A multi-scale convolutional neural network for autonomous anomaly detection and classification in a laser powder bed fusion additive manufacturing process

By Luke Scime, Jack L. Beuth. Additive Manufacturing, 2018

332 citations recorded by the source corpus.

Abstract In-situ detection of processing defects is a critical challenge for Laser Powder Bed Fusion Additive Manufacturing. Many of these defects are related to interactions between the recoater blade, which spreads the powder, and the powder bed. This work leverages Deep Learning, specifically a Convolutional Neural Network (CNN), for autonomous detection and classification of many of these spreading anomalies. Importantly, the input layer of the CNN is modified to enable the algorithm to learn both the appearance of the powder bed anomalies as well as key contextual information at multiple size scales. These modifications to the CNN architecture are shown to improve the flexibility and overall classification accuracy of the algorithm while mitigating many human biases. A case study is used to demonstrate the utility of the presented methodology and the overall performance is shown to be superior to that of methodologies previously reported by the authors.

Subfields: Industrial and Manufacturing Engineering, Materials Chemistry, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/fc9b96b0148f36392a5e9bd13fdf6eb1f3e3022e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Industrial and Manufacturing Engineering

1. W. Y. Yeong
2. Swee Leong Sing
3. T. Mukherjee
4. H. Wei
5. J. Elmer
6. J. Milewski
7. T. DebRoy
8. Guo Dong Goh

In Materials Chemistry

1. T. Mukherjee
2. T. DebRoy
3. H. Wei
4. Swee Leong Sing
5. W. Y. Yeong
6. J. Elmer
7. Guo Dong Goh
8. Gerald L. Knapp

In Mechanical Engineering

1. T. Mukherjee
2. T. DebRoy
3. H. Wei
4. W. Y. Yeong
5. J. Elmer
6. Swee Leong Sing
7. J. Milewski
8. Guo Dong Goh

Citations in the corpus

• Metallurgy, mechanistic models and machine learning in metal printing (2020, methodology): “In another example, the anomalies in powder spreading by a recoater (a blade that spreads powder during PBF-L) were detected by a computer vision sys-tem 174 .”
• A review on machine learning in 3D printing: applications, potential, and challenges (2020, methodology): “(Scime and Beuth 2018a, b).”