Prediction of mechanical properties for acrylonitrile-butadiene-styrene parts manufactured by fused deposition modelling using artificial neural network and genetic algorithm

Tayyab, M.; Ahmad, Shadab; Akhtar, Md Jamil; Sathikh, Peer M.; Singari, Ranganath M.

doi:10.1080/0951192x.2022.2104462

Cited by 12 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MATLAB software has been used for the construction, training, testing, and validation of the ANN model. According to documents [17,26] and [48] the values of the data reports have been retained. 70% of the data is for training, 15% for testing, and 15% for validation.…”

Section: Artificial Neural Network Modellingmentioning

confidence: 99%

Experimental study of the effect of different 3D printing parameters on tensile strength, using artificial neural network

Hamouti,

El Farissi,

Laouardi

2024

Mater. Res. Express

View full text Add to dashboard Cite

Numerous research studies have been conducted to optimize printing parameters using the fused deposition modeling technique (FDM) to improve mechanical properties. The large number of process parameters creates a need to search for optimal combinations of parameters to improve mechanical properties. This study examines the effects of three parameters when printing 3D with melted filament of a PLA material (Polylactic Acid) on the ultimate tensile strength of the printed parts. This search combines an experimental study of the most influential printing parameters on the tensile strength property, namely layer thickness, printing temperature, and feed rate. The experimental results are then analyzed and modeled as a linear regression model. Then develop an intelligent artificial model based on ANN (Artificial Neural Network) derived from these experimental results capable of predicting the optimal combination of parameters providing maximum tensile strength. The observed results showed that the feed rate dominates among the other variables, followed by the thickness of the layer. Also, at the level of prediction, the artificial model provides a better prediction of the tensile strength with a value of 36.1625 MPa by combining the following parameters: Feed rate: 70 mm/s, temperature: 200 °C, and layer thickness: 0.26 mm, compared to the prediction obtained by the linear regression model. Neural networks enable more accurate optimization of 3D process parameters, leading to an overall improvement in the quality of finished products. predictive models, significantly reducing the iteration time required to obtain optimal parameters. The quality of the data used to train neural networks is crucial.

show abstract

Section: Artificial Neural Network Modellingmentioning

confidence: 99%

Experimental study of the effect of different 3D printing parameters on tensile strength, using artificial neural network

Hamouti,

El Farissi,

Laouardi

2024

Mater. Res. Express

View full text Add to dashboard Cite

show abstract

“…An ANN with a backpropagation algorithm was exploited to model the combined effects of FDM printing and AFM finishing parameters on the surface finish of crescent prism parts made from PLA. The ANN was designed in three stages: training, testing and validation (Ahmad et al , 2021b; Singh et al , 2019; Tayyab et al , 2022), using experimental data (Table 7) and developed using MATLAB R2021a. The neural network consists of three layers of neurons: the input layer, the hidden layer and the output layer (Bishop, 1995).…”

Section: Modelling and Optimizationmentioning

confidence: 99%

A novel eco-friendly abrasive media based abrasive flow machining of 3D printed PLA parts using IGWO and ANN

Hashmi

Mali

Meena

et al. 2023

RPJ

Self Cite

View full text Add to dashboard Cite

Purpose Three-dimensional (3D) printed parts usually have poor surface quality due to layer manufacturing’s “stair casing/stair-stepping”. So post-processing is typically needed to enhance its capabilities to be used in closed tolerance applications. This study aims to examine abrasive flow finishing for 3D printed polylactic acid (PLA) parts. Design/methodology/approach A new eco-friendly abrasive flow machining media (EFAFM) was developed, using paper pulp as a base material, waste vegetable oil as a liquid synthesizer and natural additives such as glycine to finish 3D printed parts. Characterization of the media was conducted through thermogravimetric analysis and Fourier transform infrared spectroscopy. PLA crescent prism parts were produced via fused deposition modelling (FDM) and finished using AFM, with experiments designed using central composite design (CCD). The impact of process parameters, including media viscosity, extrusion pressure, layer thickness and finishing time, on percentage improvement in surface roughness (%ΔRa) and material removal rate were analysed. Artificial neural network (ANN) and improved grey wolf optimizer (IGWO) were used for data modelling and optimization, respectively. Findings The abrasive media developed was effective for finishing FDM printed parts using AFM, with SEM images and 3D surface profile showing a significant improvement in surface topography. Optimal solutions were obtained using the ANN-IGWO approach. EFAFM was found to be a promising method for improving finishing quality on FDM 3D printed parts. Research limitations/implications The present study is focused on finishing FDM printed crescent prism parts using AFM. Future research may be done on more complex shapes and could explore the impact of different materials, such as thermoplastics and composites for different applications. Also, implication of other techniques, such as chemical vapour smoothing, mechanical polishing may be explored. Practical implications In the biomedical field, the use of 3D printing has revolutionized the way in which medical devices, implants and prosthetics are designed and manufactured. The biodegradable and biocompatible properties of PLA make it an ideal material for use in biomedical applications, such as the fabrication of surgical guides, dental models and tissue engineering scaffolds. The ability to finish PLA 3D printed parts using AFM can improve their biocompatibility, making them more suitable for use in the human body. The improved surface quality of 3D printed parts can also facilitate their sterilization, which is critical in the biomedical field. Social implications The use of eco-friendly abrasive flow finishing for 3D printed parts can have a positive impact on the environment by reducing waste and promoting sustainable manufacturing practices. Additionally, it can improve the quality and functionality of 3D printed products, leading to better performance and longer lifespans. This can have broader economic and societal benefits. Originality/value This AFM media constituents are paper pulp, waste vegetable oil, silicon carbide as abrasive and the mixture of “Aloe Barbadensis Mill” – “Cyamopsis Tetragonoloba” powder and glycine. This media was then used to finish 3D printed PLA crescent prism parts. The study also used an IGWO to optimize experimental data that had been modelled using an ANN.

show abstract

“…This increase in MI is due to chaotic advection induced by twisting and bending, which is secondary flow, which can be described from Fig 4 which is a velocity contour. We coupled pressure and velocity using the SIMPLEC algorithm [21]. By use of second-order backward Euler techniwue, the discretization in time for transient computation was carried out.…”

Section: Variation Of Re Effect Of MImentioning

confidence: 99%

“…[18] a detailed review to show the need for microdevices, in various field, further stated that model with sharpness and smallness chaotic flow increases. Raza et al [19] introduced multi objective optimization in their model and on similar pattern heuristic algorithms [20,21] can be implemented.…”

Section: Introductionmentioning

confidence: 99%

A novel passive micromixer model computational analysis with twist and bend

Mustafa

Zunaid

Gautam

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

A dynamic mixing model for a microfluidic platform that uses bending and twisting characteristic is proposed in this work. The action of twisting and bending on mixing efficient in the microchannel is tested using Navier-Stokes equations. Micromixers being broadly applied in micro total analysis systems (µTAS). Passive micromixers are largely preferred from their heftiness, serenity of amalgamation and cost effective. However rapid mixing in this model is difficult but can be achieved with a twist in the model and offset. From the past study, we know that with a high Reynolds number mixing efficiency effectively improved. Chaotic advection allows the micromixer model to generate secondary flow which led to a drop in high-pressure drop in the model.

show abstract

Prediction of mechanical properties for acrylonitrile-butadiene-styrene parts manufactured by fused deposition modelling using artificial neural network and genetic algorithm

Cited by 12 publications

References 43 publications

Experimental study of the effect of different 3D printing parameters on tensile strength, using artificial neural network

Experimental study of the effect of different 3D printing parameters on tensile strength, using artificial neural network

A novel eco-friendly abrasive media based abrasive flow machining of 3D printed PLA parts using IGWO and ANN

A novel passive micromixer model computational analysis with twist and bend

Contact Info

Product

Resources

About