Vehicle energy management system using prognostics

• US 20050137764A1
• Filed: 12/19/2003
• Published: 06/23/2005
• Est. Priority Date: 12/19/2003
• Status: Active Grant

• Current Assignee: Lear Corporation
• Original Assignee: Lear Corporation
• Inventors: Alvarez-Troncoso, Ignacio, Pinas, Joan Fontanilles, Guasch, Jordi Mestre
• Granted Patent: US 7,076,350 B2
• Time in Patent Office: Days
• US Class Current: 701/36
• CPC Class Codes: B60R 16/03 for supply of electrical power to vehicle subsystems or for circuit arrangements for charging batteries H02J7/00
• CPC Class Codes: B60W 10/08 including control of electric propulsion units, e.g. motors or generators
• CPC Class Codes: B60W 20/11 using model predictive control [MPC] strategies, i.e. control methods based on models predicting performance utilising navigation and traffic information in the control strategy B60W20/12
• CPC Class Codes: B60W 2050/0057 Frequency analysis, spectral techniques or transforms
• CPC Class Codes: G05B 13/026 using a predictor
• CPC Class Codes: G05B 13/027 using neural networks only

Abstract

An energy management system for controlling an electrical system comprises data collection components, such as sensors, for providing quantified variables for forming an instantaneous state vector. A time series predictor generates an estimated future vector value in response to the instantaneous state vector. An electrical system manager includes predetermined decision rules invoked in response to the estimated future vector value to adapt the electrical system to expected electrical conditions.

Claims

1. An energy management system for controlling an electrical system, comprising:

data collection components providing quantified variables for forming an instantaneous state vector;

a time series predictor generating an estimated future vector value in response to said instantaneous state vector;

an electrical system manager including predetermined decision rules invoked in response to said estimated future vector value to adapt said electrical system to expected electrical conditions.

2. The energy management system of claim 1 wherein said time series predictor comprises an artificial neural network.

3. The energy management system of claim 2 wherein said artificial neural network is comprised of a feed-forward network.

4. The energy management system of claim 2 wherein said time series predictor further comprises a memory buffer coupled to said artificial neural network for time sampling contents of said artificial neural network and providing said time sampled contents to said artificial neural network when generating a subsequent estimated future vector value.

5. The energy management system of claim 2 wherein said artificial neural network provides a probability value associated with said estimated future vector value.

6. The energy management system of claim 5 wherein said time series predictor further comprises a memory buffer coupled to said artificial neural network for time sampling contents of said artificial neural network and providing said time sampled contents to said artificial neural network when generating a subsequent estimated future vector value.

7. The energy management system of claim 6 further comprising a probability calculator for generating said probability value in response to said time sampled contents.

8. The energy management system of claim 1 wherein said electrical system comprises an automotive electrical system of an automotive vehicle and wherein said data collection components are comprised of sensors connected within said automotive vehicle for generating said quantified variables in response to dynamic behavior of said automotive electrical system.

9. The energy management system of claim 8 further comprising:

a plurality of electrical system actuators responsive to commands from said electrical system manager according to said predetermined decision rules.

10. The energy management system of claim 8 further comprising:

a plurality of smart distribution nodes within said automotive electrical system; and

a communication network coupling said plurality of smart distribution nodes.

11. The energy management system of claim 10 wherein said electrical system manager is distributed among said smart distribution nodes.

12. The energy management system of claim 1 further comprising a central module containing said electrical system manager.

13. The energy management system of claim 1 wherein said electrical system manager comprises an electrical energy storing manager, a battery manager, a quiescent current manager, a dynamic load manager, and a dynamic power generation and conversion manager for providing a core functionality.

14. The energy management system of claim 13 wherein said electrical system manager further comprises a customized function manager for providing an add-on functionality.

15. A method of managing electrical energy within an electrical system, said method comprising the steps of:

collecting a plurality of quantified variables corresponding to said electrical system;

forming an instantaneous state vector;

generating an estimated future vector of said quantified variables by inputting said instantaneous state vector into a time series predictor;

adjusting said electrical system in response to said estimated future vector.

16. The method of claim 15 wherein said step of generating an estimated future vector is comprised of:

inputting said instantaneous state vector into an input layer of an artificial neural network;

processing outputs of said input layer together with outputs of a buffer memory in a hidden layer of said artificial neural network;

time sampling predetermined contents of said artificial neural network in said buffer memory for processing in said hidden layer with a subsequent time sample of said quantified variables; and

processing outputs of said hidden layer in an output layer of said artificial neural network to produce said estimated future vector.

17. The method of claim 16 further comprising the step of:

comparing said time sampled predetermined contents with a predetermined set of training vectors to identify a probability value.

18. The method of claim 15 wherein said adjusting step is comprised of:

generating commands in an electrical system energy manager in response to said estimated future vector according to predetermined decision rules; and

providing said commands to a plurality of electrical system actuators.

19. The method of claim 18 wherein said plurality of electrical system actuators include a plurality of smart distribution nodes.

20. The method of claim 19 wherein said electrical system manager is distributed among said smart distribution nodes.