Grant: Alliance Grants
University of Waterloo
$206,669.00
Deep Learning Approach to Predicting Fatigue Strength of Gas Metal Arc Welds for Automotive Frame Applications Accounting for Manufacturing Variability
FY 2024-25
Summary
The automotive sector is under pressure to reduce vehicle weight to reduce fuel consumption and green house gas emissions, while improving vehicle safety. To achieve this goal, steel manufactures have designed new high strength/high ductility steels to lighter vehicle structures. These steels have led to new vehicle structure design possibilities. To maximize options for design optimization, virtual design techniques have been developed to virtually optimize vehicle part strength and stiffness according to predetermined factors.
Material data is needed to implement virtual design methodologies. This is easily obtained for sheet materials, which is very consistent. However, static and cyclic (fatigue) weld strength is highly dependent on joint geometry, welding process parameters and weld geometry. Although weld strength may be determined experimentally, testing all possible configurations is onerous. In the past, full structures were build and tested to confirm designed strength. However, full-scale testing is cost prohibitive. The proposed project will for the first time understand how welding and manufacturing variability systemically affects static and cyclic joint strength. This understanding will be used to build an finite element model to predict joint strength and build a large data database to develop a novel machine learning (ML) predictive algorithm that can be widely applied in industry to implement the findings of this research.
This project will i) characterize how welding process and weld geometry affect fatigue strength of automotive joints, ii) develop a novel ML model to predict post-weld geometry from weld process data, iii) develop ML models to predict weld fatigue life of a weld particular weld geometry, iv) develop a methodology use the ML models to create data suitable for automotive design optimization. The know-how developed from this project will contribute to the competitiveness of Canada's automotive industry, allowing Canadian vehicle designers to easily design new light and safe automobiles made from the newest steels, reducing green house gas emissions of gas-power vehicles and enabling the production of new electric vehicles.
Program
Alliance Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
598548-2024
Name nom
Biro, Elliot EJ
Department département
Mechanical Engineering and Mechatronics
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
206669
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
602
Area of application group en
Construction, urban and rural planning
Area of application group fr
Construction, urbanisme et aménagement rural
Area of application en
Materials performance
Area of application fr
Performance des matériaux
Research subject code
2107
Research subject group en
Mechanical engineering
Research subject group fr
Génie mécanique
Research subject en
Modelling, simulation and finite element methods
Research subject fr
Modélisation, simulation et méthodes des éléments finis
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
Deep Learning Approach to Predicting Fatigue Strength of Gas Metal Arc Welds for Automotive Frame Applications Accounting for Manufacturing Variability
Keywords
advanced high strength steel; fatigue testing; gas metal arc welding; machine learning; manufacturing variability; numerical simulation
Application summary
The automotive sector is under pressure to reduce vehicle weight to reduce fuel consumption and green house gas emissions, while improving vehicle safety. To achieve this goal, steel manufactures have designed new high strength/high ductility steels to lighter vehicle structures. These steels have led to new vehicle structure design possibilities. To maximize options for design optimization, virtual design techniques have been developed to virtually optimize vehicle part strength and stiffness according to predetermined factors.
Material data is needed to implement virtual design methodologies. This is easily obtained for sheet materials, which is very consistent. However, static and cyclic (fatigue) weld strength is highly dependent on joint geometry, welding process parameters and weld geometry. Although weld strength may be determined experimentally, testing all possible configurations is onerous. In the past, full structures were build and tested to confirm designed strength. However, full-scale testing is cost prohibitive. The proposed project will for the first time understand how welding and manufacturing variability systemically affects static and cyclic joint strength. This understanding will be used to build an finite element model to predict joint strength and build a large data database to develop a novel machine learning (ML) predictive algorithm that can be widely applied in industry to implement the findings of this research.
This project will i) characterize how welding process and weld geometry affect fatigue strength of automotive joints, ii) develop a novel ML model to predict post-weld geometry from weld process data, iii) develop ML models to predict weld fatigue life of a weld particular weld geometry, iv) develop a methodology use the ML models to create data suitable for automotive design optimization. The know-how developed from this project will contribute to the competitiveness of Canada's automotive industry, allowing Canadian vehicle designers to easily design new light and safe automobiles made from the newest steels, reducing green house gas emissions of gas-power vehicles and enabling the production of new electric vehicles.