Neural network controlled power distribution element

• US 6,369,545 B1
• Filed: 08/17/2000
• Issued: 04/09/2002
• Est. Priority Date: 08/17/1999
• Status: Expired due to Fees

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Harvey, Timothy W., Williams, James D.
• Primary Examiner(s): TOATLEY, GREGORY J
• Application Number:
  US09/641,245
• Time in Patent Office: 600 Days
• Field of Search: 320/101, 455/427
• US Class Current: 320/101
• CPC Class Codes: H02J 7/35 with light sensitive cells
• CPC Class Codes: Y02E 10/56 Power conversion systems, e.g. maximum power point trackers

Abstract

The power distribution control element significantly improves the efficiency by which solar energy is distributed and controlled to large phased array antenna assemblies by providing current directly from photovoltaic cells to lithium-ion battery cells through a neural-network based charge controller. The small current required to operate each transmit/receive module is provided from an adjacent battery cell rather than a large centralized battery assembly located in the spacecraft bus. In the preferred embodiment, the charge control is regulated by a back-propagation neural network.

Claims

1. A power system, comprising:

a first electrical load;

a first power module interconnected with said first electrical load and comprising;

a first battery cell interconnected with said first electrical load;

first sensors interconnected with said first battery cell;

a first photovoltaic cell interconnected with said first battery cell, wherein said first photovoltaic cell generates a first low voltage current;

first charge electronics associated with said first battery cell; and

a first neural network interconnected with said first sensors and that outputs a first charge control signal to said first charge electronics, wherein said first photovoltaic cell provides said first low voltage current directly to said first battery cell based upon said first charge control signal;

a second electrical load; and

a second power module interconnected with said second electrical load and comprising;

a second battery cell interconnected with said second electrical load;

second sensors interconnected with said second battery cell;

a second photovoltaic cell interconnected with said second battery cell, wherein said second photovoltaic cell generates a second low voltage current;

second charge electronics associated with said second battery cell; and

a second neural network interconnected with said second sensors and that outputs a second charge control signal to said second charge electronics, wherein said second photovoltaic cell provides said second low voltage current directly to said second battery cell based upon said second charge control signal, wherein said first and second power modules are autonomous and independent of each other.

2. The system of claim 1 wherein each of said first and second battery cells comprise a lithium-ion battery cell.

3. The system of claim 1 wherein each of said first and second neural networks comprise a back-propagating neural network.

4. The system of claim 1 wherein said first sensors monitor at least one of a voltage, a temperature, and a charge current associated with said first battery cell, and wherein said second sensors monitor at least one of a voltage, a temperature, and a charge current associated with said second battery cell.

5. The system of claim 1 wherein said first battery cell is mounted directly on said first electrical load, and wherein said second battery cell is mounted directly on said second electrical load.

6. The system of claim 1 wherein said first photovoltaic cell is interconnected with each of said first battery cell and said first neural network by a first polyimide connection, said first battery cell is interconnected with said first electrical load by a second polyimide connection, said second photovoltaic cell is interconnected with each of said second battery cell and said second neural network by a third polyimide connection, and said second battery cell is interconnected with said second electrical load by a fourth polyimide connection.

7. A phased array antenna system comprising:

a first and a second transmit/receive (TR) module;

a first power module interconnected with said first TR module, wherein said first power module comprises;

a first battery cell interconnected with said first TR module;

first sensors interconnected with said first battery cell;

a first photovoltaic cell interconnected with said first battery cell, wherein said first photovoltaic cell generates a first low voltage current;

first charge electronics associated with said first battery cell; and

a first neural network interconnected with first sensors and that outputs a first charge control signal to said first charge electronics, wherein said first photovoltaic cell provides said first low voltage current directly to said first battery cell based upon said first charge control signal;

a second electrical load; and

a second power module interconnected with said second TR module and comprising;

a second battery cell interconnected with said second TR module;

second sensors interconnected with said second battery cell;

a second photovoltaic cell interconnected with said second battery cell, wherein said second photovoltaic cell generates a second low voltage current;

second charge electronics associated with said second battery cell; and

a second neural network interconnected with said second sensors and that outputs a second charge control signal to said second charge electronics, wherein said second photovoltaic cell provides said second low voltage current directly to said second battery cell based upon said second charge control signal, wherein said first and second power modules are autonomous and independent of each other.

8. The phased array antenna system of claim 7 wherein each of said first and second battery cells comprise a lithium-ion battery cell.

9. The phased array antenna system of claim 7 wherein each of said first and second neural networks comprise a back-propagating neural network.

10. The phased array antenna system of claim 7 wherein said first sensors monitor at least one of a voltage, a temperature, and a charge current associated with said first battery cell, and wherein said second sensors monitor at least one of a voltage, a temperature, and a charge current associated with said second battery cell.

11. The phased array antenna of claim 7 wherein said first battery cell is mounted directly on said first TR module, and wherein said second battery cell is mounted directly on said second TR module.

12. The phased array antenna system of claim 7 wherein said first photovoltaic cell is interconnected with each of said first battery cell and said first neural network by a first polyimide connection, said first battery cell is interconnected with said first TR module by a second polyimide connection, said second photovoltaic cell is interconnected with each of said second battery cell and said second neural network by a third polyimide connection, and said second battery cell is interconnected with said second TR module by a fourth polyimide connection.

13. A phased array antenna system comprising a plurality of radio frequency (RF) tiles, wherein at least one of said RF tiles has a front surface and a rear surface, and further includes:

a plurality of transmit/receive (TR) modules, each having at least one radiator on said front surface of said RF tile;

a battery powering said TR modules attached to said rear surface of said RF tile;

sensors monitoring predetermined parameters regarding the state of said battery;

a photovoltaic cell generating a low voltage current attached to said rear surface of said RF tile;

a charge regulator regulating current from said photovoltaic cell to charge said battery in response to a charge control signal; and

a neural network receiving said parameters from said sensors regarding the state of said battery and outputting said charge control signal for said charge regulator.

14. The phased array antenna system of claim 13 wherein said battery comprises a lithium-ion battery.

15. The phased array antenna system of claim 13 wherein said battery is sandwiched between said rear surface of said RF tile and said photovoltaic cell.

16. The phased array antenna system of claim 13 wherein said neural network comprises a back-propagating neural network.

17. The phased array antenna system of claim 13 wherein said battery parameters comprise battery voltage.

18. The phased array antenna system of claim 13 wherein said battery parameters comprises battery temperature.

19. The phased array antenna system of claim 13 wherein said battery parameters comprise charge current.

20. A phased array antenna system comprising:

a radio frequency (RF) tile that comprises a front surface and a rear surface;

a plurality of transmit/receive (TR) modules mounted on said front surface of said RF tile, wherein each said TR module comprises at least one radiator;

a battery cell attached to said rear surface of said RF tile and electrically interconnected with said plurality of TR modules;

sensors associated with said battery cell;

a photovoltaic cell electrically interconnected with said battery cell, wherein said photovoltaic cell generates a low voltage current;

charge electronics electrically interconnected with said battery cell and mounted on a surface of said battery cell that is opposite that which interfaces with said rear surface of said RF tile; and

a neural network electrically interconnected with both said sensors and said charge electronics and mounted on said surface of said battery cell that is opposite that which interfaces with said rear surface of said RF tile, wherein said photovoltaic cell provides said low voltage current to said battery cell based upon said charge control signal.