Grant: Discovery Launch Supplement
University of Waterloo
$12,500.00
Advancing Optimal Process Design and Control to Rigorously Model Space-Time
EF 2024-25
Résumé
Unprecedented wildfires, plastic-filled oceans, and rapid rising global temperatures illustrate the urgent need to establish sustainable industrial practices that align with Canada's 2050 climate and economic targets. Many emerging technologies, such as bioreactor-based plastic waste recycling and high-yield CO2 sequestration, are key enablers for developing a sustainable economy. To successfully deploy these technologies, advanced optimization tools are needed to develop safe and profitable strategies for design and control. However, the behaviour of these technologies is often determined by complicated space-time physics that cannot be modelled with traditional optimization techniques. For example, microbes in bioreactors experience complex interactions with each other that change over time and locations in the reactor. Ignoring these interactions can lead to issues with clogging, cell death, and out-of-control reactions that compromise safety and profit. Moreover, these processes are affected by uncertainty that varies over time and location (e.g., temperature, material defects) which existing optimization methods cannot fully capture. Thus, new decision-making approaches are required for complex space-time physics to reveal optimal strategies for deploying sustainable technologies via commercially viable processes.
The long-term vision of this program is to leverage state-of-the-art techniques in machine learning, optimization, and statistics to establish an optimization framework that effectively models space-time behaviours. Hence, a key objective is to develop methods to embed cutting-edge machine learning tools (i.e., neural operators) into optimization problems. This will enable the incorporation of highly detailed models (e.g., computational fluid dynamics simulators) which accurately capture space-time physics but are too computationally expensive to be used directly in advanced optimization methods. The other core objective is to develop efficient algorithms that enable the use of advanced statistical models (i.e., random fields) in the proposed framework. This important advancement will mitigate the risk imposed by uncertainties that vary over time and location. All these advancements will be guided by real-world case studies to design and control bioreactors for sustainable manufacturing, leading to immediate impact in Canada's biomanufacturing industry. Graduate students in this program will become researchers with expertise in machine learning, optimization, and computer programming, skills that are in high demand for engineering positions in manufacturing and technology. The optimization software tools produced by this research will greatly advance the capabilities of optimal design/control methods which are needed to guide the adoption of new technologies of strategic importance to Canada in engineering a sustainable economy.
Programme
Discovery Launch Supplement
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
DGECR-2024-00506
Name nom
Pulsipher, Joshua
Department département
Chemical Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
12500
Program id
DGECR
Program name en
Discovery Launch Supplement
Program name fr
Supplément Tremplin vers la découverte
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
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
1800
Research subject group en
Chemical engineering
Research subject group fr
Génie chimique
Research subject en
Chemical engineering
Research subject fr
Génie chimique
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
Advancing Optimal Process Design and Control to Rigorously Model Space-Time
Keywords
optimization under uncertainty; dynamic optimization; machine learning; mathematical optimization; process control; optimization under uncertainty; process systems; partial differential equations; random fields; biomanufacturing
Application summary
Unprecedented wildfires, plastic-filled oceans, and rapid rising global temperatures illustrate the urgent need to establish sustainable industrial practices that align with Canada's 2050 climate and economic targets. Many emerging technologies, such as bioreactor-based plastic waste recycling and high-yield CO2 sequestration, are key enablers for developing a sustainable economy. To successfully deploy these technologies, advanced optimization tools are needed to develop safe and profitable strategies for design and control. However, the behaviour of these technologies is often determined by complicated space-time physics that cannot be modelled with traditional optimization techniques. For example, microbes in bioreactors experience complex interactions with each other that change over time and locations in the reactor. Ignoring these interactions can lead to issues with clogging, cell death, and out-of-control reactions that compromise safety and profit. Moreover, these processes are affected by uncertainty that varies over time and location (e.g., temperature, material defects) which existing optimization methods cannot fully capture. Thus, new decision-making approaches are required for complex space-time physics to reveal optimal strategies for deploying sustainable technologies via commercially viable processes.
The long-term vision of this program is to leverage state-of-the-art techniques in machine learning, optimization, and statistics to establish an optimization framework that effectively models space-time behaviours. Hence, a key objective is to develop methods to embed cutting-edge machine learning tools (i.e., neural operators) into optimization problems. This will enable the incorporation of highly detailed models (e.g., computational fluid dynamics simulators) which accurately capture space-time physics but are too computationally expensive to be used directly in advanced optimization methods. The other core objective is to develop efficient algorithms that enable the use of advanced statistical models (i.e., random fields) in the proposed framework. This important advancement will mitigate the risk imposed by uncertainties that vary over time and location. All these advancements will be guided by real-world case studies to design and control bioreactors for sustainable manufacturing, leading to immediate impact in Canada's biomanufacturing industry. Graduate students in this program will become researchers with expertise in machine learning, optimization, and computer programming, skills that are in high demand for engineering positions in manufacturing and technology. The optimization software tools produced by this research will greatly advance the capabilities of optimal design/control methods which are needed to guide the adoption of new technologies of strategic importance to Canada in engineering a sustainable economy.