Grant: Alliance Grants
Université de Sherbrooke
$42,350.00
Development of Artificial Intelligence Techniques for Automated Electric Power Asset Identification_x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_ _x000d_
FY 2020-21
Summary
Classical electrical engineering still relies on working methods based on the manual analysis of photos and drawings, which can be slow and prone to human errors. We wish to apply new artificial intelligence (AI) and machine learning (ML) technologies to the field of classical electrical engineering in order to facilitate the interpretation of electrical drawings and photos of electrical equipment. Subsequently, the interpretation of this information would make it possible to build calculation models to accelerate the manual work required when performing short-circuit and arc-flash studies, while at the same time reducing the risk of human error in the process.
The first goal of this project will be to detect the type of electrical fuses (manufacturer, type, style, and rating) in photos taken by electrical engineers during site surveys in places such as factories or industrial and commercial buildings. For this purpose, imaging data of electrical fuses collected from previous projects performed by partner organizations and from the web (Google Images) will be used to train object detection algorithms, mainly from the convolutional neural network family. The second goal of this project will be to detect electrical equipment symbols on electrical drawings (fuses, breakers, transformers, motors, etc.), detect the descriptive text and information related to each symbol, detect the links between symbols and automate the creation of calculation models that can be imported in power system studies software.
This automation will bring greater accuracy and decrease the time needed to interpret surveys of electrical installations, thus increasing the efficiency of the electrical engineer's work and public safety regarding electrical installations. It will also provide access to this new technology based on artificial intelligence to the Canadian industrial partners of this research project, which will improve their competitivity in the international markets for large-scale projects, such as the construction of new power dams or electrical substations in foreign countries.
_x000d_L'ingénierie électrique classique repose toujours sur des méthodes de travail basées sur l'analyse manuelle de photos et de plans, qui peuvent être lentes et sujettes à l'erreur humaine. Nous souhaitons appliquer les nouvelles technologies d'intelligence
Program
Alliance Grants
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
558290-2020
Name nom
Vallières, Martin
Department département
Informatique
Organization id
68
Institution établissement
Université de Sherbrooke
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2020
Competition year année de concours
2020
Award amount
42350
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
304
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Electrical energy
Area of application fr
Énergie électrique
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Installment
inst:1 - 1
Partie
1
Nb partie
1
Application title
Development of Artificial Intelligence Techniques for Automated Electric Power Asset Identification_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
_x000d_
Keyword
NSERC
Application summary
Classical electrical engineering still relies on working methods based on the manual analysis of photos and drawings, which can be slow and prone to human errors. We wish to apply new artificial intelligence (AI) and machine learning (ML) technologies to the field of classical electrical engineering in order to facilitate the interpretation of electrical drawings and photos of electrical equipment. Subsequently, the interpretation of this information would make it possible to build calculation models to accelerate the manual work required when performing short-circuit and arc-flash studies, while at the same time reducing the risk of human error in the process.
The first goal of this project will be to detect the type of electrical fuses (manufacturer, type, style, and rating) in photos taken by electrical engineers during site surveys in places such as factories or industrial and commercial buildings. For this purpose, imaging data of electrical fuses collected from previous projects performed by partner organizations and from the web (Google Images) will be used to train object detection algorithms, mainly from the convolutional neural network family. The second goal of this project will be to detect electrical equipment symbols on electrical drawings (fuses, breakers, transformers, motors, etc.), detect the descriptive text and information related to each symbol, detect the links between symbols and automate the creation of calculation models that can be imported in power system studies software.
This automation will bring greater accuracy and decrease the time needed to interpret surveys of electrical installations, thus increasing the efficiency of the electrical engineer's work and public safety regarding electrical installations. It will also provide access to this new technology based on artificial intelligence to the Canadian industrial partners of this research project, which will improve their competitivity in the international markets for large-scale projects, such as the construction of new power dams or electrical substations in foreign countries.
_x000d_L'ingénierie électrique classique repose toujours sur des méthodes de travail basées sur l'analyse manuelle de photos et de plans, qui peuvent être lentes et sujettes à l'erreur humaine. Nous souhaitons appliquer les nouvelles technologies d'intelligence