The Role of Artificial Neural Networks in Prediction of Mechanical and Tribological Properties of Composites—A Comprehensive Review

Paturi, Uma Maheshwera Reddy; Cheruku, Suryapavan; Reddy, N.S.

doi:10.1007/s11831-021-09691-7

Cited by 36 publications

(14 citation statements)

References 281 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ИНС помогают обеспечить точность моделирования нелинейных зависимостей свойств композитных материалов, и в дальнейшем помогает оценить влияние многих входных параметров на характеристики материала. Группа исследователей обнаружила, что ИНС очень точно моделируют механическое поведение композитных материалов [16]. Исследователи приложили достаточные усилия для моделирования характеристик износа при скольжении с использованием ИНС.…”

Section: ______ *адрес для перепискиunclassified

Modeling of sliding wear characteristics of Polytetrafluoroethylene (PTFE) composite reinforced with carbon fiber against SS304

Chinchanikar¹

2022

Metal Working and Material Science

View full text Add to dashboard Cite

Introduction. Over the last decade, composite materials based on polytetrafluoroethylene (PTFE) have been increasingly used as alternative materials for automotive applications. PTFE is characterized by a low coefficient of friction, hardness and corrosion resistance. However, this material has a high wear rate. A group of researchers attempted to improve the wear resistance of PTFE material by reinforcing it with different fillers. The purpose of the work: This study experimentally investigates the dry sliding wear characteristics of a PTFE composite reinforced with carbon fiber (35 wt.%) compared to SS304 stainless steel. In addition, experimental mathematical and ANN models are developed to predict the specific wear rate, taking into account the influence of pressure, sliding speed, and interface temperature. The methods of investigation. Dry sliding experiments were performed on a pin-on-disk wear testing machine with varying the normal load on the pin, disk rotation, and interface temperature. Experiments were planned systematically to investigate the effect of input parameters on specific wear rates with a wide range of design space. In total, fifteen experiments were carried out at a 5-kilometer distance without repeating the central run experiment. Sliding velocities were obtained by selecting the track diameter on the disk and corresponding rotation of the disk. A feedforward back-propagation machine learning algorithm was used to the ANN model. Results and Discussion. This study finds better prediction accuracy with the ANN architecture having two hidden layers with 150 neurons on each layer. This study finds an increase in specific wear rates with normal load, sliding velocity, and interface temperature. However, the increase is more prominent at higher process parameters. The normal load followed by sliding velocity most significantly affects the specific wear rate. The results predicted by the developed models for specific wear rates are in good agreement with the experimental values with an average error close to 10%. This shows that the model could be reliably used to obtain the wear rate of PTFE composite reinforced with carbon fiber (35 wt.%) compared to SS304 stainless steel. This study finds scope for further studies considering the effect of varying ANN architectures, different amount of neurons, and hidden layers on the prediction accuracy of the wear rate.

show abstract

Section: ______ *адрес для перепискиunclassified

Modeling of sliding wear characteristics of Polytetrafluoroethylene (PTFE) composite reinforced with carbon fiber against SS304

Chinchanikar¹

2022

Metal Working and Material Science

View full text Add to dashboard Cite

show abstract

“…They have been designed to simulate the processing information in the brain and are widely used in different branches of science such as analytical, physical, organic, inorganic chemistries, and medicinal material sciences. [43][44][45]64,65 The ANNs obtain their knowledge by nding the patterns and relationships in data through experience. 66 They are made of articial neurons which are connected with coefficients (weights), constituting the neural structure and organized in layers.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Predicting the aggregation number of cationic surfactants based on ANN-QSAR modeling approaches: understanding the impact of molecular descriptors on aggregation numbers

2022

View full text Add to dashboard Cite

show abstract

“…37 Several studies have combined the design of experiments (DOE) and modeling techniques with ML to accelerate the design of tribological materials with the desired characteristics/properties. 38,39 This, in turn, has enabled researchers to analyze, predict, optimize, and accelerate the discovery of tribological materials by successfully establishing structure-property or structure-functionality relations in the existing available data. 40,41 Thus, it is no surprise that there has been a surge in the use of ML for tribological applications recently (2010-today) as compared to that until 2010.…”

Section: Introductionmentioning

confidence: 99%

A review of recent advances and applications of machine learning in tribology

Sose

Joshi

Kunche

et al. 2023

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

The Role of Artificial Neural Networks in Prediction of Mechanical and Tribological Properties of Composites—A Comprehensive Review

Cited by 36 publications

References 281 publications

Modeling of sliding wear characteristics of Polytetrafluoroethylene (PTFE) composite reinforced with carbon fiber against SS304

Modeling of sliding wear characteristics of Polytetrafluoroethylene (PTFE) composite reinforced with carbon fiber against SS304

Predicting the aggregation number of cationic surfactants based on ANN-QSAR modeling approaches: understanding the impact of molecular descriptors on aggregation numbers

A review of recent advances and applications of machine learning in tribology

Contact Info

Product

Resources

About