Method and device for operating an electrically drivable motor vehicle depending on a predicted state of health of an electrical energy store

Patent metadata

Field	Value
Publication number	US-2021373082-A1
Application number	US-202117318367-A
Country	US
Kind code	A1
Filing date	May 12, 2021
Priority date	May 27, 2020
Publication date	Dec 2, 2021
Grant date	—

Abstract

A computer-implemented method for operating a motor vehicle, in particular an electrically drivable motor vehicle, depending on a predicted state of health of an electrical energy store, in particular a vehicle battery. The method includes: providing vehicle parameters which influence the state of health of the electrical energy store; predicting the vehicle parameters at a prediction point in time; ascertaining the predicted state of health depending on the predicted vehicle parameters with the aid of a data-based state of health model which is trained to output a state of health of the electrical energy store depending on the vehicle parameters; and signaling the predicted state of health.

First claim

What is claimed is:

1 . A computer-implemented method for operating a motor vehicle depending on a predicted state of health of an electrical energy store, the method comprising the following steps:
providing vehicle parameters which influence a state of health of the electrical energy store; predicting the vehicle parameters at a prediction point in time; ascertaining the predicted state of health depending on the predicted vehicle parameters using a data-based state of health model which is trained to output a state of health of the electrical energy store depending on the vehicle parameters; and signaling the predicted state of health.

2 . The method as recited in claim 1 , wherein the motor vehicle is an electrically drivable motor vehicle, and the electrical energy store is a vehicle battery.

3 . The method as recited in claim 1 , wherein the data-based state of health model is trained and/or provided external to the vehicle using vehicle parameter sets and assigned load states of the electrical energy store based on fleet data.

4 . The method as recited in claim 1 , wherein the state of health of the electrical energy store is indicated as remaining maximum charge capacity with respect to an initial charge capacity or as an indicator of a remaining service life.

5 . The method as recited in claim 1 , wherein the vehicle parameters indicate the state of health of the electrical energy store and include one or multiple of the following parameters: a temperature of the electrical energy store, a temporal load pattern, an age of the electrical energy store, a period of use of the electrical energy store, a cumulative charging over the service life and a cumulative discharge over the service life, a maximum charge current, a maximum discharge current, a charging frequency, an average charge current, an average discharge current, a power throughput during charging and discharging, a charging frequency, and a charging temperature.

6 . The method as recited in claim 1 , wherein the ascertaining of the predicted state of health is carried out depending on the predicted vehicle parameters also using surroundings parameters, the surroundings parameters including one or multiple of the following parameters: traffic data, information about traffic volume on a predicted route, weather data, and a location of the motor vehicle.

7 . The method as recited in claim 1 , wherein the ascertaining of the predicted state of health is carried out depending on the predicted vehicle parameters, at least one of the predicted vehicle parameters being ascertained by extrapolating the vehicle parameters at a point in time of the prediction.

8 . The method as recited in claim 1 , wherein data-based state of health model is configured as a hybrid model which applies a correction value, which results from a data-based correction model, through addition or multiplication, to a modeled state of health, which is ascertained using a physical or physically-motivated aging model.

9 . The method as recited in claim 1 , wherein the data-based state of health model includes a neural network, or a Bayesian neural network, or a Gaussian process model.

10 . The method as recited in claim 1 , wherein the predicted state of health is ascertained externally to the vehicle and communicated to the motor vehicle, or model parameters of the data-based state of health model are communicated to the motor vehicle and the predicted state of health is ascertained in the motor vehicle.

11 . The method as recited in claim 1 , wherein stress factors, which are taken into consideration in the data-based state of health model to determine the predicted state of health, are ascertained from historic profiles of vehicle parameters, the stress factors including in one or multiple of the following pieces of information: a frequency of charging with high currents, a frequency of driving at constantly high output, a frequency of charging at high surroundings temperature, and a frequency of a complete charge of the electrical energy store.

12 . A control unit for operating a motor vehicle, in particular an motor vehicle based on a predicted state of health of an electrical energy store, the control unit configured to:
provide vehicle parameters which influence the state of health of the electrical energy store; predicting the vehicle parameters at a prediction point in time; ascertaining the predicted state of health depending on the predicted vehicle parameters using a data-based state of health model which is trained to output a state of health of the electrical energy store depending on the vehicle parameters; signaling the predicted state of health.

13 . The control unit as recited in claim 12 , wherein the motor vehicle is an electrically drivable motor vehicle, and the electrical energy store is a vehicle battery.

14 . A non-transitory machine-readable memory medium on which is stored a computer program including program code for operating a motor vehicle depending on a predicted state of health of an electrical energy store, the computer program, when executed by a computer, causing the computer to perform the following steps:
providing vehicle parameters which influence a state of health of the electrical energy store; predicting the vehicle parameters at a prediction point in time; ascertaining the predicted state of health depending on the predicted vehicle parameters using a data-based state of health model which is trained to output a state of health of the electrical energy store depending on the vehicle parameters; and signaling the predicted state of health.

Assignees

• Bosch Gmbh Robert

Inventors

• Kupcsik Andras Gabor
• Simonis Christian
• Woll Christoph
• Klein Reinhardt

Classifications

• Y02T10/70

  Energy storage systems for electromobility, e.g. batteries · CPC title

• G01R31/374

  with means for correcting the measurement for temperature or ageing · CPC title

• B60L58/16 Primary

  responding to battery ageing, e.g. to the number of charging cycles or the state of health [SoH] · CPC title

• G01R31/396 Primary

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

• G01R31/392 Primary

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