Intelligent energy management system for a vehicle and corresponding method

Patent metadata

Field	Value
Publication number	US-11247571-B2
Application number	US-201916686434-A
Country	US
Kind code	B2
Filing date	Nov 18, 2019
Priority date	Nov 18, 2019
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

An energy management system for a vehicle is disclosed. The vehicle includes one or more power sources configured to provide power to one or more recipients. The system includes a controller configured to determine an arbitration vector based at least partially on a state vector and an initial transformation function. The arbitration vector is determined as one or more points for which the initial transformation function attains a maximum value. The controller is configured to determine a current reward based on the arbitration vector and the state vector, the current reward being configured to minimize energy loss in the power sources. The controller is configured to determine an updated transformation function based at least partially on the initial transformation function and a total reward. The controller is configured to arbitrate a power distribution based in part on the updated arbitration vector.

First claim

What is claimed is:

1. An energy management system for a vehicle, the energy management system comprising:
one or more power sources configured to provide power for one or more recipients;
one or more sensors configured to obtain respective sensor data relative to the one or more power sources;
a controller in communication with the one or more sensors and having a processor and tangible, non-transitory memory on which instructions are recorded, execution of the instructions by the processor causing the controller to:
obtain a state vector based in part on the respective sensor data and select an initial transformation function, the state vector including a total power demand;
determine an arbitration vector based at least partially on the state vector and the initial transformation function, the arbitration vector being determined as one or more points for which the initial transformation function attains a maximum value;
determine a current reward based on the arbitration vector and the state vector;
determine a total reward as a sum of the current reward and a forecasted reward over a selected horizon size;
determine an updated transformation function based at least partially on the initial transformation function and the total reward;
obtain an updated arbitration vector based at least partially on the updated transformation function; and

wherein the controller is configured to arbitrate a power distribution based in part on the updated arbitration vector.

2. The energy management system of claim 1 , wherein:
the current reward is configured to minimize energy loss in the one or more power sources, the one or more power sources each providing a respective power (P S ); and
the controller is configured to arbitrate between the one or more power sources such that (P D =Σa i P S i ), with P D being the total power demand and a being a component of the updated arbitration vector.

3. The energy management system of claim 2 , wherein:
the one or more power sources include at least one battery module; and
the current reward is configured to minimize an electrical loss factor, a capacity loss factor and a charge depletion factor, the charge depletion factor being defined as a difference between a final state of charge and an initial charge of charge of the at least one battery module.

4. The energy management system of claim 2 , wherein:
the one or more power sources include at least one battery module defining a current to capacity ratio (I b /Q b ); and
the current reward includes a current limiting factor (SL I b ) based in part on the current to capacity ratio

(

I
b

Q
b

)

,

a first calibration parameter (m) and a second calibration parameter ( C rate ), such that SL I b =0, when [|I b /Q b |< C rate ] and

S
⁢

L

I
b

=

(



I
b

/

Q
b



-

C
¯

rate

)

·

(



I
b

/

Q
b



C
_

rate

)

m

,

when
⁢

[



I
b

/

Q
b



>

C
¯

rate

]

.

5. The energy management system of claim 4 , wherein:
the current reward includes respective normalizing factors (w i ) for an electrical loss factor (E loss ), a capacity loss factor (ΔQ loss ), a current limiting factor (SL I b ) and a charge depletion factor (ΔSoC) such that the current reward (r) is determined as: r=−(ω 1 ·E loss +ω 2 ·ΔQ loss +ω 3 ·ΔSoC+ω 4 ·SL I b ).

6. The energy management system of claim 1 , wherein:
the total reward at a time step k is determined as a sum of the current reward and a forecasted reward over the selected horizon size; and
the updated transformation function at the time step k is based in part on the total reward at the time step k.

7. The energy management system of claim 1 , wherein:
the controller is configured to selectively apply a calibrated discount factor and a calibrated robust learning rate; and
the updated transformation function at a current iteration is based in part on the updated transformation function from a prior iteration, the calibrated discount factor and the calibrated robust learning rate.

8. The energy management system of claim 1 , wherein the controller is configured to:
store the state vector and the arbitration vector at a current time step as buffered data;
obtain the updated transformation function at a previous time step (k−M) based in part on the total reward in the buffered data;
determine the forecasted reward over the selected horizon size (N); and
obtain the updated transformation function at a current time step k based in part on the forecasted reward and the current reward.

9. The energy management syst

Assignees

• Gm Global Tech Operations Llc

Inventors

• Haskara Ibrahim
• Hegde Bharatkumar
• Chang Insu
• Chang Chen-Fang

Classifications

• G06Q30/0207

  Discounts or incentives, e.g. coupons or rebates · CPC title

• B60R16/0315 Primary

  using multiplexing techniques (multiplexing for transmission of signals G08C15/00; multiplexing for electrical communication in general H04J) · CPC title

• G05B13/041

  in which a variable is automatically adjusted to optimise the performance · CPC title

• Y02T10/72

  Electric energy management in electromobility · CPC title

• Y02T10/7072

  Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors · CPC title