Autonomous in-situ correction of fused deposition modeling printers using computer vision and deep learning

Abstract Fused deposition modeling, a widely used additive manufacturing process, currently faces challenges in printed part quality such as under-extrusion and over-extrusion. In this paper, a real-time monitoring and autonomous correction system is developed, where a deep learning model and a feedback loop is used to modify 3D-printing parameters iteratively and adaptively. Results show that our system is capable of detecting in-plane printing conditions and in-situ correct defects faster than the speed of a human’s response. The fundamental elements in the framework proposed can be extended to various 3D-printing technologies to reliably fabricate high-performance materials in challenging environments without human interaction.

[1]  Seok-Hee Lee,et al.  Representation of surface roughness in fused deposition modeling , 2009 .

[2]  Grace X. Gu,et al.  Effect of Constituent Materials on Composite Performance: Exploring Design Strategies via Machine Learning , 2019, Advanced Theory and Simulations.

[3]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[4]  Yoshua Bengio,et al.  Object Recognition with Gradient-Based Learning , 1999, Shape, Contour and Grouping in Computer Vision.

[5]  Markus J. Buehler,et al.  Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment , 2018 .

[6]  Lauren L. Beghini,et al.  Additive manufacturing: Toward holistic design , 2017 .

[7]  Jun Ni,et al.  A review of 4D printing , 2017 .

[8]  P. Bártolo,et al.  Additive manufacturing of tissues and organs , 2012 .

[9]  A. Roy Choudhury,et al.  Extruder path generation for Curved Layer Fused Deposition Modeling , 2008, Comput. Aided Des..

[10]  Charlie C. L. Wang,et al.  The status, challenges, and future of additive manufacturing in engineering , 2015, Comput. Aided Des..

[11]  E. Wetzel,et al.  Fracture behavior of additively manufactured acrylonitrile butadiene styrene (ABS) materials , 2017 .

[12]  Grace X. Gu,et al.  Using convolutional neural networks to predict composite properties beyond the elastic limit , 2019, MRS Communications.

[13]  Xiang Chen,et al.  A framework for tool path optimization in fused filament fabrication , 2017, SCF.

[14]  Qian Sun,et al.  Modeling of Bond Formation Between Polymer Filaments in the Fused Deposition Modeling Process , 2004 .

[15]  Xiaodong Li,et al.  In situ real time defect detection of 3D printed parts , 2017 .

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Ian Gibson,et al.  Additive manufacturing technologies : 3D printing, rapid prototyping, and direct digital manufacturing , 2015 .

[18]  Xingming Xiao,et al.  Process parameter optimization for fused deposition modeling using response surface methodology combined with fuzzy inference system , 2014 .

[19]  Shing I. Chang,et al.  Automated Process Monitoring in 3D Printing Using Supervised Machine Learning , 2018 .

[20]  Grace X. Gu,et al.  Hierarchically Enhanced Impact Resistance of Bioinspired Composites , 2017, Advanced materials.

[21]  Zhizhou Zhang,et al.  Developments in 4D-printing: a review on current smart materials, technologies, and applications , 2019, International Journal of Smart and Nano Materials.

[22]  Omar Ahmed Mohamed,et al.  Optimization of fused deposition modeling process parameters for dimensional accuracy using I-optimality criterion , 2016 .

[23]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Grace X. Gu,et al.  Algorithm-driven design of fracture resistant composite materials realized through additive manufacturing , 2017 .