Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites
Source abstract
Abstract
This study aimed at applying machine learning (ML) methods to analyze dynamic strength of 3D-printed polypropylene (PP)-based composites. The dynamic strength of additive manufactured PP-based composites with different fillers and printing parameters was investigated by split Hopkinson pressure bars. Based on experimental results, six machine learning approaches were applied to express the relationships between the dynamic strength and materials as well as printing parameters. The performance of the six machine learning algorithms with relatively small training datasets was evaluated. The comparison results showed that artificial neural network could achieve the highest prediction accuracy but with relatively low computational efficiency, whereas the support vector regression could provide satisfactory prediction with both good accuracy and efficiency. The extreme gradient boosting and random forest approaches were recommended if the importance of input was required.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Innovations in Concrete and Construction Materials · Injection Molding Process and Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (76)
Show source-provided references
1. Additive manufacturing applications in medical cases: a literature based review
2. 2 - review of additive manufacturing technologies and applications in the aerospace industry
3. The effect of additive manufacturing adoption on supply chain flexibility and performance: an empirical analysis from the automotive industry10.1016/j.ijpe.2020.107689 ↗
4. Additive manufacturing (3D printing): a review of materials, methods, applications and challenges10.1016/j.compositesb.2018.02.012 ↗
5. Design of FDM 3D printed polymers: an experimental-modelling methodology for the prediction of mechanical properties10.1016/j.matdes.2019.108414 ↗
6. A critical review on the fused deposition modeling of thermoplastic polymer composites10.1016/j.compositesb.2020.108336 ↗
7. The mechanical testing and performance analysis of polymer-fibre composites prepared through the additive manufacturing10.1016/j.polymertesting.2020.106925 ↗
8. Effect of fused deposition modeling process parameters on the mechanical properties of a filled polypropylene10.1007/s40964-018-0053-3 ↗
9. FDM process parameters influence over the mechanical properties of polymer specimens: a review10.1016/j.polymertesting.2018.05.020 ↗
10. Long-term creep behavior prediction of polymethacrylimide foams using artificial neural networks10.1016/j.polymertesting.2020.106893 ↗
11. Composite modeling and analysis for fabrication of FDM prototypes with locally controlled properties10.1016/S1526-6125(02)70139-4 ↗
12. Raster angle mechanics in fused deposition modelling10.1177/0021998313519153 ↗
13. Mechanical property characterization and simulation of fused deposition modeling Polycarbonate parts10.1016/j.matdes.2015.06.074 ↗
14. A finite element approach for the prediction of the mechanical behaviour of layered composites produced by Continuous Filament Fabrication (CFF)10.1016/j.polymertesting.2021.107181 ↗
15. An integrated prediction model for processing related yield strength of extrusion-based additive manufactured polymers
16. Experimental investigation and empirical modelling of FDM process for compressive strength improvement10.1016/j.jare.2011.05.001 ↗
17. Machine learning in predicting mechanical behavior of additively manufactured parts10.1016/j.jmrt.2021.07.004 ↗
18. Recycling effects on the rheological and thermomechanical properties of polypropylene-based composites10.1016/j.matdes.2011.04.049 ↗
19. Parametric appraisal of mechanical property of fused deposition modelling processed parts10.1016/j.matdes.2009.06.016 ↗
20. Artificial neural network algorithms for 3D printing10.3390/ma14010163 ↗
21. Predictive ANN models for varying filler content for cotton fiber/PVC composites based on experimental load displacement curves10.1016/j.compstruct.2020.112885 ↗
22. Prediction of load-displacement curve in a complex structure using artificial neural networks: a study on a long bone10.1016/j.ijengsci.2020.103319 ↗
23. Combining simulation and machine learning as digital twin for the manufacturing of overmolded thermoplastic composites
24. Surrogate-based optimization, real-world
25. Modelling for digital twins—potential role of surrogate models10.3390/pr9030476 ↗
26. Investigation of dynamic elastic deformation of parts processed by fused deposition modeling additive manufacturing
27. Experimental study on the 3D‐printed plastic parts and predicting the mechanical properties using artificial neural networks10.1002/pat.3960 ↗
28. Prediction of tensile strength in fused deposition modeling process using artificial neural network technique10.1063/5.0034016 ↗
29. Prediction of the tensile strength of polylactic acid fused deposition models using artificial neural network technique10.1016/j.matpr.2020.01.199 ↗
30. Parameter effects and process modelling of Polyamide 12 3D-printed parts strength and toughness
31. An investigation on sliding wear of FDM built parts10.1016/j.cirpj.2011.08.003 ↗
32. Influence of processing parameters on creep and recovery behavior of FDM manufactured part using definitive screening design and ANN10.1108/RPJ-12-2015-0198 ↗
33. Analysis and prediction of printable bridge length in fused deposition modelling based on back propagation neural network10.1080/17452759.2019.1576010 ↗
34. Effects of fused deposition modeling process parameters on tensile, dynamic mechanical properties of 3D printed polylactic acid materials10.1016/j.polymertesting.2020.106483 ↗
35. An example of machine learning applied in additive manufacturing
36. Machine learning to optimize additive manufacturing parameters for laser powder bed fusion of Inconel 718
37. Simple method to construct process maps for additive manufacturing using a support vector machine
38. Wang · 2020 · 101538
39. Compressive behaviors of 3D printed polypropylene-based composites at low and high strain rates10.1016/j.polymertesting.2021.107321 ↗
40. Optimization of the filler concentration on fused filament fabrication 3D printed polypropylene with titanium dioxide nanocomposites10.3390/ma14113076 ↗
41. Characterizing the mechanical properties of fused deposition modelling natural fiber recycled polypropylene composites10.3390/jcs1010007 ↗
42. Mechanical reinforcement course of 3D printed polypropylene–antimony doped Tin Oxide nanocomposites versus filler loading
43. Thermotropic liquid crystalline polymer reinforced polypropylene composites enhanced with carbon nanotubes for use in fused filament fabrication10.1002/pc.26134 ↗
44. Preparation of polypropylene/short glass fiber composite as Fused Deposition Modeling (FDM) filament10.1016/j.rinp.2018.11.065 ↗
45. Impact absorption capacity of 3D-printed components fabricated by fused deposition modelling10.1016/j.matdes.2016.03.154 ↗
46. Evaluation of the head protection effectiveness of cyclist helmets using full-scale computational biomechanics modelling of cycling accidents10.1016/j.jsr.2021.11.005 ↗
47. On crashworthiness behaviors of 3D printed multi-cell filled thin-walled structures10.1016/j.engstruct.2022.113907 ↗
48. Recycled PP/EPDM/talc reinforced with bamboo fiber: assessment of fiber and compatibilizer content on properties using factorial design10.1016/j.polymertesting.2017.05.022 ↗
49. Recycling of pp/epdm/talc car bumpers, Chem
50. Polymer composites for the automotive industry: characterisation of the recycling effect on the strain rate sensitivity10.1080/13588260802030745 ↗
51. Bahlouli · 2009 · 703
52. Strain rate effects on the mechanical response of polypropylene-based composites deformed at small strains
53. Characterization of contamination effects for two polypropylene-based materials10.1002/pen.21451 ↗
54. Mechanical behavior of recycled polypropylene composites under tensile, bending, and creep loading: experimental and modeling10.1115/1.4004051 ↗
55. Constitutive modeling of the tensile behavior of recycled polypropylene-based composites10.3390/ma12152419 ↗
56. Parameter effects and process modeling of FFF-TPU mechanical response
57. A review on split Hopkinson bar experiments on the dynamic characterisation of concrete10.1016/j.conbuildmat.2018.09.187 ↗
58. W.W. Chen, B. Song, Split Hopkinson (Kolsky) Bar: Design, Testing and Applications, Springer Science & Business Media2010.10.1007/978-1-4419-7982-7 ↗
59. Hopkinson bar experimental technique: a critical review10.1115/1.1704626 ↗
60. Review of experimental techniques for high rate deformation and shock studies10.1016/j.ijimpeng.2004.03.005 ↗
61. Some experiments with the split hopkinson pressure bar10.1016/0022-5096(64)90028-6 ↗
62. Impact response of recycled polypropylene-based composites under a wide range of temperature: effect of filler content and recycling10.1016/j.compscitech.2014.02.014 ↗
63. Dynamic mechanical properties of cement and asphalt mortar based on SHPB test10.1016/j.conbuildmat.2014.07.092 ↗
64. Experimental investigation on the dynamic behavior of 3D printed CF-PEKK composite under cyclic uniaxial compression10.1016/j.compstruct.2020.112474 ↗
65. Strain rate effects on the dynamic compressive response and the failure behavior of polyester matrix10.1016/j.compositesb.2019.107040 ↗
66. Scikit-learn: machine learning in Python
67. XGBoost: a scalable tree boosting system
68. Comparison of design of experiment methods for modeling injection molding experiments using artificial neural networks10.1016/j.jmapro.2020.11.011 ↗
69. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization10.1023/A:1007607513941 ↗
70. Decision tree methods: applications for classification and prediction
71. Random forest in remote sensing: a review of applications and future directions10.1016/j.isprsjprs.2016.01.011 ↗
72. A novel nonlinear regression model of SVR as a substitute for ANN to predict conductivity of MWCNT-CuO/water hybrid nanofluid based on empirical data10.1016/j.physa.2019.01.055 ↗
73. Awad · 2015 · 67
74. Zhang · 2018 · 1
75. Learning representations by back-propagating errors10.1038/323533a0 ↗
76. Prediction of surface roughness in extrusion-based additive manufacturing with machine learning10.1016/j.rcim.2019.01.004 ↗