Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Engage Grants Program

University of Toronto

$21,100.00

Automated tuning system for Tenova Goodfellow Inc. process models

EF 2010-11

Résumé
We proposed to develop an optimization algorithm that tunes parameters of process models, developed by Tenova Goodfellow Inc. (TGI) to simulate a variety of furnace systems, so that the performance of the system can be maximized for a given range of operational conditions. Furnace systems need to be customized for specific operational conditions before installation and currently tuning of the key parameters is being done manually. This is very time-consuming and requires extensive human experiences as to how the changes in key parameters affect the process model. Therefore, it will be beneficial to make the tuning process automated so that it can be done without human involvement. The automated tuning system, which is the final product of the proposed research project, will attempt to find a combination of tuning parameters that make the performance, defined as a function of output variables, maximized over a range of input variables. Therefore, the tuning can be considered as an optimization problem with the performance as the objective function, the range of input variables as the feasible set and the tuning parameters as the decision variables. The major hurdle for the optimization is two-fold: (1) the complex and unknown functional relations among the input variables, the output variables and the tuning parameters and (2) point evaluation of the output variables for a given combination of the input variables and the tuning parameters is extremely time-consuming. Therefore, the project will focus on tuning of parameters based on the minimum number of evaluation of the process models.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
398082-2010
Name nom
Lee, ChiGuhn
Department département
Mechanical and Industrial Engineering
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2010
Award amount
21100
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
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
1604
Research subject group en
Industrial engineering
Research subject group fr
Génie industriel
Research subject en
Manufacturing
Research subject fr
Fabrication
Partie
1
Nb partie
1
Application title
Automated tuning system for Tenova Goodfellow Inc. process models
Keyword
NSERC
Application summary
We proposed to develop an optimization algorithm that tunes parameters of process models, developed by Tenova Goodfellow Inc. (TGI) to simulate a variety of furnace systems, so that the performance of the system can be maximized for a given range of operational conditions. Furnace systems need to be customized for specific operational conditions before installation and currently tuning of the key parameters is being done manually. This is very time-consuming and requires extensive human experiences as to how the changes in key parameters affect the process model. Therefore, it will be beneficial to make the tuning process automated so that it can be done without human involvement. The automated tuning system, which is the final product of the proposed research project, will attempt to find a combination of tuning parameters that make the performance, defined as a function of output variables, maximized over a range of input variables. Therefore, the tuning can be considered as an optimization problem with the performance as the objective function, the range of input variables as the feasible set and the tuning parameters as the decision variables. The major hurdle for the optimization is two-fold: (1) the complex and unknown functional relations among the input variables, the output variables and the tuning parameters and (2) point evaluation of the output variables for a given combination of the input variables and the tuning parameters is extremely time-consuming. Therefore, the project will focus on tuning of parameters based on the minimum number of evaluation of the process models.