Tribological Performance of Random Sinter Pores vs. Deterministic Laser Surface Textures: An Experimental and Machine Learning Approach

Abstract

This work critically scrutinizes and compares the tribological performance of randomly distributed surface pores in sintered materials and precisely tailored laser textures produced by different laser surface texturing techniques. The pore distributions and dimensions were modified by changing the sintering parameters, while the topological features of the laser textures were varied by changing the laser sources and structuring parameters. Ball-on-disc tribological experiments were carried out under lubricated combined sliding-rolling conditions. Film thickness was measured in-situ through a specific interferometry technique developed for the study of rough surfaces. Furthermore, a machine learning approach based on the radial basis function method was proposed to predict the frictional behavior of contact interfaces with surface irregularities. The main results show that both sintered and laser textured materials can reduce friction compared to the untextured material under certain operating conditions. Moreover, the machine learning model was shown to predict results with satisfactory accuracy. It was also found that the performance of sintered materials could lead to similar improvements as achieved by textured surfaces, even if surface pores are randomly distributed and not precisely controlled.

The role of manufacturing-induced texture on the tribological performance of cold work tool steels

“…It is important to note that the textures resulting from machining of the tools are stochastic, meaning they display randomness in dimensions, distribution, or organization. However, Boidi et al [21] showed that stochastic textures offer tribological performance similar to deterministic textures with precisely defined distributions and arrangements.…”

Physics-Informed Machine Learning—An Emerging Trend in Tribology

“…Meanwhile, there is a number of review articles showcasing the usages and many promises of AI and ML within tribology [1,2,[28][29][30][31]. However, a challenge remains in the training of AI/ML models, which relies heavily on the availability of large amounts of high-quality experimentally [32][33][34][35][36][37][38] or numerically [39][40][41][42] generated data. Ideally, these data should be FAIR (Findable, Accessible, Interoperable, and Reusable), meaning it should be well documented, easily accessible, compatible with different systems, and suitable for reuse in different contexts [43][44][45].…”

Numerical micro-texture optimization for lubricated contacts—A critical discussion

“…Generally, textures were able to reduce friction especially at low sliding speeds and a small texture radius with a rather high area density was reported to be most beneficial. Boidi et al [139,355] employed a Hardy multiquadric radial base function to predict the wear behaviour of sintered components under varying operating conditions in a ball-on-disk setup (mini-traction machine and lubricant film thickness measurements based on optical interferometry) as well as geometric or statistical characteristics of the dimples, grooves, and pores.…”