First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing

TL;DR

This paper explores neural networks to predict and correct fabrication deviations in 2-Photon Polymerization additive manufacturing, aiming to improve accuracy and reliability in creating complex 3D micro-structures.

Contribution

It introduces neural network models trained on experimental and theoretical data to predict and pre-correct deviations in direct laser writing, offering an alternative to iterative correction methods.

Findings

Neural networks accurately predict fabrication deviations.

Pre-correction with neural networks improves structure fidelity.

Approach applicable to other 3D printing technologies.

Abstract

Additive manufacturing using 2-Photon Polymerization (2PP, aka direct laser writing DLW) enables the fabrication of almost arbitrary complex 3D structures from the meso to the submicron scale. However, deviations between the anticipated target structure and the actual print often occur due to physico-chemical processes, limiting the accuracy and reliability of this technology. To minimize these deviations, we hereby present our latest research in developing different neural networks, targeting the above-mentioned aspect. Our networks are trained on several experimental as well as theoretical datasets and show good results in predicting fabrication deviations and (pre-) correcting 2.5D micro-structures. Hence, we demonstrate, that besides conventional iterative correction methods, neural networks are a promising alternative to significantly improving the output quality in DLW. Furthermore, there are no fundamental limitations to transferring this machine learning approach to other 3D printing technologies, as they all face the same challenge in terms of fidelity. To our point of view, the use of neural networks has the potential to enhance the capabilities of this technology, enabling the creation of complex structures with increased accuracy and precision in the near future.