Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

McMaster University

$32,000.00

Intelligent Fault Diagnosis, Prognosis and Maintenance Decision-Making: Towards A Smart Manufacturing

FY 2024-25

Summary
Big data analytics and advanced machine learning (ML) techniques offer a tremendous opportunity in the global transition of manufacturing paradigm to smart manufacturing. Smart manufacturing is a term that is used for a digitalized factory which utilizes interconnected machines and their data to improve manufacturing performance and supply chain management. Such digitalized processes allow operations improvement through a clear understanding of data patterns, fault diagnostics, prognostics, and disruptions prevention. These improvements can be made by implementing advanced ML algorithms, predictive maintenance strategies, and optimal decision-making under uncertainty. Utilizing the massive data generated by the connected systems for health diagnosis and predictive maintenance decision-making is a major challenge of digital processes. Moreover, the data-rich planning paradigm poses new methodological challenges and calls for new data-driven optimization strategies. For instance, decision making under uncertainty requires ML techniques to span the full pipeline from data to predictive models, optimization, and decisions. Thus, research is needed on data-driven optimization strategies including data preparation, model construction, optimization, and sensitivity analysis for intelligent health diagnosis and maintenance decision-making. Fortunately, the advancement of data analytics and ML techniques has enabled decision makers to exploit large amounts of data to precisely model uncertainty. Considering the existing theoretical and computational challenges, this proposal aims at creatively combining optimization models with advanced ML techniques to propose an effective and practical decision support framework. This novel framework is used to capture the uncertainty from data, predict potential process disruptions, and propose predictive maintenance decisions to eliminate unscheduled downtime and increase productivity. Another goal of this proposal is to develop computationally efficient solution algorithms to solve the optimization problems. This research will lead to development of a framework for effective remote monitoring of the process, intelligent fault diagnosis and prognosis, and predictive maintenance decisions in the context of smart manufacturing. On the methodological side, this proposal aims at developing new analytical and algorithmic tools, and predictive models using data-driven techniques such as supervised (e.g., tree-based models) and unsupervised (e.g., dimensionality reduction) learning techniques, as well as optimization methods such as stochastic dynamic programming. The proposed research program will contribute to the development of the integrated optimization models, advanced solution algorithms and practical managerial insights for practitioners. The long-term goal of the proposed research program is to develop cross-disciplinary models, and managerial insights to autonomously run the entire production process.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2023-04453
Name nom
Salari, Nooshin
Department département
Operations Management - Operations Management
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
32000
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
1509
Committee name en
Civil, Industrial and Systems Engineering
Committee name fr
Génie civil, industriel et des systèmes
Area of application code
520
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Production and operations management
Area of application fr
Production et gestion des opérations
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
Intelligent Fault Diagnosis, Prognosis and Maintenance Decision-Making: Towards A Smart Manufacturing
Keywords
maintenance decision support system; prognostic and health management; machine learning; data analytics; optimization
Application summary
Big data analytics and advanced machine learning (ML) techniques offer a tremendous opportunity in the global transition of manufacturing paradigm to smart manufacturing. Smart manufacturing is a term that is used for a digitalized factory which utilizes interconnected machines and their data to improve manufacturing performance and supply chain management. Such digitalized processes allow operations improvement through a clear understanding of data patterns, fault diagnostics, prognostics, and disruptions prevention. These improvements can be made by implementing advanced ML algorithms, predictive maintenance strategies, and optimal decision-making under uncertainty. Utilizing the massive data generated by the connected systems for health diagnosis and predictive maintenance decision-making is a major challenge of digital processes. Moreover, the data-rich planning paradigm poses new methodological challenges and calls for new data-driven optimization strategies. For instance, decision making under uncertainty requires ML techniques to span the full pipeline from data to predictive models, optimization, and decisions. Thus, research is needed on data-driven optimization strategies including data preparation, model construction, optimization, and sensitivity analysis for intelligent health diagnosis and maintenance decision-making. Fortunately, the advancement of data analytics and ML techniques has enabled decision makers to exploit large amounts of data to precisely model uncertainty. Considering the existing theoretical and computational challenges, this proposal aims at creatively combining optimization models with advanced ML techniques to propose an effective and practical decision support framework. This novel framework is used to capture the uncertainty from data, predict potential process disruptions, and propose predictive maintenance decisions to eliminate unscheduled downtime and increase productivity. Another goal of this proposal is to develop computationally efficient solution algorithms to solve the optimization problems. This research will lead to development of a framework for effective remote monitoring of the process, intelligent fault diagnosis and prognosis, and predictive maintenance decisions in the context of smart manufacturing. On the methodological side, this proposal aims at developing new analytical and algorithmic tools, and predictive models using data-driven techniques such as supervised (e.g., tree-based models) and unsupervised (e.g., dimensionality reduction) learning techniques, as well as optimization methods such as stochastic dynamic programming. The proposed research program will contribute to the development of the integrated optimization models, advanced solution algorithms and practical managerial insights for practitioners. The long-term goal of the proposed research program is to develop cross-disciplinary models, and managerial insights to autonomously run the entire production process.