FDM 3D Printing Dataset: Printer Type, Materials, Process Parameters, and Tensile, Hardness and Roughness Test Results

Dataset of FDM 3D Printing Process Parameters and Mechanical Properties for Multi-Material Characterization This dataset is "Aktepe, E., & Ergün, U. (2026). HMQ-ES-Stack-GBR: A ​​Hybrid Ensemble Learning Model for Mechanical and Physical Quality Prediction in FDM 3D Printing. Micromachines, 17(7), 859. https://doi.org/10.3390/mi17070859" is the dataset used in this study. This dataset contains comprehensive experimental data on the fused deposition modeling (FDM) 3D printing process, focusing on the relationship between manufacturing parameters and the resulting physical and mechanical properties of printed parts. It comprises 500 unique experimental runs/samples and covers a diverse range of polymer materials and printing configurations. The dataset is highly valuable for researchers in additive manufacturing, materials science, and machine learning practitioners looking to predict printed part quality, optimize manufacturing processes, or build surrogate models for mechanical behavior. Dataset Structure & Parameters: 1. Input / Process Parameters: • Printer Type: Open vs. Closed chamber printers. • Material Types (10 different filaments): PLA+, PLA, PLA phosphor, PLA-CF (carbon fiber), PLA-transparent , PETG, rPET (recycled PET), PP, TPU, and ABS. • Layer Thickness (mm): Variable layer resolutions. • Infill Density (%): Variable infill percentages. • Infill Pattern (15 different patterns): Grid, Triangles, Zigzag, Lines, Cubic, Quarter Cubic, Cross, Gyroid, Cubic Subdivision, Tri-hexagon, Lightning, Cross3D, Concentric, and Octet. • Printing Speed (mm/s): Controlled extrusion speeds. • Specimen Dimensions: Width (mm) and Thickness (mm) of each printed sample. 2. Output / Characterization Results: • Surface Roughness (Roughness AVG - µm): Average surface roughness measurements. • Hardness (Hardness AVG): Shore hardness characterization. • Tensile Properties: Peak Load (N), Peak Stress (kPa), Strain at Break (mm/mm), and Elastic Modulus (MPa). Associated Publication: If you use this dataset in your research, please cite our corresponding paper: Aktepe, E., & Ergün, U. (2026). HMQ-ES-Stack-GBR: A Hybrid Ensemble Learning Model for Mechanical and Physical Quality Prediction in FDM 3D Printing. Micromachines. Acknowledgments: This research was supported by Afyon Kocatepe University Scientific Research Projects, project number 25.FEN.BİL.11. Furthermore, this article is derived from the doctoral thesis entitled “Development of a Hybrid Artificial Intelligence-Based Quality Prediction and Defect Detection System in 3D Printing Processes”. Thanks are extended to the Izmir Katip Çelebi University Central Research Laboratory for providing support in tensile strength test analyses.