Author, Institution: Ignas Andrijauskas, Kaunas University of Technology
Science area, field of science: Technological Sciences, Electrical and Electronics Engineering, T001
Scientific Supervisors:
Prof. Dr. Rimas Adaškevičius (Kaunas University of Technology, Technological Sciences, Electrical and Electronics Engineering, T001) 2017– 2019.
Assoc. Prof. Dr. Vytautas Šiožinys (Kaunas University of Technology, Technological Sciences, Electrical and Electronics Engineering, T001) 2014– 2017.
Dissertation Defence Board of Electrical and Electronics Engineering Science Field:
Dr. Liudas Mažeika (Kaunas University of Technology, Electrical and Electronics Engineering T001) – chairman;
Dr. Renaldas Raišutis (Kaunas University of Technology, Electrical and Electronics Engineering T001);
Dr. Antans-Saulus Sauhats (Riga Technical University, Electrical and Electronics Engineering T001);
Dr. Dainius Udris(Vilnius Gediminas Technical University, Electrical and Electronics Engineering T001);
Dr. Algimantas Valinevičius (Kaunas University of Technology, Electrical and Electronics Engineering T001).
The doctoral dissertation is available at the library of Kaunas University of Technology (K. Donelaičio g. 20, Kaunas).
Annotation:
The aim of the presented study is the development of a new methodology for asynchronous motor fault diagnosis while using the well known and/or newly developed methods. The developed tools must enable ability to detect mechanical faults by use of the stator current signal. After the completion of simulating progressive unbalance, detailed dependency between information entropy and the level of unbalance has been revealed. No information has been detected in the reviewed scientific literature about the presented type of study. For the first time, the Neighborhood Component Feature Selection (NCFS) method has been applied for the selection of features for single-point fault diagnosis. The method for generalized roughness bearing fault diagnosis by the use of the stator current signal has been specified. No information has been noted on successive fault diagnosis with the use of the stator current signal.
