System and method for distinguishing and characterizing motor vehicles for control of automatic drivers

• US 5,761,626 A
• Filed: 12/26/1995
• Issued: 06/02/1998
• Est. Priority Date: 12/26/1995
• Status: Expired due to Fees

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Tascillo, Anya Lynn, Tascillo, Mark Anthony
• Primary Examiner(s): LOUIS JACQUES, JACQUES H
• Application Number:
  US08/578,354
• Time in Patent Office: 889 Days
• Field of Search: 364/431.01, 364/431.03, 364/431.08, 364/431.07, 364/431.04, 364/424.034, 364/424.032, 364/424.058, 364/424.36, 364/350, 364/551.01, 123/425, 123/436, 123/478, 123/419, 123/399, 477/117, 477/118, 477/120, 477/904, 477/155, 477/154, 477/144, 395/23, 395/24, 395/21, 395/22, 395/905, 395/911, 395/913, 395/924, 73/116, 73/117.3, 73/117.2
• US Class Current: 701/29
• CPC Class Codes: B60T 8/174 characterised by using special control logic, e.g. fuzzy logic , neural computing

Abstract

A motor vehicle related operating signal, such as a torque signal produced by operation of an engine of the motor vehicle, is monitored to produce a frequency signature for the vehicle. The frequency signature is filtered by a fuzzy spectral filter to extract a frequency membership for the vehicle which is utilized to generate characteristic signals representative of the vehicle. Signals representative of vehicle inertia (J), vehicle horsepower (HP) and relative vehicle temperature (RVT) are extracted by a radial basis function (RBF) neural network. These characteristic signals are then used to control the vehicle directly via a powertrain control module (PCM) or via a robot driver for vehicle test purposes. For robot control, an anticipated throttle lag and an anticipated brake lag are generated and used to more accurately and repeatedly control the robot to simulate a human driver in following acceleration curves for vehicle testing purposes.

Claims

1. A method for determining characteristics of a motor vehicle comprising the steps of:

monitoring a torque signal produced by operation of an engine of a motor vehicle;

filtering said torque signal to generate component frequency signals representative of component frequencies within said torque signal, by generating a frequency membership vector signal representative of the component frequencies within said torque signal; and

generating characteristic signals representative of relative temperature, inertia and horsepower of said motor vehicle in response to determined component frequencies within said torque signal by passing said frequency membership vector signal through a neural network.

2. A method for determining characteristics of a motor vehicle as claimed in claim 1 wherein said step of filtering said torque signal comprises the step of passing said torque signal through a fuzzy spectral filter.

3. A method for determining characteristics of a motor vehicle as claimed in claim 1 wherein said step of generating characteristic signals representative of characteristics of said motor vehicle comprises the step of passing said component frequency signals through a neural network.

4. A method for determining characteristics of a motor vehicle as claimed in claim 1 and wherein said method further provides for controlling said motor vehicle and further comprises the step of utilizing said characteristic signals to control operation of said motor vehicle.

5. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 4 wherein said step of utilizing said characteristic signals to control operation of said motor vehicle comprises the step of passing said characteristic signals to an electronic engine controller of said motor vehicle.

6. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 4 wherein said step of utilizing said characteristic signals to control operation of said motor vehicle comprises the step of controlling a robot vehicle driver while said motor vehicle is on a dynamometer.

7. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 6 wherein said step of monitoring a torque signal produced by operation of an engine of a motor vehicle comprises the step of monitoring torque of said dynamometer.

8. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 6 wherein the step of controlling a robot vehicle driver comprises the steps of generating an anticipated throttle lag signal in response to said characteristic signals.

9. A method for determining characteristics of and controlling a motor vehicle comprising the steps of:

monitoring a torque signal produced by operation of an engine of a motor vehicle;

filtering said torque signal to generate component frequency signals representative of component frequencies within said torque signal;

generating characteristic signals representative of characteristics of said motor vehicle in response to determined component frequencies within said torque signal;

utilizing said characteristic signals to control a robot vehicle driver and thereby operation of said motor vehicle while said motor vehicle is on a dynamometer, robot vehicle driver control including generation of an anticipated throttle lag signal generated in response to said characteristics signals;

generating speed schedule signals representative of vehicle speed over time for said motor vehicle;

generating brake and throttle action signals which are passed to said robot vehicle driver in response to a requested throttle position signal, a requested brake position signal and said anticipated throttle lag signal;

combining said speed schedule signals with a dynamometer roll speed signal, said characteristic signals, and said brake and throttle action signals to generate said requested throttle position signal and said requested brake position signal.

10. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 9 wherein said step of combining said speed schedule signals with a dynamometer roll speed signal, said characteristic signals, and said brake and throttle action signals to generate said requested throttle position signal and said requested brake position signal comprises the step of passing said speed schedule signals, said dynamometer roll speed signal, said characteristic signals, said brake action signal and said throttle action signal through a neural network.

11. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 10 wherein said step of generating brake and throttle action signals comprises the step of passing said requested throttle position signal and said requested brake position signal through a fuzzy logic scheduler.

12. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 11 further comprising the steps of:

generating shift schedule signals representative of manual gear and clutch operations over time for said motor vehicle;

generating gear and clutch action signals which are passed to said robot vehicle driver in response to gear position signals, clutch position signals and an engine speed signal; and

applying said shift schedule signals to clutch patterns to generate said gear position signals and clutch position signals.

13. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 12 wherein said step of generating gear and clutch action signals which are passed to said robot vehicle driver comprises the step of passing said gear position signals and said clutch position signals through a fuzzy logic scheduler.

14. A method for determining characteristics of and controlling a motor vehicle as claimed in claim 9 wherein said robot vehicle driver control further includes generation of an anticipated brake lag signal and said step of generating brake and throttle action signals is further responsive to said brake lag signal.

15. A system for characterizing a motor vehicle and controlling said motor vehicle via a robot vehicle driver, said motor vehicle being on a dynamometer and said system comprising:

a fuzzy spectral filter for filtering a torque signal produced by operation of an engine of a motor vehicle, said fuzzy spectral filter producing component frequencies within said torque signal;

a neural network for generating characteristic signals representative of characteristics of said motor vehicle in response to determined component frequencies within said torque signal;

a neural network for generating an anticipated throttle lag signal in response to said characteristic signals;

a source of speed schedule signals representative of speed of said motor vehicle over time;

a fuzzy scheduler for generating brake and throttle action signals which are passed to a robot vehicle driver in response to a requested throttle signal, a requested brake position signal and said anticipated throttle lag signal; and

a neural network for combining said speed schedule signals with a dynamometer roll speed signal, said characteristic signals, and said brake and throttle action signals to generate said requested throttle position signal and said requested brake position signal.

16. A system for characterizing and controlling a motor vehicle as claimed in claim 15 wherein said system connects said characteristic signals to an electronic engine controller of said motor vehicle.

17. A system for characterizing a motor vehicle and controlling said motor vehicle as claimed in claim 15 further comprising a neural network for generating an anticipated brake lag signal in response to said characteristic signals, said fuzzy scheduler being further responsive to said brake lag signal for generating said brake and throttle action signals.

18. A method for determining characteristics of a motor vehicle on a dynamometer comprising the steps of:

monitoring a dynamometer torque signal produced by operation of an engine of a motor vehicle;

filtering said dynamometer torque signal to generate component frequency signals representative of component frequencies within said torque signal by generating a frequency membership vector signal representative of the component frequencies within said torque signal; and

generating relative temperature, inertia and horsepower signals representative of characteristics of said motor vehicle in response to determined component frequencies within said dynamometer torque signal by passing said frequency membership vector signal through a neural network.