Method and apparatus for determining temperatures in an electric machine
A method for determining a temperature of a component of an electric machine includes providing a plurality of trained neural networks, providing a current measurement of a plurality of operational parameters of the electric machine, and processing the operational parameters using the neural networks. The method further includes integrating output parameters issued by the neural networks over a time period, and issuing the integrated parameters as a temperature of the component.
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.
2. The method according to claim 1 , wherein an apparatus is configured to perform the method.
3. The method according to claim 1 , wherein a computer program comprises instructions which, when the computer program is executed by a computer, prompts the computer to perform the method.
4. The method according to claim 3 , wherein the computer program is stored on a non-transitory machine-readable storage medium.
5. The method according to claim 1 , wherein the second and third neural networks are configured to issue output parameters greater than or equal to zero.
6. The method according to claim 5 , wherein a rectified linear unit (“ReLu”) or quantity function is applied to the output parameters of the second and third neural networks.