Apparatus and method for determining state of change (SOC) and state of health (SOH) of electrical cells
Systems and methods for prediction of state of charge (SOH), state of health (SOC) and other characteristics of batteries using acoustic signals, includes determining acoustic data at two or more states of charge and determining a reduced acoustic data set representative of the acoustic data at the two or more states of charge. The reduced acoustic data set includes time of flight (TOF) shift, total signal amplitude, or other data points related to the states of charge. Machine learning models use at least the reduced acoustic dataset in conjunction with non-acoustic data such as voltage and temperature for predicting the characteristics of any other independent battery.
1. A method of identifying a battery, the method comprising:
transmitting one or more input acoustic signals into at least a portion of a test battery;
detecting one or more response signals generated in response to the one or more input acoustic signals;
forming a test data set comprising at least the one or more response signals;
comparing the test data set with one or more reference data sets of one or more reference batteries, the reference data sets comprising at least respective response signals generated in response to one or more input acoustic signals transmitted into at least portions of the reference batteries; and
identifying the test battery based on the comparison.
2. The method of claim 1 , wherein the test battery is of an unknown type or chemistry, and identifying the test battery comprises determining the type or chemistry of the test battery as being the same as or most similar to a known type or chemistry of at least one of the one or more reference batteries.
3. The method of claim 2 , comprising determining that the test data set is the same as or most similar to the reference data set of the at least one of the one or more reference batteries.
4. The method of claim 1 , further comprising determining one or more characteristics of the one or more reference batteries, the one or more characteristics comprising one or more of a state of charge (SoC), state of health (SoH), or physical states of one or more internal components of the respective one or more reference batteries.
5. The method of claim 4 , comprising determining corresponding characteristics of the test battery based on the one or more characteristics of the one or more reference batteries.
6. The method of claim 1 , wherein the test battery is one or more of an unknown manufacturer, manufacturing batch or manufacturing lot, and identifying the test battery comprises determining one or more of the manufacturer, manufacturing batch or manufacturing lot of the test battery as being the same as or most similar to a known manufacturer, manufacturing batch or manufacturing lot of at least one of the one or more reference batteries.
7. The method of claim 1 , wherein:
the test data set further comprises the one or more input signals transmitted into at least the portion of the test battery, and
at least one of the one or more reference data sets further comprises the one or more input signals transmitted into at least the portion of at least one reference battery.
8. An apparatus comprising:
means for transmitting one or more input acoustic signals into at least a portion of a test battery;
means for detecting one or more response signals generated in response to the one or more input acoustic signals;
means for forming a test data set comprising at least the one or more response signals;
means for comparing the test data set with one or more reference data sets of one or more reference batteries, the reference data sets comprising at least respective response signals generated in response to one or more input acoustic signals transmitted into at least portions of the reference batteries; and
means for identifying the test battery based on the comparison.