Machine Learning-Driven Optimization of Micro-Textured Surfaces for Enhanced Tribological Performance: A Comparative Analysis of Predictive Models
Source abstract
Abstract
Micro-textured surfaces show promise in improving tribological properties, but predicting their performance remains challenging due to complex relationships between surface features and frictional behavior. This study evaluates five algorithms—linear regression, decision tree, gradient boosting, support vector machine, and neural network—for their ability to predict load-carrying capacity and friction force based on texture parameters including depth, side length, surface ratio, and shape. The neural network model demonstrated superior performance, achieving the lowest MAE (24.01) and highest R-squared value (0.99) for friction force prediction. The results highlight the potential of machine learning techniques to enhance the understanding and prediction of friction-reducing micro-textures, contributing to the development of more efficient and durable tribological systems in industrial applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Tribology and Lubrication Engineering · Lubricants and Their Additives · Adhesion, Friction, and Surface Interactions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical Engineering, Yangzhou University, Yangzhou 225009, China
Department of Engineering, Engineering Building, Lancaster University, Lancaster LA1 4YW, UK
Funding
Jiangsu Agricultural Science and Technology Innovation Fund · National Natural Science Foundation of China
References (32)
Show source-provided references
1. Robust and universal macroscale superlubricity with natural phytic acid solutions10.1016/j.triboint.2023.108387 ↗
2. Tribological behavior of femtosecond laser-textured leaded brass10.1016/j.triboint.2021.107115 ↗
3. Li, S., Yang, X., Kang, Y., Li, Z., and Li, H. (2022). Progress on Current-Carry Friction and Wear: An Overview from Measurements to Mechanism. Coatings, 12.10.3390/coatings12091345 ↗
4. Fishbone-like micro-textured surface for unidirectional spreading of droplets and lubricity improvement10.1016/j.triboint.2024.109932 ↗
5. Effect of nanoscale surface roughness on sliding friction and wear in mixed lubrication10.1016/j.wear.2023.204995 ↗
6. Liu, X., Zhang, J., and Li, L. (2021). Surface Integrity and Friction Performance of Brass H62 Textured by One-Dimensional Ultrasonic Vibration-Assisted Turning. Micromachines, 12.10.3390/mi12111398 ↗
7. Friction and wear performance of lubricated micro-textured surface formed by laser processing10.1080/02670844.2021.1952041 ↗
8. Properties of variable distribution density of micro-textures on a cemented carbide surface10.1016/j.jmrt.2021.08.051 ↗
9. Effect of a micro-textured surface with deposited MoS2-Ti film on long-term wear performance in vacuum10.1016/j.surfcoat.2022.128722 ↗
10. Improving Tribological Performance of 42CrMo under Dry Sliding Conditions by Combining Rhombic-Textured Surfaces with Sn–Ag–Cu Solid Lubricant and MXene-Ti3C2TX10.1007/s11665-022-07186-5 ↗
11. Analysis of synergistic friction reduction effect on micro-textured cemented carbide surface by laser processing10.1016/j.optlastec.2022.108343 ↗
12. Zhao, J., Li, Z., Zhang, H., and Zhu, R. (2021). Prediction of Contact and Lubrication Characteristics of Micro-textured Surface Under Thermal Line Contact EHL. Front. Mech. Eng., 7.10.3389/fmech.2021.672588 ↗
13. Yang, H., Yang, S., and Tong, X. (2023). Study on the Matching of Surface Texture Parameters and Processing Parameters of Coated Cemented Carbide Tools. Coatings, 13.10.3390/coatings13040681 ↗
14. Disassembly damage and load-carrying capacity of shaft with surface micro-texture10.1080/02670844.2022.2113775 ↗
15. Synergistic effect of micro-textures and MoS2 on the tribological properties of PTFE film against GCr15 bearing steel
16. Zheng, M., He, C., and Yang, S. (2020). Optimization of Texture Density Distribution of Carbide Alloy Micro-Textured Ball-End Milling Cutter Based on Stress Field. Appl. Sci., 10.10.3390/app10030818 ↗
17. Friction performance of DLC film textured surface of high pressure dry gas sealing ring10.1007/s40430-019-1635-9 ↗
18. Study on the relationship between machining errors and transmission accuracy of planetary roller screw mechanism using analytical calculations and machine-learning model
19. A critical assessment of surface texturing for friction and wear improvement10.1016/j.wear.2016.11.020 ↗
20. Generative design of texture for sliding surface based on machine learning10.1016/j.triboint.2022.108139 ↗
21. Machine learning: A review of classification and combining techniques10.1007/s10462-007-9052-3 ↗
22. Gas–liquid two-phase flow field analysis of two processing teeth spiral incremental cathode for the deep special-shaped hole in ECM10.1007/s00170-023-11714-5 ↗
23. Numerical simulation and experimental investigation on tribological performance of micro-dimples textured surface under hydrodynamic lubrication10.1016/j.ijmecsci.2019.105095 ↗
24. Weisberg, S. (2005). Applied Linear Regression, John Wiley & Sons.10.1002/0471704091 ↗
25. Decision tree methods: Applications for classification and prediction
26. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
27. Suthaharan, S. (2016). Support Vector Machine. Machine Learning Models and Algorithms for Big Data Classification, Springer.10.1007/978-1-4899-7641-3 ↗
28. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network10.1016/j.physd.2019.132306 ↗
29. Recent advances in convolutional neural networks10.1016/j.patcog.2017.10.013 ↗
30. Emerging trends: A gentle introduction to fine-tuning10.1017/S1351324921000322 ↗
31. Application and comparison of several machine learning algorithms and their integration models in regression problems10.1007/s00521-019-04644-5 ↗
32. Carvalho, D.V., Pereira, E.M., and Cardoso, J.S. (2019). Machine Learning Interpretability: A Survey on Methods and Metrics. Electronics, 8.10.3390/electronics8080832 ↗