3Dprint.AI: Towards Open-Source, Large-Scale 3Dprinting Beyond Intelligence (ii/ii)

Contributor

Georgios is a postgraduate student at the Bartlett School of Architecture in March Architectural design programme (2018-2019) and scholar of Lilian Voudouri Foundation. He is a member of Research Cluster I of Bartlett, which explores automated design and fabrication systems, with a focus on robotic 3D printing technologies and their application on an architectural scale. Georgios also holds a diploma in Architectural Engineering from N.T.U of Athens where he graduated achieving a first honours award. In July 2018 he submitted his diploma project which was the first 3D-printing project at his university. Throughout his undergraduate studies, he received a number of significant awards and scholarships. He participates in international conferences and architectural workshops.

Part II/II: Implementation

This article is a part of the ongoing research of Georgios Drakontaeidis at the Bartlett School of Architecture, Research Cluster I (RCI), 2019.

Figure 1. The RC1 end effector (extruder) implements all the operations of the 3Dprint.AI framework in manual mode.

”A new digital revolution is coming, this time in fabrication.”

(N. Gershenfeld,2012)


Definitions

‘’Machine Learning (ML) is the practice of using algorithms to parse data, learn from it, and make a determination or prediction. The machine is “trained” using large amounts of data and algorithms .’’ (Copeland, 2016).

‘’ Additive manufacturing (AM) is the process of joining materials to make objects from 3D model data, usually layer upon layer, as opposed to subtractive manufacturing methodologies.‘’ (Wohlers Associates, 2010).

Robotic AM is an additive manufacturing process using industrial robots due to their high speed, accuracy and freedom of movement in multiple axes and large scales. In this aricle, the term large-scale AM is entirely referring to robotic AM.

04| Implementation:Manual mode

4.1 The extruder

An extruder developed for Research Cluster I, which studies robotic 3d printing applications on an architectural scale, implemented all of the operations of the framework in the manual mode (Figure 42). The device was handmade, and cost around £400. All its parts are metal, which enables the extruder to print at high speeds with great precision and zero vibrations. Its bracket and the nozzle are made of aluminum while the heartbreak and gears are stainless steel. Arduino connects the computer with the pins 2 and 3 of the robot to synchronize the extruder motor with the robot’s moves. The bracket is designed for ABB and Kuka robots. The extruder can be further due to its open plans to students from other clusters.
Even though the implementations of the 3Dprint.AI framework through the extruder is manual, the machine has the specifications for the automatic mode, and automating the extruder is the final goal. Critical analysis and evaluation of the extruder operations are presented below.

Figure 2. Parts and components of RC1 extruder.
Figure 3. Research and development of hardware.
Figure 4. Hardware parts.
Figure 5. Electronics and connections.


AI+3Dprinting+opensource=3Dprint.AI

4.2 Implementation Steps (manual mode)

Figure 6. The 3Dprint.AI framework. The manual mode was successfully implemented.

I) 4k live streaming with an action camera

An action camera mounted near the bracket enables the 4k live streaming function for better supervision of the printing process (Figure 2). In this way, users can record the entire printing process and document the printing errors in real-time. In the future, an algorithm can process the video and change the printing settings errors are detected. The video can also be displayed live for the community and for experienced users to give more advice to the contributors during the process of printing.

II) Adaptive feedback: Manual change of robot speed and temperature while printing

A PID controller, independent of the robot and the Arduino, adjusts the extrusion temperature (Figure 4). When a printing error occurs, the user can change the temperature in real-time and observe the outcomes. The robot speed can also be adjusted manually through the robot controller (Figure 7). First, the robot stops moving and the user types the robot speed manually. Pins 2 and 3 of the robot, which is connected with Arduino, stop the stepper motor of the extruder when the robot has stopped moving. Also, the user can easily change the speed of the extruder through the Arduino code, which is connected to a local PC. In this way, the two most important parameters of spatial printing – speeds of the robot and the extruder, and temperature – can be modified in the course of printing.

Figure 7. Adaptive feedback implementation of the 3Dprint.AI framework using the RC1 extruder.

III) Documentation in excel-google sheet file

The documentation of the printing settings is done manually in a google sheet file. The file contains all the parameters for both, layers by layer (Figure 9) and lattice printing (Figure 8). The user can also add photos of both printing outcomes and digital models to the document for better evaluation of the data by the community. Users can also identify manually possible problems and propose solutions using data analytics (Figure 11,12).

Figure 8. Documentation of lattice printing parameters. After many iterations, the printing outcome is optimized.
Figure 9. Documentation of layer-by-layer printing parameters.

IV) Data distribution to other teams

Finally, the excel datasheet will be given to other students of Bartlett who also are attempting robotic printing. Because the 3Dprint.AI community does not exist yet, the data are distributed through google sheets via link.. After many iterations of spatial extrusion, it was possible to visualise with diagrams the relationship between different parameters and the trends among them. This method is simple, quick and free and it ideal for creating the first reliable datasets (Figure 10 ). At next stages of development, when big amount of data gathered private block chain network would established for the community and machine-learning algorithms would process the data, as it discussed before.

Figure 10. Sharing of printing parameters file via excel- google sheet to other students of RC1. In this way, big data are created in order to feed the algorithm of the community.

4.3 Evaluation and further steps

The technical implementation of the 3Dprint.AI framework in manual mode is a stepping-stone towards its further automation. Indeed, the DIY extruder proved that high-quality hardware could be developed and shared inside the community at a low cost. Live streaming and adaptive feedback functions amplify the effectiveness and reliability of the machine as even manual users can achieve better supervision of the process and adjust the parameters in the course of printing. The documentation of printing settings and data analytics enhances the accuracy of predictions since they illustrate the relationships among specific parameters and with printing errors.

Join our weekly newsletter to receive:

  1. Latest articles & interviews
  2. AI events: updates, free passes and discount codes
  3. Opportunities to join AI Time Journal initiatives

As regards the data distribution within the community, the fact that both designs and instructions were shared among the students helped stimulate their creativity. Students acquired skills and knowledge about spatial extrusion and that they quickly replicated the extruder thrice and adjusted it to their needs (Figure 14). The quality of spatial extrusion improved day by day due to the sharing of knowledge and experience. Students not only shared their data sheet but also spent time with other teams and help them solve specific issues in hardware and software. Students took deep interest in spatial printing as they had other students to support them. B-made workshop managers have already expressed their interest to buy some of the extruders because of their high-quality components.

However, at the time of writing, 3Dprint.AI has not achieved the use of machine-learning algorithms for processing the data and making predictions. The manual implementation, even though it solved many of the framework’s technical problems, it was not enough for bringing AM on an architectural scale. Many of the framework’s technical steps such as blockchain network have to be developed and tested.

The community has to grow and raise its popularity outside the Bartlett to bring more data sets, more ideas and experience. In this way, it would be possible for the community to develop software for strategizing robot tool-paths and use optimised settings for minimum printing errors. The software should also document automatically the slicing settings and printing errors and distribute them to the community. Finally, the software can be sold to companies and users outside of the community and support can be provided as a service to earn an income.

Figure 11. Wait times and node approach speeds of the robot for every printing iteration. The dash-lines are the trendlines for every parameter.
Figure 12. By visualizing trendlines through data analytics, users can study the interrelations between different printing parameters.

05| Conclusions

5.1 Contributions

Through this thesis, an open-source machine-learning framework for large-scale additive manufacturing was introduced. It brings together the DIY culture of open source communities, the positive prospects of artificial intelligence, and the use of industrial robots in fabrication. The thesis proposes 3Dprint.AI as a conceptual and technical framework, which has the potential to raise AM to a large scale.

The propose 3Dprint.AI can be flexibly implemented in two modes, the manual and the automatic. It consists of the following steps i)video recording and object recognition while printing, ii) adaptive feedback process, iii) documentation of printing settings and results, and iv) distribution of those settings via google sheet files-manual mode-, or an online distributed network to enable the members to use the machine learning algorithms and make predictions-automatic mode-. The 3Dprint.AI community is organized with a flexible vertical hierarchy that permits the addition or removal of groups and subgroups according to the availability of users and project requirements. This hierarchy is divided into i) the contributors, ii) the maintainers, and iii) the project leaders. Various technical and ethical challenges have been taken into consideration as well the organization of the data, protection of its knowledge; and plans for the economic efficiency of the community have been presented.

Successfully implementation of 3Dprint.AI in manual mode was achieved through the development of an extruder. The quick replication of the extruder thrice by the students of Bartlett and the advancement of AM techniques in a short time exemplified the power of open innovation in an environment of a community. In this way, 3Dprint.AI introduced a pedagogical contribution through the exchange of experience and knowledge between users quickly and without cost. However, the automatic mode using machine learning algorithms and blockchain distribution network is yet to be implemented.


The novel 3Dprint.AI framework takes advantage of human creativity and algorithmic innovation for overcoming the existing limitations of AM applications and raise it to an architectural scale. It aspires to interact, inform and empower design not only as a tool for making things but also a method for studying, developing and fabricating forms and structures unknown to humanity before.



5.2 Concluding remarks

Overall, motivated by the existing limitations of robotic 3d printing, this thesis challenged the current state of the industry by proposing an open-source machine learning framework for large scale AM. After contextualizing the framework historically and socially in the period of the post-digital era when open innovation and computational power are continuously affecting the design and making, the thesis debated the main points from various technical, ethical and historical points of view. It studied, criticised and evaluated the trajectories in large scale AM, machine learning applications digital design-fabrication, and in 3d printing platforms.


After identifying the main drawbacks and issues of the above trajectories, it proposed 3Dprint.AI as a conceptual and technical framework, which operates flexibly in two modes, the manual and the automatic. Also, it described the steps of the framework, which are object recognition while printing, adaptive feedback to the robot, and documentation of the settings and distribution of data through google sheet files-manual mode- or a private blockchain network to enable the use of machine-learning algorithms in making predictions-automatic mode-. It also presented the organization of a community with the vertical hierarchy of contributors, maintainers and project leaders; organization of data for better division of work, protection of knowledge, and evaluation of users. The thesis illustrated not only the technical challenges of the framework but also the emerging ethical questions about authorship and ownership inside the community, access restrictions, trust in the private blockchain network, and participation of users in the community. These arguments were strengthened by presenting different approached and by criticizing two polls, one from Bartlett students and the other from Autodesk Uni-
versity Conference where the idea of this thesis was presented and discussed in detail. Opportunities for the economic efficiency of the community were also studied.


Further, 3Dprint.AI was implemented successfully in manual mode through the development of a high-quality extruder. The extruder was made for all other students of research cluster I (RC1) and was replicated thrice by other students of Bartlett who learned about spatial extrusion, and by exchanging data, they managed to quickly correct the extrusion errors and develop technical skills. This shows that the framework contributes not only technically but also pedagogically.

However, the automatic mode of the framework has not yet been implemented. The creation of the community inside and outside of the Bartlett as well as the development of software for large scale AM to be marketed to companies and users outside the community to earn an income for the community are some of the future plans. Even though many years of studies will be required for bringing AM to architectural scale efficiently, 3Dprint.AI research is well underway.

Figure 13. Robot while printing. Next to the robot (right) is the box with electronics.
Figure 14. Replication of the RC1 extruder 3 times from other students of the Bartlett (up). RC1 extruder while printing (down).
Figure 15. RC1 extruder while printing layer by layer. The 4k camera has been detached since the printing parameters for this geometry have been already optimized.


Even though many years of studies will be required for bringing AM to architectural scale efficiently, 3Dprint.AI research is well underway.


AI+3Dprinting+opensource=3Dprint.AI

Bibliography

  • Ai-build (2019). Ai Build – Technology. [online] Available at: https://ai-build.com/technology.html [Ac- cessed 2 May 2019].
  • Anderson, C. (2012). Makers: The new industrial revolution. 1st ed. New York: Crown Business,p.83,101,102.
  • Autodeskresearch.com. (2019). Project Dreamcatcher. [online] Available at: https://autodeskresearch.com/projects/Dreamcatcher [Accessed 19 May 2019].
  • Bitonti, F. (2016). When Matter Becomes Media. In: A.Picon and W. Fok, ed., Digital Property: Open-Source Architecture, AD Volume 86, Issue 5. Hoboken: John Wiley & Sons, Inc, pp.101-104.
  • Brasseur, V. (2018). Forge Your Future with Open Source. 1st ed. Raleigh, NC: Pragmatic Bookshelf, pp.23-43.Carpo, M. (2017). The Second Digital Turn: Design Beyond Intelligence. Cambridge&London: MIT Press,pp 6, 132.
  • Carpo, M. (2017). The Second Digital Turn: Design Beyond Intelligence. Cambridge&London: MIT Press,pp 6, 132.
  • Carpo, M. (2018). The Post-Digital Will Be Even More Digital, Says Mario Carpo. Available from: https://www.metropolismag.com/ideas/post-digital-will-be-more-digital/ [Accessed: 7th July 2018]
  • Copeland, M. (2016). The Difference Between AI, Machine Learning, and Deep Learning? | NVIDIA Blog. [online] The Official NVidia blog, Available at https://blogs.nvidia.com/blog/2016/07/29/whats-dif-ference-artificial-intelligence-machine-learn-
  • ing-deep-learning-ai/ [Accessed 2 May 2019].
  • Fablabhouse.com. (2019). FabLab House. [online]Available at: http://www.fablabhouse.com/en [Accessed 4 Jul. 2019].
  • Gershenfeld, N. (2012). ’How to Make Almost Anything: The Digital Fabrication Revolution’, ForeignAffairs, pp. 43-45,55-57.
  • Gershenfeld, N. A. (2015) Fab: The Coming Revolution on Your Desktop—from Personal Computers to Personal Fabrication. Basic Books, pp 3-17.
  • Hebron, P. (2016). Machine Learning for Designers. 1st ed. Sebastopol: O’Reilly Media, Inc.,p.7,21,47,48,51,55,59.
  • Hermann, M., Pentek, T. and Otto, B. (2016). Design Principles for Industrie 4.0 Scenarios. In: 49th International Conference on System Sciences (HICSS).Washington DC,: IEE computer society, pp.3928-3935.
  • Johnson, J. (2019). Rocket Plan: How 3-D Printing Is Unlocking A New Space Race. [online] Forbes.Available at: https://www.forbes.com/sites/jenniferjohnson/2018/05/16/rocket-plan-how-3-d-printing-is-unlocking-a-new-space-race/ [Accessed 15 Jun.2019].
  • Keating, S. (2014). ‘Beyond 3D Printing: The New Dimensions of Additive Fabrication.’ In Follett, Jonathan (Ed.), Designing for Emerging Technologies: UX for Genomics, Robotics, and the Internet of Things(379-405). O’Reilly Media, pp 380,383-388,393,401.
  • Kumar, A. (2015). How do Open Source Companies, Do programmers make money? [online] Microsoft: TheWindows Club. Available at: https://www.thewindowsclub.com/open-source-companies-programmers make-money [Accessed 8 Jun. 2019].
  • Lansard, M. (2019). The best 3D printing forums, Facebook groups and communities in 2019. [online] Aniwaa. Available at: https://www.aniwaa.com/best-3d-printing-3d-scanning-forums-facebook-groups-and-communities/ [Accessed 1 Jul. 2019].
  • Laurence, T. (2017). Blockchain For Dummies. 1st ed.Hoboken: John Wiley & Sons, Inc., pp.19,21.
  • Leonidou, L. (2019). Engineering the AiCell. [Blog] AiBuild TechBlog. Available at: https://medium.com/aibuild-techblog/engineering-the-aicell-e65a4deb-0f3c [Accessed 19 May 2019].
  • Matejka, J., Glueck, M., Bradner, E., Hashemi, A., Gross-man, T. and Fitzmaurice, G. (2018). Dream Lens: Exploration and Visualization of Large-Scale GenerativeDesign Datasets. In: 2018 CHI Conference.Toronto: Autodesk Research, p.3.
  • MX3D. (2019). MX3D Bridge. [Online] Available at: https://mx3d.com/projects/bridge-2/ [Accessed 15 Jun. 2019]
  • Pearson, B. (2016). Common Characteristics of an Open Source Community – Open Source Today. [online] Open Source Today organization. Available at:http://opensourcetoday.org/common-characteristics-open-source-community/ [Accessed 26 May2019].
  • Picon, A. & Fok, W. (eds.) (2016). Digital Property: Open-Source Architecture. AD Volume 86, Issue 5.
  • Hoboken: John Wiley & Sons, Inc, pp 7,8.
  • Picon, A. (2016). From Authorship To Ownership. In: A. Picon and W. Fok, ed., Digital Property: Open Source Architecture, AD Volume 86, Issue 5. Hoboken: John Wiley & Sons, Inc, pp.37, 38.
  • Rayna, T., Striukova, L. and Darlington, J. (2015). Co-creation and user innovation: The role of online 3D printing platforms. Journal of Engineering and Technology Management, 37(0923-4748), pp.90-102.
  • Relativity Space. (2019). Relativity Space | Stargate —Relativity Space. [online] Available at: https://www.relativityspace.com/stargate [Accessed 1 Jul. 2019].
  • Rosic, A. (2019). What is Blockchain Technology? A Step-by-Step Guide For Beginners. [online] Block-geeks. Available at: https://blockgeeks.com/guides/what-is-blockchain-technology/ [Accessed 26 May 2019].
  • Rui, D. (2016). Serving, Owning, Authoring. In: A. Picon and W. Fok, ed., Digital Property: Open-Source Architecture, AD Volume 86, Issue 5. Hoboken: John Wiley & Sons, Inc, pp.18-21.
  • Schneier, B. (2019). There’s No Good Reason to Trust Blockchain Technology. [online] WIRED. Available at: https://www.wired.com/story/theres-no-good-reason-to-trust-blockchain-technology/ [Accessed 8,Jun. 2019].
  • Srnicek, N. (2017). Platform capitalism. 1st ed. Cambridge, UK: Polity Press, p.46,47.
  • Tamke, M., Nicholas, P. and Zwierzycki, M. (2018) ‘Machine learning for architectural design: Practices and infrastructure’, International Journal of Architectural Computing, 16(2), pp. 123–143.doi: 10.1177/1478077118778580.
  • The Bartlett School of Architecture. (2019). Architectural Design MArch. [online] Available at: https:// www.ucl.ac.uk/bartlett/architecture/programmes/postgraduate/march-architectural-design [Accessed 8 Jul. 2019].
  • Wohlers Associates (2019). What is Additive Manufacturing? | Wohlers Associates. [online] Available at: https://wohlersassociates.com/additive-manufacturing.html [Accessed 2 May 2019].
  • Zelinski, P. (2018). Where AM Meets AI. Additive manufacturing, Volume 7, Issue 1, p.25.
  • Chaillou, S. (2019). The Advent of Architectural AI, A Historical Perspective. Boston: Harvard Graduate School of Design, pp.2-15.
  • Negroponte, N. (1972). The architecture machine.Cambridge Mass.: The MIT Press, pp.1-20.

Image credits

  • Figure 1. Author.
  • Figure 2. Author.
  • Figure 3. Author
  • Figure 4. Author.
  • Figure 5. Author.
  • Figure 6. Author.
  • Figure 7. Author.
  • Figure 8. Author.
  • Figure 9. Author.
  • Figure 10. Author.
  • Figure 11. Author.
  • Figure 12. Author.
  • Figure 13. Author.
  • Figure 14. Author.
  • Figure 15. Author.

Contributor

Georgios is a postgraduate student at the Bartlett School of Architecture in March Architectural design programme (2018-2019) and scholar of Lilian Voudouri Foundation. He is a member of Research Cluster I of Bartlett, which explores automated design and fabrication systems, with a focus on robotic 3D printing technologies and their application on an architectural scale. Georgios also holds a diploma in Architectural Engineering from N.T.U of Athens where he graduated achieving a first honours award. In July 2018 he submitted his diploma project which was the first 3D-printing project at his university. Throughout his undergraduate studies, he received a number of significant awards and scholarships. He participates in international conferences and architectural workshops.

Opinions expressed by contributors are their own.

About Georgios Drakontaeidis

Georgios is a postgraduate student at the Bartlett School of Architecture in March Architectural design programme (2018-2019) and scholar of Lilian Voudouri Foundation. He is a member of Research Cluster I of Bartlett, which explores automated design and fabrication systems, with a focus on robotic 3D printing technologies and their application on an architectural scale. Georgios also holds a diploma in Architectural Engineering from N.T.U of Athens where he graduated achieving a first honours award. In July 2018 he submitted his diploma project which was the first 3D-printing project at his university. Throughout his undergraduate studies, he received a number of significant awards and scholarships. He participates in international conferences and architectural workshops.

View all posts by Georgios Drakontaeidis →