EXAMINATION OF THE WEAR BEHAVIOR OF CU-BASED BRAKEÂ PADS USED IN HIGH-SPEED TRAINS AND PREDICTION THROUGH STATISTICAL AND NEURAL NETWORKÂ MODELS

ÅžERAFETTÄ°N Ekä°ncä°, ASILTÃœRK Ä°lhan (), AKKUÅž Harun () and Akshin Mahammadzade ()
Additional contact information
ÅžERAFETTÄ°N Ekä°ncä°: Department of Mechanical Engineering, Technology Faculty, Selçuk University, Konya 42130, Turkey
ASILTÜRK İlhan: ��Department of Mechanical Engineering, Engineering Faculty, Necmettin Erbakan University, Konya 42090, Turkey
AKKUŞ Harun: ��Department of Motor Vehicles and Transportation Technologies, Vocational School of Technical Sciences, Niğde Ömer Halisdemir University, Niğde 51240, Turkey
Akshin Mahammadzade: �Department of Automotive Engineering, Selçuk University, Institute of Sciences, Selçuk University, Konya 42130, Turkey

Surface Review and Letters (SRL), 2024, vol. 31, issue 08, 1-16

Abstract: The aim of this study is to provide insights into the performance of copper-based brake pads used in high-speed trains and contribute to a more predictable braking system by leveraging mathematical and artificial intelligence (AI) models. The wear behavior of Cu-based brake pads in high-speed trains was investigated using a pin-on-disc test setup under different speeds, temperatures, and loads with a constant sliding distance. Additionally, mathematical and AI models were developed to predict the friction coefficient and wear rate values obtained from the experiments. This innovative approach initiates a significant discussion in line with a current need, and the sharing and publication of the obtained results are currently essential to address the knowledge gap in this field. The results revealed that an increase in temperature led to an increase in both the friction coefficient and wear rate. Conversely, an increase in load resulted in a decrease in both the friction coefficient and wear rate. The transition from abrasive wear to adhesive wear occurred due to the softening of copper between friction surfaces, leading to material transfer. According to the results obtained from the models, both the artificial neural network (ANN) and multiple regression models demonstrated comparable accuracy, predicting the friction coefficient with approximately 94% accuracy in both cases, indicating reliable predictions. For the wear rate, the models achieved approximately 90% and 92% accuracy, respectively.

Keywords: ANN; Cu-based brake pad; friction coefficient; mathematical model; SEM; wear rate (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0218625X24500628
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:srlxxx:v:31:y:2024:i:08:n:s0218625x24500628

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0218625X24500628

Access Statistics for this article

Surface Review and Letters (SRL) is currently edited by S Y Tong

More articles in Surface Review and Letters (SRL) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().