Modelling of shaft unbalance: Modelling a multi discs rotor using K-Nearest Neighbor and Decision Tree Algorithms.

• Unbalance parameters of multi discs rotor can be detected by artificial intelligent algorithms. • Used K-Nearest Neighbor Algorithm shows average accuracy as 86% for detecting unbalance parameters. • Decision Tree Algorithm represents lower average accuracy as 70% for detecting unbalance parameters. • So, in this case, K-Nearest Neighbor Algorithm reveals better accuracy in comparison to Decision Tree Algorithm. Multi discs rotors are widely used in the industry. Shaft unbalance in multi-discs' rotors is the main failure origin that leads to global failures in rotary systems. Unbalance parameters that must be detected in the shaft are focused on this study. Unbalance parameters are eccentric mass value, eccentric radius, and disc number which are presenting an unbalance location. The main aim of the current paper is to identify unbalance parameters of a rotating shaft having multi-discs by artificial intelligent methods namely KNN and Decision Tree Algorithm. For both algorithms, data derived from a fabricated test rig consists of a shaft in which four discs are mounted on that. The results show that the KNN presents more accuracy in estimating of unbalance parameters compared to the Decision Tree in terms of unbalance locating. [ABSTRACT FROM AUTHOR]