Multi-Task Learning of Scanning Electron Microscopy and Synthetic Thermal Tomography Images for Detection of Defects in Additively Manufactured Metals

Abstract

One of the key challenges in laser powder bed fusion (LPBF) additive manufacturing of metals is the appearance of microscopic pores in 3D-printed metallic structures. Quality control in LPBF can be accomplished with non-destructive imaging of the actual 3D-printed structures. Thermal tomography (TT) is a promising non-contact, non-destructive imaging method, which allows for the visualization of subsurface defects in arbitrary-sized metallic structures. However, because imaging is based on heat diffusion, TT images suffer from blurring, which increases with depth. We have been investigating the enhancement of TT imaging capability using machine learning. In this work, we introduce a novel multi-task learning (MTL) approach, which simultaneously performs the classification of synthetic TT images, and segmentation of experimental scanning electron microscopy (SEM) images. Synthetic TT images are obtained from computer simulations of metallic structures with subsurface elliptical-shaped defects, while experimental SEM images are obtained from imaging of LPBF-printed stainless-steel coupons. MTL network is implemented as a shared U-net encoder between the classification and the segmentation tasks. Results of this study show that the MTL network performs better in both the classification of synthetic TT images and the segmentation of SEM images tasks, as compared to the conventional approach when the individual tasks are performed independently of each other.

The Impact of Surface Roughness on Conformal Cooling Channels for Injection Molding

“…Depending on the shape, size, and orientation relative to structure surfaces, porosity defects could lead to material crack formation and cause structural failure [ 22 , 23 , 24 ]. Scanning electron microscopy (SEM) is a suitable method for determining how these defects could be detected [ 25 ].…”

Methodology for Thermal Analysis of Combustion Engines, Applied to Automobiles

“…The ICTs allow today present many solutions for the use of thermal imaging, which is thanks to the different equipment that allows the registration of thermal images, performing an analysis of the state of the art and the literature we present articles where the use of thermal imaging in the field of construction where the analysis of defects is used through the use of synthetic thermographic microscopy [1]. In the analysis of constructions, one of the mechanisms used for quality control, through the analysis of the edges and contours of the buildings, which use thermal images using the thermal polarization technique [2].…”

Methodology for the Analysis of the Operation of High-Performance Computing Equipment

“…Computer equipment, in its configurations, has many components, most of which generate heat, most of which have their own cooling mechanisms incorporated, such as processors, memories, solid disks, motherboards, The chips and especially the graphics processors, in the most advanced versions, present water-based cooling solutions, multiple ventilation systems, among other solutions, all with the intention of being able to cool the temperature of the entire system, mainly the case that contains all components of the computer equipment. Reviewing the literature we find applications of thermal images in multiple uses, such as evaluating these solutions where the texture of the concrete is analyzed in the analysis of constructions, for which tests known as non-destructive tests are used, where one of them They are thermal images, analyzing the edges of the constructions, in order to ensure the integration of the modules [1][2].…”