Towards Smart Monitored AM: Open Source in-Situ Layer-wise 3D Printing Image Anomaly Detection Using Histograms of Oriented Gradients and a Physics-Based Rendering Engine

TL;DR

This paper introduces an open source, image-based anomaly detection method for 3D printing that compares real-time layer images with synthetic references generated via physics-based rendering, enabling early error detection without prior training.

Contribution

The study presents a novel, open source approach for 3D printing anomaly detection using histogram of oriented gradients and physics-based rendered reference images, eliminating the need for training data.

Findings

Effective detection of six different failure types

Certain similarity measures outperform others in reliability

Method enables early error detection and potential automatic correction

Abstract

This study presents an open source method for detecting 3D printing anomalies by comparing images of printed layers from a stationary monocular camera with G-code-based reference images of an ideal process generated with Blender, a physics rendering engine. Recognition of visual deviations was accomplished by analyzing the similarity of histograms of oriented gradients (HOG) of local image areas. The developed technique requires preliminary modeling of the working environment to achieve the best match for orientation, color rendering, lighting, and other parameters of the printed part. The output of the algorithm is a level of mismatch between printed and synthetic reference layers. Twelve similarity and distance measures were implemented and compared for their effectiveness at detecting 3D printing errors on six different representative failure types and their control error-free print images. The results show that although Kendall tau, Jaccard, and Sorensen similarities are the most sensitive, Pearson r, Spearman rho, cosine, and Dice similarities produce the more reliable results. This open source method allows the program to notice critical errors in the early stages of their occurrence and either pause manufacturing processes for further investigation by an operator or in the future AI-controlled automatic error correction. The implementation of this novel method does not require preliminary data for training, and the greatest efficiency can be achieved with the mass production of parts by either additive or subtractive manufacturing of the same geometric shape. It can be concluded this open source method is a promising means of enabling smart distributed recycling for additive manufacturing using complex feedstocks as well as other challenging manufacturing environments.