Grant: Idea to Innovation
University of Ontario Institute of Technology
$125,000.00
Next-gen Safety Framework using Digital-twin-based Smart Battery Thermal Management Control System
FY 2023-24
Summary
The global market for electric vehicles (EVs) is rapidly growing. Irrespective of the manufacturer, lithium-ion batteries (LIB) are widely used in EVs but the internal characteristics of LIB are highly nonlinear and extremely sensitive to operating and environmental parameters. Moreover, one cell can only supply a very small amount of voltage and power, so hundreds and thousands of individual cells are connected in series and parallel to obtain the required voltage and power. Apart from nonlinearities, the thermal characteristics of every cell are slightly different due to manufacturing inconsistencies, position inside the battery pack, and the different aging profiles.It is noticed that frequent incidents of catastrophic failure of batteries leading to a fire in EVs are primarily due to inadequate temperature information and ineffective thermal management control. One of the primary drawbacks of existing BMS is considering the sample temperature at different points of the battery pack, and not considering the internal cell temperature. A significant difference between the internal and surface temperatures (10-12°C) is noticed especially with a high charging and discharging rate. Here, measuring internal temperature by intruding temperature sensors in each cell is detrimental to the cell's health while the existing estimation techniques are inaccurate and non-adaptive to cell aging and the dynamics of operating conditions. Therefore, this project aims to develop and validate a hybrid cloud and digital twin-based battery thermal management control framework powered by deep learning algorithms. The framework aims to provide ultimate safety for the EV battery without overloading the onboard BMS. Additionally, it will be capable of predicting thermal runaway at least 5 minutes before it occurs, following the IEC 62933-2-1:2017 standard. By enhancing safety and longer battery life, the framework will improve customer satisfaction leading to growth in the Canadian EV industry and supporting Canada's green economy.
Program
Idea to Innovation
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
586115-2023
Name nom
Williamson, Sheldon S
Department département
Electrical, Computer and Software Engineering
Organization id
19222
Institution établissement
University of Ontario Institute of Technology
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
125000
Program id
I2IPJ
Program name en
Idea to Innovation
Program name fr
De l'idée à l'innovation
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
305
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Energy storage and conversion
Area of application fr
Stockage et transformation de l'énergie
Research subject code
2517
Research subject group en
Electrical and electronic engineering
Research subject group fr
Industrial and power electronics
Research subject en
Génie électrique et électronique
Research subject fr
Électronique de puissance et électronique industrielle
Application title
Next-gen Safety Framework using Digital-twin-based Smart Battery Thermal Management Control System
Keyword
Batteries; Cloud computing; Deep learning; Electrification; Energy storage; Machine learning; Power Electronics; Transportation
Application summary
The global market for electric vehicles (EVs) is rapidly growing. Irrespective of the manufacturer, lithium-ion batteries (LIB) are widely used in EVs but the internal characteristics of LIB are highly nonlinear and extremely sensitive to operating and environmental parameters. Moreover, one cell can only supply a very small amount of voltage and power, so hundreds and thousands of individual cells are connected in series and parallel to obtain the required voltage and power. Apart from nonlinearities, the thermal characteristics of every cell are slightly different due to manufacturing inconsistencies, position inside the battery pack, and the different aging profiles.It is noticed that frequent incidents of catastrophic failure of batteries leading to a fire in EVs are primarily due to inadequate temperature information and ineffective thermal management control. One of the primary drawbacks of existing BMS is considering the sample temperature at different points of the battery pack, and not considering the internal cell temperature. A significant difference between the internal and surface temperatures (10-12°C) is noticed especially with a high charging and discharging rate. Here, measuring internal temperature by intruding temperature sensors in each cell is detrimental to the cell's health while the existing estimation techniques are inaccurate and non-adaptive to cell aging and the dynamics of operating conditions. Therefore, this project aims to develop and validate a hybrid cloud and digital twin-based battery thermal management control framework powered by deep learning algorithms. The framework aims to provide ultimate safety for the EV battery without overloading the onboard BMS. Additionally, it will be capable of predicting thermal runaway at least 5 minutes before it occurs, following the IEC 62933-2-1:2017 standard. By enhancing safety and longer battery life, the framework will improve customer satisfaction leading to growth in the Canadian EV industry and supporting Canada's green economy.
