Taguchi’s DOE and artificial neural network analysis for the prediction of tribological performance of graphene nano-platelets filled glass fiber reinforced epoxy composites under the dry sliding condition

Sharma, Nikhil; Kumar, Santosh; Singh, Kalyan

doi:10.1016/j.triboint.2022.107580

Cited by 19 publications

(10 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimal number of neurons in the hidden layer was determined to be 10, a value derived from previous research 38 architecture is shown in Figure 3. 39,40 A neural network consists of three main components: an input layer with units representing input data, one or more hidden layers, and an output layer representing the target field. The units are connected with varying weights and the final results are delivered to the units in the output layer.…”

Section: Artificial Neural Network (Ann) Methodsmentioning

confidence: 99%

Examining the bending test properties of bio-composites strengthened with fibers through a combination of experimental and modeling approaches

Saada,

Farsi,

Amroune

et al. 2024

Journal of Composite Materials

View full text Add to dashboard Cite

This study explores the relationship between natural fiber filling density (10%, 15%, 25%) and its impact on the bending properties of polymer compounds reinforced with Diss, Sisal and Luffa fibers. Using advanced techniques like fiber analysis and Fourier transform infrared spectrometry (FTIR), the research reveals that a 25% filling density results in the highest stress values (25.61 MPa, 22.21 MPa and 20.88 MPa) for Diss, Sisal and Luffa compounds, respectively, fostering robust bonds in Diss-reinforced polymers. The Artificial Neural Network (ANN) model demonstrates superior predictive capability with correlation coefficients exceeding 0.99 for stress and displacement, outperforming Response Surface Methodology (RSM). Analysis of Variance (ANOVA) underscores the impact of sample section parameters and fiber rate on stress, establishing the significance of type parameters and fiber rate on displacement. This integration of ANN and RSM represents a paradigm shift in predicting bending mechanical properties, advancing our understanding of composite materials for innovative applications.

show abstract

Section: Artificial Neural Network (Ann) Methodsmentioning

confidence: 99%

Examining the bending test properties of bio-composites strengthened with fibers through a combination of experimental and modeling approaches

Saada,

Farsi,

Amroune

et al. 2024

Journal of Composite Materials

View full text Add to dashboard Cite

show abstract

“…34 In this study, a total of 124 independent pin-on-disk sliding wear test data is used. Another artificial neural network application for the prediction of tribological performance was reported by Sharma et al 35 In this study, an artificial neural network model was developed for the prediction of specific wear rate and coefficient of friction. In another study, the prediction of tribological properties of short fiber composites by using artificial neural networks are introduced by Zhang et al 36 In this study, specific wear rate and frictional coefficient were predicted by using a multi-layer feed-forward artificial neural network.…”

Section: Analysis With Artificial Neural Networkmentioning

confidence: 99%

Tribological and mechanical properties of nanofilled glass fiber reinforced composites and analyzing the tribological behavior using artificial neural networks

Demir,

Cetkin,

Ergün

et al. 2024

Polymer Composites

View full text Add to dashboard Cite

This study investigates the effects of filler content and type on the mechanical (tensile strength and impact resistance) and tribological properties of woven glass fiber‐reinforced composites (WGFC) produced using three different nanofillers (MgO, CuO, and Al2O3) at various loading levels (0.7, 1.4, and 2.8 wt%). Additionally, analyses of the artificial neural network algorithm were reported for the predictions of wear rate, mass loss, and coefficient of friction (COF) by given applied load, sliding distance, filler ratio, and filler type. The composites were fabricated using the hand lay‐up method. The filled composites were characterized using Fourier Transform Infrared (FTIR) spectroscopy, and the worn surfaces of the samples after the wear test were analyzed using Scanning Electron Microscopy (SEM). The wear resistance of the composite samples improved at 0.7 wt% CuO and 1.4 wt% MgO filler contents. At 200 m sliding distance and 1.4 wt% filler ratio, the highest wear ratio was determined as 55 mm3/m × 10−3 in the Al2O3‐filled composite, and the lowest was determined as 31 mm3/m × 10−3 in the MgO‐filled composite. At 1.4% filler ratio and 15 N load, the lowest friction coefficient was determined as 0.45 μ in MgO‐filled composite, and the highest was 0.56 μ in Al2O3‐filled composite. Al2O3 filler increased the mass loss and wear rate of the composite material. In Charpy impact tests, the maximum impact energy of 13.9 J/m2 was obtained with a 2.8 wt% Al2O3 filler content. Tensile tests showed an increase in tensile strength for all filler contents compared to unfilled composites. The highest tensile strength of 242.1 MPa was achieved with 0.7 wt% CuO reinforcement.Highlights In all applied wear parameters and filler ratios, the Al2O3 filler adversely affected the wear resistance of the composite, while the MgO filler showed the best performance in terms of wear resistance. All types and ratios of fillers increased the tensile strength compared to the unfilled composite. Contrary to its negative effect on wear, the Al2O3‐filled composites exhibited the highest impact resistance. The prediction analysis of the tribological behavior of composite material using ANN reveals that the Levenberg–Marquardt algorithm fits very well.

show abstract

“…Data collection techniques in this study were carried out by [6], [13], [23]- [25]: 1. Observation is collecting data using direct words of the object under investigation to obtain relevant data.…”

Section: Data Collection Techniquesmentioning

confidence: 99%

A Model Experiment Design Using the Taguchi Method: A Case Study Of Making Concrete Roof

Nur Permadi,

Basiratun Nisa

2023

JURIT

View full text Add to dashboard Cite

This research was conducted at a company manufacturing paving blocks, ceramics, ventilation, concrete, and roof tiles. This study aims to improve the quality of concrete tile products, which experience the most cracks and breaks. Research to determine the composition of concrete roof tiles can be carried out by design experiments using the Taguchi method. This experiment used raw materials such as cement, sand, milled flour, and water. The concluding results show that the quality of concrete roof tiles is based on the results of the Taguchi method and confirmation experiments which are characterized by an increase in the compressive strength of the concrete tile based on the average value (μ) and its variability (SNR). The average compressive strength (µ) of concrete roof tiles increased from 19,814 ≤ 21,208 ≤ 22,602 in the Taguchi experiment to 26,406 ≤ µconfirmation ≤ 29,894 in the confirmation experiment. While the variability (SNR) increased from 25.532 ≤ 27.521 ≤ 29.510 in the Taguchi experiment to 26.473 ≤ S/N confirmed ≤ 31.469 in the confirmation experiment. The optimal composition of cement, sand, milled flour, and water that produces the best compressive strength based on the response factor and SNR is 0.9 kg: 0.5 kg: 0.4 kg: 0.3 kg, respectively. The most influential factors on the compressive strength of concrete roof tiles are the amount of sand and the number of flour mills.

show abstract

Taguchi’s DOE and artificial neural network analysis for the prediction of tribological performance of graphene nano-platelets filled glass fiber reinforced epoxy composites under the dry sliding condition

Cited by 19 publications

References 46 publications

Examining the bending test properties of bio-composites strengthened with fibers through a combination of experimental and modeling approaches

Examining the bending test properties of bio-composites strengthened with fibers through a combination of experimental and modeling approaches

Tribological and mechanical properties of nanofilled glass fiber reinforced composites and analyzing the tribological behavior using artificial neural networks

A Model Experiment Design Using the Taguchi Method: A Case Study Of Making Concrete Roof

Contact Info

Product

Resources

About