Method and apparatus for operating a system for providing states of health of electrical energy stores for a multiplicity of devices with the aid of machine learning methods

Patent metadata

Field	Value
Publication number	US-11733313-B2
Application number	US-202117487800-A
Country	US
Kind code	B2
Filing date	Sep 28, 2021
Priority date	Sep 29, 2020
Publication date	Aug 22, 2023
Grant date	Aug 22, 2023

Abstract

A method for operating a central processing unit which is communicatively connected to a plurality of devices having electrical energy stores, includes determining a data-based state of health model which is trained to assign a state of health to an operating feature point which characterizes operation of a corresponding electrical energy store of the electrical energy stores of the plurality of devices and results from a plurality of operating features, determining operating feature points for the electrical energy stores of the plurality of devices, and selecting at least one of the operating feature points based on state uncertainties of the states of health of all operating feature points of the corresponding electrical energy store, such that the at least one operating feature point has a highest relevance for improving the state uncertainties of the operating feature points determined.

First claim

What is claimed is:

1. A method for operating a central processing unit which is communicatively connected to a plurality of devices having electrical energy stores, comprising:
determining a data-based state of health model which is trained to assign a state of health to a corresponding operating feature point of a plurality of operating feature points which characterizes operation of a corresponding electrical energy store of the electrical energy stores of the plurality of devices and results from a plurality of operating features;
determining the plurality of operating feature points for the electrical energy stores of the plurality of devices;
selecting at least one of the operating feature points based on state uncertainties of the states of health of all operating feature points of the corresponding electrical energy store, such that the at least one operating feature point has a highest relevance for improving the state uncertainties of the operating feature points determined;
selecting at least one device from the plurality of devices based on the at least one selected operating feature point;
measuring a present actual state of health in the at least one selected device; and
retraining or updating the data-based state of health model based on a result of the measurement of the actual state of health.

2. The method according to claim 1 , wherein at least one of the operating feature points is selected by:
determining a predefined number of the operating feature points with highest state uncertainties of the state of health; and
selecting, from the predefined number of the operating feature points, that operating feature point which is closest to a centroid of a cluster area found using a clustering method.

3. The method according to claim 2 , wherein the clustering method is carried out using at least one of K-means, EM clustering, Gaussian mixture models, and competitive learning.

4. The method according to claim 1 , further comprising:
determining the plurality of operating features for an evaluation period from temporal characteristics of operating variables of the corresponding electrical energy store.

5. The method according to claim 1 , wherein the data-based state of health model is a purely data-based or hybrid model with a probabilistic regression model including a Gaussian process model or a Bayesian neural network.

6. The method according to claim 1 , wherein:
the at least one selected operating feature point is checked for physical safety limits and limitations of an operation of the corresponding electrical energy store according to at least one predefined criterion, and
a selection of at least one device from the plurality of devices based on the at least one selected operating feature point for measuring the present actual state of health depends on a result of the check for physical safety limits and limitations.

7. The method according to claim 1 , wherein the selection of at least one device from the plurality of devices with states of the corresponding electrical energy store which correspond optimally to the operating feature point is carried out using an active learning method including pool-based sampling, uncertainty sampling, variance reduction, and/or expected error reduction.

8. The method according to claim 1 , wherein:
model parameters of a retrained state of health model are transmitted to the plurality of devices, and
the state of health is determined in the plurality of devices.

9. The method according to claim 1 , wherein the plurality of devices comprise a motor vehicle, a pedelec, an aircraft, a drone, a machine tool, a consumer electronics device including a mobile telephone, an autonomous robot, and/or a household appliance.

10. The method according to claim 1 , wherein a computer program product includes instructions which, when the computer program product is executed by at least one data processing device, causes the at least one data processing device to carry out the method.

11. The method according to claim 10 , the computer program product is stored on a non-transitory machine-readable storage medium.

12. An apparatus for operating a central processing unit which is communicatively connected to a plurality of devices having electrical energy stores, comprising:
at least one data processing device configured to:
determine a data-based state of health model which is trained to assign a state of health to a corresponding operating feature point of a plurality of operating feature points which characterizes operation of a corresponding electrical energy store of the electrical energy stores of the plurality of devices and results from a plurality of operating features;
determine the plurality of operating feature points for the electrical energy stores of the plurality of devices;
select at least one of the operating feature points based on state uncertainties of the states of health of all operating feature points of the corresponding electrical energy store, such that the at least one operating feature point has a highest relevance for improving the state uncertainties of the operating feature points determined;
select at least one device from the plurality of devices based on the at least one selected operating feature point;
measure a present actual state of health in the at least one selected device; and
retrain or update the data-based state of health model based on a result of the measurement of the actual state of health.

Assignees

• Bosch Gmbh Robert

Inventors

• Simonis Christian
• Woll Christoph

Classifications

• G06N3/091

  Active learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G01R31/392 Primary

  Determining battery ageing or deterioration, e.g. state of health · CPC title

• G01R31/367

  Software therefor, e.g. for battery testing using modelling or look-up tables · CPC title

• G01R31/396

  Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery · CPC title