Guy Lamouche
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Guy Lamouche has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Mutahar Safdar
McGill University
8 shared publications - Yaoyao Fiona Zhao
Department of Mechanical Engineering, McGill University, Montreal, QC H3A 0C3, Canada
8 shared publications - Gentry Wood
Apollo Machine and Welding Ltd
7 shared publications - Padma Polash Paul
Braintoy AI
6 shared publications - Sébastien Vergnole
Industrial Materials Institute, National Research Council Canada, Boucherville, Québec, Canada
5 shared publications - Maxime Rivard
National Research Council Canada, Boucherville, Quebec, Canada
4 shared publications
Latest Publications
- 1 April 2024
- Published by Wiley in Journal of Computing and Information Science in Engineering
- Vol. 24 (5) , 1-42
Transferability Analysis of Data-Driven Additive Manufacturing Knowledge: A Case Study Between Powder Bed Fusion and Directed Energy Deposition
Data-driven research in additive manufacturing (AM) has gained significant success in recent years. This has led to a plethora of scientific literature emerging. The knowledge in these works consists of AM and artificial intelligence (AI) contexts that haven't been mined and formalized in an integrated way. Moreover, no tools or guidelines exist to support data-driven knowledge transfer from one context to another. As a result, data-driven solutions using specific AI techniques are being developed and validated only for specific AM process technologies. There is a potential to exploit the inherent similarities across various AM technologies and adapt the existing solutions from one process or problem to another using AI, such as transfer learning (TL). We propose a three-step knowledge transferability analysis framework in AM to support data-driven AM knowledge transfer. As a prerequisite to transferability analysis, AM knowledge is featured into identified knowledge components. The framework consists of pre-transfer, transfer, and post-transfer steps to accomplish knowledge transfer. A case study is conducted between two flagship metal AM processes: laser powder bed fusion (LPBF) and directed energy deposition (DED). The relatively mature LPBF is the source while the less developed DED is the target. We show successful transfer at different levels of the data-driven solution, including data representation, model architecture, and model parameters. The pipeline of AM knowledge transfer can be automated in the future to allow efficient cross-context or cross-process knowledge exchange.
- 1 April 2024
- Published by Wiley in Journal of Computing and Information Science in Engineering
- Vol. 24 (5) , 1-42
Transferability Analysis of Data-Driven Additive Manufacturing Knowledge: A Case Study Between Powder Bed Fusion and Directed Energy Deposition
Data-driven research in additive manufacturing (AM) has gained significant success in recent years. This has led to a plethora of scientific literature emerging. The knowledge in these works consists of AM and artificial intelligence (AI) contexts that haven't been mined and formalized in an integrated way. Moreover, no tools or guidelines exist to support data-driven knowledge transfer from one context to another. As a result, data-driven solutions using specific AI techniques are being developed and validated only for specific AM process technologies. There is a potential to exploit the inherent similarities across various AM technologies and adapt the existing solutions from one process or problem to another using AI, such as transfer learning (TL). We propose a three-step knowledge transferability analysis framework in AM to support data-driven AM knowledge transfer. As a prerequisite to transferability analysis, AM knowledge is featured into identified knowledge components. The framework consists of pre-transfer, transfer, and post-transfer steps to accomplish knowledge transfer. A case study is conducted between two flagship metal AM processes: laser powder bed fusion (LPBF) and directed energy deposition (DED). The relatively mature LPBF is the source while the less developed DED is the target. We show successful transfer at different levels of the data-driven solution, including data representation, model architecture, and model parameters. The pipeline of AM knowledge transfer can be automated in the future to allow efficient cross-context or cross-process knowledge exchange.
- Open Access
Evaluation of Key Spatiotemporal Learners for Print Track Anomaly Classification Using Melt Pool Image Streams
Recent applications of machine learning in metal additive manufacturing (MAM) have demonstrated significant potential in addressing critical barriers to the widespread adoption of MAM technology. Recent research in this field emphasizes the importance of utilizing melt pool signatures for real-time defect prediction. While high-quality melt pool image data holds the promise of enabling precise predictions, there has been limited exploration into the utilization of cutting-edge spatiotemporal models that can harness the inherent transient and sequential characteristics of the additive manufacturing process. This research introduces and puts into practice some of the leading deep spatiotemporal learning models that can be adapted for the classification of melt pool image streams originating from various materials, systems, and applications. Specifically, it investigates two-stream networks comprising spatial and temporal streams, a recurrent spatial network, and a factorized 3D convolutional neural network. The capacity of these models to generalize when exposed to perturbations in melt pool image data is examined using data perturbation techniques grounded in real-world process scenarios. The implemented architectures demonstrate the ability to capture the spatiotemporal features of melt pool image sequences. However, among these models, only the Kinetics400 pre-trained SlowFast network, categorized as a two-stream network, exhibits robust generalization capabilities in the presence of data perturbations.
Open AccessEvaluation of Key Spatiotemporal Learners for Print Track Anomaly Classification Using Melt Pool Image Streams
Recent applications of machine learning in metal additive manufacturing (MAM) have demonstrated significant potential in addressing critical barriers to the widespread adoption of MAM technology. Recent research in this field emphasizes the importance of utilizing melt pool signatures for real-time defect prediction. While high-quality melt pool image data holds the promise of enabling precise predictions, there has been limited exploration into the utilization of cutting-edge spatiotemporal models that can harness the inherent transient and sequential characteristics of the additive manufacturing process. This research introduces and puts into practice some of the leading deep spatiotemporal learning models that can be adapted for the classification of melt pool image streams originating from various materials, systems, and applications. Specifically, it investigates two-stream networks comprising spatial and temporal streams, a recurrent spatial network, and a factorized 3D convolutional neural network. The capacity of these models to generalize when exposed to perturbations in melt pool image data is examined using data perturbation techniques grounded in real-world process scenarios. The implemented architectures demonstrate the ability to capture the spatiotemporal features of melt pool image sequences. However, among these models, only the Kinetics400 pre-trained SlowFast network, categorized as a two-stream network, exhibits robust generalization capabilities in the presence of data perturbations.
- 2 June 2023
- Published by Springer Nature
- p. 123-133
Analyzing Additive Manufacturing Feature Spaces
- 2 June 2023
- Published by Springer Nature
- p. 139-141
Summary
- Open Access
- 2 June 2023
- Published by Springer Nature
- p. 45-121
Applications in Data-Driven Additive Manufacturing
- 2 June 2023
- Published by Springer Nature
- p. 45-121
Open AccessApplications in Data-Driven Additive Manufacturing
- 2 June 2023
- Published by Springer Nature
- p. 1-15
Introduction
- 2 June 2023
- Published by Springer Nature
- p. 135-138
Challenges and Opportunities in Additive Manufacturing Data Preparation
- 2 June 2023
- Published by Springer Nature
- p. 135-138
Challenges and Opportunities in Additive Manufacturing Data Preparation
- Open Access
- 25 November 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 27 (11) , 116006-23
Calibration procedure for enhanced mirror artifact removal in full-range optical coherence tomography using passive quadrature demultiplexing
SignificancePassive quadrature demultiplexing allows full-range optical coherence tomography (FR-OCT). However, imperfections in the wavelength- and frequency-response of the demodulation circuits can cause residual mirror artifacts, which hinder high-quality imaging on both sides of zero delay.AimWe aim at achieving high mirror artifact extinction by calibrated postprocessing of the FR-OCT signal.ApproachWe propose a mathematical framework for the origin of the residual mirror peaks as well as a protocol allowing the precise measurement and correction of the associated errors directly from mirror measurements.ResultsWe demonstrate high extinction of the mirror artifact over the entire imaging range, as well as an assessment of the method’s robustness to time and experimental conditions. We also provide a detailed description of the practical implementation of the method to ensure optimal reproducibility.ConclusionThe proposed method is simple to implement and produces high mirror artifact extinction. This may encourage the adoption of FR-OCT in clinical and industrial systems or loosen the performance requirements on the optical demodulation circuit, as the imperfections can be handled in postprocessing.
- 25 November 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 27 (11) , 116006-23
Open AccessCalibration procedure for enhanced mirror artifact removal in full-range optical coherence tomography using passive quadrature demultiplexing
SignificancePassive quadrature demultiplexing allows full-range optical coherence tomography (FR-OCT). However, imperfections in the wavelength- and frequency-response of the demodulation circuits can cause residual mirror artifacts, which hinder high-quality imaging on both sides of zero delay.AimWe aim at achieving high mirror artifact extinction by calibrated postprocessing of the FR-OCT signal.ApproachWe propose a mathematical framework for the origin of the residual mirror peaks as well as a protocol allowing the precise measurement and correction of the associated errors directly from mirror measurements.ResultsWe demonstrate high extinction of the mirror artifact over the entire imaging range, as well as an assessment of the method’s robustness to time and experimental conditions. We also provide a detailed description of the practical implementation of the method to ensure optimal reproducibility.ConclusionThe proposed method is simple to implement and produces high mirror artifact extinction. This may encourage the adoption of FR-OCT in clinical and industrial systems or loosen the performance requirements on the optical demodulation circuit, as the imperfections can be handled in postprocessing.
- 15 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-19
Frequency Shift Method: A Technique for 3-D Shape Acquisition in the Presence of Strong Interreflections
This paper presents a structured-light codification technique called Frequency Shift Method which is especially designed for scenes containing strong interreflections. The method works by projecting multiple sine wave patterns having different frequencies. While the phase shift method associates a phase to each column of the projector, in the proposed codification, each column of the projector is uniquely encoded by the frequencies used, and explicitly decoded using the Discrete Fourier Transform. This encoding allows the method to recover all the projector columns that contribute to a camera pixel’s observed intensity. An energy minimization is then used to separate direct and indirect illuminations. Objects presenting diffuse and specular interreflections are considered and our experimental results illustrate the efficiency of our method compared to previously proposed methods.
- 15 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-19
Frequency Shift Method: A Technique for 3-D Shape Acquisition in the Presence of Strong Interreflections
This paper presents a structured-light codification technique called Frequency Shift Method which is especially designed for scenes containing strong interreflections. The method works by projecting multiple sine wave patterns having different frequencies. While the phase shift method associates a phase to each column of the projector, in the proposed codification, each column of the projector is uniquely encoded by the frequencies used, and explicitly decoded using the Discrete Fourier Transform. This encoding allows the method to recover all the projector columns that contribute to a camera pixel’s observed intensity. An energy minimization is then used to separate direct and indirect illuminations. Objects presenting diffuse and specular interreflections are considered and our experimental results illustrate the efficiency of our method compared to previously proposed methods.