A machine learning case study with limited data for prediction of carbon fiber mechanical properties

2019 ◽  
Vol 105 ◽  
pp. 123-132 ◽  
Author(s):  
Gelayol Golkarnarenji ◽  
Minoo Naebe ◽  
Khashayar Badii ◽  
Abbas S. Milani ◽  
Reza N. Jazar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Carbon Fiber ◽  
Limited Data

Optimization of Design Process of Fused Filament Fabrication (FFF) 3D Printing

2018 ◽  
Author(s):  
Jaeyoon Kim ◽  
Bruce S. Kang
Keyword(s):  
Mechanical Properties ◽  
Carbon Fiber ◽  
3D Printing ◽  
Design Process ◽  
Design Methodology ◽  
Tool Path ◽  
Fiber Reinforced ◽  
Fused Filament Fabrication ◽  
Principal Directions

Fused Filament Fabrication (FFF) is one of the most common Additive Manufacturing (AM) technologies for thermoplastic materials. PLA, ABS, and nylon have generally been used for prototype development. With the development of carbon fiber reinforced polymer (CFRP) filament for FFF, AM parts with improved strength and functionality can be realized. While mechanical properties of various CFRP have been well studied, design methodology for structural optimization of CFRP parts remains an active research area. In this paper, a systematic optimization of design process of FFF 3D printing methodology is proposed for CFRP. Starting with standard coupon specimen tests including tensile, bending, and creep tests to obtain mechanical properties of CFRP. Finite element analyses (FEA) are conducted to find principal directions of the AM part and computed principal directions are utilized as fiber orientations. Then, the connecting lines of principal directions are used to develop a customized tool-path in FFF 3D printing to extrude fibers aligned with principal directions. Since currently available infill-patterns in 3D printing cannot precisely draw customized lines, a specific tool-path algorithm has been developed to distribute fibers with the desired orientations. To predict/assess mechanical behavior of the AM part, 3D printing process was simulated followed by FEA to obtain the anisotropic structural behavior induced by the customized tool-path. To demonstrate the design/manufacturing methodology, spur gears of a ball milling machine were selected as a case study and carbon fiber reinforced nylon filament was chosen as the AM materials. Relevant compression tests were conducted to assess their performance compared with those printed at regular tool-path patterns. Preliminary results show that CFRP gear printed by customized tool-path has about 8% higher stiffness than those printed by regular patterns. Also, flow distribution of printed fibers was verified using scanning electron microscope (SEM). SEM images showed that approximately 91% of fibers were oriented as intended. In summary, assisted by FEA, a customized 3D printing tool-path for CFRP has been developed with a case study to verify the proposed AM design methodology.

scholarly journals Reuse and upcycling of thermoset prepreg scrap: Case study with out-of-autoclave carbon fiber/epoxy prepreg

2017 ◽  
Vol 52 (3) ◽  
pp. 341-360 ◽  
Author(s):  
Gaurav Nilakantan ◽  
Steven Nutt
Keyword(s):  
Mechanical Properties ◽  
Carbon Fiber ◽  
Composite Laminates ◽  
Processing Conditions ◽  
End Products ◽  
And Performance ◽  
Out Of Autoclave ◽  
Carbon Fiber Epoxy ◽  
Microstructure And Performance

A large amount of uncured thermoset prepreg scrap is generated during manufacturing, including both ply cutter trim waste and out-of-spec material. While techniques to recycle end-of-life cured composite waste and reclaim carbon fiber are well established and commercialized, there is little effort made presently towards reusing uncured scrap prepreg. Here, we present a viable and scalable technique to process scrap prepreg into intermediate forms that can be readily manufactured into commercial end-products. Using out-of-autoclave carbon fiber/epoxy prepreg as an example, we report the mechanical properties, microstructure, and performance of composite laminates fabricated with scrap prepreg under various processing conditions. Demonstrator parts manufactured with scrap prepreg are also presented.

Paper2Wire – A Case Study of User-Centred Development of Machine Learning Tools for UX Designers

i-com ◽  
2021 ◽  
Vol 20 (1) ◽  
pp. 19-32
Author(s):  
Daniel Buschek ◽  
Charlotte Anlauff ◽  
Florian Lachner
Keyword(s):  
Machine Learning ◽  
Development Process ◽  
User Study ◽  
Concept Development ◽  
Lessons Learned ◽  
Design Tool ◽  
Learning Tools ◽  
Interface Elements ◽  
Industry Partner

Abstract This paper reflects on a case study of a user-centred concept development process for a Machine Learning (ML) based design tool, conducted at an industry partner. The resulting concept uses ML to match graphical user interface elements in sketches on paper to their digital counterparts to create consistent wireframes. A user study (N=20) with a working prototype shows that this concept is preferred by designers, compared to the previous manual procedure. Reflecting on our process and findings we discuss lessons learned for developing ML tools that respect practitioners’ needs and practices.

Sign in / Sign up

Export Citation Format

Share Document