Ryan Scott
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ryan Scott has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Robin Gras
School of Computer Science, University of Windsor, Windsor, ON N9B 3P4, Canada
4 shared publications - Roman Gr. Maev
Institute for Diagnostic Imaging Research, University of Windsor , Windsor, Ontario N9A 5R5, Canada
3 shared publications Vlad Tusinean
2 shared publicationsA. Ouellette
1 shared publication- Adib Salandari-Rabori
Centre for Advanced Materials Joining, Department of Mechanical & Mechatronics Engineering, University of Waterloo
1 shared publication Andriy Chertov
1 shared publication
Latest Publications
- 1 January 2023
- Published by The American Society for Nondestructive Testing, Inc.
Real-Time In-Process Ultrasonic M-Scan Segmentation of Resistance Spot Welds Using Deep Learning
New developments in manufacturing have increased the need for automated analysis of resistance spot welds (RSWs). Many approaches exist to evaluate RSWs in a nondestructive manner, but there is currently a need for an adaptive system that can dynamically modify weld process parameters to prevent defects from occurring. Such a system must perform nondestructive evaluation (NDE) of the RSW process during weld formation, and feed information to a weld controller so that it can alter the welding parameters. To that end, we have developed an artificial intelligence (AI) system using deep learning (DL) that is capable of in-process NDE of RSW using ultrasonic imaging. By embedding an ultrasonic transducer directly into a welding electrode, we can obtain ultrasonic A-scans of the welding process every millisecond, which are then horizontally stacked to form M-scans. Using this ultrasonic setup, we developed and labeled a diverse dataset of ultrasonic M-scans for semantic segmentation. The model trained with this data can then be used to process ultrasonic A-scans to characterize important information about the weld nugget throughout the welding process, such as its position within the stack and its relative penetration into each metal sheet. Our work shows the feasibility of the application of DL for an adaptive welding system via ultrasonic process monitoring and is an important step towards the Industry/NDE 4.0 dream of zero-defect welding.
- 1 January 2023
- Published by The American Society for Nondestructive Testing, Inc.
Real-Time In-Process Ultrasonic M-Scan Segmentation of Resistance Spot Welds Using Deep Learning
New developments in manufacturing have increased the need for automated analysis of resistance spot welds (RSWs). Many approaches exist to evaluate RSWs in a nondestructive manner, but there is currently a need for an adaptive system that can dynamically modify weld process parameters to prevent defects from occurring. Such a system must perform nondestructive evaluation (NDE) of the RSW process during weld formation, and feed information to a weld controller so that it can alter the welding parameters. To that end, we have developed an artificial intelligence (AI) system using deep learning (DL) that is capable of in-process NDE of RSW using ultrasonic imaging. By embedding an ultrasonic transducer directly into a welding electrode, we can obtain ultrasonic A-scans of the welding process every millisecond, which are then horizontally stacked to form M-scans. Using this ultrasonic setup, we developed and labeled a diverse dataset of ultrasonic M-scans for semantic segmentation. The model trained with this data can then be used to process ultrasonic A-scans to characterize important information about the weld nugget throughout the welding process, such as its position within the stack and its relative penetration into each metal sheet. Our work shows the feasibility of the application of DL for an adaptive welding system via ultrasonic process monitoring and is an important step towards the Industry/NDE 4.0 dream of zero-defect welding.
- 1 January 2023
- Published by The American Society for Nondestructive Testing, Inc.
Post-Process Semantic Segmentation of Ultrasonic M-scans from Resistance Spot Weld Process Monitoring
Combinations into modern vehicles. These new challenges necessitate new solutions. Resistance spot welding (RSW), a key joining process in several industries including automotive manufacturing, has become increasingly challenging in its own right, especially due to the use of novel advanced materials. Consequently, there is an increased need for nondestructive evaluation (NDE) systems that are high-resolution, fast, accurate, and fully automated – and the same needs apply to the interpretation of their outputs. Such systems also align with smart factory and Industry 4.0 ideals. In this work, we developed a semantic segmentation approach using deep learning (DL) for the automated characterization of ultrasonic M-scan data from RSW process monitoring. The approach segments nugget and stack regions in the data, and the segmentation mask outputs can be used downstream for further weld process characterization e.g. computation of nugget penetration into each sheet, nugget growth rate, nugget solidification rate, etc. Our approach yielded overall intersection-over-union (IoU) of 0.978 which shows a very strong ability to localize the nugget and stack regions in the M-scans, and an F1 score of 0.995 which indicates that it rarely misjudges nugget or stack region presence. Our work demonstrates that semantic segmentation using DL can be an extremely powerful approach for RSW ultrasonic NDE data interpretation. The approach can be used to similar effect on NDE data from other modalities and from other use cases. Our work provides the capability for immediate, accurate, and comprehensive post-process inspection for RSW which can be used for quality control as well as post-process feedback, and it represents another major advancement toward Industry/NDE 4.0.
- 1 January 2023
- Published by The American Society for Nondestructive Testing, Inc.
Post-Process Semantic Segmentation of Ultrasonic M-scans from Resistance Spot Weld Process Monitoring
Combinations into modern vehicles. These new challenges necessitate new solutions. Resistance spot welding (RSW), a key joining process in several industries including automotive manufacturing, has become increasingly challenging in its own right, especially due to the use of novel advanced materials. Consequently, there is an increased need for nondestructive evaluation (NDE) systems that are high-resolution, fast, accurate, and fully automated – and the same needs apply to the interpretation of their outputs. Such systems also align with smart factory and Industry 4.0 ideals. In this work, we developed a semantic segmentation approach using deep learning (DL) for the automated characterization of ultrasonic M-scan data from RSW process monitoring. The approach segments nugget and stack regions in the data, and the segmentation mask outputs can be used downstream for further weld process characterization e.g. computation of nugget penetration into each sheet, nugget growth rate, nugget solidification rate, etc. Our approach yielded overall intersection-over-union (IoU) of 0.978 which shows a very strong ability to localize the nugget and stack regions in the M-scans, and an F1 score of 0.995 which indicates that it rarely misjudges nugget or stack region presence. Our work demonstrates that semantic segmentation using DL can be an extremely powerful approach for RSW ultrasonic NDE data interpretation. The approach can be used to similar effect on NDE data from other modalities and from other use cases. Our work provides the capability for immediate, accurate, and comprehensive post-process inspection for RSW which can be used for quality control as well as post-process feedback, and it represents another major advancement toward Industry/NDE 4.0.
- 1 October 2022
- Published by British Institute of Non-Destructive Testing (BINDT) in Insight - Non-Destructive Testing and Condition Monitoring
- Vol. 64 (10) , 560-565
Application of a chord transducer for ultrasonic detection and characterisation of defects in MDPE butt fusion joints
Butt fusion (BF) is the standard method for joining polyethylene (PE) pipes during gas and water pipeline construction. The joints require simple, inexpensive and effective non-destructive testing techniques. Ultrasonic inspection is the most suitable approach; however, joint geometry requires specific configuration of the acoustic beam. In this article, a custom-designed ultrasonic chord transducer optimised for a specific pipe diameter is described. It is demonstrated how variations of sound speed and attenuation in pipe material with temperature variations affects the operation of this type of transducer. A variety of common defects, including cold fusion, dust, dirt, grass contamination, voids, etc, are simulated inside the joint and used for technique development. Analysis of an A-scan produced in pitch-catch mode allows for the evaluation of joint quality and the classification of defect type.
- 1 October 2022
- Published by British Institute of Non-Destructive Testing (BINDT) in Insight - Non-Destructive Testing and Condition Monitoring
- Vol. 64 (10) , 560-565
Application of a chord transducer for ultrasonic detection and characterisation of defects in MDPE butt fusion joints
Butt fusion (BF) is the standard method for joining polyethylene (PE) pipes during gas and water pipeline construction. The joints require simple, inexpensive and effective non-destructive testing techniques. Ultrasonic inspection is the most suitable approach; however, joint geometry requires specific configuration of the acoustic beam. In this article, a custom-designed ultrasonic chord transducer optimised for a specific pipe diameter is described. It is demonstrated how variations of sound speed and attenuation in pipe material with temperature variations affects the operation of this type of transducer. A variety of common defects, including cold fusion, dust, dirt, grass contamination, voids, etc, are simulated inside the joint and used for technique development. Analysis of an A-scan produced in pitch-catch mode allows for the evaluation of joint quality and the classification of defect type.
- 1 September 2020
- Published by Elsevier in Ecological Modelling
- Vol. 431
A simulation study shows impacts of genetic diversity on establishment success of digital invaders in heterogeneous environments
- 1 September 2020
- Published by Elsevier in Ecological Modelling
- Vol. 431
A simulation study shows impacts of genetic diversity on establishment success of digital invaders in heterogeneous environments
- Open Access
- 22 April 2020
- Published by Wiley in Diversity and Distributions
- Vol. 26 (7) , 867-880
Density dependence mediates the ecological impact of an invasive fish
Aim: The way in which habitat heterogeneity and predator density affect predator–prey dynamics, space use and prey risk are understudied aspects of foraging ecology, particularly for invasive species. Likewise, how an invasive species’ impact scales with its abundance is poorly understood. We used a model invasive species—lionfish (Pterois volitans)—to understand emergent multiple predator effects and influences of habitat heterogeneity on consumption rate and prey mortality risk.Location: Florida, USA.Methods: We considered effects of both predator and prey abundance on density‐dependent impact. We used functional response methodology to quantify the per‐capita effect ofP. volitans, assessing concomitant influences of prey refuge (3 levels) and predator density (3 levels) on predator–prey space use and predation efficiency across increasing prey densities (7 levels). We then assessed intraspecific interaction outcomes by comparing observed per‐capita effects with predicted estimates based on consumption rates of individual predators. This allowed us to detect the presence of emergent multiple predator effects (MPEs) and tease apart density‐dependent impacts.Results: Lionfish predatory impact was mediated by predator and prey density but unaffected by refugia. Despite incongruent patch preferences between predators and their prey, predator impacts were context‐independent. We also detected nonlinear scaling of impact with increasing predator abundance. Pairs of lionfish had the greatest per‐capita effect, whose cumulative impact on prey matched that expected of independently foraging predators. At the highest predator density (four fish), antagonistic multiple predator effects precipitated prey risk reduction, in which we observed the lowest per‐capita effect. Across predator abundances, prey mortality rates were inversely density‐dependent.Main conclusions: Quantifying non‐independent consumptive effects of multiple conspecific predators across levels of prey abundance can inform better prediction and understanding of invasive species' density‐dependent effects. Additionally, consideration of heterogeneity‐mediated FRs and predator–prey spatial distributions may facilitate more precise and realistic predictions of invader impact across their invaded range.
- 22 April 2020
- Published by Wiley in Diversity and Distributions
- Vol. 26 (7) , 867-880
Open AccessDensity dependence mediates the ecological impact of an invasive fish
Aim: The way in which habitat heterogeneity and predator density affect predator–prey dynamics, space use and prey risk are understudied aspects of foraging ecology, particularly for invasive species. Likewise, how an invasive species’ impact scales with its abundance is poorly understood. We used a model invasive species—lionfish (Pterois volitans)—to understand emergent multiple predator effects and influences of habitat heterogeneity on consumption rate and prey mortality risk.Location: Florida, USA.Methods: We considered effects of both predator and prey abundance on density‐dependent impact. We used functional response methodology to quantify the per‐capita effect ofP. volitans, assessing concomitant influences of prey refuge (3 levels) and predator density (3 levels) on predator–prey space use and predation efficiency across increasing prey densities (7 levels). We then assessed intraspecific interaction outcomes by comparing observed per‐capita effects with predicted estimates based on consumption rates of individual predators. This allowed us to detect the presence of emergent multiple predator effects (MPEs) and tease apart density‐dependent impacts.Results: Lionfish predatory impact was mediated by predator and prey density but unaffected by refugia. Despite incongruent patch preferences between predators and their prey, predator impacts were context‐independent. We also detected nonlinear scaling of impact with increasing predator abundance. Pairs of lionfish had the greatest per‐capita effect, whose cumulative impact on prey matched that expected of independently foraging predators. At the highest predator density (four fish), antagonistic multiple predator effects precipitated prey risk reduction, in which we observed the lowest per‐capita effect. Across predator abundances, prey mortality rates were inversely density‐dependent.Main conclusions: Quantifying non‐independent consumptive effects of multiple conspecific predators across levels of prey abundance can inform better prediction and understanding of invasive species' density‐dependent effects. Additionally, consideration of heterogeneity‐mediated FRs and predator–prey spatial distributions may facilitate more precise and realistic predictions of invader impact across their invaded range.
- 30 July 2014
- Published by MIT Press
- p. 719-725
Testing the Effects of Speciation and Mutation Rates on Distance-Based Phylogenetic Tree Construction Accuracy Using EcoSim
- 30 July 2014
- Published by MIT Press
- p. 719-725
Testing the Effects of Speciation and Mutation Rates on Distance-Based Phylogenetic Tree Construction Accuracy Using EcoSim
- 2 July 2012
- Published by MIT Press
- p. 105-110
Comparing Distance-Based Phylogenetic Tree Construction Methods Using An Individual-Based Ecosystem Simulation, EcoSim
- 2 July 2012
- Published by MIT Press
- p. 105-110
Comparing Distance-Based Phylogenetic Tree Construction Methods Using An Individual-Based Ecosystem Simulation, EcoSim