US 12,233,789 B2
Predicting failures of electrical loads and wiring harnesses of a vehicle
Xinyu Du, Oakland Township, MI (US); Lyall Kenneth Winger, Waterloo (CA); Infane Lowe, Grand Blanc, MI (US); and Suresh Gopalakrishnan, Troy, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Jan. 4, 2023, as Appl. No. 18/149,802.
Prior Publication US 2024/0217460 A1, Jul. 4, 2024
Int. Cl. B60R 16/02 (2006.01); B60R 16/023 (2006.01); B60R 16/03 (2006.01); G06N 3/0464 (2023.01)
CPC B60R 16/0232 (2013.01) [B60R 16/0207 (2013.01); B60R 16/03 (2013.01); G06N 3/0464 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method for training a model for predicting electrical failures within a vehicle comprising:
selectively enabling and disabling an electrical load for the vehicle, wherein the selectively enabling comprises enabling and disabling the electrical load with high frequency for a short period of time using an electronic-fuse (e-fuse);
collecting operational data about the electrical load during the selectively enabling and disabling of the electrical load, wherein collecting the operational data comprises recording transient/static responses during the enabling and disabling; and
training the model based at least in part on the operational data to predict a failure associated with the electrical load or a wiring harness associated with the electrical load.