions on the inputs provided to it. When the distribution of production data changes over time, we talk about data drift. Then the model is likely to become less efficient, or even obsolete. The project consists of building an intelligent system capable of alerting in the event of a data drift that would have a significant impact on the system.
In this project Wind-Do and ETS will work together to optimize the Wind-Do technology by integrating new functionality to their developed microgrid to detect and to localize in real-time the faults and anomalies. This new development will help technicians to get a fast response on the behavior of the system and turn the system ON rapidly without scanning all installation equipment as well as without revising the programmable logical controller program, which is used for monitoring the Wind-Do microgrid’s equipment.
The research project aims at integrating artificial intelligence (AI) into a user interface (UI) in the context of engineering design. Based on this context, the AI-aided UI of the CAD software will actively return hints and advice on missing parts of the product and/or what will be the next steps of the design. Such a tool will reduce human-related errors, like unwanted redundancy or a forgotten component, problems that are generally identified later in the design process.
Service robots are robots made to work alongside and be of aid to humans in every day environments. These robots must be safe, reliable, and easy to interact without endangering humans nor the environment. The purpose of this partnership aims to develop and implement advanced control methods to enhance the safety and functionality of a class of human-like service robots, called humanoid robots. We first propose a method that enhances a robot’s ability to ensure that it is, in fact, able to detect interaction forces by analyzing the positioning of the robot limbs.
With the development of advance telecommunication systems, new opportunities for real-time public transport monitoring has been created. Traffic congestion in the vehicular ad-hoc network can be typically caused by an accident, construction zones, special events, and adverse weather. This research presents a cognitive framework to address real-time routing problem and and arrival time prediction for bus system using a machine learning method.
Le monitoring en temps réel des bioprocédés permet d’augmenter les performances et de réduire les pertes. La principale
difficulté provient de la quantité limitée d’information accessible en temps réel et des phénomènes complexes et fortement
non-linéaires en présence. Ainsi, les algorithmes statistiques conventionnels ne permettent pas d’interpréter adéquatement et
avec la précision requise en pharmaceutique les signaux mesurés par des sondes spectrales.
La compagnie RMDS est très présente dans le domaine de la communication par courant porteur. Cette technologie permet de communiquer sur les réseaux d’alimentation. Cela apporte différents défis de taille puisque ces réseaux ne sont pas conçus pour la communication, mais sont conçus par la transmission d’énergie à très basse fréquence. La technologie de RMDS doit être mise à jour. Plusieurs aspects de celle-ci seront améliorés notamment la vitesse de transmission, la robustesse du système face au bruit, les coûts de production du système ainsi que la puissance requise pour communiquer.
Advances in semiconductor technology allow the increase of the efficiency and the power density of power
converters using high switching frequency converters (HSFC). The integration of such energy conversion systems
is continuously growing and in high demand for applications such as electric vehicle battery chargers, more electric
aircrafts, and distributed energy resources. However, the real-time simulation (RTS) of HSFC is challenging, since
very small time-steps — in the order of tens nanoseconds —are mandatory to achieve high fidelity.
Infrared thermography represents an attractive solution in the field of Non-Destructive Testing (NDT) by overcoming some drawbacks of the traditional surveys. However, the labor and the amount of data to be analyzed, stored, and communicated are extensive when inspections are scaled to a large network of structures. In addition, the information about the damages is usually analyzed and stored using manually-based approaches.
Current RFID tags process reveals that it is impossible to set the cost per tag to less than 5 cents. Similarly, area is a precious quantity. Much of the area in a tag is used by digital logic and capacitors. Merely adding more area is not a sustainable solution. This project will help the community to decrease the cost per tag to less than 5 cents as expected with much more compactness as compared to available tags.
The partner will benefit from the research by collaborating with one of the top research labs in the field.