scholarly journals Nozzle Thermal Estimation for Fused Filament Fabricating 3D Printer Using Temporal Convolutional Neural Networks

2021 ◽  
Vol 11 (14) ◽  
pp. 6424
Author(s):  
Danielle Jaye S. Agron ◽  
Jae-Min Lee ◽  
Dong-Seong Kim
Keyword(s):  
Fused Deposition Modeling ◽  
Performance Metrics ◽  
Monitoring Program ◽  
Integrated System ◽  
Machine Learning Algorithms ◽  
Monitoring And Control ◽  
Nozzle Clogging ◽  
Fused Deposition ◽  
Deposition Modeling ◽  
And Control

A preventive maintenance embedded for the fused deposition modeling (FDM) printing technique is proposed. A monitoring and control integrated system is developed to reduce the risk of having thermal degradation on the fabricated products and prevent printing failure; nozzle clogging. As for the monitoring program, the proposed temporal neural network with a two-stage sliding window strategy (TCN-TS-SW) is utilized to accurately provide the predicted thermal values of the nozzle tip. These estimated thermal values are utilized to be the stimulus of the control system that performs countermeasures to prevent the anomaly that is bound to happen. The performance of the proposed TCN-TS-SW is presented in three case studies. The first scenario is when the proposed system outperforms the other existing machine learning algorithms namely multi-look back LSTM, GRU, LSTM, and the generic TCN architecture in terms of obtaining the highest training accuracy and lowest training loss. TCN-TS-SW also outperformed the mentioned algorithms in terms of prediction accuracy measured by the performance metrics like RMSE, MAE, and R2 scores. In the second case, the effect of varying the window length and the changing length of the forecasting horizon. This experiment reveals the optimized parameters for the network to produce an accurate nozzle thermal estimation.

scholarly journals Experimental investigation on flexural properties of FDM-processed PET-G specimen using response surface methodology

2021 ◽  
Vol 349 ◽  
pp. 01008
Author(s):  
Nikolaos A. Fountas ◽  
Ioannis Papantoniou ◽  
John D. Kechagias ◽  
Dimitrios E. Manolakos ◽  
Nikolaos M. Vaxevanidis
Keyword(s):  
Flexural Strength ◽  
Response Surface ◽  
Fused Deposition Modeling ◽  
Performance Metrics ◽  
Optimal Parameter ◽  
Strong Dependence ◽  
Control Parameters ◽  
Fused Deposition ◽  
Deposition Modeling ◽  
3D Printed

The properties of fused deposition modeling (FDM) products exhibit strong dependence on process parameters which may be improved by setting suitable levels for parameters related to FDM. Anisotropic and brittle nature of 3D-printed components makes it essential to investigate the effect of FDM control parameters to different performance metrics related to resistance for improving strength of functional parts. In this work the flexural strength of polyethylene terephthalate glycol (PET-G) is examined under by altering the levels of different 3D-printing parameters such as layer height, infill density, deposition angle, printing speed and printing temperature. A response surface experiment was established having 27 experimental runs to obtain the results for flexural strength (MPa) and to further investigate the effect of each control parameter on the response by studying the results using statistical analysis. The experiments were conducted as per the ASTM D790 standard. The regression model generated for flexural strength adequately explains the variation of FDM control parameters on flexural strength and thus, it can be implemented to find optimal parameter settings with the use of either an intelligent algorithm, or neural network.

Switchable Bistability in 3D Printed Shells With Bio-Inspired Architectures and Spatially Distributed Pre-Stress

2018 ◽  
Author(s):  
Karl Jin Ang ◽  
Katherine S. Riley ◽  
Jakob Faber ◽  
Andres F. Arrieta
Keyword(s):  
3D Printing ◽  
Room Temperature ◽  
Fused Deposition Modeling ◽  
Element Analysis ◽  
Fused Deposition ◽  
Spatially Distributed ◽  
Deposition Modeling ◽  
3D Printed ◽  
And Control ◽  
Careful Design

Using fused deposition modeling (FDM) 3D printing, we combine a bio-inspired bilayer architecture with distributed pre-stress and the shape memory behavior of polylactic acid (PLA) to manufacture shells with switchable bistability. These shells are stiff and monostable at room temperature, but become elastic and bistable with fast morphing when heated above their glass transition temperature. When cooled back down, the shells retain the configuration they were in at the elevated temperature and return to being stiff and monostable. These programmed deformations result from the careful design and control of how the filament is extruded by the printer and therefore, the resulting directional pre-stress. Parameter studies are presented on how to maximize the pre-stress for this application. The shells are analyzed using nonlinear finite element analysis. By leveraging the vast array of geometries accessible with 3D printing, this method can be extended to complex, multi-domain shells, including bio-inspired designs.

Experimental Investigation of Nozzle Clogging Using Vibration Signal-Based Condition Monitoring for Fused Deposition Modeling

2021 ◽  
Vol 1037 ◽  
pp. 55-64
Author(s):  
Durwesh Jhodkar ◽  
Ankit Nayak ◽  
Kapil Gupta
Keyword(s):  
3D Printing ◽  
Condition Monitoring ◽  
Surface Finish ◽  
Fused Deposition Modeling ◽  
Vibration Signal ◽  
Nozzle Clogging ◽  
Vibration Signals ◽  
Fused Deposition ◽  
Material Deposition ◽  
Deposition Modeling

Fused deposition modeling (FDM) or 3D printing is one of the promising techniques widely preferred to fabricate complex and customized 3D objects or prototypes for various engineering and non-engineering applications. With the growing demands of customized prototypes, researchers are facing a major challenge for maintaining effective part quality with adequate surface finish and strength; and minimizing the cost, defects, and waste in 3D printing. Condition monitoring is one of the strategies to achieve the aforementioned. It has a huge potential to minimize defects and print failures in 3D printing. The main objective of this research work is to perform online condition monitoring of the nozzle status with the help of vibration signals in fused deposition modelling process. The effect of nozzle clogging on the consistency of material deposition and its effect on surface finish has experimentally investigated in this work. The set of experiments were performed by artificially creating the condition of nozzle clogging to investigate the effect of nozzle clogging on print quality (surface finish). Nozzle clogging condition was created by increasing the feed rate of polylactic acid (PLA) filament at a low heat supply rate to the nozzle by modifying the commands of 3D printer. The layer thickness was varied throughout the experiments to observe the nozzle clogging. The vibrations signals were acquired by using an accelerometer that was mounted near the nozzle. The data acquisition frequency of the accelerometer was 12500Hz. Further, the acquired vibration signals were analyzed using the Fast Fourier transformation (FFT) signal processing technique. Results revealed that nozzle clogging severely affects surface quality and geometrical accuracy of the fabricated 3D part due to nozzle vibration and non-uniform material deposition. Moreover, nozzle clogging and its relevant consequences like non uniform material deposition can be monitored using vibration signal-based condition monitoring during part fabrication and based upon that appropriate measures can be taken for defects and waste elimination.

Knowledge-Based Optimization of Artificial Neural Network Topology for Process Modeling of Fused Deposition Modeling

2018 ◽  
Author(s):  
Hari P. N. Nagarajan ◽  
Hesam Jafarian ◽  
Azarakhsh Hamedi ◽  
Hossein Mokhtarian ◽  
Romaric Prod'hon ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fused Deposition Modeling ◽  
Performance Metrics ◽  
Expert Knowledge ◽  
Production Quality ◽  
Fused Deposition ◽  
Knowledge Based ◽  
Deposition Modeling ◽  
Artificial Neural

Additive manufacturing (AM) continues to rise in popularity due to its various advantages over traditional manufacturing processes. AM interests industry, but achieving repeatable production quality remains problematic for many AM technologies. Thus, modeling the influence of process variables on the production quality in AM can be highly beneficial in creating useful knowledge of the process and product. An approach combining dimensional analysis conceptual modeling, mutual information based analysis, experimental sampling, factors selection, and modeling based on Knowledge-Based Artificial Neural Network (KB-ANN) is proposed for Fused Deposition Modeling (FDM) process. KB-ANN reduces the excessive amount of training samples required in traditional neural networks. The developed KB-ANN’s topology for FDM, integrates existing literature and expert knowledge of the process. The KB-ANN is compared to conventional ANN using prescribed performance metrics. This research presents a methodology to concurrently perform experiments, classify influential factors, limit the effect of noise in the modeled system, and model using KB-ANN. This research can contribute to the qualification efforts of AM technologies.

Process Analysis and Application for Rapid Prototyping Based on Fused Deposition Modeling

2011 ◽  
Vol 179-180 ◽  
pp. 875-880 ◽  
Author(s):  
Dong Man Yu ◽  
Cheng Jun Zhu ◽  
Jun Su ◽  
Di Wang
Keyword(s):  
Rapid Prototyping ◽  
Fused Deposition Modeling ◽  
Process Analysis ◽  
Control Cell ◽  
Fused Deposition ◽  
Deep Groove ◽  
Deep Groove Ball Bearing ◽  
Design Function ◽  
Deposition Modeling ◽  
And Control

This paper presents the working principle of rapid prototyping technology based on fused deposition modeling (FDM) and summaries its technology features. The basic constitution of FDM system, such as mechanical device and control cell, are discussed, respectively. Selecting a deep groove ball bearing as experimental object and manufactured in the MEM320A rapid prototyping machine to demonstrate the FDM fabrication process. Investigate into the application of FDM on production design, function demonstration and biomedical engineering. Finally, the future development of FDM is prospected.

Moisture and Humidity Effects on the ABS Used in Fused Deposition Modeling Machine

2012 ◽  
Vol 576 ◽  
pp. 641-644 ◽  
Author(s):  
Siti Nur Amalina Mohd Halidi ◽  
Jamaluddin Abdullah
Keyword(s):  
Thermal Stability ◽  
Fused Deposition Modeling ◽  
Acrylonitrile Butadiene Styrene ◽  
Nozzle Clogging ◽  
Humidity Effects ◽  
Fused Deposition ◽  
Deposition Modeling ◽  
Nozzle Blockage ◽  
Physical Changes ◽  
Butadiene Styrene

The environment seems to have an effect on Acrylonitrile-Butadiene-Styrene (ABS) which consequently causes physical, morphological and thermal stability changes to the polymer. Not only that, these changes may have caused nozzle blockage on the liquefier of the Fused Deposition Modeling (FDM) rapid prototyping machine. Experiments are conducted to support and verify whether ABS does affect the blockage. It has been observed that physical changes may have not caused nozzle clogging.

Robot Arm Platform for Additive Manufacturing Using Multi-Plane Toolpaths

2016 ◽  
Author(s):  
Ismayuzri Bin Ishak ◽  
Joseph Fisher ◽  
Pierre Larochelle
Keyword(s):  
Additive Manufacturing ◽  
Fused Deposition Modeling ◽  
Industrial Robot ◽  
Integrated System ◽  
Robot Arm ◽  
Fused Deposition ◽  
Modeling Techniques ◽  
3D Printers ◽  
Deposition Modeling ◽  
3D Printed

This article discusses the concept of using an industrial robot arm platform for additive manufacturing. The concept being explored is the integration of existing additive manufacturing process technologies with an industrial robot arm to create a 3D printer with a multi-plane layering capability. The objective is to develop multi-plane toolpath motions that will leverage the increased capability of the robot arm platform compared to conventional gantry-style 3D printers. This approach enables print layering in multiple planes whereas existing conventional 3D printers are restricted to a single toolpath plane (e.g. x-y plane). This integration combines the fused deposition modeling techniques using an extruder head that is typically used in 3D printing and a 6 degree of freedom robot arm. Here, a Motoman SV3X is used as the platform for the robot arm. A higher level controller is used to control the robot and the extruder. To communicate with the robot, MotoCom SDK libraries is used to develop the interfacing software between the higher level controller and the robot arm controller. The integration of these systems enabled multi-plane toolpath motions to be utilized to produce 3D printed parts. A test block has been 3D printed using this integrated system.

Biodegradable 3D Printed Polymer Microneedles for Transdermal Drug Delivery

2018 ◽  
Author(s):  
Michael A. Luzuriaga ◽  
Danielle R. Berry ◽  
John C. Reagan ◽  
Ronald A. Smaldone ◽  
Jeremiah J. Gassensmith
Keyword(s):  
Drug Delivery ◽  
3D Printing ◽  
Transdermal Drug Delivery ◽  
Fused Deposition Modeling ◽  
Fused Deposition ◽  
Modeling Software ◽  
Deposition Modeling ◽  
3D Printed ◽  
Microfabrication Technique ◽  
Mechanical Strengths

Biodegradable polymer microneedle (MN) arrays are an emerging class of transdermal drug delivery devices that promise a painless and sanitary alternative to syringes; however, prototyping bespoke needle architectures is expensive and requires production of new master templates. Here, we present a new microfabrication technique for MNs using fused deposition modeling (FDM) 3D printing using polylactic acid, an FDA approved, renewable, biodegradable, thermoplastic material. We show how this natural degradability can be exploited to overcome a key challenge of FDM 3D printing, in particular the low resolution of these printers. We improved the feature size of the printed parts significantly by developing a post fabrication chemical etching protocol, which allowed us to access tip sizes as small as 1 μm. With 3D modeling software, various MN shapes were designed and printed rapidly with custom needle density, length, and shape. Scanning electron microscopy confirmed that our method resulted in needle tip sizes in the range of 1 – 55 µm, which could successfully penetrate and break off into porcine skin. We have also shown that these MNs have comparable mechanical strengths to currently fabricated MNs and we further demonstrated how the swellability of PLA can be exploited to load small molecule drugs and how its degradability in skin can release those small molecules over time.

Sign in / Sign up

Export Citation Format

Share Document