Grant: Alliance Grants
University of Toronto
$26,000.00
Machine learning algorithm for three dimensional magnetic flux leakage defect evaluation
FY 2024-25
Summary
This proposal is centered on the development of a machine learning algorithm for the quantitative evaluation of defects using magnetic flux leakage (MFL) signals in all three dimensions. The primary application would be the nondestructive evaluation of the steel floor of large outdoor storage tanks. These tanks may have an area of thousands of square meters, and any leakage of their contents into the surrounding soil or groundwater can pose a significant environmental hazard. We propose to implement an extension to traditional MFL systems such that triaxis hall effect sensors are applied to acquire MFL signals along all three axes and use that data to predict defect dimensions.
Extensive finite element modeling will be required in the process of developing the algorithm. Based on initial predictions and experiments, use of all three axes of MFL signals will greatly enhance the user's ability to quantitatively characterize any corrosion on the floor plates (inside surface of the tank, or outside). As the system would utilize the MFL technique, it would be viable for the inspection of tank floors with a protective coating up to several mm thick.
The industrial partner, Groupe Mequaltech (Montreal QC) sees great potential of the new system for meeting the inspection requirements of many of its industrial customers, both in Canada and internationally. The scanner will also help to protect the environment, by giving advance warning if corrosion threatens a tank's integrity.
Program
Alliance Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
583428-2023
Name nom
Filleter, Tobin T
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
2024
Competition year année de concours
2023
Award amount
26000
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
519
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Other manufactured products and processes
Area of application fr
Autres produits et procédés de fabrication
Research subject code
2109
Research subject group en
Mechanical engineering
Research subject group fr
Génie mécanique
Research subject en
Mechanical systems and instrumentation
Research subject fr
Instrumentation et systèmes mécaniques
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
Machine learning algorithm for three dimensional magnetic flux leakage defect evaluation
Keywords
3d; defect detection; machine learning; magnetic flux leakage; magnetics; nde; ndt; pipelines; steel structures; storage tanks
Application summary
This proposal is centered on the development of a machine learning algorithm for the quantitative evaluation of defects using magnetic flux leakage (MFL) signals in all three dimensions. The primary application would be the nondestructive evaluation of the steel floor of large outdoor storage tanks. These tanks may have an area of thousands of square meters, and any leakage of their contents into the surrounding soil or groundwater can pose a significant environmental hazard. We propose to implement an extension to traditional MFL systems such that triaxis hall effect sensors are applied to acquire MFL signals along all three axes and use that data to predict defect dimensions.
Extensive finite element modeling will be required in the process of developing the algorithm. Based on initial predictions and experiments, use of all three axes of MFL signals will greatly enhance the user's ability to quantitatively characterize any corrosion on the floor plates (inside surface of the tank, or outside). As the system would utilize the MFL technique, it would be viable for the inspection of tank floors with a protective coating up to several mm thick.
The industrial partner, Groupe Mequaltech (Montreal QC) sees great potential of the new system for meeting the inspection requirements of many of its industrial customers, both in Canada and internationally. The scanner will also help to protect the environment, by giving advance warning if corrosion threatens a tank's integrity.