Triboinformatic modeling of the friction force and friction coefficient in a cam-follower contact using machine learning algorithms

Prediction of friction coefficient and torque in self-lubricating polymer radial bearings produced by additive manufacturing: A machine learning approach

“…Temperature, bearing load, and shaft rotation speed are other vital parameters that affect the frictional behavior of the bearing. 52 These parameters represent the complex interactions within FT and FC. To obtain a comprehensive knowledge of the bearing's tribological behavior, it is essential to consider more parameters related to operating conditions and material properties.…”

“…The calculation can be performed using equations 1 and 2, where T f denotes the FT, μ signifies the FC, F f denotes the friction force, and r indicates the bearing radius. 52 …”

“…It should also be noted that the results obtained may require experimental validation. [51][52][53] In recent years, there has been a growing utilization of ML techniques in the field of engineering tribology, as evidenced by the research conducted in the literature. Thankachan et al 54 conducted a study where they utilized statistical and ML techniques to optimize the tribological behavior of hybrid copper surface composites.…”

“…By utilizing historical tribological data, these models can make predictions about the future behavior of the system. 51–53 Diverse approaches are employed by ML algorithms to examine tribological data and identify relevant features. These techniques encompass linear regression, decision trees, support vector machines, neural networks, and deep learning models.…”

“…on tribological performance. 51–53 Analyzing tribological properties using ML can be useful in many areas such as material design, lubrication systems optimization, friction and wear reduction. However, a good dataset and appropriate feature selection are needed to obtain accurate results.…”