Adaptive Real-Time Driver Advisory Control for a Hybrid Electric Vehicle to Achieve Fuel Economy Improvement

• US 20110172864A1
• Filed: 06/08/2010
• Published: 07/14/2011
• Est. Priority Date: 06/08/2010
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Filev, Dimitar Petrov, Syed, Fazal Urrahman, Tseng, Fling
• Granted Patent: US 8,190,319 B2
• Time in Patent Office: Days
• US Class Current: 701/22
• CPC Class Codes: B60K 6/445 Differential gearing distribution type
• CPC Class Codes: B60L 2240/486 Operating parameters
• CPC Class Codes: B60W 10/06 including control of combustion engines
• CPC Class Codes: B60W 10/08 including control of electric propulsion units, e.g. motors or generators
• CPC Class Codes: B60W 20/00 Control systems specially adapted for hybrid vehicles hybrid vehicle design, B60K6/00; electric vehicles B60L
• 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 2050/0095 Automatic control mode change
• CPC Class Codes: B60W 2510/1005 Transmission ratio engaged
• CPC Class Codes: B60W 2540/103 Accelerator thresholds, e.g. kickdown
• CPC Class Codes: B60W 2540/12 Brake pedal position
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 30/1882 characterised by the working point of the engine, e.g. by using engine output chart
• CPC Class Codes: B60W 50/16 Tactile feedback to the driver, e.g. vibration or force feedback to the driver on the steering wheel or the accelerator pedal
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: Y02T 10/40 Engine management systems
• CPC Class Codes: Y02T 10/62 Hybrid vehicles
• CPC Class Codes: Y02T 10/84 Data processing systems or methods, management, administration
• CPC Class Codes: Y10S 903/903 having energy storing means, e.g. battery, capacitor

Abstract

A vehicle powertrain controller includes a fuzzy logic-based adaptive algorithm with a learning capability that estimates a driver'"'"'s long term driving preferences. An adaptive algorithm arbitrates competing requirements for good fuel economy, avoidance of intrusiveness and vehicle drivability. Vehicle performance is maintained in accordance with a driver'"'"'s driving style.

Claims

1. An adaptive driver advisory control system for a powertrain in a vehicle for managing power distribution to vehicle traction wheels from at least one of two power sources;

the powertrain comprising a driver controlled vehicle accelerator pedal, the control system comprising;

an adaptive real-time driver advisory controller with a logic-based algorithm for learning a driver'"'"'s driving style;

the controller being calibrated with powertrain operating data corresponding to maximum fuel economy;

the controller being configured for monitoring the driver'"'"'s style and driver-controlled power demands including a driver-readable driving style information feedback sub-system, whereby fuel economy of the power source is maximized for a given learned driving style of a driver during a vehicle driving event under monitored sets of vehicle driving conditions.

2. The control system set forth in claim 1 wherein the controller is configured to normalize a variable indication of driver accelerator pedal response to changes in vehicle driving conditions and to normalize vehicle operating variables;

the controller being configured to develop output signals based on the operating variables, the output signals indicating an advised accelerator pedal position within advised accelerator pedal position boundaries;

the feedback sub-system being configured to provide driver advisory information based on the output signals whereby the driver may accept and reject the advisory information.

3. The control system set forth in claim 2 wherein the controller includes an adaptive algorithm for use in monitoring the driver'"'"'s acceptance and rejection of the advisory information, the controller being adapted to receive monitored driver'"'"'s acceptance and rejection information whereby values of preferred driving style of the driver are learned and used in developing the advisory information.

4. The control system set forth in claim 3 wherein the adaptive algorithm is used to continually monitor a reaction of the driver to the advisory information whereby driver preferences over time are estimated to achieve informed consumption of fuel for the power source in accordance with a driver'"'"'s driving style while reducing intrusiveness for the driver.

5. The control system set forth in claim 4 wherein the adaptive algorithm is a fuzzy rule-based algorithm.

6. The control system set forth in claim 5 wherein the controller is adapted to determine driving conditions for developing the learned information regarding the driver'"'"'s driving style.

7. The control system set forth in claim 5 wherein the controller is adapted to learn a long-term identification of a driver'"'"'s style by monitoring over a long term with a slow forgetting factor based learning of the advisory information.

8. The system set forth in claim 2 wherein the controller is configured to recognize steady state conditions based on driver accelerator pedal response, vehicle speed, vehicle acceleration, and vehicle fuel consumption where driver driving behaviour is acceptable and the advised accelerator pedal position may remain unchanged while improving fuel economy of a vehicle.

9. The system set forth in claim 2 wherein the controller is configured to respond to a driver'"'"'s temporary change in driving style by interrupting sub-system feedback driving time interval corresponding to the temporary change.

10. The system set forth in claim 2 wherein the controller is configured to recognize steady state conditions based on driver accelerator pedal response, vehicle speed, vehicle acceleration, and vehicle fuel consumption where driver driving behavior can be improved by changing the advised accelerator pedal position to improve fuel economy of the vehicle.

11. The system set forth in claim 2 wherein the controller is configured to recognize transient efficient conditions based driver accelerator pedal response, vehicle speed, vehicle acceleration, and vehicle fuel consumption where driver driving behavior is acceptable and the advised accelerator pedal position remains unchanged for a given set of driving conditions as fuel economy of the vehicle is improved.

12. The system set forth in claim 2 wherein the controller is configured to recognize transient conditions based driver accelerator pedal response, vehicle speed, vehicle acceleration, and vehicle fuel consumption where driver driving behavior can be improved by reducing the advised accelerator pedal position to improve fuel economy of the vehicle.

13. The system set forth in claim 2 wherein the controller is adapted to monitor driver style during a short time interval determined by a defined forgetting factor whereby monitored driving style during that time interval has limited effect on a driver'"'"'s long term learned driving style.

14. A control method for controlling an accelerator pedal controlled hybrid electric vehicle powertrain having a mechanical power source and an electro-mechanical power source, an adaptive real-time fuel economy advisory system including a controller with an adaptive algorithm for learning a vehicle driver'"'"'s driving preference;

the method comprising;

monitoring a driver'"'"'s driving style during a defined term of a given driving event characterized by multiple vehicle operating conditions; and

providing advisory feedback information to a vehicle driver for changing driver behavior for a given vehicle operating condition, the feedback information being based on driving preference of the driver, whereby vehicle performance acceptable for a driver'"'"'s style of driving is achieved while maintaining good fuel economy corresponding to that driving style.

15. The method set forth in claim 14 wherein the advisory feedback is an advised change in accelerator pedal position is maintained within upper and lower calculated boundaries.

16. The method set forth in claim 15 wherein the adaptive algorithm dynamically adapts parameters of fuzzy logic rules to each of multiple sets of vehicle driving conditions whereby feedback information includes driver advice for adjusting accelerator pedal position to conform driving style to current driving conditions while reducing intrusiveness.

17. The method set forth in claim 15 wherein the adaptive algorithm monitors a reaction of the driver to the advisory feedback information to determine frequency of a driver'"'"'s acceptance and a driver'"'"'s reaction of the advisory feedback information, whereby driving style over a long term and over a short term can be identified.

18. The method set forth in claim 17 wherein the controller is configured to calculate a forgetting factor value, the controller adjusting the forgetting factor to learn driving style during either a long term or a short term.

19. The method set forth in claim 18 wherein a fast forgetting factor is used in a short term when the driver wishes to disregard feedback information during a temporary driver command for increased vehicle performance, whereby such human control experience with use of a fuzzy-based advisory information will reduce unwanted intrusiveness for the driver during a long term.

20. The method set forth in claim 18 wherein the controller is adapted to respond to input variables based on fuzzy rules, a first of the input variables being fuel economy error between actual fuel economy and optimal fuel economy, and a second of the variables being rate of change of the fuel economy error.

21. The method set forth in claim 20 wherein a third of the input variables is input power from the mechanical power source.

22. The method set forth in claim 20 wherein a first portion of the fuzzy rules governs steady state vehicle operating conditions and a second portion governs transient operating conditions.