US 12,314,098 B2
Method and apparatus for determining temperatures in an electric machine
Daniel Neyer, Stuttgart (DE); Leon Glass, Renningen (DE); Matthias Kraenzler, Dettingen (DE); and Wael Hilali, Stuttgart (DE)
Assigned to Robert Bosch GmbH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Apr. 12, 2023, as Appl. No. 18/299,631.
Claims priority of application No. 10 2022 203 727.8 (DE), filed on Apr. 13, 2022.
Prior Publication US 2023/0333614 A1, Oct. 19, 2023
Int. Cl. G06F 1/00 (2006.01); G06F 1/20 (2006.01); G06N 3/045 (2023.01); G06F 1/3203 (2019.01)
CPC G06F 1/206 (2013.01) [G06N 3/045 (2023.01); G06F 1/3203 (2013.01)] 6 Claims
OG exemplary drawing
 
1. A method for determining a temperature of a component of an electric machine, comprising:
providing a plurality of trained neural networks;
determining power losses of the component using a first neural network of the plurality of trained neural networks;
determining a thermal conductivity between the component and coolant using a second neural network of the plurality of trained neural networks;
determining a thermal conductivity between the component and an adjacent further component of the electric machine using a third neural network of the plurality of trained neural networks;
providing a current measurement of a plurality of operational parameters of the electric machine;
processing the plurality of operational parameters using the plurality of trained neural networks;
integrating output parameters output by the plurality of trained neural networks over a predetermined period of time; and
issuing the integrated output parameters as the determined temperature of the component,
wherein the first neural network is configured to issue output parameters greater than or equal to zero for any desired operational parameters and to issue an output parameter of zero for operational parameters that do not characterize operation of the electric machine.