Smart battery management systems
Various implementations of a smart battery management system are provided. An example method includes identifying sensor data of a cell in a battery system; predicting, based on the sensor data, a failure event of the cell; and preventing the failure event by activating a control circuit connected to the cell.
1. A Smart Battery Management System (SBMS), comprising:
sensors configured to measure one or more metrics of a plurality of cells in a battery system, the sensors include at least movement sensors configured to measure movement of the plurality of cells, and the one or more metrics include at least acceleration of the plurality of cells associated with the at least movement sensors;
control circuits electrically coupled to the plurality of cells in the battery system;
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
identifying sensor data measured by at least one first sensor among the sensors, the sensor data indicating the one or more metrics of a first cell among the plurality of cells in the battery system;
predicting, by inputting the sensor data into a trained neural network, a failure event of the first cell; and
preventing the failure event by causing a first control circuit among the control circuits to disconnect the first cell from one or more additional cells among the plurality of cells in the battery system.
2. The SBMS of claim 1 , wherein the metrics comprise at least movement of the first cell and further at least one of a pressure, a temperature, a voltage, a current, a resistance, an impedance, or a capacitance associated with the first cell.
3. The SBMS of claim 1 , wherein the failure event comprises thermal runaway of the first cell.
4. The SBMS of claim 1 , wherein the battery system is powering a vehicle.
5. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by a pressure sensor, a pressure associated with the first cell.
6. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by a temperature sensor, a temperature associated with the first cell.
7. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by the at least movement sensors, a movement associated with the first cell.
8. The SBMS of claim 7 , wherein the at least movement sensors are accelerometers.
9. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by a voltage sensor, a voltage across with the first cell.
10. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by a current sensor, a current through the first cell.
11. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by an impedance sensor, an impedance associated with the first cell.
12. The SBMS of claim 2 , wherein operations of the at least one processor further comprising:
measuring, by the impedance sensor, a resistance associated with the first cell.
13. The SBMS of claim 12 , wherein the impedance and resistance associated with the first cell determines capacitance of the first cell.
14. The SBMS of claim 1 , wherein operations of the at least one processor further comprising:
identifying second sensor data of a second cell of the plurality of cells, the second sensor data being obtained during at least one second failure event of the second cell; and
training the neural network based on the second sensor data and an indication of the at least one second failure event.
15. The SBMS of claim 14 , the second failure event comprises thermal runaway of the second cell.
16. The SBMS of claim 1 , wherein preventing the failure event comprises:
modifying a current flowing through the first cell.
17. The SBMS of claim 1 , wherein preventing the failure event comprises:
disconnecting the first cell from the one or more additional cells.
18. The SBMS of claim 1 , wherein preventing the failure event comprises:
inputting the acceleration data obtained from the at least movement sensors;
predicting by inputting data from the at least movement sensors into the trained neural network, a failure event of the first cell based on the associated acceleration data from the first cell;
disconnecting the first cell from the one or more additional cells in response to the prediction of the trained neural network.