XCT Images of Additively Manufactured Cobalt Chrome with Processing Defects

National Institute of Standards and Technology provides a dataset of X-ray computed tomography (XCT) images for five additively manufactured cobalt chrome samples. Each sample contains approximately 1000 x 1000 x 1000 voxel three-dimensional images at a 2.5 µm resolution, with raw and segmented TIFF stacks. The samples were produced with varying laser powder bed fusion parameters to intentionally create defects.

Use Cases

• Train a 3D convolutional neural network on the segmented TIFF stacks to classify defect types created by varying scan speed and hatch spacing parameters.
• Analyze the relationship between processing parameters (scan speed, hatch spacing) and defect morphology visible in the raw 16-bit XCT reconstructed images.
• Develop an image segmentation model to distinguish material from voids using the paired raw and segmented image folders for each sample.
• Quantify defect volume and distribution within the 5 mm diameter cylindrical regions of interest extracted from the 40 mm diameter disks.

Strengths

• High-resolution 3D imaging with a consistent voxel size of approximately 2.5 µm.
• Contains paired data for each sample with original 16-bit raw images and corresponding segmented images.
• Includes five distinct samples produced with intentionally varied laser powder bed fusion processing parameters.

Limitations

• Limited sample size of only five distinct cobalt chrome disks.
• No post-processing (e.g., heat treatment) was applied, limiting analysis to as-built conditions only.
• Geographic and material scope is narrow, focusing on a specific alloy and manufacturing method.

Provenance

Source

National Institute of Standards and Technology

Collection Method

X-ray computed tomography (XCT) scanning of laser powder bed fusion manufactured cobalt chrome samples.

Freshness

Last updated in July 2025.