Curved CFRP Specimens: Thermographic Inspection and Simulation using a Thermal Model and AI tool using CNN and PPT
Tracks
NDT Methods
| Thursday, October 24, 2024 |
| 8:00 AM - 8:30 AM |
| 209/210 - Technical Session |
Details
Specific Objectives:
1. Modelling Defects on Curved Aeronautical Surfaces: Discuss the process of modelling defects on curved aeronautical surfaces, highlighting how the models help understand defect signals. Present modelling results to illustrate the nature and implications of defects in aeronautical materials.
2. Development of a CNN Model for Semantic Segmentation: Explain the creation of a Convolutional Neural Network model based on the Unet architecture for semantic segmentation. Detail the model's application in accurately segmenting and localizing defects, and present the segmentation results and the evaluation metrics used to validate the model's effectiveness.
3. Classification of Defect Areas by Depth: Outline the methods for segmenting defects into depth categories. Describe how the classification enhances the diagnostic process by differentiating defect severity, and share the classification results to demonstrate the practical benefits of the approach in assessing aeronautical defects.
In the presentation these objectives will be detailed and demonstrated through various examples.
1. Modelling Defects on Curved Aeronautical Surfaces: Discuss the process of modelling defects on curved aeronautical surfaces, highlighting how the models help understand defect signals. Present modelling results to illustrate the nature and implications of defects in aeronautical materials.
2. Development of a CNN Model for Semantic Segmentation: Explain the creation of a Convolutional Neural Network model based on the Unet architecture for semantic segmentation. Detail the model's application in accurately segmenting and localizing defects, and present the segmentation results and the evaluation metrics used to validate the model's effectiveness.
3. Classification of Defect Areas by Depth: Outline the methods for segmenting defects into depth categories. Describe how the classification enhances the diagnostic process by differentiating defect severity, and share the classification results to demonstrate the practical benefits of the approach in assessing aeronautical defects.
In the presentation these objectives will be detailed and demonstrated through various examples.
Speaker
Dr Xavier Maldague
Professor
Universite Laval
Curved CFRP Specimens: Thermographic Inspection and Simulation using a Thermal Model and AI tool using CNN and PPT
Presentation Description
Specific Objectives:
1. Modelling Defects on Curved Aeronautical Surfaces: Discuss the process of modelling defects on curved aeronautical surfaces, highlighting how the models help understand defect signals. Present modelling results to illustrate the nature and implications of defects in aeronautical materials.
2. Development of a CNN Model for Semantic Segmentation: Explain the creation of a Convolutional Neural Network model based on the Unet architecture for semantic segmentation. Detail the model's application in accurately segmenting and localizing defects, and present the segmentation results and the evaluation metrics used to validate the model's effectiveness.
3. Classification of Defect Areas by Depth: Outline the methods for segmenting defects into depth categories. Describe how the classification enhances the diagnostic process by differentiating defect severity, and share the classification results to demonstrate the practical benefits of the approach in assessing aeronautical defects.
In the presentation these objectives will be detailed and demonstrated through various examples.
1. Modelling Defects on Curved Aeronautical Surfaces: Discuss the process of modelling defects on curved aeronautical surfaces, highlighting how the models help understand defect signals. Present modelling results to illustrate the nature and implications of defects in aeronautical materials.
2. Development of a CNN Model for Semantic Segmentation: Explain the creation of a Convolutional Neural Network model based on the Unet architecture for semantic segmentation. Detail the model's application in accurately segmenting and localizing defects, and present the segmentation results and the evaluation metrics used to validate the model's effectiveness.
3. Classification of Defect Areas by Depth: Outline the methods for segmenting defects into depth categories. Describe how the classification enhances the diagnostic process by differentiating defect severity, and share the classification results to demonstrate the practical benefits of the approach in assessing aeronautical defects.
In the presentation these objectives will be detailed and demonstrated through various examples.
Biography
Xavier Maldague, P. Eng., Ph.D. is professor at the Department of Electrical and Computing Engineering, Université Laval, Québec City, Canada. He has trained over 50 graduate students (M.Sc. and Ph.D.) and contributed to over 400 publications. His research interests are in infrared thermography, NonDestructive Evaluation (NDE) techniques and vision / digital systems for industrial inspection. He is an honorary fellow of the Indian Society of Nondestructive Testing, fellow of the Canadian Engineering Institute, Canadian Institute for NonDestructive Evaluation, American Society of NonDestructive Testing.
