Surface Topography-Based Classification of Coefficient of Friction in Strip-Drawing Test Using Kohonen Self-Organising Maps

One of the important parameters of the sheet metal forming process is the coefficient of friction (CoF). Therefore, monitoring the friction coefficient value is essential to ensure product quality, increase productivity, reduce environmental impact, and avoid product defects. Conventional CoF monitoring techniques pose a number of problems, including the difficulty in identifying the features of force signals that are sensitive to the variation in the coefficient of friction. To overcome these difficulties, this paper proposes a new approach to apply unsupervised artificial intelligence techniques with unbalanced data to classify the CoF of DP780 (HCT780X acc. to EN 10346:2015 standard) steel sheets in strip-drawing tests. During sheet metal forming (SMF), the CoF changes owing to the evolution of the contact conditions at the tool-sheet metal interface. The surface topography, the contact loads, and the material behaviour affect the phenomena in the contact zone. Therefore, classification is required to identify possible disturbances in the friction process causing the change in the CoF, based on the analysis of the friction process parameters and the change in the sheet metal's surface roughness. The Kohonen self-organising map (SOM) was created based on the surface topography parameters collected and used for CoF classification. The CoF determinations were performed in the strip-drawing test under different lubrication conditions, contact pressures, and sliding speeds. The results showed that it is possible to classify the CoF using an SOM for unbalanced data, using only the surface roughness parameter Sq and selected friction test parameters, with a classification accuracy of up to 98%.