scholarly journals Machine Learning for Warpage Prediction of Fused Deposition Modelling Processed Parts

2021 ◽  
Author(s):  
Davide Nardi
Keyword(s):  
Machine Learning ◽  
Future Research ◽  
Fused Deposition Modelling ◽  
Analytic Equation ◽  
Fused Deposition ◽  
Part Geometry ◽  
Material Part ◽  
Data Points ◽  
Problem Design ◽  
First Time

Abstract This paper provides a methodology for the application of a machine learning-based framework for fused deposition modelling manufacturing. The approach was developed to take into account the influence of the material, the part geometry, the process parameters on the maximum part warpage defined by the user. The results showed the effectiveness of machine learning for both classification and regression purposes so that the printability of the part is firstly provided, based on the selected warpage threshold, and secondly, the part warpage can be predicted within the problem design space variables, i.e. part material, part height, part length, and layer thickness. The limitations of the use of the analytic equation as a data-points generator are widely discussed, along with the future research based on the obtained preliminary results. In conclusion, the described methodology represents a concrete step towards a first-time-right strategy in the field of manufacturing processes.

An overview of fused deposition modelling (FDM): research, development and process optimisation

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mohammadreza Lalegani Dezaki ◽  
Mohd Khairol Anuar Mohd Ariffin ◽  
Saghi Hatami
Keyword(s):  
Metal Alloys ◽  
Future Research ◽  
Fused Deposition Modelling ◽  
Process Optimisation ◽  
Content Type ◽  
Novel Materials ◽  
Fused Deposition ◽  
Bed Temperature ◽  
Vast Range ◽  
Research Studies

Purpose The purpose of this paper is to review research studies on process optimisation and machine development that lead to the enhancement of final products in various aspects of the fused deposition modelling (FDM) process. Design/methodology/approach An overview of the literature, focussing on process parameters, machine developments and material characterisations. This study investigates recent research studies that studied FDM capabilities in printing a vast range of materials from thermoplastics to metal alloys. Findings FDM is one of the most common techniques in additive manufacturing (AM) processes. Many parameters in this technology have effects on three-dimensional printed products. Therefore, it is necessary to obtain the optimum elements, for example, build orientation, layer thickness, nozzle diameter, infill pattern and bed temperature. By selecting a proper variable range of parameters, the layers adhere strongly and building end-use products of high quality are achievable. A vast range of materials and their properties from polymers to composite-based polymers are presented. Novel techniques to print metal alloys and composites are examined to increase the productivity of the FDM process. Additionally, defects such as shrinkage and warpage are discussed to eliminate the system’s limitations and improve the quality of final products. Multi-axis and mobile machines brought enhancements throughout the process to eliminate obstacles such as staircase defects in the conventional FDM process. In brief, recent developments were identified and a summary of major improvements was discussed in this study for future research. Originality/value This paper is an overview that provides information about research and developments in FDM. This review focusses on process optimisation and obstacles in printing polymers, composites, geopolymers and novel materials. Therefore, machine characteristics were examined to find out the accessibility of printing novel materials for different applications.

A review on advancements in applications of fused deposition modelling process

2020 ◽  
Vol 26 (4) ◽  
pp. 669-687 ◽  
Author(s):  
Sathies T. ◽  
Senthil P. ◽  
Anoop M.S.
Keyword(s):  
Additive Manufacturing ◽  
Research Work ◽  
Rapid Tooling ◽  
Future Research ◽  
Fused Deposition Modelling ◽  
Content Type ◽  
Fused Deposition ◽  
Low Volume ◽  
Customized Products

Purpose Fabrication of customized products in low volume through conventional manufacturing incurs a high cost, longer processing time and huge material waste. Hence, the concept of additive manufacturing (AM) comes into existence and fused deposition modelling (FDM), is at the forefront of researches related to polymer-based additive manufacturing. The purpose of this paper is to summarize the research works carried on the applications of FDM. Design/methodology/approach In the present paper, an extensive review has been performed related to major application areas (such as a sensor, shielding, scaffolding, drug delivery devices, microfluidic devices, rapid tooling, four-dimensional printing, automotive and aerospace, prosthetics and orthosis, fashion and architecture) where FDM has been tested. Finally, a roadmap for future research work in the FDM application has been discussed. As an example for future research scope, a case study on the usage of FDM printed ABS-carbon black composite for solvent sensing is demonstrated. Findings The printability of composite filament through FDM enhanced its application range. Sensors developed using FDM incurs a low cost and produces a result comparable to those conventional techniques. EMI shielding manufactured by FDM is light and non-oxidative. Biodegradable and biocompatible scaffolds of complex shapes are possible to manufacture by FDM. Further, FDM enables the fabrication of on-demand and customized prosthetics and orthosis. Tooling time and cost involved in the manufacturing of low volume customized products are reduced by FDM based rapid tooling technique. Results of the solvent sensing case study indicate that three-dimensional printed conductive polymer composites can sense different solvents. The sensors with a lower thickness (0.6 mm) exhibit better sensitivity. Originality/value This paper outlines the capabilities of FDM and provides information to the user about the different applications possible with FDM.

Impact of 3D-printing structure on the tribological properties of polymers

2020 ◽  
Vol 72 (6) ◽  
pp. 811-818 ◽  
Author(s):  
Muammel M. Hanon ◽  
Róbert Marczis ◽  
László Zsidai
Keyword(s):  
3D Printing ◽  
Tribological Properties ◽  
Future Research ◽  
Fused Deposition Modelling ◽  
Wear Depth ◽  
Printing Process ◽  
Content Type ◽  
Fused Deposition ◽  
Polylactide Acid ◽  
The Impact

Purpose The purpose of this paper is to examine the impact of three-dimensional (3D)-printing process settings (particularly print orientation) on the tribological properties of different polymers. Design/methodology/approach In this study, fused deposition modelling 3D-printing technology was used for fabricating the specimens. To evaluate the influence of print orientation, the test pieces were manufactured horizontally (X) and vertically (Z). The tribological properties of various printed polymers, which are polylactide acid, high tensile/high temperature-polylactide acid and polyethylene terephthalate-glycol have been studied. The tribological tests have been carried out under reciprocating sliding and dry condition. Findings The results show that the presence of various orientations during the 3D-printing process makes a difference in the coefficient of friction and the wear depth values. Findings suggest that printing structure in the horizontal orientation (X) assists in reducing friction and wear. Originality/value To date, there has been very limited research on the tribology of objects produced by 3D printing. This work was made as an attempt to pave the way for future research on the science of tribology of 3D-printed polymers.

Precision investment casting: A state of art review and future trends

2016 ◽  
Vol 230 (12) ◽  
pp. 2143-2164 ◽  
Author(s):  
Sunpreet Singh ◽  
Rupinder Singh
Keyword(s):  
Rapid Prototyping ◽  
Investment Casting ◽  
Biomedical Applications ◽  
Medical Science ◽  
Future Research ◽  
Fused Deposition Modelling ◽  
Future Trends ◽  
Fused Deposition ◽  
Cast Specimen ◽  
State Of Art

Investment casting process is known to its capability of producing clear net shape, high-dimensional accuracy and intricate design. Consistent research effort has been made by various researchers with an objective to explore the world of investment casting. Literature review revealed the effect of processing parameters on output parameters of cast specimen. This article highlights the advancements made and proposed at each step of investment casting and its hybridization with other process. Besides, investment casting has always been known to manufacture parts such as weapons, jewellery item, idols and statues of god and goddess since 3000 BC; this article reviews the present applications and trends in combination of rapid prototyping technique as integrated investment casting to serve in medical science. Advancements in shell moulding with incorporation of fibre and polymer, development of alternative feedstock filament to fused deposition modelling are duly discussed. The aim of this review article is to present state of art review of investment casting since 3200 BC. This article is organized as follows: in section ‘Introduction’, introduction to investment casting steps is given along with researches undertaken at each step; in section ‘Rapid prototyping technique’, background is given on the concept of rapid prototyping technique by examining the various approaches taken in the literature for defining rapid prototyping technique; section ‘Biomedical applications of RPT’ presents the medicine or biomedical applications of investment casting and rapid prototyping technique; section ‘Future trends’ provides some perspectives on future research and section ‘Conclusion’ closes the article by offering conclusions.

scholarly journals Comparing additive manufacturing technologies for customised wrist splints

2015 ◽  
Vol 21 (3) ◽  
pp. 230-243 ◽  
Author(s):  
Abby Megan Paterson ◽  
Richard Bibb ◽  
R. Ian Campbell ◽  
Guy Bingham
Keyword(s):  
Additive Manufacturing ◽  
Upper Extremity ◽  
Digital Design ◽  
Future Research ◽  
Fused Deposition Modelling ◽  
Full Potential ◽  
Content Type ◽  
Fused Deposition ◽  
Am Processes ◽  
Design For Am

Purpose – The purpose of this paper is to compare four different additive manufacturing (AM) processes to assess their suitability in the context of upper extremity splinting. Design/methodology/approach – This paper describes the design characteristics and subsequent fabrication of six different wrist splints using four different AM processes: laser sintering (LS), fused deposition modelling (FDM), stereolithography (SLA) and polyjet material jetting via Objet Connex. The suitability of each process was then compared against competing designs and processes from traditional splinting. The splints were created using a digital design workflow that combined recognised clinical best practice with design for AM principles. Findings – Research concluded that, based on currently available technology, FDM was considered the least suitable AM process for upper extremity splinting. LS, SLA and material jetting show promise for future applications, but further research and development into AM processes, materials and splint design optimisation is required if the full potential is to be realised. Originality/value – Unlike previous work that has applied AM processes to replicate traditional splint designs, the splints described are based on a digital design for AM workflow, incorporating novel features and physical properties not previously possible in clinical splinting. The benefits of AM for customised splint fabrication have been summarised. A range of AM processes have also been evaluated for splinting, exposing the limitations of existing technology, demonstrating novel and advantageous design features and opportunities for future research.

scholarly journals Enhancing Surface Fault Detection Using Machine Learning for 3D Printed Products

2021 ◽  
Vol 4 (2) ◽  
pp. 34
Author(s):  
Vaibhav Kadam ◽  
Satish Kumar ◽  
Arunkumar Bongale ◽  
Seema Wazarkar ◽  
Pooja Kamat ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fault Detection ◽  
Computer Aided Design ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Fused Deposition Modelling ◽  
Layer By Layer ◽  
Fused Deposition ◽  
Detection Approach ◽  
3D Printed

In the era of Industry 4.0, the idea of 3D printed products has gained momentum and is also proving to be beneficial in terms of financial and time efforts. These products are physically built layer-by-layer based on the digital Computer Aided Design (CAD) inputs. Nonetheless, 3D printed products are still subjected to defects due to variation in properties and structure, which leads to deterioration in the quality of printed products. Detection of these errors at each layer level of the product is of prime importance. This paper provides the methodology for layer-wise anomaly detection using an ensemble of machine learning algorithms and pre-trained models. The proposed combination is trained offline and implemented online for fault detection. The current work provides an experimental comparative study of different pre-trained models with machine learning algorithms for monitoring and fault detection in Fused Deposition Modelling (FDM). The results showed that the combination of the Alexnet and SVM algorithm has given the maximum accuracy. The proposed fault detection approach has low experimental and computing costs, which can easily be implemented for real-time fault detection.

scholarly journals Effects of In-Process Temperatures and Blending Polymers on Acrylonitrile Butadiene Styrene Blends

Inventions ◽  
2021 ◽  
Vol 6 (4) ◽  
pp. 93
Author(s):  
Muhammad Harris ◽  
Johan Potgieter ◽  
Hammad Mohsin ◽  
Karnika De Silva ◽  
Marie-Joo Le Guen
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Large Scale ◽  
Acrylonitrile Butadiene Styrene ◽  
Fused Deposition Modelling ◽  
Fused Deposition ◽  
High Thermal Resistance ◽  
3D Printed ◽  
First Time ◽  
Butadiene Styrene

Acrylonitrile butadiene styrene (ABS) is a renowned commodity polymer for additive manufacturing, particularly fused deposition modelling (FDM). The recent large-scale applications of 3D-printed ABS require stable mechanical properties than ever needed. However, thermochemical scission of butadiene bonds is one of the contemporary challenges affecting the overall ABS stability. In this regard, literature reports melt-blending of ABS with different polymers with high thermal resistance. However, the comparison for the effects of different polymers on tensile strength of 3D-printed ABS blends was not yet reported. Furthermore, the cumulative studies comprising both blended polymers and in-process thermal variables for FDM were not yet presented as well. This research, for the first time, presents the statistical comparison of tensile properties for the added polymers and in-process thermal variables (printing temperature and build surface temperature). The research presents Fourier transform infrared spectroscopy (FTIR) and thermogravimetric analysis (TGA) to explain the thermochemical reasons behind achieved mechanical properties. Overall, ABS blend with PP shows high tensile strength (≈31 MPa) at different combinations of in-process parameters. Furthermore, some commonalities among both blends are noted, i.e., the tensile strength improves with increase of surface (bed) and printing temperature.

The fabrication of long carbon fiber reinforced polylactic acid composites via fused deposition modelling: Experimental analysis and machine learning

2020 ◽  
pp. 002199832097217
Author(s):  
Chao Hu ◽  
Winson NG Joon Hau ◽  
Weiqi Chen ◽  
Qing-Hua Qin
Keyword(s):  
Machine Learning ◽  
Carbon Fiber ◽  
Polylactic Acid ◽  
Experimental Analysis ◽  
Hot Spot ◽  
Morphological Properties ◽  
Fused Deposition Modelling ◽  
Fiber Reinforced ◽  
Fused Deposition ◽  
Long Carbon Fiber

As a promising technology to revolutionize traditional manufacturing processes, additive manufacturing has received great attention by virtue of its cost savings, minimum material waste, and tool-less production of complex geometries. The development of fiber-reinforced composites via this technique that exhibits superior strength is thus becoming a hot spot in recent years. This paper focused on the 3 D printing of polylactic acid (PLA) composites with the incorporation of chopped long carbon fiber (CF) with an average length of 4.6 mm via FDM fabrication. By varying its loading quantity, the effect of CF contents on the mechanical, thermal, and morphological properties of these 3 D printed composites was thoroughly investigated. The results showed that with the increase of CF contents, all assessed properties of CF/PLA composites including tensile properties, flexural properties, hardness, and thermal conductivity were effectively improved compared to the neat PLA. Their performance exhibited the same upward-downward-upward trend with the addition of CF. It can be attributed to the mutual influence generated from inter-/intra filament porosities and the high stiffness of CF. Meanwhile, a machine learning technique, Gaussian Process modeling was also introduced in this study for the property prediction of the composites. In comparison with the experimental analysis, the optimal CF content of 6.7 wt% with the best overall performance was predicted using this model, which was very close to the best experimental results at 5 wt% CF.

Online Detection and Prediction of Fused Deposition Modelled Parts Using Artificial Intelligence

2022 ◽  
pp. 194-209
Author(s):  
Sachin Salunkhe ◽  
G. Kanagachidambaresan ◽  
C. Rajkumar ◽  
K. Jayanthi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Critical Issue ◽  
Extrusion Process ◽  
Human Interaction ◽  
Fused Deposition Modelling ◽  
Fused Deposition ◽  
Machine Learning Model ◽  
Proposed Model ◽  
Complex Parts

Fused deposition modelling (FDM) is a technology used for filament deposition of heated plastic filaments by a given pattern by the melted extrusion process. Delamination is a critical issue of FDM's incredibly complex parts. In this chapter, the artificial intelligence (machine learning) model is used for online detections and prediction of FDM parts. The proposed machine learning and convolutional neural network model is capable of online detect delamination of FDM parts. The proposed model can also be applied for different types of additive manufacturing materials with less human interaction.

Sign in / Sign up

Export Citation Format

Share Document