Method and apparatus for estimating state of battery
According to one aspect, a method to estimate a state of a battery includes receiving physical quantity information about a sensed physical quantity of a battery, obtaining estimated information of the battery from a battery model based on the received physical quantity information. The battery model includes a training model configured to determine internal battery information comprising potential information of an internal material of the battery based on the physical quantity information and a mathematical function. The method further includes calculating an ion concentration in the battery using the mathematical function based on the internal battery information to determine the estimated information of the battery.
1. A processor-implemented battery method to estimate a state of a battery, the method comprising:
receiving physical quantity information about a sensed physical quantity of a battery in a current period;
determining internal battery information comprising potential information of an internal material of the battery based on the physical quantity information by using a battery model;
calculating ion concentration in the battery based on the internal battery information by using the battery model; and
determining state information of the battery based on the ion concentration by using the battery model,
wherein the battery model is a model obtained by replacing a first function of an electrochemical model with a neural network model, and
wherein the neural network model is configured to generate the internal battery information in the current period using current information in the current period, an ion concentration in an electrolyte calculated in a previous period, electronic potential information determined in the previous period, and ionic potential information determined in the previous period.
2. The method of claim 1 , wherein the potential information of the internal material comprises solid-phase electrode potential information and electrolyte potential information.
3. The method of claim 1 , wherein
the sensed physical quantity comprises any one or any combination of any two or more of a sensed current, a sensed voltage, and a sensed temperature, and
the state information comprises any one or any combination of any two or more of an internal temperature, an estimated voltage, and a state of charge (SoC) of the battery.
4. The method of claim 1 , wherein the internal battery information further comprises either one or both of a current density distribution of an electrode of the battery and overpotential information related to the electrode of the battery.
5. The method of claim 1 , wherein
the neural network model is trained based on an output value in response to an input parameter of a reference battery and on an output parameter of the reference battery,
the input parameter comprises any one or any combination of any two or more of potential information about an internal substance of the reference battery from a first period, information about an ion concentration in an electrolyte of the reference battery from the first period, information about an ion concentration in a solid-phase of an electrode of the reference battery from the first period, internal temperature information about the reference battery from the first period, open-circuit voltage (OCV) information about the reference battery from the first period, and input current information about the reference battery from a second period, and
the output parameter comprises any one or any combination of any two or more of potential information of the internal material of the reference battery from the second period, information on a current density distribution in the electrode of the reference battery from the second period, and overpotential information of the reference battery from the second period.
6. The method of claim 5 , wherein the reference battery is the battery.
7. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1 .
8. The method of claim 1 , wherein the physical quantity information comprises any one or any combination of any two or more of current, voltage, and temperature.
9. An apparatus for estimating a state of a battery, the apparatus comprising:
a memory configured to store a battery model; and
a controller configured to receive physical quantity information about a sensed physical quantity of a battery in a current period, determine internal battery information comprising potential information of an internal material of the battery based on the physical quantity information by using the battery model, calculate ion concentration in the battery based on the internal battery information by using the battery model, and determine state information of the battery based on the ion concentration by using the battery model,
wherein the battery model is a model obtained by replacing a first function of an electrochemical model with a neural network model, and
wherein the neural network model is configured to generate the internal battery information in the current period using current information in the current period, an ion concentration in an electrolyte calculated in a previous period, electronic potential information determined in the previous period, and ionic potential information determined in the previous period.
10. The apparatus of claim 9 , wherein the potential information of the internal material comprises solid-phase electrode potential information of the battery and electrolyte potential information of the battery.
11. The apparatus of claim 9 , wherein
the sensed physical quantity comprises any one or any combination of any two or more of a sensed current, a sensed voltage, and a sensed temperature, and
the state information comprises any one or any combination of any two or more of an internal temperature, an estimated voltage, and a state of charge (SoC) of the battery.
12. The apparatus of claim 9 , wherein the internal battery information further comprises either one or both of a current density distribution of an electrode of the battery and overpotential information related to the electrode of the battery.
13. The apparatus of claim 9 , wherein
the neural network model is trained based on an output value in response to an input parameter of a reference battery and on an output parameter of the reference battery,
the input parameter comprises any one or any combination of any two or more of potential information about an internal substance of the reference battery from a first period, information about an ion concentration in an electrolyte of the reference battery from the first period, information about an ion concentration in a solid-phase of an electrode of the reference battery from the first period, internal temperature information about the reference battery from the first period, open-circuit voltage (OCV) information about the reference battery from the first period, and input current information about the reference battery from a second period, and
the output parameter comprises any one or any combination of any two or more of potential information of the internal material of the reference battery from the second period, information on a current density distribution in the electrode of the reference battery from the second period, and overpotential information of the reference battery from the second period.
14. The apparatus of claim 13 , wherein the reference battery is the battery.