Automated Real‐Time Detection and Prediction of Interlayer Imperfections in Additive Manufacturing Processes Using Artificial Intelligence

Abstract

Although fused deposition modeling (FDM) additive manufacturing technologies have advanced in the past decade, interlayer imperfections such as delamination and warping are still dominant when printing complex parts. Herein, a selfmonitoring system based on real-time camera images and deep learning algorithms is developed to classify the various extents of delamination in a printed part. In addition, a novel method incorporating strain measurements is established to measure and predict the onset of warping. Results show that the machine-learning model is capable of detecting different levels of delamination conditions, and the strain measurements setup successfully reflects and determines the extent and tendency of warping before it actually occurs in the print job. This multifunctional system can be applied to assess other manufacturing processes to realize autocalibration and prediagnosis of imperfections without human interaction.

Investigation of Compressive Behavior of Pre-folded Thin-walled Column Fabricated by 3D Printing

“…This is the reason why the non-folded specimen shows a very random fracture shape. As the compressive load is applied, the stress concentration is generated at a random position where some imperfections by the 3D printing process may be present (Jin et al, 2020). Imperfection is considered as the weakest part of the structure.…”

Machine Learning for Advanced Additive Manufacturing

“…(F) Four conditions of the nozzle height (high+, high, good, and low) that may cause delamination. Adapted with permission from Jin et al 81 Copyright 2020, Wiley-VCH. (G) Six categories of anomalies in L-PBF: (a) recoater hopping, (b) recoater streaking, (c) debris, (d) super-elevation, (e) part failure, and (f) incomplete spreading.…”

“…By establishing imaging systems to monitor the fabrication process, computer vision and ML algorithms can be applied for recognizing and classifying various defects in real time during the FFF process. 17,81 In the following study, a universal serial bus (USB) camera was attached to the print nozzle providing a fixed filming view of the printing area around the nozzle ( Figure 4D). In-plane printing conditions, including over-and under-extrusion ( Figure 4E), were analyzed by training CNN models based on real-time images.…”

Application of Unsupervised Anomaly Detection Techniques to Moisture Content Data from Wood Constructions

“…Currently, as part of the well-known Internet of Things phenomenon, we see an increase in the use-and associated market segment [10]-of systems that provide realtime information about manufacturing processes [11], the status of different types of infrastructure [12], or the consumption of resources such as power or water [13]. In some cases, the capabilities of such systems go beyond simple monitoring, for instance raising alarms when some abnormal measurements are detected, or even locating the possible root causes of failures.…”