Method for soft-computing supervision of dynamical processes with multiple control objectives

• US 20070067050A1
• Filed: 09/20/2005
• Published: 03/22/2007
• Est. Priority Date: 09/20/2005
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Fregene, Kingsley, Lamba, Nitin, Ghosh, Ranjana
• Granted Patent: US 7,769,474 B2
• Time in Patent Office: Days
• US Class Current: 700/31
• CPC Class Codes: G05B 13/0275 using fuzzy logic only

Abstract

A method to supervise a local dynamical system having multiple preset control objectives and operating in conjunction with other dynamical systems. The method includes receiving state input from dynamical systems in an environment at a distributed soft computing level, generating weights and applying the weights to the preset control objectives using soft computing methods to form weighted control objectives. The weights are computed based on the received state input. The method also includes generating a command signal for the local dynamical system based on the weighted control objectives and transmitting the command signal to a controller in the local dynamical system.

Claims

1. A method to supervise a local dynamical system having multiple preset control objectives and operating in conjunction with other dynamical systems, the method comprising:

receiving state input from dynamical systems in an environment at a distributed soft computing level;

generating weights and applying the weights to the preset control objectives using soft computing methods to form weighted control objectives, wherein the weights are generated based on the received state input;

generating a command signal for the local dynamical system based on the weighted control objectives; and

transmitting the command signal to a controller in the local dynamical system.

2. The method of claim 1, wherein the command signal is a target value for a selected state of the local dynamical system.

3. The method of claim 1, the method further comprising:

modifying a reasoning/inference system in the distributed soft computing level based on the receiving and applying.

4. The method of claim 1, wherein receiving state input further comprises:

receiving local state input at an information coordination level from the local dynamical system;

receiving other-system state input at the information coordination level from other dynamical systems;

receiving external environment input at the information coordination level from an environment of the local dynamical system;

generating other state input at the information coordination level based on receiving the other-system state input and the external environment input; and

transmitting the other state input and the local state input to the distributed soft computing level as the state input.

5. The method of claim 4, wherein the local dynamical system and the other dynamical systems are on a dynamical system level at a lower level than the information coordination level.

6. The method of claim 4, wherein the information coordination level is internal to the distributed soft computing level.

7. The method of claim 1, wherein the distributed soft computing level comprises one or more soft computing schemes including fuzzy logic, fuzzy inference schemes, neural networks, evolutionary computation schemes, neural networks with on-line training, simulated annealing schemes, genetic algorithms and randomized heuristical algorithms located in a distributed intelligence system.

8. A system, the system comprising:

a local dynamical system at a dynamical system level;

a local intelligence system at a distributed soft computing level in communication with the local dynamical system, wherein the distributed soft computing level is higher than the dynamical system level; and

other dynamical systems at the dynamical system level in communication with respective other intelligence systems at the distributed soft computing level, wherein the local intelligence system generates a command signal for the local dynamical system and the other intelligence systems generate other command signals for the respective other dynamical systems.

9. The system of claim 8, wherein the local intelligence system is co-located with the local dynamical system and the other intelligence systems are co-located with respective other dynamical systems, wherein the local dynamical system and the other dynamical systems are autonomous dynamical systems.

10. The system of claim 8, wherein a local intelligence system is remotely located from the local dynamical system and the other intelligence systems are remotely located from respective other dynamical systems, wherein the local dynamical system and the other dynamical systems are semi-autonomous dynamical systems.

11. The system of claim 8, the system further comprising:

a local information exchanger at an information coordination level, the information coordination level between the dynamical system level and the distributed soft computing level, wherein the other dynamical systems communicate with the local intelligence system via the local information exchanger, and wherein the information coordination level includes other information exchangers.

12. The system of claim 11, wherein the local intelligence system and the local information exchanger are co-located with the local dynamical system and other intelligence systems and respective other information exchangers are co-located with respective other dynamical systems, wherein the local dynamical systems and the other dynamical systems are autonomous dynamical systems.

13. The system of claim 11, wherein the local intelligence system and the local information exchanger are remotely located from the local dynamical system, wherein the other intelligence systems and respective other information exchangers are remotely located from respective other dynamical systems, and wherein the local dynamical systems and the other dynamical systems are semi-autonomous dynamical systems.

14. The system of claim 8, wherein the intelligence system includes

a soft computing based supervisor receiving the state input of the local dynamical system;

a memory storing the preset control objectives of the local dynamical system;

a mixing system to apply weights to the respective preset control objectives, wherein the weights are based on the state input; and

a summation processor to generate the command signals, wherein the soft computing based supervisor modifies an initial set of intelligent reasoning algorithms based on the received state input.

15. The system of claim 8, wherein the local dynamical system comprises:

a controller operable to initiate an action for the dynamical system based on the command signal;

a plant operable to be modified according to the initiated action;

sensors to sense selected states; and

a transceiver to transmit the sensed selected states and to receive the command signal.

16. The system of claim 8, wherein the other dynamical systems are similar in structure and function to the local dynamical system, and wherein the local dynamical system is an other dynamical system for the other dynamical systems.

17. The system of claim 8, further comprising:

an environment in which the local dynamical system and the other dynamical systems are located; and

environmental sensors to sense selected states of the environment; and

a transmitter to transmit the sensed environmental selected states to the intelligence system.

18. The system of claim 8, wherein the local intelligence system comprises one or more soft computing schemes including fuzzy logic, fuzzy inference schemes, neural networks, evolutionary computation schemes, neural networks with on-line training, simulated annealing schemes, genetic algorithms and randomized heuristical algorithms.

19. A computer readable medium storing a computer program comprising:

computer readable code to receive state input from dynamical systems in an environment at a distributed soft computing level;

computer readable code in a soft computing methodology to generate weights and to apply the weights to preset control objectives to form weighted control objectives, wherein the weights are generated based on the received state input;

computer readable code to generate a command signal for the local dynamical system based on the weighted control objectives; and

computer readable code to transmit the command signal from the distributed soft computing level to the local dynamical system.

20. The medium of claim 19, further including:

computer readable code to modify a reasoning/inference system in the distributed soft computing level.

21. A local dynamical system, the system comprising:

means for receiving a state input from other dynamical systems sharing an environment;

means for determining a priority for control objectives of the dynamical system based on the received state input; and

means for receiving a command signal based on the determined priority.

22. The system of claim 21, further comprising:

means for modifying rules for determining the priority for control objectives of the dynamical system based on the received state input.