Machine learning supports the rapid development of high-resolution 3D printing technology

Biomedical engineers at Queensland University of Technology (QUT) have developed a new automated process to dramatically improve melt electrowriting, a new high-resolution 3D printing technology used in tissue science and regenerative medicine.

MEW has established itself over the last decade as a versatile technique in fields such as bioengineering, biomaterial science and soft robotics. However, progress has been hampered by slow printing speeds, inconsistent results and heavy reliance on manual operations.

“MEW is a multifaceted 3D printing technology that also has applications in bioengineering, biomaterials science, and soft robotics,” Dr Mieszczanek said. “However, it has faced many challenges from its early stages more than 10 years ago to its current stage, hampered by long experimentation times, low printing speeds, poor consistency in results, and dependence on the user for printer operation. To address these problems, we used machine learning (ML) to create a closed-loop process control system for MEW. The novel MEW system design is effective because it monitors the fibre-flight pass, allowing us to use real-time imaging for continuous analysis.”

The technology is based on a neural feedforward network combined with optimization techniques and feedback loops. This enables continuous monitoring and adjustment of the printing process.

Dietmar W. Hutmacher, Director of the Max Planck-Queensland Center for Materials Science of Extracellular Matrices, emphasized:

“We use a feedforward neural network, optimization techniques, and feedback loop to ensure that printed parts are consistently reproducible. This work shows that machine learning can automate MEW operations and support the engineering of effective closed-loop control in complex 3D printing technology.”

The research results were published in the journal Communications Engineering and show how AI-driven processes can handle the complexity of modern 3D printing processes. The team, consisting of scientists from QUT and the University of Oregon, hopes that these advances will lay the foundation for an industrial application of MEW. With the automation of data processing and process control, MEW could play a key role in medical manufacturing and beyond in the future.