Grant: Engage Grants Program
Ryerson University
$24,971.00
A robot vision system for inspection and coverage measurement of blasted surfaces
FY 2012-13
Summary
Material finishing techniques, such as abrasive blasting, is applicable to many manufacturing industries such as
aerospace and automotive industries. The quality of the work is usually measured by the blasting coverage
measurements, which is traditionally done by human experts. However, these measurements are usually costly,
time consuming, qualitative, and subject to misjudgements. Vibra Finish Ltd. is a company with three decades
of experience in providing material finishing and in particular abrasive blasting services to Canadian and
International manufacturing companies. Vibra Finish Ltd. is in immediate need to replace conventional surface
inspection and, in particular, blasting coverage measurement methods with automated techniques to enhance its
productivity and products quality.
This work proposes a novel blasting coverage measurement technique based on image processing and robot
manipulation. The approach involves finding an optimal path to ensure imaging the whole surface by a set of
images acquired sequentially through two cameras mounted at the end-point of a robot. The planned path is
optimized to minimize potential artifacts related to the illumination condition, obstructions, and surface
properties. A neuro-fuzzy system is also proposed to determine the coverage of the part, making it robust to
changes in illumination and surface conditions. The technology is particularly important for surface finishing
companies (such as Vibra Finish Ltd.) which need to automate and quantify the quality of their finished
surfaces. Having the developed technology in hand, the company will reliably and quickly measure the
coverage of each part, eliminating the need for human expertise and related training costs. The company may
also choose to commercialize the technology in the future.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
436620-2012
Name nom
JanabiSharifi, Farrokh
Department département
Mechanical and Industrial Engineering
Organization id
43
Institution établissement
Ryerson University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
24971
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
2600
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Robotics
Research subject fr
Robotique
Partie
1
Nb partie
1
Application title
A robot vision system for inspection and coverage measurement of blasted surfaces
Keyword
NSERC
Application summary
Material finishing techniques, such as abrasive blasting, is applicable to many manufacturing industries such as
aerospace and automotive industries. The quality of the work is usually measured by the blasting coverage
measurements, which is traditionally done by human experts. However, these measurements are usually costly,
time consuming, qualitative, and subject to misjudgements. Vibra Finish Ltd. is a company with three decades
of experience in providing material finishing and in particular abrasive blasting services to Canadian and
International manufacturing companies. Vibra Finish Ltd. is in immediate need to replace conventional surface
inspection and, in particular, blasting coverage measurement methods with automated techniques to enhance its
productivity and products quality.
This work proposes a novel blasting coverage measurement technique based on image processing and robot
manipulation. The approach involves finding an optimal path to ensure imaging the whole surface by a set of
images acquired sequentially through two cameras mounted at the end-point of a robot. The planned path is
optimized to minimize potential artifacts related to the illumination condition, obstructions, and surface
properties. A neuro-fuzzy system is also proposed to determine the coverage of the part, making it robust to
changes in illumination and surface conditions. The technology is particularly important for surface finishing
companies (such as Vibra Finish Ltd.) which need to automate and quantify the quality of their finished
surfaces. Having the developed technology in hand, the company will reliably and quickly measure the
coverage of each part, eliminating the need for human expertise and related training costs. The company may
also choose to commercialize the technology in the future.