Device and method for predicting state of battery

1. A device for predicting a state of a battery, the device comprising:

a data measuring unit configured to measure information about the battery and output first data;

a data producing unit configured to reflect a change in available capacity of the battery based on at least a portion of the first data to calculate a corrected state of charge and process the first data based on the corrected state of charge to generate second data, and output the second data; and

a battery state estimating unit configured to estimate state information of the battery based on the second data,

wherein the data producing unit includes:

a data arithmetic unit configured to generate the corrected state of charge and battery cycle data based on current data and output the corrected state of charge and the battery cycle data; and

a data generator configured to process the first data based on the corrected state of charge and the battery cycle data to generate the second data.

2. The device of claim 1 , wherein the data arithmetic unit calculates the corrected state of charge using the current data and a rated capacity of the battery, when the battery is in a first state, and calculates the corrected state of charge using the current data and the previously estimated state information, when the battery is in a second state.

3. The device of claim 1 , wherein the battery state estimating unit performs machine learning.

4. The device of claim 3 , wherein the machine learning is based on at least one of decision tree learning, a support vector machine, a genetic algorithm, an artificial neural network, a convolutional neural network, a recurrent neural network, and reinforcement learning.

5. The device of claim 1 , wherein the state information includes at least one of an available capacity of the battery, a current remaining capacity of the battery, and a remaining useful life of the battery.

6. A device for predicting a state of a battery, the device comprising:

a data measuring unit configured to measure information about the battery and output first data;

a data producing unit configured to reflect a change in available capacity of the battery based on at least a portion of the first data to calculate a corrected state of charge and process the first data based on the corrected state of charge to generate second data, and output the second data; and

a battery state estimating unit configured to estimate state information of the battery based on the second data,

wherein the data producing unit includes a plurality of buffers, classifies the first data depending on a classification criterion based on the corrected state of charge, and stores the first data in the plurality of buffers depending on the classification criterion.

7. The device of claim 6 , wherein the data producing unit outputs the second data to the battery state estimating unit, when the first data is stored in each of the plurality of buffers.

8. A method for predicting a state of a battery, the method comprising:

measuring current data, voltage data, and temperature data for the battery;

calculating a corrected state of charge based on the current data;

generating battery cycle data based on the corrected state of charge;

classifying the current data, the voltage data, and the temperature data for each interval of a value of the corrected state of charge;

processing the current data, the voltage data, and the temperature data classified for each interval of the value of the corrected state of charge;

storing the data processed for each interval of the value of the corrected state of charge in a buffer; and

estimating the state of the battery based on the stored data.

9. The method of claim 8 , further comprising:

performing machine learning for the state of the battery.

10. The method of claim 9 , wherein the machine learning is based on at least one of decision tree learning, a support vector machine, a genetic algorithm, an artificial neural network, a convolutional neural network, a recurrent neural network, and reinforcement learning.