pith. the verified trust layer for science. sign in

arxiv: 2605.01100 · v1 · submitted 2026-05-01 · 💻 cs.AI

A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

Basit Mahmud Shahriar , Md Habibor Rahman This is my paper

Pith reviewed 2026-05-09 19:12 UTC · model grok-4.3

classification 💻 cs.AI
keywords laser powder bed fusiondefect analysislarge language modelsontologydecision support systemexplainable AIadditive manufacturingmitigation guidance
0
0 comments X p. Extension

The pith

Integrating structured knowledge of 27 laser powder bed fusion defects into an LLM-based system improves defect diagnosis accuracy to a macro-average F1 score of 0.808 with substantial expert agreement.

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

The paper develops a decision-support system that integrates structured defect knowledge with LLM-based reasoning to provide explainable defect diagnosis and mitigation guidance in laser powder bed fusion manufacturing. The system uses an ontology containing 27 defect types organized hierarchically with causal relationships to guide the large language model in handling natural language queries, generating explanations, and suggesting mitigations, while also incorporating a multimodal module for image-based defect interpretation. A sympathetic reader would care because laser powder bed fusion is a safety-critical additive manufacturing process where accurate defect identification can prevent failures in important components, and knowledge-driven approaches may make LLM outputs more reliable and usable in practice. Evaluation demonstrates that the complete system configuration outperforms ablated versions and achieves substantial agreement with literature-based expert labels.

Core claim

The proposed ontology-integrated LLM-based decision support system for LPBF defect analysis and mitigation guidance is built on a knowledge base containing 27 known LPBF defect types organized into hierarchical categories and causal relationships. The developed system supports fuzzy natural language queries for systematic knowledge retrieval, literature-supported explanation of defects, and guidance on defect causes and mitigation strategies derived from encoded process knowledge. Furthermore, a multimodal image-assessment module based on foundation models enables descriptor-guided interpretation of representative microscopic defect images through semantic alignment scoring. The fully integ

What carries the argument

The ontology of 27 defect types with hierarchical categories and causal relationships that guides the LLM reasoning for improved consistency and interpretability.

Load-bearing premise

The manually encoded ontology of 27 defect types and their causal relationships is both complete and accurate enough to guide reliable LLM reasoning on real, previously unseen LPBF defects outside the literature-derived test set.

What would settle it

Testing the system on a fresh set of LPBF defect examples with independent expert labels not based on the original literature would reveal if the F1 score remains high or if agreement drops.

read the original abstract

This work presents a knowledge-driven decision-support system that integrates structured defect knowledge with LLM-based reasoning to provide explainable defect diagnosis and mitigation guidance in manufacturing, using LPBF as a representative, safety-critical case study. The proposed ontology-integrated LLM-based decision support system for LPBF defect analysis and mitigation guidance is built on a knowledge base containing 27 known LPBF defect types organized into hierarchical categories and causal relationships. The developed system supports fuzzy natural language queries for systematic knowledge retrieval, literature-supported explanation of defects, and guidance on defect causes and mitigation strategies derived from encoded process knowledge. Furthermore, a multimodal image-assessment module based on foundation models enables descriptor-guided interpretation of representative microscopic defect images through semantic alignment scoring. The proposed framework was evaluated through qualitative comparisons with general-purpose vision-language models, an ablation study, and an inter-rater reliability analysis. Evaluation on the literature-derived dataset showed that the fully integrated configuration outperformed the other three evaluated system configurations, achieving a macro-average F1 score of 0.808. Additionally, inter-rater reliability analysis using Cohen's kappa indicated substantial agreement between the model outputs and the literature-derived reference labels. These findings suggest that ontology-guided knowledge representation can improve the consistency, interpretability, and practical usefulness of LLM-assisted LPBF defect analysis.

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.

Referee Report

2 major / 1 minor

Summary. The manuscript presents a knowledge-driven decision-support system for LPBF defect analysis that integrates a manually encoded ontology of 27 defect types and their causal relationships with LLM-based reasoning. The system handles fuzzy natural-language queries, generates literature-supported explanations and mitigation guidance, and incorporates a multimodal image-assessment module using foundation models for semantic alignment on microscopic images. Evaluation consists of qualitative comparisons, an ablation study across four system configurations, and inter-rater reliability analysis (Cohen's kappa) on a literature-derived dataset; the fully integrated configuration reports a macro-average F1 of 0.808 and substantial agreement with reference labels.

Significance. If the central performance claims hold under independent scrutiny, the work supplies a concrete, reproducible template for embedding structured domain knowledge into LLMs to improve consistency and explainability in a safety-critical manufacturing domain. The ablation study and quantitative metrics (F1, kappa) provide measurable evidence that the ontology integration adds value over the ablated baselines. The approach could serve as a model for other specialized industrial applications where pure LLM reasoning lacks reliability.

major comments (2)
  1. [evaluation section / abstract] The evaluation is performed exclusively on a literature-derived dataset whose construction, size, filtering steps, and exact overlap with the sources used to build the 27-defect ontology are not detailed. Because both the knowledge base and the reference labels originate from the same published LPBF corpus, the reported F1 of 0.808 and Cohen's kappa primarily measure in-distribution retrieval and reasoning rather than generalization to previously unseen, real-world defects. This directly undermines the claim of practical usefulness for novel LPBF cases (abstract and evaluation section).
  2. [evaluation section] No external validation set, cross-validation against independent industrial data, or ablation on ontology completeness is described. The weakest assumption—that the manually encoded ontology is sufficiently complete and accurate to guide reliable reasoning outside the training literature—therefore remains untested and is load-bearing for the broader applicability claims.
minor comments (1)
  1. [methods / evaluation] The exact prompting templates, alignment scoring procedure for the multimodal module, and any post-hoc filtering applied to the literature-derived dataset should be supplied (e.g., in an appendix or supplementary material) to support reproducibility of the F1 score.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed comments, which have helped clarify the scope and limitations of our evaluation. We address each major comment point by point below, with revisions made to improve transparency.

read point-by-point responses

  1. Referee: [evaluation section / abstract] The evaluation is performed exclusively on a literature-derived dataset whose construction, size, filtering steps, and exact overlap with the sources used to build the 27-defect ontology are not detailed. Because both the knowledge base and the reference labels originate from the same published LPBF corpus, the reported F1 of 0.808 and Cohen's kappa primarily measure in-distribution retrieval and reasoning rather than generalization to previously unseen, real-world defects. This directly undermines the claim of practical usefulness for novel LPBF cases (abstract and evaluation section).

    Authors: We agree that greater detail on the evaluation dataset is needed and that the current setup primarily assesses performance on established LPBF knowledge rather than generalization to novel defects. In the revised manuscript, we have expanded the evaluation section with a new subsection that specifies the dataset construction process, including the total number of test queries, the literature sources used, the filtering criteria for relevance and non-duplication, and explicit steps taken to select cases from publications distinct from those used to manually encode the ontology. We have also revised the abstract and discussion to state that the reported metrics (macro F1 of 0.808 and substantial Cohen's kappa) reflect consistent reasoning with literature-derived reference labels, rather than claiming direct applicability to previously unseen defects. The ablation study still provides evidence that ontology integration improves over baselines on this set. We believe this addresses the concern by clarifying the evaluation's scope while preserving the contribution for known defect analysis in safety-critical contexts. revision: yes

  2. Referee: [evaluation section] No external validation set, cross-validation against independent industrial data, or ablation on ontology completeness is described. The weakest assumption—that the manually encoded ontology is sufficiently complete and accurate to guide reliable reasoning outside the training literature—therefore remains untested and is load-bearing for the broader applicability claims.

    Authors: We acknowledge that the original manuscript lacks an external validation set from independent industrial sources and does not include an explicit ablation study on ontology completeness, leaving the assumption of sufficient coverage untested for novel scenarios. In the revised version, we have added a dedicated 'Limitations and Future Work' subsection in the discussion that explicitly states this assumption, notes that the ontology was derived from a finite but comprehensive review of LPBF literature, and describes planned follow-up work with industrial partners to collect and evaluate on real-world data. The existing ablation across the four system configurations (including with/without ontology) already quantifies the contribution of the structured knowledge on the available test set. These changes make the paper more transparent without overstating current evidence. revision: yes

Circularity Check

0 steps flagged

No circularity: evaluation measures system use of encoded knowledge on literature-derived cases without reduction to input by construction

full rationale

The paper manually encodes an ontology of 27 defect types and causal relations from LPBF literature, then evaluates the ontology-augmented LLM system (plus multimodal module) on a separate literature-derived test set via macro F1 and Cohen's kappa against reference labels. This is standard in-distribution testing of a knowledge-driven system rather than a fitted parameter renamed as prediction, a self-definitional loop, or a self-citation chain that forces the result. No equations or steps equate the reported 0.808 F1 or kappa directly to the ontology construction; the ablation study and comparisons to general VLMs supply independent content. The derivation chain is self-contained against the chosen benchmark.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on the assumption that a manually curated ontology of 27 defect types accurately encodes domain causality and that LLM outputs guided by this ontology remain faithful to the encoded knowledge when answering fuzzy queries.

axioms (2)
  • domain assumption The 27 defect types and their hierarchical causal relationships drawn from literature constitute a sufficient and accurate model of LPBF defect phenomena.
    Invoked when the knowledge base is used to retrieve explanations and mitigation guidance.
  • domain assumption Semantic alignment scores from foundation vision models can be trusted to interpret microscopic defect images without additional calibration on LPBF-specific data.
    Invoked in the multimodal image-assessment module.

pith-pipeline@v0.9.0 · 5532 in / 1595 out tokens · 56465 ms · 2026-05-09T19:12:41.141655+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

48 extracted references · 34 canonical work pages

  1. [1]

    Process Defects Knowledge Modeling in Laser Powder Bed Fusion Additive Manufacturing: An Ontological Framework,

    Hasan, N., Rahman, M. H., Wessman, A., Smith, T. M., and Shafae, M., 2023, “Process Defects Knowledge Modeling in Laser Powder Bed Fusion Additive Manufacturing: An Ontological Framework,” Manuf. Lett., 35(August), pp. 822–

    2023

  2. [2]

    https://doi.org/https://doi.org/10.1016/j.mfglet.2023.08.132

    work page doi:10.1016/j.mfglet.2023.08.132 2023

  3. [3]

    Optimization of Process Parameters for Powder Bed Fusion Additive Manufacturing by Combination of Machine Learning and Finite Element Method: A Conceptual Framework,

    Baturynska, I., Semeniuta, O., and Martinsen, K., 2018, “Optimization of Process Parameters for Powder Bed Fusion Additive Manufacturing by Combination of Machine Learning and Finite Element Method: A Conceptual Framework,” Procedia CIRP, 67, pp. 227–232. https://doi.org/10.1016/j.procir.2017.12.204

    work page doi:10.1016/j.procir.2017.12.204 2018

  4. [4]

    Enhanced Detection of Surface Deformations in LPBF Using Deep Convolutional Neural Networks and Transfer Learning from a Porosity Model,

    Ansari, M. A., Crampton, A., and Mubarak, S. M. J., 2024, “Enhanced Detection of Surface Deformations in LPBF Using Deep Convolutional Neural Networks and Transfer Learning from a Porosity Model,” Sci. Rep., 14(1), pp. 1–

    2024

  5. [5]

    https://doi.org/10.1038/s41598-024-76445-3

    work page doi:10.1038/s41598-024-76445-3

  6. [6]

    Knowledge Graph Embedding Learning System for Defect Diagnosis in Additive Manufacturing,

    Wang, R., and Cheung, C. F., 2023, “Knowledge Graph Embedding Learning System for Defect Diagnosis in Additive Manufacturing,” Comput. Ind., 149(December 2022), p. 103912. https://doi.org/10.1016/j.compind.2023.103912

    work page doi:10.1016/j.compind.2023.103912 2023

  7. [7]

    Artificial Intelligence for Control in Laser -Based Additive Manufacturing: A Systematic Review,

    Sousa, J., Brandau, B., Darabi, R., Sousa, A., Brueckner, F., Reis, A., and Reis, L. P., 2025, “Artificial Intelligence for Control in Laser -Based Additive Manufacturing: A Systematic Review,” IEEE Access, 13(February), pp. 30845– 30860. https://doi.org/10.1109/ACCESS.2025.3537859

    work page doi:10.1109/access.2025.3537859 2025

  8. [8]

    Machine Learning Applications for Quality Improvement in Laser Powder Bed Fusion: A State -of-the-Art Review,

    Zhang, J., Yin, C., Xu, Y., and Sing, S. L., 2024, “Machine Learning Applications for Quality Improvement in Laser Powder Bed Fusion: A State -of-the-Art Review,” Int. J. AI Mater. Des., 1 (1), p. 26. https://doi.org/10.36922/ijamd.2301

    work page doi:10.36922/ijamd.2301 2024

  9. [9]

    Towards Next -Gen Smart Manufacturing Systems: The Explainability Revolution,

    Abhilash, P. M., Luo, X., Liu, Q., Madarkar, R., and Walker, C., 2024, “Towards Next -Gen Smart Manufacturing Systems: The Explainability Revolution,” npj Adv. Manuf., 1(1). https://doi.org/10.1038/s44334-024-00006-9

    work page doi:10.1038/s44334-024-00006-9 2024

  10. [11]

    Conversational LLM -Based Decision Support for Defect Classification in AFM Images,

    Biswas, A., Rade, J., Masud, N., Hasib, M. H. H., Balu, A., Zhang, J., Sarkar, S., Krishnamurthy, A., Ren, J., and Sarkar, A., 2025, “Conversational LLM -Based Decision Support for Defect Classification in AFM Images,” IEEE Open J. Instrum. Meas., 4(June), pp. 1–12. https://doi.org/10.1109/OJIM.2025.3592284

    work page doi:10.1109/ojim.2025.3592284 2025

  11. [12]

    Automatic Detection of Hidden Defects and Qualification of Additively Manufactured Parts Using X-Ray Computed Tomography and Computer Vision,

    Bimrose, M. V., Hu, T., McGregor, D. J., Wang, J., Tawfick, S., Shao, C., Liu, Z., and King, W. P., 2024, “Automatic Detection of Hidden Defects and Qualification of Additively Manufactured Parts Using X-Ray Computed Tomography and Computer Vision,” Manuf. Lett., 41, pp. 1216–1224. https://doi.org/10.1016/j.mfglet.2024.09.147

    work page doi:10.1016/j.mfglet.2024.09.147 2024

  12. [13]

    Industry 5 and the Human in Human -Centric Manufacturing,

    Briken, K., Moore, J., Scholarios, D., Rose, E., and Sherlock, A., 2023, “Industry 5 and the Human in Human -Centric Manufacturing,” Sensors, 23(14), p. 6416

    2023

  13. [14]

    Industry 5.0: The Human-Centric Future of Manufacturing,

    Rajkumar, N., Nachiappan, B., Mathews, A., Radha, V., Viji, C., and Kovilpillai, J. A., 2025, “Industry 5.0: The Human-Centric Future of Manufacturing,” Challenges in Information, Communication and Computing Technology , CRC Press, pp. 562–567

    2025

  14. [15]

    A Survey of LLM -Based Agents in Medicine: How Far Are We from Baymax?,

    Wang, W., Ma, Z., Wang, Z., Wu, C., Ji, J., Chen, W., Li, X., and Yuan, Y., 2025, “A Survey of LLM -Based Agents in Medicine: How Far Are We from Baymax?,” pp. 10345–10359. https://doi.org/10.18653/v1/2025.findings-acl.539

    work page doi:10.18653/v1/2025.findings-acl.539 2025

  15. [16]

    Natural Language -Driven Production Planning : Integrating Large Language Models with Automatic Simulation Model Generation in Manufacturing Systems

    Elbasheer, M., Laili, Y., Longo, F., Solina, V., Tao, Y., and Veltri, P., 2025, “Natural Language -Driven Production Planning : Integrating Large Language Models with Automatic Simulation Model Generation in Manufacturing Systems.”

    2025

  16. [17]

    Jannelli, S

    Ma, Y., Zheng, S., Yang, Z., Pan, H., and Hong, J., 2025, “A Knowledge -Graph Enhanced Large Language Model - Based Fault Diagnostic Reasoning and Maintenance Decision Support Pipeline towards Industry 5.0,” Int. J. Prod. Res. https://doi.org/10.1080/00207543.2025.2472298

    work page doi:10.1080/00207543.2025.2472298 2025

  17. [18]

    CausalKGPT: Industrial Structure Causal Knowledge - Enhanced Large Language Model for Cause Analysis of Quality Problems in Aerospace Product Manufacturing,

    Zhou, B., Li, X., Liu, T., Xu, K., Liu, W., and Bao, J., 2024, “CausalKGPT: Industrial Structure Causal Knowledge - Enhanced Large Language Model for Cause Analysis of Quality Problems in Aerospace Product Manufacturing,” Adv. Eng. Informatics, 59(September 2023), p. 102333. https://doi.org/10.1016/j.aei.2023.102333

    work page doi:10.1016/j.aei.2023.102333 2024

  18. [19]

    Joint Knowledge Graph and Large Language Model for Fault Diagnosis Page 27 of 28 and Its Application in Aviation Assembly,

    Liu, P., Qian, L., Zhao, X., and Tao, B., 2024, “Joint Knowledge Graph and Large Language Model for Fault Diagnosis Page 27 of 28 and Its Application in Aviation Assembly,” IEEE Trans. Ind. Informatics, 20(6), pp. 8160 –8169. https://doi.org/10.1109/TII.2024.3366977

    work page doi:10.1109/tii.2024.3366977 2024

  19. [20]

    AdditiveLLM: Large Language Models Predict Defects in Metals Additive Manufacturing,

    Pak, P., and Barati Farimani, A., 2025, “AdditiveLLM: Large Language Models Predict Defects in Metals Additive Manufacturing,” Addit. Manuf. Lett., 14(June), p. 100292. https://doi.org/10.1016/j.addlet.2025.100292

    work page doi:10.1016/j.addlet.2025.100292 2025

  20. [21]

    Chandrasekhar, J

    Chandrasekhar, A., Chan, J., Ogoke, F., Ajenifujah, O., and Barati Farimani, A., 2024, “AMGPT: A Large Language Model for Contextual Querying in Additive Manufacturing,” Addit. Manuf. Lett., 11(May), p. 100232. https://doi.org/10.1016/j.addlet.2024.100232

    work page doi:10.1016/j.addlet.2024.100232 2024

  21. [22]

    SerpApi: Python Integration

    “SerpApi: Python Integration.”

  22. [23]

    Materials Science and Ontologies,

    Friis, J., Goldbeck, G., Gouttebroze, S., Bleken, F. L., and Ghedini, E., 2024, “Materials Science and Ontologies,” Digitalization and Sustainable Manufacturing, Routledge, pp. 117–135

    2024

  23. [24]

    Semantic Web Ontology for Structured Knowledge Representation and Clinical Decision Support in Eye Diseases,

    Anjum, F., Maqbool, F., Razzaq, M. S., Shehzad, H. M. F., Ali, S., Shah, D., Tahir, M., and Ilyas, M., 2025, “Semantic Web Ontology for Structured Knowledge Representation and Clinical Decision Support in Eye Diseases,” Sci. Rep., 15(1), p. 29986

    2025

  24. [25]

    Metal Additive Manufacturing Defect Formation and Nondestructive Evaluation Detectability,

    Dutton, B., Vesga, W., Waller, J., James, S., Seifi, M., and Seifi, M., 2020, “Metal Additive Manufacturing Defect Formation and Nondestructive Evaluation Detectability,” N. Shamsaei, S. Daniewicz, N. Hrabe, S. Beretta, J. Waller, and M. Seifi, eds., ASTM International, West Conshohocken, PA, pp. 1– 50. https://doi.org/10.1520/STP162020180136

    work page doi:10.1520/stp162020180136 2020

  25. [26]

    Common Defects and Contributing Parameters in Powder Bed Fusion AM Process and Their Classification for Online Monitoring and Control: A Review,

    Malekipour, E., and El -Mounayri, H., 2018, “Common Defects and Contributing Parameters in Powder Bed Fusion AM Process and Their Classification for Online Monitoring and Control: A Review,” Int. J. Adv. Manuf. Technol., 95(1–4), pp. 527–550. https://doi.org/10.1007/s00170-017-1172-6

    work page doi:10.1007/s00170-017-1172-6 2018

  26. [27]

    Defect Formation Mechanisms in Selective Laser Melting: A Review,

    Zhang, B., Li, Y., and Bai, Q., 2017, “Defect Formation Mechanisms in Selective Laser Melting: A Review,” Chinese J. Mech. Eng., 30(3), pp. 515–527

    2017

  27. [28]

    Defects in Metal Additive Manufacturing Processes

    Brennan, M. C., Keist, J. S., and Palmer, T. A., 2021, “Defects in Metal Additive Manufacturing Processes.”

    2021

  28. [29]

    Laser Powder Bed Fusion Process Parameters’ Optimization for Fabrication of Dense IN 625,

    Paraschiv, A., Matache, G., Condruz, M. R., Frigioescu, T. F., and Pambaguian, L., 2022, “Laser Powder Bed Fusion Process Parameters’ Optimization for Fabrication of Dense IN 625,” Materials (Basel)., 15(16). https://doi.org/10.3390/ma15165777

    work page doi:10.3390/ma15165777 2022

  29. [30]

    Kosasih and A

    Ameri, F., Sormaz, D., Psarommatis, F., and Kiritsis, D., 2022, “Industrial Ontologies for Interoperability in Agile and Resilient Manufacturing,” Int. J. Prod. Res., 60(2), pp. 420–441. https://doi.org/10.1080/00207543.2021.1987553

    work page doi:10.1080/00207543.2021.1987553 2022

  30. [31]

    Discontinuities in the Laser Powder Bed Fusion Alloys: A Review,

    Yeganeh, M., Shahryari, Z., Shoushtari, M. T., and Eskandari, M., 2025, “Discontinuities in the Laser Powder Bed Fusion Alloys: A Review,” J. Mater. Res. Technol., 37(June), pp. 3193– 3229. https://doi.org/10.1016/j.jmrt.2025.06.202

    work page doi:10.1016/j.jmrt.2025.06.202 2025

  31. [32]

    Critical Review of LPBF Metal Print Defects Detection: Roles of Selective Sensing Technology,

    Guillen, D., Wahlquist, S., and Ali, A., 2024, “Critical Review of LPBF Metal Print Defects Detection: Roles of Selective Sensing Technology,” Appl. Sci., 14(15). https://doi.org/10.3390/app14156718

    work page doi:10.3390/app14156718 2024

  32. [33]

    Difflib — Helpers for Computing Deltas — Python 3.14.0 Documentation

    “Difflib — Helpers for Computing Deltas — Python 3.14.0 Documentation.” [Online]. Available: https://docs.python.org/3/library/difflib.html. [Accessed: 13-Nov-2025]

    2025

  33. [34]

    SO -Softmax Loss for Discriminable Embedding Learning in CNNs,

    Zhang, Q., Yang, J., Zhang, X., and Cao, T., 2022, “SO -Softmax Loss for Discriminable Embedding Learning in CNNs,” Pattern Recognit., 131, p. 108877. https://doi.org/10.1016/j.patcog.2022.108877

    work page doi:10.1016/j.patcog.2022.108877 2022

  34. [35]

    Towards the next Generation of Machine Learning Models in Additive Manufacturing: A Review of Process Dependent Material Evolution,

    Parsazadeh, M., Sharma, S., and Dahotre, N., 2023, “Towards the next Generation of Machine Learning Models in Additive Manufacturing: A Review of Process Dependent Material Evolution,” Prog. Mater. Sci., 135(September 2022), p. 101102. https://doi.org/10.1016/j.pmatsci.2023.101102

    work page doi:10.1016/j.pmatsci.2023.101102 2023

  35. [36]

    Prediction of Lack- of-Fusion Porosity for Powder Bed Fusion,

    Tang, M., Pistorius, P. C., and Beuth, J. L., 2017, “Prediction of Lack- of-Fusion Porosity for Powder Bed Fusion,” Addit. Manuf., 14, pp. 39–48. https://doi.org/10.1016/j.addma.2016.12.001

    work page doi:10.1016/j.addma.2016.12.001 2017

  36. [37]

    Observation of Keyhole -Mode Laser Melting in Laser Powder -Bed Fusion Additive Manufacturing,

    King, W. E., Barth, H. D., Castillo, V. M., Gallegos, G. F., Gibbs, J. W., Hahn, D. E., Kamath, C., and Rubenchik, A. M., 2014, “Observation of Keyhole -Mode Laser Melting in Laser Powder -Bed Fusion Additive Manufacturing,” J. Mater. Process. Technol., 214(12), pp. 2915–2925. https://doi.org/10.1016/j.jmatprotec.2014.06.005

    work page doi:10.1016/j.jmatprotec.2014.06.005 2014

  37. [38]

    A Holistic Analysis of Laser Powder Bed Fusion Process Page 28 of 28 Parameters for Inconel 625 Superalloy: Microstructural Features and Mechanical Performance,

    Yildiz, R. A., Gokcekaya, O., and Malekan, M., 2026, “A Holistic Analysis of Laser Powder Bed Fusion Process Page 28 of 28 Parameters for Inconel 625 Superalloy: Microstructural Features and Mechanical Performance,” Prog. Addit. Manuf., 11(1), pp. 863–888. https://doi.org/10.1007/s40964-025-01385-x

    work page doi:10.1007/s40964-025-01385-x 2026

  38. [39]

    Confidence Interval for Micro-Averaged F 1 and Macro-Averaged F 1 Scores,

    Takahashi, K., Yamamoto, K., Kuchiba, A., and Koyama, T., 2022, “Confidence Interval for Micro-Averaged F 1 and Macro-Averaged F 1 Scores,” pp. 4961–4972

    2022

  39. [40]

    Microstructural Porosity in Additive Manufacturing: The Formation and Detection of Pores in Metal Parts Fabricated by Powder Bed Fusion,

    Sola, A., and Nouri, A., 2019, “Microstructural Porosity in Additive Manufacturing: The Formation and Detection of Pores in Metal Parts Fabricated by Powder Bed Fusion,” J. Adv. Manuf. Process., 1 (3), pp. 1 –21. https://doi.org/10.1002/amp2.10021

    work page doi:10.1002/amp2.10021 2019

  40. [41]

    Assessing Dependency of Part Properties on the Printing Location in Laser- Powder Bed Fusion Meta l Additive Manufacturing,

    Mussatto, A., Groarke, R., Vijayaraghavan, R. K., Hughes, C., Obeidi, M. A., Doğu, M. N., Yalçin, M. A., McNally, P. J., Delaure, Y., and Brabazon, D., 2022, “Assessing Dependency of Part Properties on the Printing Location in Laser- Powder Bed Fusion Meta l Additive Manufacturing,” Mater. Today Commun., 30(August 2021). https://doi.org/10.1016/j.mtcomm.2...

    work page doi:10.1016/j.mtcomm.2022.103209 2022

  41. [42]

    Directly from Surface to Bulk: Rapid Prediction of Internal Densification in Laser Powder Bed Fusion Additively Manufactured Nickel -Based S uperalloy Using Machine Learning,

    Hu, L., Shi, K., Gu, D., Zhang, H., Chang, M., Yin, M., Xing, J., Wang, R., Tang, K., Feng, K., and Hei, X., 2025, “Directly from Surface to Bulk: Rapid Prediction of Internal Densification in Laser Powder Bed Fusion Additively Manufactured Nickel -Based S uperalloy Using Machine Learning,” Virtual Phys. Prototyp., 2759. https://doi.org/10.1080/17452759.2...

    work page doi:10.1080/17452759.2025.2541829 2025

  42. [43]

    A Simple Scaling Model for Balling Defect Formation during Laser Powder Bed Fusion,

    Lindström, V., Lupo, G., Yang, J., Turlo, V., and Leinenbach, C., 2023, “A Simple Scaling Model for Balling Defect Formation during Laser Powder Bed Fusion,” Addit. Manuf., 63 (June 2022). https://doi.org/10.1016/j.addma.2023.103431

    work page doi:10.1016/j.addma.2023.103431 2023

  43. [44]

    Production of C ylindrical Specimens Based on the Ni -Ti System by Selective Laser Melting from Elementary Powders,

    Vieira de Oliveira, R., Pereira de Lima, Y., Hoisler Sallet, E., Abilio Correa Goncalves, D., Vieira Le Senechal, N., Alves Oliveira Melo, E., Teixeira, R., Freitas Rodrigues, P., Inforcatti Neto, P., and Vicente Lopes da Silva, J., 2021, “Production of C ylindrical Specimens Based on the Ni -Ti System by Selective Laser Melting from Elementary Powders,” ...

    2021

  44. [45]

    Establishing a Process Route for Additive Manufacturing of NiCu- Based Alloy 400: An Alignment of Gas Atomization, Laser Powder Bed Fusion, and Desi gn of Experiments,

    Roth, J. P., Šulák, I., Kruml, T., Polkowski, W., Dudziak, T., Böhlke, P., Krupp, U., and Jahns, K., 2024, “Establishing a Process Route for Additive Manufacturing of NiCu- Based Alloy 400: An Alignment of Gas Atomization, Laser Powder Bed Fusion, and Desi gn of Experiments,” Int. J. Adv. Manuf. Technol., 134(7–8), pp. 3433– 3452. https://doi.org/10.1007/...

    work page doi:10.1007/s00170-024-14328-7 2024

  45. [46]

    Effects of Scanning Strategies, Part Orientation, and Hatching Distance on the Porosity and Hardness of AlSi10Mg Parts Produced by Laser Powder Bed Fusion,

    Dejene, N. D., Tucho, W. M., and Lemu, H. G., 2025, “Effects of Scanning Strategies, Part Orientation, and Hatching Distance on the Porosity and Hardness of AlSi10Mg Parts Produced by Laser Powder Bed Fusion,” J. Manuf. Mater. Process., 9(3). https://doi.org/10.3390/jmmp9030078

    work page doi:10.3390/jmmp9030078 2025

  46. [47]

    In-Situ Sensing, Process Monitoring and Machine Control in Laser Powder Bed Fusion: A Review,

    McCann, R., Obeidi, M. A., Hughes, C., McCarthy, É., Egan, D. S., Vijayaraghavan, R. K., Joshi, A. M., Acinas Garzon, V., Dowling, D. P., McNally, P. J., and Brabazon, D., 2021, “In-Situ Sensing, Process Monitoring and Machine Control in Laser Powder Bed Fusion: A Review,” Addit. Manuf., 45 (April). https://doi.org/10.1016/j.addma.2021.102058

    work page doi:10.1016/j.addma.2021.102058 2021

  47. [48]

    Laser Powder Bed Fusion of Metal Coated Copper Powders,

    Lindström, V., Liashenko, O., Zweiacker, K., Derevianko, S., Morozovych, V., Lyashenko, Y., and Leinenbach, C., 2020, “Laser Powder Bed Fusion of Metal Coated Copper Powders,” Materials (Basel)., 13(16). https://doi.org/10.3390/MA13163493

    work page doi:10.3390/ma13163493 2020

  48. [49]

    Lessons in Biostatistics Interrater Reliability : The Kappa Statistic,

    Mchugh, M. L., “Lessons in Biostatistics Interrater Reliability : The Kappa Statistic,” pp. 276 –282