ELECTRIC VEHICLE BATTERY MONITORING SYSTEM

• US 20180086222A1
• Filed: 09/23/2016
• Published: 03/29/2018
• Est. Priority Date: 09/23/2016
• Status: Active Grant

• Current Assignee: Faraday & Future Inc.
• Original Assignee: Faraday & Future Inc.
• Inventors: Juang, Larry Way-Jay, Yan, Xu, Sikaria, Mayank, Zhao, Ruxiu, Weicker, Phillip John, Paryani, Anil
• Granted Patent: US 10,183,590 B2
• Time in Patent Office: Days
• CPC Class Codes: B60L 2240/545 Temperature
• CPC Class Codes: B60L 58/12 responding to state of charge [SoC]
• CPC Class Codes: B60L 58/24 for controlling the temperature of batteries
• CPC Class Codes: G01R 31/367 Software therefor, e.g. for battery testing using modelling or look-up tables
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: H02J 2310/48 for electric vehicles [EV] or hybrid vehicles [HEV]
• CPC Class Codes: H02J 7/0063 with circuits adapted for supplying loads from the battery
• CPC Class Codes: H02J 7/007182 in response to battery voltage
• CPC Class Codes: H02J 7/007194 of the battery
• CPC Class Codes: Y02T 10/70 Energy storage systems for electromobility, e.g. batteries

Abstract

Systems and methods for monitoring and controlling a battery are disclosed. Systems can include a battery having an output voltage and an output current when delivering power, a load driven by power delivered from the battery, battery output voltage and current sensing circuits, and processing circuitry coupled to the battery output voltage and current sensing circuits. The processing circuitry may implement a recurrent neural network for battery state estimation.

Claims

1. A battery powered apparatus comprising:

a battery comprising one or more electrochemical cells, the battery having an output voltage and an output current when delivering power;

a load driven by power delivered from the battery;

a battery output current sensing circuit; and

a battery management system comprising processing circuitry coupled to the battery output current sensing circuit, the processing circuitry configured to model behavior of the battery with at least one recurrent neural network, the at least one recurrent neural network comprising a set of input layer nodes, a set of hidden layer nodes, and a set of output layer nodes, and wherein at least some of the hidden layer nodes receive at least one input from an input layer node and at least one input from a previous time state of a hidden layer node.

2. The battery powered apparatus of claim 1, wherein the at least one recurrent neural network has a single output layer node corresponding to battery output voltage.

3. The battery powered apparatus of claim 1, wherein the at least one recurrent neural network has two input layer nodes corresponding to battery output current and integrated battery output current.

4. The battery powered apparatus of claim 1, comprising at least two recurrent neural networks, wherein each recurrent neural network comprises a set of input layer nodes, a set of hidden layer nodes, and a set of output layer nodes, and wherein at least some of the hidden layer nodes receive at least one input from an input layer node and at least one input from a previous time state of a hidden layer node.

5. The battery powered apparatus of claim 4, wherein a first recurrent neural network has a single output layer node corresponding to battery temperature.

6. The battery powered apparatus of claim 5, wherein a second neural network has an input layer node corresponding to the battery temperature output layer node of the first recurrent neural network.

7. The battery powered apparatus of claim 6, wherein the second recurrent neural network has a single output layer node corresponding to battery output voltage.

8. The battery powered apparatus of claim 1, wherein the at least one neural network includes gating for generating a state of the hidden layer.

9. A method of operating a battery powered apparatus, the method comprising:

driving a load of the apparatus with a battery;

sensing the output current of the battery at defined intervals while driving the load;

predicting an output voltage that will be exhibited by the battery under selected output current conditions using at least one recurrent neural network, the at least one recurrent neural network comprising a set of input layer nodes, a set of hidden layer nodes, and a set of output layer nodes, and wherein at least some of the hidden layer nodes receive at least one input from an input layer node and at least one input from a previous time state of a hidden layer node; and

driving the load of the apparatus with the selected current sourced from the battery.

10. The method of claim 9, comprising sensing a battery temperature.

11. The method of claim 9, comprising using a recurrent neural network to predict a battery temperature.

12. The method of claim 11, comprising using the predicted battery temperature as an input to a second neural network, wherein the second neural network generates the predicted output voltage.

13. The method of claim 9, comprising sensing a battery output voltage and a battery temperature.

14. The method of claim 13, comprising retraining the at least one neural network while driving the load of the apparatus with the battery.

15. An electric vehicle with a battery monitoring system, the vehicle comprising:

a battery;

a powertrain comprising at least one electric motor driven by the battery;

a battery output current sensing circuit; and

processing circuitry coupled to the battery output voltage sensing circuit and the battery output current sensing circuit, the processing circuitry configured to model behavior of the battery with at least one recurrent neural network, the at least one recurrent neural network comprising a set of input layer nodes, a set of hidden layer nodes, and a set of output layer nodes, and wherein at least some of the hidden layer nodes receive at least one input from an input layer node and at least one input from a previous time state of a hidden layer node.

16. The electric vehicle of claim 15, wherein the at least one recurrent neural network has a single output layer node corresponding to battery output voltage.

17. The electric vehicle of claim 15, wherein the at least one recurrent neural network has two input layer nodes corresponding to battery output current and integrated battery output current.

18. The electric vehicle of claim 15, comprising at least two recurrent neural networks, wherein each recurrent neural network comprises a set of input layer nodes, a set of hidden layer nodes, and a set of output layer nodes, and wherein at least some of the hidden layer nodes receive at least one input from an input layer node and at least one input from a previous time state of a hidden layer node.

19. The electric vehicle of claim 18, wherein a first recurrent neural network has a single output layer node corresponding to battery temperature.

20. The electric vehicle of claim 19, wherein a second neural network has an input layer node corresponding to the battery temperature output layer node of the first recurrent neural network.

21. The electric vehicle of claim 20, wherein the second recurrent neural network has a single output layer node corresponding to battery output voltage.

22. The electric vehicle of claim 17, comprising powertrain control circuitry that is configured to receive an output from the at least one recurrent neural network and control the powertrain based at least in part on the output.

23. The electric vehicle of claim 15, wherein the processing circuitry is further configured to calculate a state of health of the battery using outputs of the at least one recurrent neural network.

24. The electric vehicle of claim 15, wherein the processing circuitry is further configured to estimate an instantaneous power limit of the battery pack in real time based at least in part on outputs of the at least one recurrent neural network.

25. The electric vehicle of claim 24, further comprising updating a pedal map of the electric vehicle based on the estimated instantaneous power limit.