3D Printing

Leveraging Active Machine Learning to Optimize 3D Printing Autonomously

Posted on by
Prof. Anson Ma demonstrates the machine learning capabilities of the HuskyJet 3D printer at the SHAP3D lab in IPB.
Prof. Anson Ma demonstrates the machine learning capabilities of the HuskyJet 3D printer at the SHAP3D lab in IPB.

Inkjet printing has evolved from a graphics and marking technology to a broader variety of additive manufacturing and 3D printing processes for electronic, optical, pharmaceutical, and biological applications. The success of adopting inkjet technology for these newer applications is contingent on whether the ink materials can be consistently and reliably jetted by the print systems. Currently, each printer-and-ink combination requires calibration by trial and error, which consumes a considerable amount of time and materials. IPB researcher, Prof. Anson Ma, Site Director of SHAP3D, teamed up with UConn machine learning expert, Prof. Qian Yang, to demonstrate a new concept of “autonomous 3D printing”, leveraging an active machine learning method they developed to efficiently create a jettability diagram that predicts the best conditions for jetting an ink from a printhead.

Briefly, a camera is used to image the printhead and capture the behavior of ink jetted from a printhead. Starting with a few randomly chosen conditions, a machine learning algorithm predicts the optimal jetting conditions and then “cleverly decides” on the next set of experiments that can further improve prediction accuracy. After performing those experiments, the algorithm analyzes the newly acquired images, updates the prediction for the desired jetting conditions, and iteratively selects the next experiments, continuing autonomously until a small experimental budget is reached. This approach has achieved a prediction accuracy of more than 95% while considerably reducing the number of experiments required by 80% compared to a typical grid-search approach. This novel approach is especially powerful for optimizing complex print systems with many tunable process parameters.

This work was recently published in the journal 3D Printing and Additive Manufacturing (http://doi.org/10.1089/3dp.2023.0023) and led to a pending patent application (WO 2023/2788542).

Manufacturers Proactive in Response to COVID-19

Posted on by

The COVID-19 pandemic has affected manufacturers in every sector. In the face of disruptions to production and supply chains, disproportionate decreases in product demand and many other challenges, manufacturers are taking a close look at strategies that will help them be better prepared for future pandemics or other disasters. How will they protect their core businesses and keep their companies afloat?

Connecticut Manufacturing Resource Center (CMRC) at Tech Park is working with small- and medium-size manufacturers to develop long term solutions to this critical issue. 

Using funds from a recently awarded $300K EDA CARES Act grant, CMRC is proactively helping companies establish contingency plans for effectively maintaining operations from an off-site location during a crisis. Participating companies receive access to product lifecycle digital technologies that establish a kind of smart backup at Tech Park, a digital twin of a company’s operations that helps ensure minimal disruption.

Joe Luciani, Director of the Proof of Concept Center (POCC) at Tech Park, helps manage the grant. He believes that this vital support is coming at a crucial time, stressing that “The pandemic has severely impacted these companies and they are eager to put safeguards in place.” Hadi Bozorgmanesh, PI for the grant and Director of CMRC, adds with conviction, “Our manufacturing sector is a major source of economic strength for Connecticut and we need to help these organizations find long term solutions as they start to recover from the crisis.”

CMRC is already seeing success. Sunil Agrawal, Vice President of R&D Dynamics Corporation, a manufacturing company in Bloomfield, CT, recently completed the program. He contacted Hadi with gratitude and praise for UConn’s outstanding dedication and support throughout the project. He affirmed his organization’s commitment to implement the recommended changes, and his conviction that “The result will be a company that is not only more efficient and capable, but more resilient in a crisis like the one brought on by the events of the last twelve months.”

UConn is seeking additional partners who will receive funding support in a cost-share arrangement. Contact Hadi Bozorgmanesh, hadi.bozorgmanesh@uconn.edu.

The Enterprise Solution Center (ESC) at UConn Tech Park comprises four research centers: Quiet Corner Innovation Cluster (QCIC), Proof of Concept Center (POCC), Connecticut Manufacturing Simulation Center (CMSC), and Connecticut Manufacturing Resource Center (CMRC).

ESC takes an integrated approach to co-development of technology products and services to support the competitiveness of small and medium manufacturers.

3D Printing the Extracellular Matrix

Posted on by

Anna Tarakanova, Assistant Professor in Mechanical Engineering and Biomedical Engineering at UConn, studies ways that the structural features of complex networks like extracellular matrices (ECM) support their function. To explore this further, she decided to find a way to recreate her ECM micro-structure data into enlarged physical models that are visible to the naked eye.

photo of 3D print
ECM printed with the Stratasys Design F370

She approached Joe Luciani, Director of the Proof of Concept Center (POCC), an experienced innovator at Tech Park. His extensive collaborative experience with faculty, students and companies of all sizes paired with his expertise utilizing POCC’s state-of-the-art prototyping and fabrication equipment was well aligned with Anna’s research goals.

To kick off the project, Anna provided her structural data set as a shareable source. Joe converted the file using 3D modeling software, Rhinoceros3D, with a visual programming plugin, Grasshopper3D, that crunched the data to produce a network of nodes and linkages – i.e., a 3D model. Joe used this 3D model to successfully print larger-than-life ECM samples in POCC’s Stratasys 3D printers. He also recorded the printing process by programming one of the center’s robots to hold a camera and move through a few waypoints.

Anna provides some additional insight into her research. She explains, “Our research is focused on understanding the structure-function connectivity of complex heterogeneous systems like extracellular matrix (ECM) networks [the printed specimen] by establishing a microstructure-resolved deep learning framework that couples imaging data of matrix microstructure with multiscale computational modeling from the nanoscale, 3D printed prototyping, and in vitro mechanical testing of tissue specimens.”

The project is a new collaboration between Professor Tarakanova, Hongyi Xu, Assistant Professor in Mechanical Engineering at UConn, and David M. Pierce, Associate Professor in Mechanical Engineering and Biomedical Engineering at UConn. 

“This is an exciting new line of convergent research that utilizes heterogeneous 2D experimental microscopic imaging data to stochastically reconstruct realistic 3D matrix structures through a statistically-driven, generative deep learning approach for a representative model system: healthy and osteoarthritic articular cartilage, ” says Pierce.