Detection of Damage of Rotor-bearing Systems Using Experimental Data Analysis

Rolling element bearings are critical components and widely used in many rotating machines such as automobiles, aerospace, weaving, machine tools that frequently fail. The vibration of the bearing-rotor influences the security, performance of the rotating machines and working life of the whole plant. In the present research work, a mathematical model of the vibration amplitude of the bearing is established through experimental data based analysis (EDBA). A new mathematical model technique for rotor-bearing systems is established. Furthermore, a model analysis on bearing system is carried out by using EDBA, the defect frequencies and vibration amplitude responses of the rotor-bearing system are obtained, and experimental result has been validated. The Neural Network (NN) is tested to verify the validation of the new EDBA. The method proposed in this paper for vibration characteristics calculation of a rotor-bearing is credible and save time and costs by timely detection of eminent bearing failure