A deep learning solution for real-time quality assessment and control in additive manufacturing using point cloud data
Authors: 
Javid Akhavan, Jiaqi Lyu, and Souran ManoochehriAuthors Info & Claims
Javid Akhavan, Jiaqi Lyu, and Souran ManoochehriAuthors Info & ClaimsPages 1389 - 1406
Abstract
This work presents an in-situ quality assessment and improvement technique using point cloud and AI for data processing and smart decision making in Additive Manufacturing (AM) fabrication to improve the quality and accuracy of fabricated artifacts. The top surface point-cloud containing top surface geometry and quality information is pre-processed and passed to an improved deep Hybrid Convolutional Auto-Encoder decoder (HCAE) model used to statistically describe the artifact's quality. The HCAE’s output is comprised of 9 × 9 segments, each including four channels with the segment's probability to contain one of four labels, Under-printed, Normally-printed, Over-printed, or Empty region. This data structure plays a significant role in command generation for fabrication process optimization. The HCAE’s accuracy and repeatability were measured by a multi-label multi-output metric developed in this study. The HCAE’s results are used to perform a real-time process adjustment by manipulating the future layer's fabrication through the G-code modification. By adjusting the machine's print speed and feed-rate, the controller exploits the subsequent layer’s deposition, grid-by-grid. The algorithm is then tested with two defective process plans: severe under-extrusion and over-extrusion conditions. Both test artifacts' quality advanced significantly and converged to an acceptable state by four iterations.
References
[1]
Akhavan, J., & Manoochehri, S. (2022). Sensory Data fusion using machine learning methods for in-situ defect registration in additive manufacturing: A review. In 2022 IEEE International IOT, Electronics and Mechatronics Conference, IEMTRONICS 2022.
[2]
Alammar, A., Kois, J. C., Revilla-León, M., & Att, W. (2022). Additive manufacturing technologies: Current status and future perspectives. In Journal of Prosthodontics (Vol. 31, pp. 4–12). John Wiley and Sons Inc.
[3]
Askari, I., Badnava, B., Woodruff, T., Zeng, S., & Fang, H. (2022). Sampling-based nonlinear MPC of neural network dynamics with application to autonomous vehicle motion planning. In Proceedings of the American Control Conference, 2022-June, 2084–2090.
[4]
Azimirad V, Ramezanlou MT, Sotubadi SV, and Janabi-Sharifi F A consecutive hybrid spiking-convolutional (CHSC) neural controller for sequential decision making in robots Neurocomputing 2022 490 319-336
[5]
Bakhshi, A., Sedghi, R., & Hojati, M. (2021). A preliminary study on the mix design of 3D-printable engineered cementitious composite. In Tran-SET 2021-Proceedings of the Tran-SET Conference 2021.
[6]
Baumann F and Roller D Vision based error detection for 3D printing processes MATEC Web of Conferences 2016
[7]
Borish M, Post BK, Roschli A, Chesser PC, and Love LJ Real-time defect correction in large-scale polymer additive manufacturing via thermal imaging and laser profilometer Procedia Manufacturing 2020
[8]
Delli U and Chang S Automated process monitoring in 3D printing using supervised machine learning Procedia Manufacturing 2018 26 865-870
[9]
Devesse W, de Baere D, Hinderdael M, and Guillaume P Hardware-in-the-loop control of additive manufacturing processes using temperature feedback Journal of Laser Applications 2016 28 2 1022302
[10]
Dosovitskiy A, Springenberg JT, Riedmiller M, and Brox T Discriminative unsupervised feature learning with convolutional neural networks Advances in Neural Information Processing Systems 2014
[11]
Durão LFCS, Barkoczy R, Zancul E, Lee Ho L, and Bonnard R Optimizing additive manufacturing parameters for the fused deposition modeling technology using a design of experiments Progress in Additive Manufacturing 2019 4 3 291-313
[12]
Farbiz F, Habibullah MS, Hamadicharef B, Maszczyk T, and Aggarwal S Knowledge-embedded machine learning and its applications in smart manufacturing Journal of Intelligent Manufacturing 2022
[13]
Fastowicz J, Grudziński M, Tecław M, and Okarma K Objective 3D printed surface quality assessment based on entropy of depth maps Entropy 2019 21 1 1-13
[14]
Gockel J, Sheridan L, Koerper B, and Whip B The influence of additive manufacturing processing parameters on surface roughness and fatigue life International Journal of Fatigue 2019
[15]
Harbig J, Wenzler DL, Baehr S, Kick MK, Merschroth H, Wimmer A, Weigold M, and Zaeh MF Methodology to determine melt pool anomalies in powder bed fusion of metals using a laser beam by means of process monitoring and sensor data fusion Materials 2022
[16]
Heydarian, M., Doyle, T. E., & Samavi, R. (2022). MLCM: Multi-label confusion matrix. IEEE Access, 10, 19083–19095.
[17]
Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In 32nd International Conference on Machine Learning, ICML 2015, 1.
[18]
Jin Z, Zhang Z, and Gu GX Automated real-time detection and prediction of interlayer imperfections in additive manufacturing processes using artificial intelligence Advanced Intelligent Systems 2020 2 1 1900130
[19]
Kumar S, Gopi T, Harikeerthana N, Gupta MK, Gaur V, Krolczyk GM, and Wu C Machine learning techniques in additive manufacturing: A state of the art review on design, processes and production control Journal of Intelligent Manufacturing 2022
[20]
Kwon O, Kim HG, Ham MJ, Kim W, Kim GH, Cho JH, Kim N, and il, & Kim, K. A deep neural network for classification of melt-pool images in metal additive manufacturing Journal of Intelligent Manufacturing 2020 31 2 375-386
[21]
Larsen S and Hooper PA Deep semi-supervised learning of dynamics for anomaly detection in laser powder bed fusion Journal of Intelligent Manufacturing 2022 33 2 457-471
[22]
Li J, Zhou Q, Huang X, Li M, and Cao L In situ quality inspection with layer-wise visual images based on deep transfer learning during selective laser melting Journal of Intelligent Manufacturing 2021
[23]
Li X, Jia X, Yang Q, and Lee J Quality analysis in metal additive manufacturing with deep learning Journal of Intelligent Manufacturing 2020 31 8 2003-2017
[24]
Li Z, Zhang Z, Shi J, and Wu D Prediction of surface roughness in extrusion-based additive manufacturing with machine learning Robotics and Computer-Integrated Manufacturing 2019 57 January 488-495
[25]
Luo C, Wang X, Migler KB, and Seppala JE Effects of feed rates on temperature profiles and feed forces in material extrusion additive manufacturing Additive Manufacturing 2020
[26]
Lyu, J., Boroujeni, J. A. T., & Manoochehri, S. (2021). In-situ laser-based process monitoring and in-plane surface anomaly identification for additive manufacturing using point cloud and machine learning. In International Design Engineering Technical Conferences and Computers and Information in Engineering Conference.
[27]
Lyu J, Akhavan J, and Manoochehri S Image-based dataset of artifact surfaces fabricated by additive manufacturing with applications in machine learning Data in Brief 2022
[28]
Lyu J and Manoochehri S Online convolutional neural network-based anomaly detection and quality control for fused filament fabrication process Virtual and Physical Prototyping 2021 16 2 160-177
[29]
Mahmoud, Y., & Manoochehri, S. (2021). In-situ temperature monitoring of ABS during Fused Filament Fabrication (FFF) process with varying process parameters. In Proceedings of the ASME Design Engineering Technical Conference, 3A-2021.
[30]
Mondal S, Gwynn D, Ray A, and Basak A Investigation of melt pool geometry control in additive manufacturing using hybrid modeling Metals 2020 10 5 1-23
[31]
Moretti M, Rossi A, and Senin N In-process monitoring of part geometry in fused filament fabrication using computer vision and digital twins Additive Manufacturing 2021 37 101609
[32]
Obilanade D, Dordlofva C, and Törlind P Surface roughness considerations in design for additive manufacturing: A literature review Proceedings of the Design Society 2021
[33]
Pandiyan V, Drissi-Daoudi R, Shevchik S, Masinelli G, Le-Quang T, Logé R, and Wasmer K Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process Journal of Materials Processing Technology 2022
[34]
Papon EA, Haque A, and Sharif MAR Numerical study for the improvement of bead spreading architecture with modified nozzle geometries in additive manufacturing of polymers Rapid Prototyping Journal 2021
[35]
Petsiuk AL and Pearce JM Open source computer vision-based layer-wise 3D printing analysis Additive Manufacturing 2020 36 7 101473
[36]
Preissler M, Broghammer J, Rosenberger M, and Notni G Inline process monitoring method for geometrical characteristics in additive manufacturing Journal of Physics 2018
[37]
Ravi AK, Deshpande A, and Hsu KH An in-process laser localized pre-deposition heating approach to inter-layer bond strengthening in extrusion based polymer additive manufacturing Journal of Manufacturing Processes 2016
[38]
Rusu RB and Cousins S 3d is here: Point cloud library (pcl) IEEE International Conference on Robotics and Automation 2011 2011 1-4
[39]
Suzuki T, Fukushige S, and Tsunori M Load path visualization and fiber trajectory optimization for additive manufacturing of composites Additive Manufacturing 2020
[40]
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07-12-June-2015.
[41]
Tercan, H., & Meisen, T. (2022). Machine learning and deep learning based predictive quality in manufacturing: a systematic review. In Journal of Intelligent Manufacturing (Vol. 33, Issue 7, pp. 1879–1905). Springer.
[42]
Tian Q, Guo S, Melder E, Bian L, and Guo W Deep learning-based data fusion method for in situ porosity detection in laser-based additive manufacturing Journal of Manufacturing Science and Engineering, Transactions of the ASME, Doi 2021 10 1115/1 4048957
[43]
Xu K, Lyu J, and Manoochehri S In situ process monitoring using acoustic emission and laser scanning techniques based on machine learning models Journal of Manufacturing Processes 2022 84 357-374
[44]
Zhao C, Du S, Lv J, Deng Y, and Li G A novel parallel classification network for classifying three-dimensional surface with point cloud data Journal of Intelligent Manufacturing 2021
Recommendations
Real-time control for large scale additive manufacturing using thermal images
2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)Large scale additive manufacturing has process mechanisms similar to Fused Filament Fabrication (FFF) and can print parts with large sizes, such as car bodies. This capability provides large scale additive manufacturing great application potentials in a ...
Quality control for deep x-ray lithography (LIGA): a preliminary metrology study
The x-ray lithography process is time-consuming and costly. The use of process design rules is essential along with CAD designs that should fulfil the specifications of dimension and roughness. Parameters such as the material of mask membrane, the ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 11 April 2023
Accepted: 20 March 2023
Received: 24 June 2022
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in