Physics-informed data-driven machine health monitoring for two-photon lithography

Chenhui Shao; Sixian Jia; Zhiqiao Dong

arxiv: 2510.15075 · v1 · submitted 2025-10-16 · 💻 cs.LG · stat.ML

Physics-informed data-driven machine health monitoring for two-photon lithography

Sixian Jia , Zhiqiao Dong , Chenhui Shao This is my paper

Pith reviewed 2026-05-18 05:45 UTC · model grok-4.3

classification 💻 cs.LG stat.ML

keywords two-photon lithographymachine health monitoringphysics-informeddata-drivenadditive manufacturingcondition-based maintenancepredictive modeling

0 comments

The pith

Physics-informed data-driven approaches enable accurate monitoring of two-photon lithography machine health.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops three methods that combine physics-informed predictive models for the dimensions of fabricated structures with statistical techniques to monitor the health of two-photon lithography machines. This integration allows handling of complex scenarios with different degrees of generalizability. Experimental data from six process parameter sets and six structure dimensions under two health conditions shows high accuracies for the methods. Such monitoring supports shifting from experience-based to condition-based maintenance, which can reduce unnecessary downtime and maintain fabrication quality.

Core claim

Integrating physics-informed data-driven predictive models for structure dimensions with statistical approaches yields three methods capable of accurate and timely TPL machine health monitoring across scenarios with varying generalizability, validated through high accuracies on a dataset of six process parameter combinations under two machine health states.

What carries the argument

Physics-informed predictive models for structure dimensions integrated with statistical approaches for health monitoring

If this is right

High accuracies achieved across all test scenarios with different generalizability levels
Effective handling of complex monitoring scenarios in TPL systems
Support for condition-based maintenance practices to minimize downtime and quality issues
Robustness and generalizability demonstrated in experimental evaluations

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

These methods could extend to real-time monitoring in production environments for proactive maintenance
Similar physics-data hybrid approaches might apply to other precision manufacturing processes like 3D printing variants
Further validation on larger datasets could strengthen applicability to diverse production variabilities

Load-bearing premise

The physics-informed predictive models for structure dimensions remain accurate even as machine health conditions change, and the dataset from six parameter combinations under two health states represents broader real-world production variability.

What would settle it

A test showing substantially reduced accuracy in health monitoring when using the models on data from a new machine health state or additional process parameters not included in the original six combinations would challenge the central claim.

Figures

Figures reproduced from arXiv: 2510.15075 by Chenhui Shao, Sixian Jia, Zhiqiao Dong.

**Figure 2.** Figure 2: Distribution of geometric features under two machine statuses: (a) [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗

**Figure 3.** Figure 3: Type I and Type II error rates of the two-sample [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗

**Figure 4.** Figure 4: Illustration of predicting the mean value of D1P2 for Machine Status 1 using available [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗

**Figure 5.** Figure 5: Predicted mean values (red dashed lines) compared with observed distributions from [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗

**Figure 6.** Figure 6: Distribution of geometric features under two machine statuses (D1P6) with predicted [PITH_FULL_IMAGE:figures/full_fig_p014_6.png] view at source ↗

**Figure 7.** Figure 7: Distribution of 𝑇 2 for D1P6 with predicted value: (a) Status 1; (b) Status 2 [PITH_FULL_IMAGE:figures/full_fig_p015_7.png] view at source ↗

**Figure 8.** Figure 8: Hotelling’s 𝑇 2 monitoring results for (a) in-control and (b) out-of-control scenarios. Green cells indicate non-rejection of the null hypothesis, implying that the machine status remains unchanged; red cells indicate rejection suggesting a changed machine status. monitoring compared to Method 1. 5. Method 3: Monitoring Model Parameters 5.1. Approach Overview As detailed in Method 2, we leverage the establ… view at source ↗

**Figure 9.** Figure 9: Data efficiency of Hotelling’s 𝑇 2 : (a) Type I Error; (b) Type II Error, as a function of the number of designs (D) and parameters (P) used for training. themselves. Shifts in parameter values can serve as indicators of a change in machine status [PITH_FULL_IMAGE:figures/full_fig_p016_9.png] view at source ↗

**Figure 10.** Figure 10: Variation of model parameters with respect to structure dimension [PITH_FULL_IMAGE:figures/full_fig_p017_10.png] view at source ↗

**Figure 11.** Figure 11: Bootstrap-derived distributions of model parameters: (a) [PITH_FULL_IMAGE:figures/full_fig_p019_11.png] view at source ↗

**Figure 12.** Figure 12: Algorithm 1 details the procedure. Thresholds estimated with this approach successfully contain parameter distributions from the same machine status while excluding distributions from a different status, as shown in [PITH_FULL_IMAGE:figures/full_fig_p019_12.png] view at source ↗

**Figure 12.** Figure 12: Data usage for leave-one-out threshold estimation. Thresholds for an unseen [PITH_FULL_IMAGE:figures/full_fig_p020_12.png] view at source ↗

**Figure 13.** Figure 13: Threshold for unknown parameter groups: (a) [PITH_FULL_IMAGE:figures/full_fig_p020_13.png] view at source ↗

read the original abstract

Two-photon lithography (TPL) is a sophisticated additive manufacturing technology for creating three-dimensional (3D) micro- and nano-structures. Maintaining the health of TPL systems is critical for ensuring consistent fabrication quality. Current maintenance practices often rely on experience rather than informed monitoring of machine health, resulting in either untimely maintenance that causes machine downtime and poor-quality fabrication, or unnecessary maintenance that leads to inefficiencies and avoidable downtime. To address this gap, this paper presents three methods for accurate and timely monitoring of TPL machine health. Through integrating physics-informed data-driven predictive models for structure dimensions with statistical approaches, the proposed methods are able to handle increasingly complex scenarios featuring different levels of generalizability. A comprehensive experimental dataset that encompasses six process parameter combinations and six structure dimensions under two machine health conditions was collected to evaluate the effectiveness of the proposed approaches. Across all test scenarios, the approaches are shown to achieve high accuracies, demonstrating excellent effectiveness, robustness, and generalizability. These results represent a significant step toward condition-based maintenance for TPL systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This paper applies physics-informed dimension prediction plus stats to monitor TPL machine health on real experimental data, but the tests use only two discrete health states so the robustness claims need more scrutiny.

read the letter

The main point is that the authors combine physics-informed models for predicting structure dimensions with statistical monitoring to detect TPL machine health issues. They ran experiments on six process parameter sets and six dimensions under two health conditions and report high accuracy across their test scenarios. This is a practical step for a process where maintenance still leans on experience rather than data. The experimental dataset from actual fabrication is the clearest strength; it gives concrete numbers instead of just simulation. The hybrid approach also looks reasonable for handling different levels of complexity in monitoring. That said, the dataset limitation is real. Two health states do not cover gradual wear, other failure modes, or how dimension predictions shift when health changes. The abstract gives no model architecture details, training procedure, cross-validation, or error bars, which makes it hard to judge whether the accuracies are stable or just fitted to this narrow case. If the full paper has those elements and shows the physics component actually adapts to health shifts, the work improves. Otherwise the generalizability claim stays provisional. This is aimed at engineers doing condition-based maintenance in micro- and nano-fabrication and at researchers applying hybrid ML to precision manufacturing. A reader who needs a case study on TPL monitoring or wants to adapt the fusion method could get usable ideas from the data and setup. The paper engages the practical problem and prior techniques without obvious internal contradictions, so it deserves a serious referee. I would send it for review with a request to expand the health-state coverage and add proper validation stats.

Referee Report

2 major / 1 minor

Summary. The paper proposes three physics-informed data-driven methods for monitoring the health of two-photon lithography (TPL) systems. These methods integrate predictive models for structure dimensions with statistical approaches to handle scenarios of varying complexity and generalizability. The evaluation uses a collected experimental dataset covering six process parameter combinations and six structure dimensions under two machine health conditions, with reported high accuracies across test scenarios supporting claims of effectiveness, robustness, and generalizability toward condition-based maintenance.

Significance. If the central claims hold after addressing the noted issues, this work would contribute to the application of physics-informed machine learning in additive manufacturing by providing a data-driven yet physically grounded approach to TPL machine health monitoring. The experimental dataset collection under controlled conditions represents a concrete strength that could support future condition-based maintenance strategies, reducing downtime and improving fabrication consistency in micro- and nano-structure production.

major comments (2)

[Abstract] Abstract: The central claim that the approaches achieve high accuracies demonstrating excellent effectiveness, robustness, and generalizability is presented without any details on model architectures, training procedures, cross-validation methods, or error bars. This omission is load-bearing because the soundness of the reported performance cannot be assessed or reproduced from the given information.
[Experimental dataset description] Experimental dataset description (as summarized in the abstract): The evaluation is restricted to exactly two discrete machine health conditions. The generalizability claim requires that the physics-informed predictive models for structure dimensions remain accurate as health varies, yet the design does not examine continuous degradation, additional failure modes, or explicit modeling of health-induced parameter shifts; performance on this narrow discrete set therefore does not securely establish the broader robustness assertion.

minor comments (1)

[Abstract] The abstract would be clearer if it briefly named the three methods and reported the specific accuracy values rather than the qualitative statement 'high accuracies'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major comment point by point below, with proposed revisions to the manuscript where appropriate.

read point-by-point responses

Referee: [Abstract] Abstract: The central claim that the approaches achieve high accuracies demonstrating excellent effectiveness, robustness, and generalizability is presented without any details on model architectures, training procedures, cross-validation methods, or error bars. This omission is load-bearing because the soundness of the reported performance cannot be assessed or reproduced from the given information.

Authors: We agree that the abstract, as a concise summary, omits specific details on model architectures, training procedures, cross-validation methods, and error bars. These elements are described in full in Sections 3 (Methods) and 4 (Results) of the manuscript, including the physics-informed neural network structures, the use of k-fold cross-validation on the six parameter sets, and performance metrics with standard deviations. To address the concern, we will revise the abstract to include a brief statement on the evaluation methodology and report key accuracies with uncertainties. revision: yes
Referee: [Experimental dataset description] Experimental dataset description (as summarized in the abstract): The evaluation is restricted to exactly two discrete machine health conditions. The generalizability claim requires that the physics-informed predictive models for structure dimensions remain accurate as health varies, yet the design does not examine continuous degradation, additional failure modes, or explicit modeling of health-induced parameter shifts; performance on this narrow discrete set therefore does not securely establish the broader robustness assertion.

Authors: The experimental dataset is limited to two discrete health conditions, as collected under controlled laboratory settings with the available TPL system states. We do not model continuous degradation or additional failure modes in this work. The generalizability claims pertain to performance across the six process parameter combinations within these conditions, enabled by the physics-informed dimension predictions. We will revise the abstract and add a dedicated limitations paragraph in the discussion to clarify the scope and outline future directions for continuous monitoring. revision: partial

Circularity Check

0 steps flagged

No circularity: empirical validation on collected dataset

full rationale

The paper proposes three methods that integrate physics-informed data-driven predictive models for structure dimensions with statistical approaches for TPL machine health monitoring. These are evaluated directly on an experimental dataset of six process parameter combinations and six structure dimensions collected under two discrete machine health conditions. Claims of high accuracy, robustness, and generalizability rest on reported performance metrics from this dataset rather than any derivation, equation, or prediction that reduces to fitted parameters by construction. No self-definitional steps, fitted-input predictions, or load-bearing self-citation chains appear in the abstract or described approach; the chain is self-contained via empirical testing.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the assumption that physics-based relationships between process parameters and printed dimensions remain stable enough to serve as a baseline for detecting health changes. No new physical constants or entities are introduced.

axioms (1)

domain assumption Physics-informed models can accurately predict structure dimensions from process parameters under healthy machine conditions.
Invoked when the paper states that predictive models for structure dimensions are integrated with statistical approaches to monitor health.

pith-pipeline@v0.9.0 · 5710 in / 1248 out tokens · 33364 ms · 2026-05-18T05:45:59.643238+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

R(LP,SR)=a_R [ln(b_R LP²/SR)]^{1/2}+c_R ; H(LP,SR)=a_H [(b_H LP²/SR)^{1/2}-1]^{1/2}+c_H (Eqs. 4-5); Hotelling T² on bootstrap parameter distributions; leave-one-out thresholding + majority voting (Alg. 1, Tables 4-7)
IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

Two machine health conditions; six process-parameter combinations; accuracies 82-100% on this narrow set

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

32 extracted references · 32 canonical work pages

[1]

Harinarayana, Y

V. Harinarayana, Y. Shin, Two-photon lithography for three-dimensional fabrication in micro/nanoscale regime: A comprehensive review, Optics & Laser Technology 142 (2021) 107180. 22

work page 2021
[2]

Vyatskikh, S

A. Vyatskikh, S. Delalande, A. Kudo, X. Zhang, C. M. Portela, J. R. Greer, Additive manufacturing of 3d nano-architected metals, Nature communi- cations 9 (1) (2018) 593

work page 2018
[3]

S.Maddox, M.Afshar-Mohajer, M.Zou, Digitization, replication, andmod- ification of physical surfaces using two-photon lithography, Journal of Man- ufacturing Processes 54 (2020) 180–189

work page 2020
[4]

Z. Dong, S. Jia, C. Shao, Filtered kriging for improved interpolation of periodic manufacturing surfaces, Journal of Manufacturing Processes 131 (2024) 1–12

work page 2024
[5]

J. Sun, S. Jia, C. Shao, M. R. Dawson, K. C. Toussaint, Emerging tech- nologies for multiphoton writing and reading of polymeric architectures for biomedical applications, Annual Review of Biomedical Engineering 27 (2025)

work page 2025
[6]

Williams, M

G. Williams, M. Hunt, B. Boehm, A. May, M. Taverne, D. Ho, S. Giblin, D. Read, J. Rarity, R. Allenspach, et al., Two-photon lithography for 3d magnetic nanostructure fabrication, Nano Research 11 (2018) 845–854

work page 2018
[7]

S. Jia, S. Li, J. Sun, M. R. Dawson, K. C. Toussaint Jr, C. Shao, End-to- end part quality classification for two-photon lithography using computer vision, Manufacturing Letters 44 (2025) 1369–1377

work page 2025
[8]

J. Sun, A. M. Howes, S. Jia, J. A. Burrow, P. F. Felzenszwalb, M. R. Daw- son, C. Shao, K. C. Toussaint Jr, Automated brightfield layerwise evalua- tion in three-dimensional micropatterning via two-photon polymerization, Optics Express 32 (7) (2024) 12508–12519

work page 2024
[9]

Maruo, O

S. Maruo, O. Nakamura, S. Kawata, Three-dimensional microfabrica- 23 tion with two-photon-absorbed photopolymerization, Optics letters 22 (2) (1997) 132–134

work page 1997
[10]

Shunhua, D

Y. Shunhua, D. Chenliang, Z. Dazhao, Y. Zhenyao, L. Yong, K. Cuifang, L. Xu, High-speed two-photon lithography based on femtosecond laser, Opto-Electronic Engineering 50 (3) (2023) 220133–1

work page 2023
[11]

Beermann, S

J. Beermann, S. M. Novikov, T. Søndergaard, A. E. Boltasseva, S. I. Bozhevolnyi, Two-photon mapping of localized field enhancements in thin nanostrip antennas, Optics Express 16 (22) (2008) 17302–17309

work page 2008
[12]

Noronha, J

J. Noronha, J. Dash, J. Rogers, M. Leary, M. Brandt, M. Qian, Titanium multi-topology metamaterials with exceptional strength, Advanced Mate- rials 36 (34) (2024) 2308715

work page 2024
[13]

J. U. Surjadi, L. Gao, H. Du, X. Li, X. Xiong, N. X. Fang, Y. Lu, Mechan- ical metamaterials and their engineering applications, Advanced Engineer- ing Materials 21 (3) (2019) 1800864

work page 2019
[14]

Jalali, V

B. Jalali, V. Raghunathan, D. Dimitropoulos, O. Boyraz, Raman-based silicon photonics, IEEE Journal of Selected Topics in Quantum Electronics 12 (3) (2006) 412–421

work page 2006
[15]

Langfelder, A

G. Langfelder, A. F. Longoni, A. Tocchio, E. Lasalandra, Mems motion sensors based on the variations of the fringe capacitances, IEEE Sensors Journal 11 (4) (2010) 1069–1077

work page 2010
[16]

X. Zhou, Y. Hou, J. Lin, A review on the processing accuracy of two-photon polymerization, Aip Advances 5 (3) (2015)

work page 2015
[17]

H. Wang, W. Zhang, D. Ladika, H. Yu, D. Gailevičius, H. Wang, C.-F. Pan, P. N. S. Nair, Y. Ke, T. Mori, et al., Two-photon polymerization lithogra- 24 phy for optics and photonics: fundamentals, materials, technologies, and applications, Advanced Functional Materials 33 (39) (2023) 2214211

work page 2023
[18]

J. Lee, S. J. Park, S. C. Han, P. Prabhakaran, C. W. Ha, Enhanced me- chanical property through high-yield fabrication process with double laser scanning method in two-photon lithography, Materials & Design 235 (2023) 112389

work page 2023
[19]

S. Yu, Q. Du, C. R. Mendonca, L. Ranno, T. Gu, J. Hu, Two-photon lithog- raphy for integrated photonic packaging, Light: Advanced Manufacturing 4 (4) (2024) 486–502

work page 2024
[20]

X. Y. Lee, S. K. Saha, S. Sarkar, B. Giera, Automated detection of part quality during two-photon lithography via deep learning, Additive Manu- facturing 36 (2020) 101444

work page 2020
[21]

Y. Yang, V. A. Kelkar, H. S. Rajput, A. C. S. Coariti, K. C. Toussaint Jr, C. Shao, Machine-learning-enabled geometric compliance improvement in two-photon lithography without hardware modifications, Journal of Man- ufacturing Processes 76 (2022) 841–849

work page 2022
[22]

S. Jia, J. Sun, A. Howes, M. R. Dawson, K. C. Toussaint Jr, C. Shao, Hy- brid physics-guided data-driven modeling for generalizable geometric ac- curacy prediction and improvement in two-photon lithography, Journal of Manufacturing Processes 110 (2024) 202–210

work page 2024
[23]

K.Khanafer, J.Cao, H.Kokash, Conditionmonitoringinadditivemanufac- turing: A critical review of different approaches, Journal of Manufacturing and Materials Processing 8 (3) (2024) 95

work page 2024
[24]

K.Zhu, J.Y.H.Fuh, X.Lin, Metal-basedadditivemanufacturingcondition 25 monitoring: A review on machine learning based approaches, IEEE/ASME Transactions on Mechatronics 27 (5) (2021) 2495–2510

work page 2021
[25]

Q. Fang, G. Xiong, M. Zhou, T. S. Tamir, C.-B. Yan, H. Wu, Z. Shen, F.-Y. Wang, Processmonitoring, diagnosisandcontrolofadditivemanufacturing, IEEE Transactions on Automation Science and Engineering 21 (1) (2022) 1041–1067

work page 2022
[26]

J. Liu, Y. Hu, B. Wu, Y. Wang, An improved fault diagnosis approach for fdm process with acoustic emission, Journal of Manufacturing Processes 35 (2018) 570–579

work page 2018
[27]

Tlegenov, G

Y. Tlegenov, G. S. Hong, W. F. Lu, Nozzle condition monitoring in 3d printing, Robotics and Computer-Integrated Manufacturing 54 (2018) 45– 55

work page 2018
[28]

M. Wang, N. Kashaev, On the maintenance of processing stability and con- sistency in laser-directed energy deposition via machine learning, Journal of Manufacturing Systems 73 (2024) 126–142

work page 2024
[29]

Meng, K.-C

Y. Meng, K.-C. Lu, Z. Dong, S. Li, C. Shao, Explainable few-shot learn- ing for online anomaly detection in ultrasonic metal welding with varying configurations, Journal of Manufacturing Processes 107 (2023) 345–355

work page 2023
[30]

Y. Meng, Z. Dong, K.-C. Lu, S. Li, C. Shao, Meta-learning-based do- main generalization for cost-effective tool condition monitoring in ultra- sonic metal welding, IEEE Transactions on Industrial Informatics (2024)

work page 2024
[31]

X. Dong, C. Zhang, H. Liu, D. Wang, Y. Chen, T. Wang, A new cross- domain bearing fault diagnosis method with few samples under different working conditions, Journal of Manufacturing Processes 135 (2025) 359– 374. 26

work page 2025
[32]

J. Sun, A. Howes, S. Jia, J. A. Burrow, M. Dawson, C. Shao, K. C. Tous- saint, In-situ monitoring and process control of two-photon lithography for tissue scaffold fabrication, in: 3D Image Acquisition and Display: Tech- nology, Perception and Applications, Optica Publishing Group, 2023, pp. DTu3A–3. 27

work page 2023

[1] [1]

Harinarayana, Y

V. Harinarayana, Y. Shin, Two-photon lithography for three-dimensional fabrication in micro/nanoscale regime: A comprehensive review, Optics & Laser Technology 142 (2021) 107180. 22

work page 2021

[2] [2]

Vyatskikh, S

A. Vyatskikh, S. Delalande, A. Kudo, X. Zhang, C. M. Portela, J. R. Greer, Additive manufacturing of 3d nano-architected metals, Nature communi- cations 9 (1) (2018) 593

work page 2018

[3] [3]

S.Maddox, M.Afshar-Mohajer, M.Zou, Digitization, replication, andmod- ification of physical surfaces using two-photon lithography, Journal of Man- ufacturing Processes 54 (2020) 180–189

work page 2020

[4] [4]

Z. Dong, S. Jia, C. Shao, Filtered kriging for improved interpolation of periodic manufacturing surfaces, Journal of Manufacturing Processes 131 (2024) 1–12

work page 2024

[5] [5]

J. Sun, S. Jia, C. Shao, M. R. Dawson, K. C. Toussaint, Emerging tech- nologies for multiphoton writing and reading of polymeric architectures for biomedical applications, Annual Review of Biomedical Engineering 27 (2025)

work page 2025

[6] [6]

Williams, M

G. Williams, M. Hunt, B. Boehm, A. May, M. Taverne, D. Ho, S. Giblin, D. Read, J. Rarity, R. Allenspach, et al., Two-photon lithography for 3d magnetic nanostructure fabrication, Nano Research 11 (2018) 845–854

work page 2018

[7] [7]

S. Jia, S. Li, J. Sun, M. R. Dawson, K. C. Toussaint Jr, C. Shao, End-to- end part quality classification for two-photon lithography using computer vision, Manufacturing Letters 44 (2025) 1369–1377

work page 2025

[8] [8]

J. Sun, A. M. Howes, S. Jia, J. A. Burrow, P. F. Felzenszwalb, M. R. Daw- son, C. Shao, K. C. Toussaint Jr, Automated brightfield layerwise evalua- tion in three-dimensional micropatterning via two-photon polymerization, Optics Express 32 (7) (2024) 12508–12519

work page 2024

[9] [9]

Maruo, O

S. Maruo, O. Nakamura, S. Kawata, Three-dimensional microfabrica- 23 tion with two-photon-absorbed photopolymerization, Optics letters 22 (2) (1997) 132–134

work page 1997

[10] [10]

Shunhua, D

Y. Shunhua, D. Chenliang, Z. Dazhao, Y. Zhenyao, L. Yong, K. Cuifang, L. Xu, High-speed two-photon lithography based on femtosecond laser, Opto-Electronic Engineering 50 (3) (2023) 220133–1

work page 2023

[11] [11]

Beermann, S

J. Beermann, S. M. Novikov, T. Søndergaard, A. E. Boltasseva, S. I. Bozhevolnyi, Two-photon mapping of localized field enhancements in thin nanostrip antennas, Optics Express 16 (22) (2008) 17302–17309

work page 2008

[12] [12]

Noronha, J

J. Noronha, J. Dash, J. Rogers, M. Leary, M. Brandt, M. Qian, Titanium multi-topology metamaterials with exceptional strength, Advanced Mate- rials 36 (34) (2024) 2308715

work page 2024

[13] [13]

J. U. Surjadi, L. Gao, H. Du, X. Li, X. Xiong, N. X. Fang, Y. Lu, Mechan- ical metamaterials and their engineering applications, Advanced Engineer- ing Materials 21 (3) (2019) 1800864

work page 2019

[14] [14]

Jalali, V

B. Jalali, V. Raghunathan, D. Dimitropoulos, O. Boyraz, Raman-based silicon photonics, IEEE Journal of Selected Topics in Quantum Electronics 12 (3) (2006) 412–421

work page 2006

[15] [15]

Langfelder, A

G. Langfelder, A. F. Longoni, A. Tocchio, E. Lasalandra, Mems motion sensors based on the variations of the fringe capacitances, IEEE Sensors Journal 11 (4) (2010) 1069–1077

work page 2010

[16] [16]

X. Zhou, Y. Hou, J. Lin, A review on the processing accuracy of two-photon polymerization, Aip Advances 5 (3) (2015)

work page 2015

[17] [17]

H. Wang, W. Zhang, D. Ladika, H. Yu, D. Gailevičius, H. Wang, C.-F. Pan, P. N. S. Nair, Y. Ke, T. Mori, et al., Two-photon polymerization lithogra- 24 phy for optics and photonics: fundamentals, materials, technologies, and applications, Advanced Functional Materials 33 (39) (2023) 2214211

work page 2023

[18] [18]

J. Lee, S. J. Park, S. C. Han, P. Prabhakaran, C. W. Ha, Enhanced me- chanical property through high-yield fabrication process with double laser scanning method in two-photon lithography, Materials & Design 235 (2023) 112389

work page 2023

[19] [19]

S. Yu, Q. Du, C. R. Mendonca, L. Ranno, T. Gu, J. Hu, Two-photon lithog- raphy for integrated photonic packaging, Light: Advanced Manufacturing 4 (4) (2024) 486–502

work page 2024

[20] [20]

X. Y. Lee, S. K. Saha, S. Sarkar, B. Giera, Automated detection of part quality during two-photon lithography via deep learning, Additive Manu- facturing 36 (2020) 101444

work page 2020

[21] [21]

Y. Yang, V. A. Kelkar, H. S. Rajput, A. C. S. Coariti, K. C. Toussaint Jr, C. Shao, Machine-learning-enabled geometric compliance improvement in two-photon lithography without hardware modifications, Journal of Man- ufacturing Processes 76 (2022) 841–849

work page 2022

[22] [22]

S. Jia, J. Sun, A. Howes, M. R. Dawson, K. C. Toussaint Jr, C. Shao, Hy- brid physics-guided data-driven modeling for generalizable geometric ac- curacy prediction and improvement in two-photon lithography, Journal of Manufacturing Processes 110 (2024) 202–210

work page 2024

[23] [23]

K.Khanafer, J.Cao, H.Kokash, Conditionmonitoringinadditivemanufac- turing: A critical review of different approaches, Journal of Manufacturing and Materials Processing 8 (3) (2024) 95

work page 2024

[24] [24]

K.Zhu, J.Y.H.Fuh, X.Lin, Metal-basedadditivemanufacturingcondition 25 monitoring: A review on machine learning based approaches, IEEE/ASME Transactions on Mechatronics 27 (5) (2021) 2495–2510

work page 2021

[25] [25]

Q. Fang, G. Xiong, M. Zhou, T. S. Tamir, C.-B. Yan, H. Wu, Z. Shen, F.-Y. Wang, Processmonitoring, diagnosisandcontrolofadditivemanufacturing, IEEE Transactions on Automation Science and Engineering 21 (1) (2022) 1041–1067

work page 2022

[26] [26]

J. Liu, Y. Hu, B. Wu, Y. Wang, An improved fault diagnosis approach for fdm process with acoustic emission, Journal of Manufacturing Processes 35 (2018) 570–579

work page 2018

[27] [27]

Tlegenov, G

Y. Tlegenov, G. S. Hong, W. F. Lu, Nozzle condition monitoring in 3d printing, Robotics and Computer-Integrated Manufacturing 54 (2018) 45– 55

work page 2018

[28] [28]

M. Wang, N. Kashaev, On the maintenance of processing stability and con- sistency in laser-directed energy deposition via machine learning, Journal of Manufacturing Systems 73 (2024) 126–142

work page 2024

[29] [29]

Meng, K.-C

Y. Meng, K.-C. Lu, Z. Dong, S. Li, C. Shao, Explainable few-shot learn- ing for online anomaly detection in ultrasonic metal welding with varying configurations, Journal of Manufacturing Processes 107 (2023) 345–355

work page 2023

[30] [30]

Y. Meng, Z. Dong, K.-C. Lu, S. Li, C. Shao, Meta-learning-based do- main generalization for cost-effective tool condition monitoring in ultra- sonic metal welding, IEEE Transactions on Industrial Informatics (2024)

work page 2024

[31] [31]

X. Dong, C. Zhang, H. Liu, D. Wang, Y. Chen, T. Wang, A new cross- domain bearing fault diagnosis method with few samples under different working conditions, Journal of Manufacturing Processes 135 (2025) 359– 374. 26

work page 2025

[32] [32]

J. Sun, A. Howes, S. Jia, J. A. Burrow, M. Dawson, C. Shao, K. C. Tous- saint, In-situ monitoring and process control of two-photon lithography for tissue scaffold fabrication, in: 3D Image Acquisition and Display: Tech- nology, Perception and Applications, Optica Publishing Group, 2023, pp. DTu3A–3. 27

work page 2023