US 12,216,972 B2
Method for obtaining a temporal model of a magnetic bearing, device for modelling the magnetic bearing and associated systems
Francois Caire, Paris (FR); and Lakdar Sadi-Haddad, Nogent sur Marne (FR)
Assigned to SKF Magnetic Mechatronics, Saint-Marcel (FR)
Filed by SKF Magnetic Mechatronics, Saint-Marcel (FR)
Filed on Feb. 12, 2021, as Appl. No. 17/174,744.
Prior Publication US 2021/0279387 A1, Sep. 9, 2021
Int. Cl. G06F 30/27 (2020.01)
CPC G06F 30/27 (2020.01) 5 Claims
OG exemplary drawing
 
1. A method for obtaining a temporal model of a magnetic bearing comprising:
providing a magnetic bearing modelling device, the magnetic bearing modelling device having a at least one processing unit,
providing the magnetic bearing, the first processing unit being configured to receive reference data from the magnetic bearing,
generating the reference data representative of characteristics of the magnetic bearing created by operation of the magnetic bearing, and
producing, by the at the least one processing unit, the temporal model of the magnetic bearing from the reference data comprising temporal data, wherein the reference data comprise learning data and validation data, the learning data comprising at least one input reference data set and at least one output reference data set, and the validation data comprising a first validation data set comprising a first input validation data set and a first output validation data set, and
wherein the method further comprises generation of learning data by the at least one processor comprising:
a) generating a first transient temporal data set of wave forms and of random amplitudes,
b) determining the input reference data set from the first transient temporal data set of wave forms and of random amplitudes,
c) injecting the input reference data set into a nonlinear model of the magnetic bearing or in the magnetic bearing,
d) collecting the output reference data set, the output reference data resulting from exciting the nonlinear model of the magnetic bearing or of the magnetic bearing by the input reference data set, and
e) saving the input reference data set and of the associated output reference data set, and
generating the first validation data set comprising:
f) generating a second transient temporal data set of wave forms and of random amplitudes different from the first transient temporal data set,
g) determining the first input validation data set from the second transient temporal data set of wave forms and of random amplitudes,
h) injecting the first input validation data set into the nonlinear model of the magnetic bearing or into the magnetic bearing,
i) collecting the first output validation data set, the first output validation data set resulting from the excitation of the nonlinear model of the magnetic bearing or of the magnetic bearing by the first input validation data set, and
j) saving the first input validation data set and of the associated first output validation data set.