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

arXiv:2511.23306 · physics.optics · Submitted 2025-11-28 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Physics. The day in general physics: instruments, methods and results across the field.

Kai: We're looking at the paper: "First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing".

Mira: Here's the gist of the paper. 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 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 µ-structures Hence, we demonstrate, that besides conventional iterative correction methods, neural networks are a promising alternative to significantly improving the output quality in DLW.

Kai: Problem Context The major challenge in this field is the – mostly undesired – deviation between the envisaged target structure and its corresponding, experimentally 3D printed counterpart While these deviations are negligible for large structures (e.g.

Mira: those in the cm-range), they become more significant as the size of the prints decreases.

Kai: Unfortunately, this is fundamentally unavoidable with today’s photo resins.

Title and authors: Kai: So we're looking at this paper called "First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing". The title itself points directly to their main goal, which is using machine learning for both predicting what will happen and correcting it before you even start printing.

Mira: And the authors are Sven Enns, Julian Hering-Stratemeier, and Georg von Freymann. They come from the Physics Department and Research Center OPTIMAS at RPTU University Kaiserslautern-Landau.

Lev: I've seen their work on error correction methods before, so I'm interested in how they are framing this as a prediction and pre-correction problem rather than just a post-printing fix.

Kai: It seems they are moving beyond just simple adjustments and aiming for something that can generate a pre-compensated version of the design that matches the original geometry as closely as possible.

Mira: That's what they are targeting, trying to get the print to reproduce the original geometry with maximum accuracy, not just fixing errors after the fact.

The paper's summary: Kai: So they summarize their work by saying that while deviations between target structures and printed ones happen in direct laser writing because of physical processes, neural networks show good results when trained on experimental and theoretical datasets.

Mira: They are focusing on predicting the target print deviation first, which is one approach called predicting the optimal exposure parameters for two photon polymerization based on scanning electron images.

Lev: So they're trying to use machine learning to figure out what settings you need before you print so the resulting structure is closer to your original design.

Kai: They also introduced a second approach called Direct Correction, where the network directly predicts a corrected design, which they are testing with three different network architectures based on their specific tasks.

Mira: And they use a customized loss function for evaluation that includes the Pearson correlation coefficient and the absolute value of the difference between the mean height value of prediction and label.

The paper's improvements: Lev: They suggest a few things for improvement, like using iterative correction methods, which show convergent behavior towards higher correlation as you iterate through steps.

Kai: But they admit that iterative correction doesn't always preserve the symmetry of the structure, and it needs more effort than the direct correction approach because the real error doesn't always converge with more iteration numbers.

Mira: The authors also mention that their improved AI system can perform structure correction by calculating a deviation matrix to correct tilt within measurement data, which involves calculating a regression plane.

Lev: They also incorporated fabrication parameters like slicing distance, hatching distance, and laser power into the learning and prediction process so the network can account for those influences on printing results.

Kai: And they use a customized loss function that prioritizes small surface features by including a term involving the Pearson correlation coefficient, which is implemented in such a way that even small surface features are given greater importance during training.

Conclusion: Mira: So to wrap up, the paper shows promising attempts using neural networks for direct structure prediction and pre-compensation in direct laser writing.

Kai: They show that while iterative correction works well for finding good designs, the direct correction approach is a strong alternative because it directly predicts a corrected design.

Lev: From my side, I think the main challenge they tackle is moving from simple structures to more complex ones and ensuring those corrections are robust enough for real hardware.

Kai: They also flag that while they show good results, the transferability of their methods to completely arbitrary DLW geometries isn't fully proven yet.

Mira: So, overall, it's a first step towards using machine learning to make two-photon polymerization more accurate and reliable for complex three dee structures <ref:2511.23306#pg1>.

Lev: It sets up a clear path for future work on improving the neural networks further and extending their applicability to different structure types.

Physics Department and Research Center OPTIMAS, RPTU University · Opti-Cal GmbH · Fraunhofer Institute for Industrial Mathematics ITWM

physics.optics

Submitted: 2025-11-28

Updated: 2026-11-12

DOI: 10.37188/lam.2026.128

License: http://creativecommons.org/licenses/by/4.0/

Importance score: 77/100

The gist: 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 Our…

Key concepts

Direct Correction (DC)
This approach uses the neural network to directly predict a corrected design from an initial target structure. The goal is for the network to output a design that, when printed, will be as close as possible to the desired final structure without needing multiple manual correction steps.
Iterative Correction (IC)
This method involves repeatedly using the neural network to suggest improvements. Each suggested correction is then printed in a single job under consistent conditions. This allows for quick iteration and comparison of results, although it may not always preserve the original structure's symmetry.
Customized Loss Function
The loss function used during training is tailored to prioritize specific features. It combines the Pearson correlation coefficient (CC) with the absolute difference in mean height values. This setup ensures that small surface features are given greater importance during the learning process, leading to better final print quality.
Network Architectures
The researchers tested three different neural network architectures, each optimized for a specific task—either predicting deviation or performing direct correction. The choice of architecture depends on whether the network is trying to forecast errors or generate a fully corrected design.

Terminology

Summary

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 Our networks are trained on several experimental as well as theoretical datasets and show good results in predicting fabrication deviations and (pre-) correcting 2. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

5D µ-structures Hence, we demonstrate, that besides conventional iterative correction methods, neural networks are a promising alternative to significantly improving the output quality in DLW. p. 0
Where the paper says it

5D µ-structures. Hence, we demonstrate, that besides conventional iterative correction methods, neural networks are a promising alternative to significantly improving the output quality in DLW.

Problem Context

The major challenge in this field is the – mostly undesired – deviation between the envisaged target structure and its corresponding, experimentally 3D printed counterpart While these deviations are negligible for large structures (e.g. those in the cm-range), they become more significant as the size of the prints decreases. p. 1

Where the paper says it

While these deviations are negligible for large structures (e. those in the cm-range), they become more significant as the size of the prints decreases.

Unfortunately, this is fundamentally unavoidable with today’s photo resins. p. 1
Where the paper says it

those in the cm-range), they become more significant as the size of the prints decreases. Unfortunately, this is fundamentally unavoidable with today’s photo resins.

The complexity and computational intensity of the processes to be modeled still exceed the capacities of today’s computers. p. 1
Where the paper says it

A few more approaches focused really successfully on the estimation of printed line dimensions and structure characterization [8, 9], but, unfortunately still not taking into account all of the most relevant physico-chemical processes. The complexity and computational intensity of the processes to be modeled still exceed the capacities of today’s computers.

Data Generation and Preparation

The fabrication and measurement techniques described before are used to generate training and test data for our neural networks Different 2.5D structure designs are chosen to build a training data-pool from scratch. p. 3

Where the paper says it

more computational resources and is more time consuming and furthermore a suitable measurement technique to generate accurate training data is not available, different 2. 5D structure designs are chosen to build a training data-pool from scratch.

Data augmentation can be used by rotating or mirroring existing non-symmetric datasets. p. 3
Where the paper says it

Data augmentation is an often used technique to increase the amount of training data by creating new data on basis of already existing datasets [27]. In our work, data augmentation can be used by rotating or mirroring existing non-symmetric datasets.

Starting from the measurement data obtaindataed by confocal microscopy, the following data processing steps are performed, based on the steps by Eifler et al. p. 4
Where the paper says it

Profiles along the x -axis and the deviations are shown in (d) and (e), respectively. Starting from the measurement data obtaindataed by confocal microscopy, the following data processing steps are performed, based on the steps by Eifler et al.

[28]. This leads to a resolution of 0. p. 5
Where the paper says it

size of (50 × 50) µm2 and the confocal microscope’s lateral resolution of 0. 3125 µm, this leads to a resolution of 0.

391 µm for further treatment. p. 5
Where the paper says it

3125 µm, this leads to a resolution of 0. 391 µm for further treatment.

A data-pool of in total 5217 labeled datasets is generated. p. 5
Where the paper says it

The combination of a structure design and its corresponding processed measurement result is a single dataset for our neural networks, where either the design or the measured print can be used as either input or label. Based on these procedures and tools, a data-pool of in total 5217 labeled datasets is generated.

Network Architectures and Loss Function

We present three different network architectures depending on used parameters and tasks. The first logical task is to predict the target-print-deviation. p. 6

Where the paper says it

Hence, we present three different network architectures depending on used parameters and tasks. The first logical task is to predict the target-print-deviation.

The second approach is called Direct Correction (DC), since the goal is a direct prediction of a corrected design. p. 5
Where the paper says it

Since this step can be performed multiple times we call it the Iterative Correction (IC) approach from now on. The second approach is called Direct Correction (DC), since the goal is a direct prediction of a corrected design.

A customized loss function (see Eq. p. 8
Where the paper says it

However, applying mse as loss function will lead to averaging over small feature sizes during the training and therefore does not provide sufficiently accurate results, as illustrated in Fig. For this reason a customized loss function (see Eq.

3) is determined to evaluate the train and test performances of neural networks. p. 8
Where the paper says it

4 Loss Function So-called loss functions are defined to evaluate the train and test performances of neural networks and allow for the comparison between different architectures. Furthermore, choosing a loss function is essential for the convergence of the network results and has an effect on which features are more important along the training process.

This loss function includes the Pearson correlation coefficient CC and the absolute value of the difference between the mean height value of prediction and label. p. 8
Where the paper says it

Since the loss function will be minimized during the training process, we define the first part of the loss function as L1 = 1−CC so that L1 −→ 0 + in case of perfect correlation between prediction and label, and L1 −→ 2 for anti-correlation. Second, the absolute value of the difference between the mean height value of prediction and label is calculated and added so that the average height of the predicted structure matches the label.

Performance Evaluation

The Iterative Correction (IC) approach is illustrated in Fig. 6, where based on the examples of an AIR-type structure (a-g) and the logo structure (h-n), the network’s prediction of the corrected designs show convergent behavior towards higher correlation and lower rmse values for ongoing iteration steps. p. 7

Where the paper says it

The target designs (a, d, g) are compared with the respective measured prints (b, e, h) and the respective network’s predictions for a block (a-c), an AIR-type structure (d-f) and the logo of the former University of Kaiserslautern (g-i). For the logo, (j) and (k) show profiles along the x-axis and the corresponding height difference ∆z between print and target, as well as print and prediction.

The Iterative Correction method delivers the best results regarding the design. p. 6
Where the paper says it

All parameters, such as filter size or stride, are chosen empirically to find the best possible combination. The shown architecture can be used for both, the Iterative Correction and the Direct Correction by switching the input and output.

However, the correction does not necessarily preserve the symmetry of the structure. p. 4
Where the paper says it

not only to the degree of symmetry. Since the structure is additively fabricated by printing single lines, a writing direction is introduced which can lead to an anisotropy that has to be taken into account while using data augmentation.

The Iterative Correction approach leads to the best possible results, but needs more effort than the DC-approach since the real error of the corrected structure does not converge with higher iteration numbers. p. 5
Where the paper says it

[13]: Mk = MDesign − α · ((MPrediction − MDesign) ∗ gcorr), (1) Mk+1 = Mk − α · ((MPrediction,k − MDesign) ∗ gcorr), (2) with M as surface matrix, k as iteration numerator, gcorr denoting a two-dimensional Gaussian distribution, and α as correction strength factor. Since this step can be performed multiple times we call it the Iterative Correction (IC) approach from now on.

Future Directions

For future work, more investigations are necessary to further improve the performance of neural networks and to extend its applicability to various structure types and sizes, such as real 3D and stitched structures. Additionally, more fabrication parameters, like (varying) hatching directions, fabrication speed or the objective magnification are to be implemented to cover a way more broadened application area in the field of DLW. Furthermore, calibration structures for transferring the neural network outputs to different DLW machines must be developed, to make this machine learning approach beneficial for all DLW working groups. p. 0

Where the paper says it

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.

Acknowledgements

The authors gratefully acknowledge the institute for measurement and sensor technology (MTS) at the RPTU University Kaiserslautern-Landau for the opportunity of taking confocal measurements and the measuring know how.

References

[1] S. Maruo, O. Nakamura, and S. Kawata, “Three-dimensional microfabrication with two-photonabsorbed photopolymerization,” Optics letters, vol. p. 5

Where the paper says it

Therefore the following correction mechanism is used analogous to Lang et al. [13]: Mk = MDesign − α · ((MPrediction − MDesign) ∗ gcorr), (1) Mk+1 = Mk − α · ((MPrediction,k − MDesign) ∗ gcorr), (2) with M as surface matrix, k as iteration numerator, gcorr denoting a two-dimensional Gaussian distribution, and α as correction strength factor.

22, no. 2, pp. 132–134, 1997

[7] R. Pingali and S. p. 1

Where the paper says it

Nevertheless, rather simple straight forward calculations of the widths of single lines [5] or voxel and pillar dimensions [6] have been published in 2013 and 2019, respectively. Taking more physico-chemical processes correctly into account, however, already prevents the prediction of line heights or aspect ratios, as stated in 2022 by Pingali et al.

K. Saha, “Reaction-diffusion modeling of photopolymerization during femtosecond projection two-photon lithography,” Journal of Manufacturing Science and Engineering, vol. p. 1
Where the paper says it

The complexity and computational intensity of the processes to be modeled still exceed the capacities of today’s computers. In contrast to such holistic simulation approaches, some research work exists on modeling and investigating partial aspects, such as the molecular diffusion [10], the so-called Schwarzschild- [11] and proximity-effects [10] or the shrinkage behaviour [12].

144, no. 2, p. 021011, 2022

[8] M. Guney and G. Fedder, “Estimation of line dimensions in 3d direct laser writing lithography,” Journal of Micromechanics and Microengineering, vol. p. 1

Where the paper says it

Taking more physico-chemical processes correctly into account, however, already prevents the prediction of line heights or aspect ratios, as stated in 2022 by Pingali et al. A few more approaches focused really successfully on the estimation of printed line dimensions and structure characterization [8, 9], but, unfortunately still not taking into account all of the most relevant physico-chemical processes.

26, no. 10, p. 105011, 2016

[9] R. M. Adão, T. L. Alves, C. Maibohm, B. Romeira, and J. B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

30, no. 6, pp. 9623–9642, 2022

[10] E. H. Waller and G. von Freymann, “Spatio-temporal proximity characteristics in 3d µ-printing via multi-photon absorption,” Polymers, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

8, no. 8, p. 297, 2016

[11] L. Yang, A. Münchinger, M. Kadic, V. Hahn, F. Mayer, E. Blasco, C. Barner-Kowollik, and M. Wegener, “On the schwarzschild effect in 3d two-photon laser lithography,” Advanced Optical Materials, vol. 7, no. 22, p. 1901040, 2019

[13] N. Lang, S. Enns, J. Hering, and G. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

von Freymann, “Towards efficient structure prediction and pre-compensation in multi-photon lithography,” Opt. p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

Express, vol. 30, pp. 28805–28816

[14] C. Wang, X. Tan, S. Tor, and C. Lim, “Machine learning in additive manufacturing: State-ofthe-art and perspectives,” Additive Manufacturing, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

36, p. 101538, 2020

[15] J. Qin, F. Hu, Y. Liu, P. Witherell, C. C Wang, D. W Rosen, T. W Simpson, Y. Lu, and Q Tang, “Research and application of machine learning for additive manufacturing,” Additive Manufacturing, vol. p. 1

Where the paper says it

Due to these limitations and the general complexity of the physico-chemical processes and their dependence of many external factors, machine learning (ML) approaches could be a solution. Numerous studies have investigated the application of these approaches in additive manufacturing (AM) in general.

52, p. 102691, 2022

[16] M. Faegh, S. Ghungrad, J. P Oliveira, P Rao, and A Haghighi, “A review on physics-informed machine learning for process-structure-property modeling in additive manufacturing,” Journal of Manufacturing Processes, vol. p. 1

Where the paper says it

Due to these limitations and the general complexity of the physico-chemical processes and their dependence of many external factors, machine learning (ML) approaches could be a solution. Numerous studies have investigated the application of these approaches in additive manufacturing (AM) in general.

133, pp. 524–555

[17] A. J Thompson, M. Power, and G. p. 0

Where the paper says it

There, photo sensitive materials, so-called photo resins, are locally exposed by a (tightly) focused femtosecond laser beam and subsequently cured. Depending on the laser power using an objective with high NA (NA ≈ 1.

-Z Yang, “Micro-scale fiber-optic force sensor fabricated using direct laser writing and calibrated using machine learning,” Opt. p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

Express, vol. 26, p. 14186

[18] X. Y Lee, S. K Saha, S. Sarkar, and B Giera, “Automated detection of part quality during two-photon lithography via deep learning,” Additive Manufacturing, vol. p. 1

Where the paper says it

Numerous studies have investigated the application of these approaches in additive manufacturing (AM) in general. Thereby, they are used in multiple stages of the AM workflow, including material design – to optimize geometries, topologies, and predict material properties – process optimization during fabrication, and post-processing tasks such as defect detection, quality control, and data analysis.

36, p. 101444

[20] Y. Yang, V. A Kelkar, H. S Rajput, A C S Coariti, K C Toussaint Jr, and C Shao, “Machine-learning-enabled geometric compliance improvement in two-photon lithography without hardware modifications,” Journal of Manufacturing Processes, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

76, pp. 841–849

[22] Nanoscribe GmbH & Co. KG, NanoGuide – IP-S, December 2023

[40] J. Fischer and M. Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

21, no. 22, pp. 26244–26260

[41] M Abadi, A Agarwal, P Barham, E Brevdo, Z Chen, C Citro, G S Corrado, A Davis, J Dean, M Devin, S Ghemawat, I Goodfellow et al., “TensorFlow: Large-scale machine learning on heterogeneous systems,” 2015

[42] F Chollet et al., “Keras,” https://keras.io, 2015

[497] 497 1000 1.5 8 - 0:11:59

[628] 628 1000 1.8 4 - 1:14:41

[5] J. Fischer, J. B Mueller, J Kaschke, T J Wolf, A-N Unterreiner, and M Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

p. 0
Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

21, no. 22, pp. 26244–26260

[9] R. M Adão, T L Alves, C Maibohm, B Romeira, and J B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. p. 0

Where the paper says it

First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing Sven Enns1*, Julian Hering-Stratemeier1,2, and Georg von Freymann1,2,3 1Physics Department and Research Center OPTIMAS, RPTU University Kaiserslautern-Landau, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 2Opti-Cal GmbH, Erwin-Schrödinger-Straße 56, 67663 Kaiserslautern, Germany 3Fraunhofer Institute for Industrial Mathematics ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany *Correspondence to: Sven Enns: enns@rptu. de 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.

30, no. 6, pp. 9623–9642

[18] X Y Lee, S K Saha, S Sarkar, and B Giera, “Automated detection of part quality during two-photon lithography via deep learning,” Additive Manufacturing, vol. 36, p. 101444

[29] E J Abbott and F A Firestone, “Specifying surface quality: a method based on accurate measurement and comparison,” Mechanical Engineering, vol. 55, pp. 569—-572, 1933

[4] R Haria, “Nanoscribe Photonic Professional GT 3D printer produces microscopic molds in series.,” 11 2017

[5] J. Fischer, J. B Mueller, J Kaschke, T J Wolf, A-N Unterreiner, and M Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. 21, no. 22, pp. 26244–26260

[9] R M Adão, T L Alves, C Maibohm, B Romeira, and J B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. 30, no. 6, pp. 9623–9642

[8] M Guney and G Fedder, “Estimation of line dimensions in 3d direct laser writing lithography,” Journal of Micromechanics and Microengineering, vol. 26, no. 10, p. 105011

[4] R Haria, “Nanoscribe Photonic Professional GT 3D printer produces microscopic molds in series.,” 11 2017

[5] J. Fischer, J. B Mueller, J Kaschke, T J Wolf, A-N Unterreiner, and M Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. 21, no. 22, pp. 26244–26260

[9] R M Adão, T L Alves, C Maibohm, B Romeira, and J B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. 30, no. 6, pp. 9623–9642

[8] M Guney and G Fedder, “Estimation of line dimensions in 3d direct laser writing lithography,” Journal of Micromechanics and Microengineering, vol. 26, no. 10, p. 105011

[4] R Haria, “Nanoscribe Photonic Professional GT 3D printer produces microscopic molds in series.,” 11 2017

[5] J. Fischer, J. B Mueller, J Kaschke, T J Wolf, A-N Unterreiner, and M Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. 21, no. 22, pp. 26244–26260

[9] R M Adão, T L Alves, C Maibohm, B Romeira, and J B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. 30, no. 6, pp. 9623–9642

[8] M Guney and G Fedder, “Estimation of line dimensions in 3d direct laser writing lithography,” Journal of Micromechanics and Microengineering, vol. 26, no. 10, p. 105011

[4] R Haria, “Nanoscribe Photonic Professional GT 3D printer produces microscopic molds in series.,” 11 2017

[5] J. Fischer, J. B Mueller, J Kaschke, T J Wolf, A-N Unterreiner, and M Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. 21, no. 22, pp. 26244–26260

[9] R M Adão, T L Alves, C Maibohm, B Romeira, and J B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. 30, no. 6, pp. 9623–9642

[8] M Guney and G Fedder, “Estimation of line dimensions in 3d direct laser writing lithography,” Journal of Micromechanics and Microengineering, vol. 26, no. 10, p. 105011

[4] R Haria, “Nanoscribe Photonic Professional GT 3D printer produces microscopic molds in series.,” 11 2017

[5] J. Fischer, J. B Mueller, J Kaschke, T J Wolf, A-N Unterreiner, and M Wegener, “Threedimensional multi-photon direct laser writing with variable repetition rate,” Optics express, vol. 21, no. 22, pp. 26244–26260

[9] R M Adão, T L Alves, C Maibohm, B Romeira, and J B Nieder, “Two-photon polymerization simulation and fabrication of 3d microprinted suspended waveguides for on-chip optical interconnects,” Optics Express, vol. 30, no. 6, pp. 9623–9642

[8] M Guney and G Fedder, “Estimation of line dimensions in 3d direct laser writing lithography,” Journal of Micromechanics and Microengineering, vol. 26, no. 10, p.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Direct Structure Prediction via Direct Correction (DC) allows an anticipated design to be input, and it will predict a corrected version of the design to get a printed structure as close as possible to the input design.

  2. Iterative Correction (IC) can be used to improve results, as it can be prepared at once and printed within one single job, saving time and ensure same printing conditions throughout all iteration steps for good comparability.

  3. The improved AI system can perform structure correction by calculating a deviation matrix to correct tilt within measurement data, which is described as a regression plane can be calculated and used to finally correct the tilt within the measurement data.

  4. The network architecture can incorporate fabrication parameters such as slicing distance, hatching distance, and laser power into the learning and prediction process, enabling it to account for these influences on printing results.

  5. The system can reduce overall printing error by using a customized loss function that prioritizes small surface features through a term involving the Pearson correlation coefficient CC, which is implemented in such a way that even small surface features are given greater importance during the training process.

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.

Sources

Related papers