Grant: Alliance Grants
Queen's University
$20,000.00
A reinforcement learning based control approach for grinding circuits to decarbonize mineral processes
EF 2024-25
Résumé
In order to meet the goals outlined in Canada's 2030 Agenda for Sustainable Development to combat climate change, developing technologies that will enable efficient energy use is essential. As Canada transitions to renewable energy sources like solar and wind, along with energy storage solutions such as lithium-ion batteries, it is vital to mitigate climate change impacts of battery production and mineral extraction. This research aims to increase energy efficiency during the mineral processing step of mineral production, more specifically, the comminution process, including crushing and grinding, which accounts for approximately 50% of the energy consumption at mine sites and 4% of electrical energy used globally. Depending on how the energy is produced, this process can directly translate into high GHG emissions.
The proposed project will develop an improved machine learning recommendation agent that is robust to random sensor noise and fluctuations to reduce carbon emissions in mineral processing. The outcome of this research, a machine learning based control system, will be validated through surrogate models and further tested through deployment at a mineral processing plant in order to optimize energy consumption in processing plants to support the sustainable production of critical minerals. This work aims to prevent sub-optimal use of Canadian resources and supports Canada's economic shift towards low-carbon emissions and aligns with national climate-resilient development pathways through reducing ore loss or waste processing and decreasing produced waste in tailings.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
602119-2024
Name nom
Sari, Yuksel Asli YA
Department département
Mining Engineering
Organization id
29
Institution établissement
Queen's University
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
20000
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
202
Area of application group en
Natural resources (economic aspects)
Area of application group fr
Ressources naturelles (aspects économiques)
Area of application en
Mineral resources ( prospecting, exploration, mining, extraction, processing)
Area of application fr
Ressources minérales (prospection, exploration, mines, extraction et préparation)
Research subject code
1400
Research subject group en
Mining and mineral processing
Research subject group fr
Génie minier et minéral
Research subject en
Mining and mineral processing
Research subject fr
Génie minier et minéral
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
A reinforcement learning based control approach for grinding circuits to decarbonize mineral processes
Keywords
data analysis; grinding; machine learning; mineral processing; mining engineering; reinforcement learning
Application summary
In order to meet the goals outlined in Canada's 2030 Agenda for Sustainable Development to combat climate change, developing technologies that will enable efficient energy use is essential. As Canada transitions to renewable energy sources like solar and wind, along with energy storage solutions such as lithium-ion batteries, it is vital to mitigate climate change impacts of battery production and mineral extraction. This research aims to increase energy efficiency during the mineral processing step of mineral production, more specifically, the comminution process, including crushing and grinding, which accounts for approximately 50% of the energy consumption at mine sites and 4% of electrical energy used globally. Depending on how the energy is produced, this process can directly translate into high GHG emissions.
The proposed project will develop an improved machine learning recommendation agent that is robust to random sensor noise and fluctuations to reduce carbon emissions in mineral processing. The outcome of this research, a machine learning based control system, will be validated through surrogate models and further tested through deployment at a mineral processing plant in order to optimize energy consumption in processing plants to support the sustainable production of critical minerals. This work aims to prevent sub-optimal use of Canadian resources and supports Canada's economic shift towards low-carbon emissions and aligns with national climate-resilient development pathways through reducing ore loss or waste processing and decreasing produced waste in tailings.