Method and system for carrying out a simulation

Patent metadata

Field	Value
Publication number	US-12468870-B2
Application number	US-202217578672-A
Country	US
Kind code	B2
Filing date	Jan 19, 2022
Priority date	Feb 3, 2021
Publication date	Nov 11, 2025
Grant date	Nov 11, 2025

Abstract

A simulation includes loading a first generator of a Cycle Generative Adversarial Network (CycleGAN) with a model dataset during a training phase in order to train the first generator in cooperation with a first discriminator of the CycleGAN assigned to the first generator, and loading a second generator of the CycleGAN with a hardware dataset in order to train the second generator in cooperation with a second discriminator of the CycleGAN assigned to the second generator, and loading the first generator with an input dataset during an operational phase in order to provide an output dataset.

First claim

The invention claimed is:

1 . A method for performing a simulation, comprising:
loading a first generator of a Cycle Generative Adversarial Network (CycleGAN) with a model dataset based on an emulator for a first vehicle powertrain during a training phase to train the first generator in cooperation with a first discriminator of the CycleGAN assigned to the first generator; loading a second generator of the CycleGAN with a hardware dataset based on test bed experiments for the first vehicle powertrain to train the second generator in cooperation with a second discriminator of the CycleGAN assigned to the second generator; and loading the first generator with an input dataset based on an emulator for a second vehicle powertrain during an operational phase to provide an output dataset that simulates the second vehicle powertrain.

2 . The method of claim 1 , further including evaluating the output dataset with the first generator during the operational phase.

3 . The method of claim 1 , wherein the CycleGAN is a conditional CycleGAN and the method further includes parameterizing the output dataset with a parameterization vector.

4 . The method of claim 1 , wherein the first generator and/or the second generator and/or the first discriminator and/or the second discriminator include a deep neural network.

5 . The method of claim 1 , wherein the first generator and/or the second generator and/or the first discriminator and/or the second discriminator include a recurrent neural network.

6 . A non-transitory computer-readable medium having stored thereon instructions to cause a computer to perform the method of claim 1 .

7 . A computer-implemented system for performing simulations, comprising:
a computing device comprising a processor and a memory, the memory storing instructions executable by the processor, the instructions including instructions to: train a Cycle Generative Adversarial Network (CycleGAN), the CycleGAN including:
a first generator,
a second generator,
a first discriminator assigned to the first generator, and a second discriminator assigned to the second generator,
to load the first generator with a model dataset based on an emulator for a first vehicle powertrain during a training phase to train the first generator in cooperation with the first discriminator and to load the second generator with a hardware dataset in order to train the second generator in cooperation with the second discriminator, and to load the first generator with an input dataset based on an emulator for a second vehicle powertrain during an operational phase to provide an output dataset that simulates the second vehicle powertrain.

8 . The system of claim 7 , wherein the instructions include instructions to evaluate the output dataset with the first generator during the operational phase.

9 . The system of claim 7 , wherein the CycleGAN is designed as a conditional CycleGAN, and wherein the instructions include instructions to parameterize the output dataset with a parameterization vector.

10 . The system of claim 7 , wherein the first generator and/or the second generator and/or the first discriminator and/or the second discriminator include a deep neural network.

11 . The system of claim 7 , wherein the first generator and/or the second generator and/or the first discriminator and/or the second discriminator include a recurrent neural network.

Assignees

• Ford Global Tech Llc

Inventors

• Aslandere Turgay Isik
• Perez Guzman Eduardo
• De Smet Frederik
• Roettger Daniel

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06F2111/08

  Probabilistic or stochastic CAD · CPC title

• G06N3/08

  Learning methods · CPC title

• G06F30/27 Primary

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title