Damage classification plays a crucial role in the process of management in nearly every branch of industry. In fact, is becomes equally important as damage detection, since it can provide information of malfunction severity and hence lead to improvement of a production or manufacturing process. Within this paper selected supervised and unsupervised pattern recognition methods are employed for this purpose. The attention of the authors is given to assessment of selection, performance benchmarking and applicability of selected pattern recognition methods. The investigation is performed on the data collected using an experimental test grid and rolling element bearing with deteriorating condition of an outer race.