In data-driven bearing fault diagnosis, sufficient fault data is fundamental for algorithm training and validation, however, in most industry applications, only very few fault measurements can be provided, which brings bearing dynamics model as an alternative to produce bearing response under defects. In this paper, a Modelica model for the whole bearing test rig was built, including test bearing, driving motor and hydraulic loading system. For the test bearing, a 5 degree-of-freedom (5-DoF)

more »

... el was proposed to identify the normal bearing dynamics, and a fault model was employed to characterize the defect position, defect size, defect shape and multiple defects. Theory and process to implement the virtual bearing test bench in Modelica were detailed, and 3 cases were conducted to validate the effectiveness of the proposed model.