Patent · US Active

Battery system state of health prediction modeling

US12228613B1 · kind B1 · utility

0Cited by
2References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 15, 2024
Grant dateFeb 18, 2025
Priority date
Expiry dateApr 15, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG01R31/378
  • WIPO fieldMeasurement
  • WIPO sectorInstruments

Abstract

A machine learning model may be trained for a target battery system. Reference initialization data may be generated by a reference battery system sharing one or more characteristics with the target battery system. Synthetic training data may be generated for the target battery system by determining simulated input parameters and simulated output parameters by supplying the simulated input parameters to a physics model. Upon determining that a subset of the reference initialization data matches a subset of the synthetic training data, a trained machine learning model based on the synthetic training data is determined. The trained machine learning model may be trained to predict a state of the target battery system based at least in part on one or more observed input parameters generated by the target battery system.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.