Towards Online Monitoring and Data-driven Control: A Study of Segmentation Algorithms for Laser Powder Bed Fusion Processes

TL;DR

This paper evaluates over 30 segmentation algorithms for infrared images in laser powder bed fusion, aiming to enhance online monitoring and data-driven control by improving image processing and reducing memory needs.

Contribution

It provides a comprehensive comparison of segmentation algorithms, identifying promising solutions to improve infrared image processing in laser powder bed fusion.

Findings

Certain algorithms achieve high segmentation accuracy

Some algorithms are computationally efficient for real-time use

Selected methods improve spatter detection capabilities

Abstract

An increasing number of laser powder bed fusion machines use off-axis infrared cameras to improve online monitoring and data-driven control capabilities. However, there is still a severe lack of algorithmic solutions to properly process the infrared images from these cameras that has led to several key limitations: a lack of online monitoring capabilities for the laser tracks, insufficient pre-processing of the infrared images for data-driven methods, and large memory requirements for storing the infrared images. To address these limitations, we study over 30 segmentation algorithms that segment each infrared image into a foreground and background. By evaluating each algorithm based on its segmentation accuracy, computational speed, and spatter detection characteristics, we identify promising algorithmic solutions. The identified algorithms can be readily applied to the laser powder bed fusion machines to address each of the above limitations and thus, significantly improve process control.