Method and apparatus for estimating state of battery

1. A battery state estimation apparatus comprising:

a sensing data acquirer configured to acquire sensing data of a battery; and

a state of health (SOH) information estimator configured to

divide the sensing data based on a predetermined time interval,

extract a segment comprising a predetermined number of items of the divided sensing data, and

estimate SOH information of the battery based on a changing pattern of the divided sensing data included in the segment, and previous SOH information corresponding to a previous segment.

2. The apparatus of claim 1 , wherein the sensing data comprises any one or any combination of voltage data, current data, temperature data, pressure data, and humidity data of the battery, which are sensed by a sensor configured to sense the battery.

3. The apparatus of claim 1 , wherein the sensing data acquirer is configured to:

update the sensing data based on an update cycle.

4. The apparatus of claim 1 , wherein the sensing data acquirer is configured to:

acquire the sensing data based on a control signal received from an external source.

5. The apparatus of claim 1 , wherein the SOH information estimator is configured to:

generate a segment vector based on the divided sensing data included in the segment.

6. The apparatus of claim 5 , wherein the SOH information estimator is configured to:

generate the segment vector for each item of the sensing data.

7. The apparatus of claim 5 , wherein the SOH information estimator is configured to:

map the segment vector to a feature space of which a dimension is lower than a dimension of the segment vector, based on a predetermined mapping parameter; and

convert the mapped segment vector into a feature vector having a dimension equal to the dimension of the feature space.

8. The apparatus of claim 7 , wherein the SOH information estimator is configured to:

apply the feature vector and a predetermined learning parameter to a predetermined learning model to estimate a remaining capacity of the battery; and

estimate the SOH information of the battery based on the remaining capacity of the battery.

9. The apparatus of claim 8 , wherein the SOH information estimator is configured to:

apply the feature vector, a pre-estimated remaining capacity of the battery, and the predetermined learning parameter to the predetermined learning model to estimate the remaining capacity of the battery.

10. The apparatus of claim 8 , wherein the SOH information estimator is configured to:

acquire either one or both of the predetermined mapping parameter and the predetermined learning parameter from an external source.

11. The apparatus of claim 1 , wherein a size of the segment is between 1000 and 9000 seconds.

12. The apparatus of claim 11 , wherein the size of the segment is between 3000 and 9000 seconds.

13. The apparatus of claim 1 , wherein the SOH information estimator is configured to extract the segment from two or more of voltage data, current data, temperature data, pressure data, and humidity data of the battery.

14. A battery state estimation apparatus comprising:

a sensing data acquirer configured to acquire sensing data of a battery; and

a state of health (SOH) information estimator configured to:

periodically estimate SOH information of the battery and

perform the estimating based on a changing pattern of processed data generated by processing the sensing data and previous SOH information of the battery estimated in a previous cycle.

15. The apparatus of claim 14 , further comprise a buffer configured to store the previous SOH information.

16. The apparatus of claim 14 , wherein the processed data comprises any one or any combination of divided sensing data into which the sensing data is divided based on a predetermined time interval, a segment including a predetermined quantity of divided sensing data, a segment vector generated based on the divided sensing data included in the segment, and a feature vector into which the segment vector is converted.

17. The apparatus of claim 16 , wherein the SOH information estimator is configured to generate the segment based on an estimation cycle of the SOH information.

18. The apparatus of claim 14 , wherein the SOH information estimator is configured to apply the previous SOH information and the processed data to a learning model, and estimate the SOH information of the battery based on a result of the applying.

19. A battery state estimation method comprising:

acquiring sensing data of a battery;

dividing the sensing data based on a predetermined time interval;

extracting a segment comprising a predetermined number of items of the divided sensing data; and

estimating state of health (SOH) information of the battery based on a changing pattern of the divided sensing data included in the segment, and previous SOH information corresponding to a previous segment.

20. An apparatus comprising:

a processor configured to

divide data of a battery into items based on a predetermined time interval,

extract a segment comprising a predetermined number of the items, and

estimate a remaining capacity of the battery based on a changing pattern of the divided data included in the segment, and previous SOH information corresponding to a previous segment.

21. The apparatus of claim 20 , wherein the processor is configured to:

generate a vector comprising the predetermined number of the items included in the segment; and

estimate the remaining capacity based on the vector.

22. The apparatus of claim 20 , wherein the processor is configured to:

estimate the remaining capacity of the battery during a partial charging or discharging of the battery.

23. The apparatus of claim 20 , wherein the processor is configured to:

estimate the remaining capacity of the battery further based on a pre-estimated remaining capacity of the battery.