Degradation estimation apparatus, computer program, and degradation estimation method

Patent metadata

Field	Value
Publication number	US-11243262-B2
Application number	US-201916981865-A
Country	US
Kind code	B2
Filing date	Mar 14, 2019
Priority date	Mar 20, 2018
Publication date	Feb 8, 2022
Grant date	Feb 8, 2022

Abstract

This deterioration estimation device is provided with: an SOH acquisition unit which acquires the SOH of a power storage element at a first time and the SOH at a second time after the first time; and a learning processing unit which trains a learning model on the basis of learning data which, as input data, includes time series data relating to the state of the power storage element from the first time to the second time, and the SOH at the first time and, as output data, includes the SOH at the second time.

First claim

The invention claimed is:

1. A degradation estimation apparatus for estimating degradation of an energy storage device, the apparatus comprising:
a state of health (SOH) acquisition unit that acquires a SOH of an energy storage device at a first time point and a SOH at a second time point after the first time point; and
a learning processing unit that causes a learning model to learn based on learning data with time-series data relating to a state of the energy storage device from the first time point to the second time point and the SOH at the first time point as input data and with the SOH at the second time point as output data.

2. The degradation estimation apparatus according to claim 1 , wherein:
the apparatus further comprises a current data acquisition unit that acquires current data of the energy storage device detected in time series, and
the learning processing unit causes the learning model to learn based on time-series data relating to a state of charge (SOC) of the energy storage device from the first time point to the second time point based on the current data acquired by the current data acquisition unit.

3. The degradation estimation apparatus according to claim 2 , further comprising:
a voltage data acquisition unit that acquires voltage data of the energy storage device; and
a correction unit that corrects data at a certain time point among the time-series data relating to the SOC based on the voltage data acquired by the voltage data acquisition unit.

4. The degradation estimation apparatus according to claim 2 , further comprising:
a storage unit that stores the current data acquired by the current data acquisition unit; and
an erasing unit that erases the current data from the first time point to the second time point among the current data stored in the storage unit when the learning model is caused to learn based on time-series data relating to the SOC from the first time point to the second time point.

5. The degradation estimation apparatus according to claim 1 , wherein:
the apparatus further comprises a temperature data acquisition unit that acquires temperature data of the energy storage device detected in time series, and
the learning processing unit causes the learning model to learn based on learning data with time-series data relating to temperature data of the energy storage device from the first time point to the second time point as input data.

6. The degradation estimation apparatus according to claim 1 , wherein the learning processing unit causes the learning model to learn based on learning data with an elapsed period from a point of manufacturing the energy storage device to the first time point as input data.

7. The degradation estimation apparatus according to claim 1 , wherein the learning processing unit causes the learning model to learn based on learning data with a total energized electricity amount from the point of manufacturing the energy storage device to the first time point as input data.

8. The degradation estimation apparatus according to claim 1 , wherein the learning processing unit provides a plurality of learning periods from the first time point to the second time point over a use period of the energy storage device to cause the learning model to learn based on learning data.

9. The degradation estimation apparatus according to claim 1 , wherein degradation of the energy storage device is estimated using a learning-completed learning model caused to learn by the learning processing unit.

10. A degradation estimation apparatus for estimating degradation of an energy storage device, the apparatus comprising:
a state of health (SOH) acquisition unit that acquires a SOH at a first time point of the energy storage device; and
a learning-completed learning model that uses time-series data relating to a state of the energy storage device from the first time point to a second time point and the SOH at the first time point as input data to estimate a SOH at the second time point.

11. A degradation estimation apparatus for estimating degradation of an energy storage device, the apparatus comprising:
an output value acquisition unit that inputs time-series data relating to a state of charge (SOC) to a degradation simulator configured to estimate a state of health (SOH) of the energy storage device based on variation in a SOC of the energy storage device, and acquires a SOH output by the degradation simulator;
an input value acquisition unit that acquires the time-series data relating to the SOC, input to the degradation simulator;
a learning processing unit that uses the time-series data relating to the SOC acquired by the input value acquisition unit and the SOH acquired by the output value acquisition unit as learning data to cause a learning model to learn;
a SOC acquisition unit that acquires a time-series data relating to the SOC of the energy storage device;
a SOH acquisition unit that acquires a SOH of the energy storage device; and
a relearning processing unit that uses the time-series data relating to the SOC acquired by the SOC acquisition unit and the SOH acquired by the SOH acquisition unit as learning data to cause relearning of the learning model caused to learn by the learning processing unit.

12. The degradation estimation apparatus according to claim 11 , wherein:
the SOH acquisition unit acquires a SOH of the energy storage device at a first time point and a SOH at a second time point after the first time point, and
the SOC acquisition unit acquires time-series data relating to the SOC of the energy storage device from the first time point to the second time point.

13. The degradation estimation apparatus according to claim 11 , wherein:
the learning model has a convolutional neural network,
the apparatus comprises a two-dimensional data generation unit that generates two-dimensional SOC data containing a plurality of time points and SOC values at the respective plurality of time points based on the time-series data relating to the SOC acquired by the input value acquisition unit, and
the learning processing unit uses the two-dimensional SOC data generated by the two-dimensional data generation unit as learning data to cause the learning model to learn.

14. The degradation estimation apparatus according to claim 13 , wherein:
the two-dimensional data generation unit generates two-dimensional SOC data containing a plurality of time points and SOC values at the respective plurality of time points based on the time-series data relating to the SOC acquired by the SOC acquisition unit, and
the relearning processing unit uses the two-dimensional SOC data generated by the two-dimensional data generation unit as learning data to cause the learning model, caused to learn by the learning processing unit, to relearn.

15. The degradation estimation apparatus according to claim 11 , wherein the output value acquisition unit acquires a SOH that is output by the degradation simulator to which time-series data relating to a temperature is input together with the time-series data relating to the SOC.

16. The degradation estimation apparatus according to claim 15 , wherein:
the input value acquisition unit acquires time-series data relating to the temperature input to the degradation simulator, and
the learning processing unit uses the time-series data relating to the temperature acquired by the input value acquisition unit and the SOH acquired by the output value acquisition unit as learning data to cause the learning model to learn.

17. The degradation estimation apparatus according to claim

Assignees

• Gs Yuasa Int Ltd

Inventors

• Ukumori Nan

Classifications

• H01M10/48 Primary

  Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte (constructional details of current conducting connections for detecting conditions inside cells or batteries, e.g. details of voltage sensing terminals, H01M50/569) · CPC title

• G01R31/367

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

• G01R31/382

  Arrangements for monitoring battery or accumulator variables, e.g. SoC · CPC title

• G01R31/392 Primary

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

• H01M10/42

  Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells (H01M10/60 takes precedence) · CPC title