Use of Artificial Neural Network (ANN) to Determining Surface Parameters, Friction and Wear during Pin-on-Disc Tribotesting

Abstract

In tribological analysis of machine elements (such as gears, ball/roller bearings etc.), surface roughness plays very important role, ultimately it affects the friction coefficient, wear, rolling contact fatigue (micro pitting) and other failure mechanisms. Surface geometry and topography changes with time (number of cycles) during rolling/sliding motion of contacting surfaces. So, it is important to show the variation of surface topography parameter during wear process. This work presents the evolution of roughness parameters, wear and friction coefficient during pin-on-disc tribotesting under dry condition. The test is performed using pin on disc apparatus under room temperature condition. The pin (25mm long, 6mm diameter) is made of medium carbon steel (AISI 1038) whereas the disc (165mm diameter, 8mm thickness) is made of high carbon steel (SAE 52100). This works demonstrates the potential of Artificial Neural Network (ANN) for prediction of roughness parameters, friction coefficient and wear coefficient. Experimental results obtained from wear testing are compared with those obtained using artificial neural network (ANN) analysis. A very good agreement in results suggests that a well trained neural network is capable to predict the parameters in wear process.