Artificial Neural Network technique to assess tribological performance of GFRP composites incorporated with graphene nano-platelets

Kumar, Santosh; Sharma, Nikhil; Singh, Kalyan

doi:10.1016/j.triboint.2022.108194

Cited by 8 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some approaches are based on the Fuzzy-neuro system which is the combination of the two materials on the contact effect and the characteristics of the sliding system [11]. Therefore, successful case studies using these approaches in a tribological context demonstrate their ability to accurately and efficiently predict tribological features [12] in the design of materials composition [13], lubricant formulations [14], lubrication and fluid film establishment [15], and interaction first bodies-environment [16]. However, certain models had certain limitations like they cannot be applicable for estimating the tribological behavior of wider varieties of materials that contain rigid structures with high wear resistance levels [17].…”

Section: Introductionmentioning

confidence: 99%

A data-driven approach for studying tribology based on experimentation and artificial intelligence coupling tools

Kchaou

2024

Sustainable Engineering and Innovation

View full text Add to dashboard Cite

Tribology problems generally, and particularly high-temperature tribology (HTT), is a critical and complex topic based on the interaction between several intrinsic and extrinsic parameters. This involved complex phenomena, resulting in synergistic effects between mechanical, physical, chemical, and thermal solicitations. Introducing artificial intelligence tools, coupled with the design of the experiment, is an original approach to implement a successful transition from traditional "experimental guidance" to "experimental guidance associated with a data-driven" approach. The current study delves into the utilization of machine learning (ML) with simulation to help in the choice of the parameters for experimentation, and the development of predictive models. A detailed framework that takes into account the coupling between such tools is presented. Different scenarios are discussed to data drive the collaborative schema between the design of experiment, numerical development, and ML algorithms. This approach gives several opportunities such as the identification of the well-impacted parameters, optimization of the experimental design, and the proposition of predictive models. With the suitable proposed model, time loss, production costs, precision results, and man-hours could be saved or improved.

show abstract

Section: Introductionmentioning

confidence: 99%

A data-driven approach for studying tribology based on experimentation and artificial intelligence coupling tools

Kchaou

2024

Sustainable Engineering and Innovation

View full text Add to dashboard Cite

show abstract

“…Researchers have developed many statistical models in order to optimize the various parameters for tribological performance of the composites. Many modelling techniques recently being used are Response surface methodology (RSM), Artificial Neural Network (ANN), Taguchi for the optimization of parameters for tribological performance of composites with the aid of statistical tools like Python, Minitab, Design of Experiments, Matlab, etc [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

“…The wear test parameters (load, wt% reinforcement and sliding distance) were optimized for minimising specific wear rate and COF. Magibalan et al [15] was successful in applying RSM for improving wear characteristics of the fly ash reinforced Al composites. Mandava et al [16] analysed wear properties of Al7075 based composites having fly ash and SiC as reinforcements with help of RSM approach with MINITAB software and optimised the wear parameters concluding load is the dominant factor for wear rate.…”

Section: Introductionmentioning

confidence: 99%

Prediction of tribological performance of Cu-Gr-TiC composites based on response surface methodology and worn surface analysis

Ankit,

Kumar,

Yadav

et al. 2023

Phys. Scr.

View full text Add to dashboard Cite

In the current study, the prediction of tribological performance of Cu-Gr-TiC composites and correlative with surface topography has been studied. For this purpose, the Cu-Gr composites reinforced with TiC ceramic particles were prepared via the powder metallurgy route. The prepared composites microstructure, mechanical characteristics, and dry sliding wear behaviour were assessed. A pin on disc setup was taken for tribological testing where sliding velocity is 1.5 m/s. Wear behaviour of composites was examined using a central composite design (CCD) with three levels. The wear behavior optimization was accomplished through the utilization of response surface methodology (RSM). The input parameters in RSM consisted of sliding distance, varying load, and weight percentage (wt.%) of reinforcements, while the wear rate and coefficient of friction served as the two responses. An analysis of variance (ANOVA) using RSM was conducted to identify the significant parameters influencing the wear rate and coefficient of friction. A quadratic model was suggested based on best fit and a regression equation was established for predicting the tribological properties at any given input parameter. Comparative of experimental and predicted values shows close tolerance. It was observed that RSM is significant tool to predict and optimize the tribological properties. The composite having 3.08 wt.% of TiC particles was optimized for minimum wear rate & COF at 20 N load and 2000 m sliding distance.

show abstract

Optimization of tribological characteristics in cryo-treated plastic/graphene oxide modified CFRP via ANN-based predictive modeling for aerospace applications

et al. 2024

Composites Science and Technology

View full text Add to dashboard Cite

Artificial Neural Network technique to assess tribological performance of GFRP composites incorporated with graphene nano-platelets

Cited by 8 publications

References 47 publications

A data-driven approach for studying tribology based on experimentation and artificial intelligence coupling tools

A data-driven approach for studying tribology based on experimentation and artificial intelligence coupling tools

Prediction of tribological performance of Cu-Gr-TiC composites based on response surface methodology and worn surface analysis

Optimization of tribological characteristics in cryo-treated plastic/graphene oxide modified CFRP via ANN-based predictive modeling for aerospace applications

Contact Info

Product

Resources

About