ItemArticle

Performance comparison of tree-based and neural network models for wear prediction in coated and uncoated Al6061

Title
Performance comparison of tree-based and neural network models for wear prediction in coated and uncoated Al6061
Creator
Naveena, B.E.; Santhosh, K.; Keshavamurthy, R.; Shrivathsa, T.V.; Ganesha, B.B.; Sahil; Mahesh, B.R.
Description
This study compares the performance of machine learning (ML) and deep learning (DL) models in predicting the dry sliding wear of uncoated Al6061, plasma-sprayed flyash-Al2O3 and flyash-SiC coatings. Ensemble models, including random forest (RF), XGBoost and LightGBM, along with neural network models such as multilayer perceptron (MLP) regressors, backpropagation neural networks (BPNN) and deep neural networks (DNN), were trained on experimental data that varied load, sliding speed and sliding distance. The dataset was scaled and split into training (80%) and testing (20%) subsets. Model performance was evaluated using the coefficient of determination (R2), mean absolute error (MAE) and root mean square error (RMSE). ML regressors accurately predicted the properties of uncoated alloys, with R2 scores above 0.97, though their performance decreased on coated samples. RF experienced the largest decline in accuracy, particularly flyash-SiC (R2 = 0.736). Gradient boosting models exhibited improved robustness, with LightGBM achieving R2 values of 0.977, 0.936 and 0.794 for uncoated, flyash-Al2O3 and flyash-SiC samples, respectively. Neural networks outperformed tree-based methods for coated systems, with MLP and DNN attaining R2 values up to 0.992, alongside lower MAE and RMSE. SEM analysis corroborated the predictions, showing severe wear in uncoated alloys, minimal surface damage in flyash-Al2O3 coatings and cracking and delamination in flyash-SiC coatings. 2026 The Authors.
Source
Results in Surfaces and Interfaces;Volume;23;Issue;;Article No.;100788;
Date
01-01-2026
Publisher
Elsevier B.V.
Subject
Aluminum alloys; Deep learning; Flyash; Machine learning; Neural network; Plasma coating
Coverage
Naveena B.E., Department of Automobile Engineering, Dayananda Sagar College of Engineering, Karnataka, Bangalore, 560078, India; Santhosh K., Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India; Keshavamurthy R., Department of Mechanical and Automobile Engineering, CHRIST University, Karnataka, Bengaluru, 560074, India; Shrivathsa T.V., Department of Artificial Intelligence and Machine Learning, Shri Madhwa Vadiraja Institute of Technology & Management, Bantakal, Karnataka, 574115, India; Ganesha B.B., Department of Mechanical Engineering, Vidyavardhaka College of Engineering, Karnataka, Mysuru, 570002, India; Sahil, Department of Automobile Engineering, Dayananda Sagar College of Engineering, Karnataka, Bangalore, 560078, India; Mahesh B.R., Department of Automobile Engineering, Dayananda Sagar College of Engineering, Karnataka, Bangalore, 560078, India
Rights
All Open Access; Gold Open Access; Green Open Access
Relation
ISSN: 26668459;
Format
online
Language
English
Type
Article

Citation

Naveena, B.E.; Santhosh, K.; Keshavamurthy, R.; Shrivathsa, T.V.; Ganesha, B.B.; Sahil; Mahesh, B.R., “Performance comparison of tree-based and neural network models for wear prediction in coated and uncoated Al6061,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/22448.

Output Formats