Grant: Discovery Grants Program - Individual
University of Calgary
$50,000.00
Synergistic blending of physics-based and data-driven approaches for wind turbine modeling
FY 2023-24
Summary
According to the 2022 Global Wind Report, total global wind power capacity is now up to 837 GW, helping the world avoid over 1.2 billion tons of CO2 annually. To facilitate such growth, wind turbines are getting bigger and are more often placed in remote and offshore locations. It is imperative that wind turbines be continuously monitored for their operational and health conditions to inform timely decisions for production and maintenance planning. This is necessary to reduce costs and maximize turbines' availability for wind energy to be a viable player in the green economy. Specifically, to allow effective preventative measures to be taken, condition monitoring needs to be automated, requiring little-to-no expert intervention, able to detect problems early, and able to identify fault locations and their root causes accurately. A condition-based maintenance system should also be able to provide predictions on fault progression, how other components might be affected, and when and how the system might fail. These call for solutions to the inverse problems best served with a sophisticated model that encompasses all essential elements as well as necessary nuances of the actual wind turbine being monitored. In the next five years, we will focus on developing a combined physics-based and data-driven model and its applications to model-based control and monitoring for wind turbine systems. The goal is for such a model to contain sufficient details to provide predictive simulations for the purpose of control strategy evaluation, root cause and severity determination when an anomaly has been detected and remaining useful life estimation. To achieve these goals, we will focus on answering fundamental questions including how good is "good enough" for a model, how to capture all necessary details including scenarios where limited knowledge exists, and how to combine the two approaches to achieve the best of both worlds. The success of this project will support Canada's leadership role in meeting renewable energy targets by advancing fundamental knowledge, transferring technology best practices to industry, and training of HQP for this growing industry.
Program
Discovery Grants Program - Individual
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-03774
Name nom
Sun, Qiao
Department département
Mechanical and Manufacturing Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
50000
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
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
9999
Research subject group en
Not available
Research subject group fr
Not available
Research subject en
Non disponible
Research subject fr
Non disponible
Application title
Synergistic blending of physics-based and data-driven approaches for wind turbine modeling
Keyword
fault diagnosis and prognosis; machine condition monitoring; model-based control; multi-body dynamics; multi-domain and multi-scale modeling; predictive simulation; remaining useful life estimiation; root cause determination; system identification; uncertainty quantification
Application summary
According to the 2022 Global Wind Report, total global wind power capacity is now up to 837 GW, helping the world avoid over 1.2 billion tons of CO2 annually. To facilitate such growth, wind turbines are getting bigger and are more often placed in remote and offshore locations. It is imperative that wind turbines be continuously monitored for their operational and health conditions to inform timely decisions for production and maintenance planning. This is necessary to reduce costs and maximize turbines' availability for wind energy to be a viable player in the green economy. Specifically, to allow effective preventative measures to be taken, condition monitoring needs to be automated, requiring little-to-no expert intervention, able to detect problems early, and able to identify fault locations and their root causes accurately. A condition-based maintenance system should also be able to provide predictions on fault progression, how other components might be affected, and when and how the system might fail. These call for solutions to the inverse problems best served with a sophisticated model that encompasses all essential elements as well as necessary nuances of the actual wind turbine being monitored. In the next five years, we will focus on developing a combined physics-based and data-driven model and its applications to model-based control and monitoring for wind turbine systems. The goal is for such a model to contain sufficient details to provide predictive simulations for the purpose of control strategy evaluation, root cause and severity determination when an anomaly has been detected and remaining useful life estimation. To achieve these goals, we will focus on answering fundamental questions including how good is "good enough" for a model, how to capture all necessary details including scenarios where limited knowledge exists, and how to combine the two approaches to achieve the best of both worlds. The success of this project will support Canada's leadership role in meeting renewable energy targets by advancing fundamental knowledge, transferring technology best practices to industry, and training of HQP for this growing industry.