Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

École Polytechnique de Montréal

$53,000.00

Digital Twin-Driven Advanced Repair and Remanufacturing

EF 2024-25

Résumé
Automated repair using 3D scan data, combined with additive manufacturing, offers an effective solution for restoring damaged parts. Yet, ensuring the reliability of this advanced repair method requires overcoming various challenges. The long-term objective of the proposed research program is to establish an automated repair process integrating 3D scanning, wire arc additive manufacturing (WAAM), machining, and modeling to ensure reliable and cost-effective repair for high-value components across various industries. Given the challenges of current technologies integral to the envisioned repair process, namely the lack of a reliable geometric model of the part, the absence of optimal pre-additive machining strategies, and the issues with WAAM process quality, a 5-year research program is proposed, focusing on: 1) Developing accurate and efficient algorithms for creating geometric digital twin models of damaged parts using 3D scan data, effectively generating repair volumes while factoring in measurement uncertainty. Using voxelization, we will improve computational efficiency. Voxel size adjustments will be made iteratively, balancing detail capture and processing speed. 2) Developing algorithms to optimize pre-additive machining cut-off volumes, minimizing waste. Different strategies will be devised for various damages (deep damages, superficial damages, and cracks). Data will be gathered from parts with known damages, enabling damage classification using supervised machine learning. 3) Developing an in-situ multi-sensor monitoring and adaptive process control system for WAAM. Data fusion algorithms will integrate collected data, while adaptive process control strategies adjust process parameters in real time to correct defects and geometric deviations. The closed-loop system will integrate artificial neural networks. Both supervised and reinforcement learning will be explored for process optimization. Real-world case studies will validate these tools. Automated repair through additive manufacturing aligns with green manufacturing principles by extending the lifecycle of damaged parts and reducing waste generation. The proposed research program facilitates knowledge transfer and practical implementation of sustainable repair and remanufacturing practices through the dissemination of research outcomes and collaboration with industrial partners. The program supports the training of Highly Qualified Personnel (HQP) in exciting and high-demand areas within the industry and enables hands-on experience in automated repair via additive manufacturing, 3D metrology, geometry processing, as well as data science, artificial intelligence, and machine learning in manufacturing. Through interdisciplinary collaboration, HQP will develop critical thinking, innovation, and technical skills; and by working in a diverse and inclusive research team, they will foster a deep commitment to equity, diversity, and inclusion, preparing them for future leadership roles.
Programme
Discovery Grants Program - Individual
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2024-06867
Name nom
Khameneifar, Farbod
Department département
Mechanical Engineering
Organization id
64
Institution établissement
École Polytechnique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
53000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1512
Committee name en
Mechanical Engineering
Committee name fr
Génie mécanique
Area of application code
500
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Manufacturing processes and products
Area of application fr
Procédés et produits industriels
Research subject code
1702
Research subject group en
Design and manufacturing
Research subject group fr
Conception et fabrication
Research subject en
Advanced manufacturing
Research subject fr
Méthodes de fabrication avancées
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Digital Twin-Driven Advanced Repair and Remanufacturing
Keywords
automated repair; additive and hybrid manufacturing; digital twin; 3d scanning; 3d metrology; point cloud data; geometry processing; in-situ monitoring; adaptive process control; artificial intelligence and machine learning
Application summary
Automated repair using 3D scan data, combined with additive manufacturing, offers an effective solution for restoring damaged parts. Yet, ensuring the reliability of this advanced repair method requires overcoming various challenges. The long-term objective of the proposed research program is to establish an automated repair process integrating 3D scanning, wire arc additive manufacturing (WAAM), machining, and modeling to ensure reliable and cost-effective repair for high-value components across various industries. Given the challenges of current technologies integral to the envisioned repair process, namely the lack of a reliable geometric model of the part, the absence of optimal pre-additive machining strategies, and the issues with WAAM process quality, a 5-year research program is proposed, focusing on: 1) Developing accurate and efficient algorithms for creating geometric digital twin models of damaged parts using 3D scan data, effectively generating repair volumes while factoring in measurement uncertainty. Using voxelization, we will improve computational efficiency. Voxel size adjustments will be made iteratively, balancing detail capture and processing speed. 2) Developing algorithms to optimize pre-additive machining cut-off volumes, minimizing waste. Different strategies will be devised for various damages (deep damages, superficial damages, and cracks). Data will be gathered from parts with known damages, enabling damage classification using supervised machine learning. 3) Developing an in-situ multi-sensor monitoring and adaptive process control system for WAAM. Data fusion algorithms will integrate collected data, while adaptive process control strategies adjust process parameters in real time to correct defects and geometric deviations. The closed-loop system will integrate artificial neural networks. Both supervised and reinforcement learning will be explored for process optimization. Real-world case studies will validate these tools. Automated repair through additive manufacturing aligns with green manufacturing principles by extending the lifecycle of damaged parts and reducing waste generation. The proposed research program facilitates knowledge transfer and practical implementation of sustainable repair and remanufacturing practices through the dissemination of research outcomes and collaboration with industrial partners. The program supports the training of Highly Qualified Personnel (HQP) in exciting and high-demand areas within the industry and enables hands-on experience in automated repair via additive manufacturing, 3D metrology, geometry processing, as well as data science, artificial intelligence, and machine learning in manufacturing. Through interdisciplinary collaboration, HQP will develop critical thinking, innovation, and technical skills; and by working in a diverse and inclusive research team, they will foster a deep commitment to equity, diversity, and inclusion, preparing them for future leadership roles.