Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

Université Laval

$50,000.00

Deep modular learning and explainable artificial intelligence for multimodal diagnosis, prognosis and maintenance

FY 2024-25

Summary
The faults detection, diagnosis, and prognostic (FDDP) play a crucial role to ensure efficient predictive maintenance (PdM). In the era of Industry 4.0, there is a rising trend towards the use machine learning and deep learning. Artificial intelligence (AI) methods have been shown to be powerful. However, many important challenges arise when using AI in industrial applications. First, different monitoring data are used and their collection is usually limited, leading to sparse and insufficient training data. Processing such multi-modal data inputs requires the application of advanced and innovative methodologies. The second challenge lies on the lack of explainability of the AI methods applied to FDDP. Third, the existing methods may not perform well when applied to data from new units of a fleet that operate under different conditions than those they were trained on. Considering these challenges and the current literature, there is a growing need to develop new methods to leverage the full potential of AI in faults detection, diagnosis, and prognostic and maintenance optimization. The objectives of this project are: (1) to ensure an efficient FDDP using multi-modal learning and explainable artificial intelligence; (2) to optimize PdM for a fleet of equipment assets using transfer learning; and (3) to validate the proposed general methodology using real-life industrial data provided by the industrial partner, Hydro-Québec. The proposed research will generate fundamental and general AI frameworks for FDDP, efficient algorithms for PdM optimization, and practical models for engineering systems analysis. In particular, the anticipated outcomes and impact are substantial for Hydro-Québec and for Canada. While focusing on power grids, the general concepts that will be developed could be adapted for other critical systems, such as spacecraft, telecommunication networks, control systems, and oil and gas pipelines. The research activities of this proposal will build for a foundation model that can be applied across a wide range of use cases. Highly qualified personnel will be trained through this research program to contribute to the current industrial revolution.
Program
Alliance Grants
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
602262-2024
Name nom
Nourelfath, Mustapha M
Department département
Génie mécanique
Organization id
51
Institution établissement
Université Laval
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
50000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
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
1600
Research subject group en
Industrial engineering
Research subject group fr
Génie industriel
Research subject en
Industrial engineering
Research subject fr
Génie industriel
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
Deep modular learning and explainable artificial intelligence for multimodal diagnosis, prognosis and maintenance
Keywords
artificial intelligence; asset management; faults detection and diagnosis; industrial engineering; maintenance management; operations research; optimization methods; power systems; prognostics and health management; reliability engineering
Application summary
The faults detection, diagnosis, and prognostic (FDDP) play a crucial role to ensure efficient predictive maintenance (PdM). In the era of Industry 4.0, there is a rising trend towards the use machine learning and deep learning. Artificial intelligence (AI) methods have been shown to be powerful. However, many important challenges arise when using AI in industrial applications. First, different monitoring data are used and their collection is usually limited, leading to sparse and insufficient training data. Processing such multi-modal data inputs requires the application of advanced and innovative methodologies. The second challenge lies on the lack of explainability of the AI methods applied to FDDP. Third, the existing methods may not perform well when applied to data from new units of a fleet that operate under different conditions than those they were trained on. Considering these challenges and the current literature, there is a growing need to develop new methods to leverage the full potential of AI in faults detection, diagnosis, and prognostic and maintenance optimization. The objectives of this project are: (1) to ensure an efficient FDDP using multi-modal learning and explainable artificial intelligence; (2) to optimize PdM for a fleet of equipment assets using transfer learning; and (3) to validate the proposed general methodology using real-life industrial data provided by the industrial partner, Hydro-Québec. The proposed research will generate fundamental and general AI frameworks for FDDP, efficient algorithms for PdM optimization, and practical models for engineering systems analysis. In particular, the anticipated outcomes and impact are substantial for Hydro-Québec and for Canada. While focusing on power grids, the general concepts that will be developed could be adapted for other critical systems, such as spacecraft, telecommunication networks, control systems, and oil and gas pipelines. The research activities of this proposal will build for a foundation model that can be applied across a wide range of use cases. Highly qualified personnel will be trained through this research program to contribute to the current industrial revolution.