STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Polymer & Composites Original Research Special issue

Explainable Machine Learning for Process Parameter Optimization in Gradient 3D-Printed Polymer Composites

  1. Harish Reddy Gantla Department of Computer Science and Engineering, Vignan Institute of Technology and Science, Hyderabad
  2. Harish Chandra Mohanta Department of Electronics and Communication Engineering, Centurion University of Technology and Management
  3. Deepika Singh Singraur Department of Mechanical Engineering, SGT University, Gurugram
  4. Sandeep Bansal Department of Mechanical Engineering, SGT University, Gurugram
  5. Varinder Singh School of Engineering and Technology, CGC University, Mohali
  6. Pacha Supriya Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Guntur

Abstract

The explainable machine learning-based structure may be employed to achieve a favorable process parameter of the graduate 3D-printed polymer composite structures to improve the mechanical and thermal properties without compromising the transparency of the decisions made during the fabrication process. Gradient composite specimens were made by systematically varied process parameters like nozzle temperature, raster orientation, deposition speed, gradient transition rate and fused filament fabrication. A predictive model of tensile strength and thermal conductivity was developed as a supervised learning model using process-property data, which was obtained experimentally. Later, explainable parameter attribution methods were applied to attribute the effect of the parameters of individual fabrication to explain the performance of composite. Optimization of the parameter setting led to potential tensile strength increase of 14.6 % and thermal conductivity increase of 9.2 % relative to process settings at the baseline. The predictive model recorded coefficient of determination (R2) of 0.937 which meant high level of agreement between the predictive and experimentally measured composite performance. The explainability-based optimization strategy contributes to the process of parameter selection as well as promoting reliability in gradient polymer composite manufacturing processes. The framework suggested here is an incorporation of predictive modeling and interpretable analytics provided as a transparent yet performance-efficient solution to optimization of processes in gradient additive manufacturing of polymer composite systems.

Keywords

References (34)

  1. Kharate N, Anerao P, Kulkarni A, Abdullah M. Explainable AI Techniques for Comprehensive Analysis of the Relationship between Process Parameters and Material Properties in FDM-Based 3D-Printed Biocomposites. Journal of Manufacturing and Materials Processing. 2024;8(4):171. doi:10.3390/jmmp8040171
  2. Shanto TA. Leveraging Large Language Models for Process Parameter Optimization in 3D-Printed ABS Polymer Specimens. 2025. doi:10.21203/rs.3.rs-7437594/v1
  3. Hiralal Dhage B, Khedkar NK. Predictive machine learning and printing parameter optimization for enhanced impact performance of 3D-printed Onyx-Kevlar composites. Discover Materials. 2025;5(1). doi:10.1007/s43939-025-00307-6
  4. Patil S, Sathish T, Nelson M, Ghodhbani R, Tarawneh B, Othman NA. Optimization and Prediction of Tensile Strength in 3D‐Printed PLA/HAp Composites Using Response Surface Methodology and Integrated Machine Learning Technique. Journal of Applied Polymer Science. 2025;142(39). doi:10.1002/app.57505
  5. Abdullah AC, Ozarslan O, Farshi SS, Dabbagh SR, Tasoglu S. Machine learning‐enabled optimization of melt electro‐writing three‐dimensional printing. Aggregate. 2024;5(3). doi:10.1002/agt2.495
  6. Yossef M, Noureldin M, Alqabbany A. Explainable artificial intelligence framework for FRP composites design. Composite Structures. 2024;341:118190. doi:10.1016/j.compstruct.2024.118190
  7. Shi X, Sun Y, Zhang H, Yuan Z, Tian H, Liu H. 3D printed piezoelectric composite filament width and height prediction using individual and stacking ensemble of machine learning algorithms. MATEC Web of Conferences. 2024;401:02009. doi:10.1051/matecconf/202440102009
  8. Ziadia A, Habibi M, Kelouwani S. Machine Learning Study of the Effect of Process Parameters on Tensile Strength of FFF PLA and PLA-CF. Eng. 2023;4(4):2741-2763. doi:10.3390/eng4040156
  9. Kamarulzaman AF, Alli YA, Anuar H, Isiolaotan M, Manshor MR, Atinuke BO, et al. The optimization of 3D printed PLA/EPO/Lignin Biocomposite’s tensile strength using three different supervised learning applications. International Journal of Progressive Sciences and Technologies. 2025;51(1):16. doi:10.52155/ijpsat.v51.1.7250
  10. Padhy C, Simhambhatla S, Bhattacharjee D. Ensembled Surrogate Assisted Material Extrusion Based 3D Printing Process Parameter Optimization for Enhanced Mechanical Properties of PEEK. 2023. doi:10.21203/rs.3.rs-3427921/v1
  11. Kim Y, Park SH. Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique. Advanced Intelligent Systems. 2023;5(7). doi:10.1002/aisy.202200462
  12. Gim J, Lin CY, Turng LS. In-mold condition-centered and explainable artificial intelligence-based (IMC-XAI) process optimization for injection molding. Journal of Manufacturing Systems. 2024;72:196-213. doi:10.1016/j.jmsy.2023.11.013
  13. Dwivedi K, Joshi S, Nair R, Sapre MS, Jatti V. Optimizing 3D printed diamond lattice structure and investigating the influence of process parameters on their mechanical integrity using nature-inspired machine learning algorithms. Materials Today Communications. 2024;38:108233. doi:10.1016/j.mtcomm.2024.108233
  14. Schoenholz C, Zobeiry N. An Accelerated Process Optimization Method to Minimize Deformations in Composites Using Theory-guided Probabilistic Machine Learning. Composites Part A: Applied Science and Manufacturing. 2024;176:107842. doi:10.1016/j.compositesa.2023.107842
  15. Ghandehari A, Tavares-Negrete JA, Rajendran J, Yi Q, Esfandyarpour R. Optimization of process parameters in 3D-nanomaterials printing for enhanced uniformity, quality, and dimensional precision using physics-guided artificial neural network. Discover Nano. 2024;19(1). doi:10.1186/s11671-024-04155-w
  16. Park JM, Jung J, Lee S, Park H, Kim YW, Yu JH. Data-driven Approach to Explore the Contribution of Process Parameters for Laser Powder Bed Fusion of a Ti-6Al-4V Alloy. journal of Korean Powder Metallurgy Institute. 2024;31(2):137-145. doi:10.4150/jpm.2024.00038
  17. Kadri K, Ali B, Jaradat MA, Alkhader M, Abuzaid W. Hybrid Intelligent-Assisted Approach for Process Parameters Optimization to Enhance the Sustainable Manufacturing of Thermoplastic Laminates. Key Engineering Materials. 2024;1002:13-23. doi:10.4028/p-dar3uj
  18. Pelzer L, Schulze T, Buschmann D, Enslin C, Schmitt R, Hopmann C. Acquiring Process Knowledge in Extrusion-Based Additive Manufacturing via Interpretable Machine Learning. Polymers. 2023;15(17):3509. doi:10.3390/polym15173509
  19. Samadiani N, Barnard AS, Gunasegaram D, Fayyazifar N. Best practices for machine learning strategies aimed at process parameter development in powder bed fusion additive manufacturing. Journal of Intelligent Manufacturing. 2024;36(7):4477-4517. doi:10.1007/s10845-024-02490-4
  20. Yeh HP, Bayat M, Arzani A, Hattel JH. Accelerated process parameter selection of polymer-based selective laser sintering via hybrid physics-informed neural network and finite element surrogate modelling. Applied Mathematical Modelling. 2024;130:693-712. doi:10.1016/j.apm.2024.03.030
  21. Saleh S, Guo YB, Guo WG. Enhanced Counterfactual Explanations for Optimizing Three-Dimensional Printing Parameters Using SHAP and Nearest-Neighbor Constraints With Physics-Based Validation. Journal of Manufacturing Science and Engineering. 2025;147(11). doi:10.1115/1.4069715
  22. Zhang Z, Wang Y, Wang W. Machine Learning in Gel-Based Additive Manufacturing: From Material Design to Process Optimization. Gels. 2025;11(8):582. doi:10.3390/gels11080582
  23. Okolo C. Investigation of the influence of AI-controlled process parameter adjustment on the mechanical properties of LBPF-manufactured parts. Materials Research Proceedings. 2025;54:218-227. doi:10.21741/9781644903599-24
  24. Heistracher C, Wachsenegger A, Weißenfeld A, Casas P. MOXAI – Manufacturing Optimization through Model-Agnostic Explainable AI and Data-Driven Process Tuning. PHM Society European Conference. 2024;8(1):7. doi:10.36001/phme.2024.v8i1.4111
  25. Raja S, Mohammad Iliyas AJ, Vishnu PS, John Rajan A, Rusho MA, Reda Refaai MR, et al. Sustainable manufacturing of FDM-manufactured composite impellers using hybrid machine learning and simulation-based optimization. Materials Science in Additive Manufacturing. 2025;4(3):025200033. doi:10.36922/msam025200033
  26. Toprak CB, Dogruer CU. Optimal process parameter determination in selective laser melting via machine learning-guided sequential quadratic programing. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. 2024;239(3):807-820. doi:10.1177/09544062241288948
  27. Ramasubbu R, Kayambu A, Palanisamy S, Ayrilmis N. Mechanical properties of epoxy composites reinforced with Areca catechu fibers containing silicon carbide. BioResources. 2024;19(2):2353-2370. doi:10.15376/biores.19.2.2353-2370
  28. Pelzer L, Posada-Moreno AF, Müller K, Greb C, Hopmann C. Process Parameter Prediction for Fused Deposition Modeling Using Invertible Neural Networks. Polymers. 2023;15(8):1884. doi:10.3390/polym15081884
  29. Gawade V, Guo YB, Guo WG. Layer-Wise Emission Prediction for Laser Powder Bed Fusion With an Attribution-Based Explainable Deep Learning Model. Journal of Manufacturing Science and Engineering. 2025;147(8). doi:10.1115/1.4068937
  30. Dharmadhikari S, Menon N, Basak A. A reinforcement learning approach for process parameter optimization in additive manufacturing. Additive Manufacturing. 2023;71:103556. doi:10.1016/j.addma.2023.103556
  31. Guo W, Wang Y, Zhao X, Li W, Yan K, Deng M, et al. Optimizing Parameters for Microcellular Foaming and In‐Mold Decoration of Talc/ PP Composites Using PSOBP Neural Network. Journal of Applied Polymer Science. 2025;142(47). doi:10.1002/app.57817
  32. Hoffmann M, Pai SM, Albuquerque RQ, Kastl S, Ruckdäschel H. Active Learning‐Driven Inverse Design of Polyurethane Foams for EV Battery Applications. Journal of Polymer Science. 2025;63(21):4621-4630. doi:10.1002/pol.20250250
  33. Meinhold KL, Tankersley T, Darlington R, Robinson JL. Mandrel Diameter Is a Dominating Parameter for Fiber Alignment Control in Rotating Mandrel Electrospinning Systems. Journal of Applied Polymer Science. 2025;142(34). doi:10.1002/app.57364
  34. Sivasubramanian P, Palanisamy S, et al. Mater Res Express. 2023;10:08550.
Support