Patent US6098012A successfully refreshed from Google Patents.
US6098012A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Neural network based transient fuel control method
Assignee: FCA US LLC
•
Filing: 1998-02-04
•
Granted: 2000-08-01
•
Expires: 2018-02-04
Abstract
Abstract A system and method for use in a motor vehicles is disclosed for calculating a fuel multiplier during transient engine operation. The fuel multiplier modifies the amount of fuel released from a fuel actuator into an engine. The fuel control system uses neural network logic to establish the fuel multiplier. The neural network logic involves taking inputs from engine sensors, processing the inputs through an input layer, a hidden layer and an output layer resulting in a fuel multiplier.
Inventors
- 👤 Douglas M. Stander
- 👤 Sam K. Liu
- 👤 Min Sway-Tin
- 👤 William O. Robinson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-03 21:53
CPC Classifications
F; F02; F02D; F02D41/00; F02D41/02; F02D41/14; F02D41/1401; F02D41/1405; F02D37/00; F02D37/02; F02D41/24; F02D41/2406; F02D41/2425; F02D41/2429; G; G05; G05B; G05B13/00; G05B13/02; G05B13/0265; G05B13/027
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
111 words
A vehicle fuel control system for controlling a fuel flow to an engine of a motor vehicle operating in a transient mode, comprising: a plurality of input sensors for detecting an engine state, including a speed sensor, a manifold absolute pressure sensor, a throttle position sensor, an AIS motor position sensor, an oxygen sensor, and a spark advance position sensor; a neural network for calculating a fuel multiplier based on input from each of said plurality of sensors, whereby the fuel multiplier controls fuel flow in the vehicle fuel control system; and a fuel actuator for receiving the fuel multiplier and adjusting the fuel flow to the engine of the vehicle.
Claim 2
Dependent Claim
111 words
A vehicle fuel control system for controlling a fuel flow to an engine of a motor vehicle operating in a transient mode, comprising: a plurality of input sensors for detecting an engine state, including a speed sensor, a manifold absolute pressure sensor, a throttle position sensor, an AIS motor position sensor, an oxygen sensor, and a spark advance position sensor; a neural network for calculating a fuel multiplier based on input from each of said plurality of sensors, whereby the fuel multiplier controls fuel flow in the vehicle fuel control system; and a fuel actuator for receiving the fuel multiplier and adjusting the fuel flow to the engine of the vehicle.
Claim 3
Dependent Claim
58 words
The vehicle fuel control system of claim 1 further comprising a means for training said neural network using input data from each of said plurality of sensors and a desired fuel multiplier, where the desired fuel multiplier is determined by measuring an fuel/air ratio which corresponds to the input data from each of said plurality of input sensors.
Claim 4
Dependent Claim
138 words
The vehicle fuel control system of claim 1 wherein said neural network includes: an input node for each of said input sensors for normalizing each of said inputs and multiplying each of said inputs by an input weight; two hidden nodes receiving and summing the output from each of said input nodes into an intermediate output; a hyperbolic tangent function for each hidden node receiving said intermediate output and transmitting a hidden layer output; an output node receiving the hidden layer output from each of said hidden nodes, multiplying each of said hidden layer outputs by an output weight resulting in a weighted output, and summing said weighted output into a summed output; and a output hyperbolic tangent function receiving said summed output, transmitting an output layer output and denormalizing said output layer output into said fuel multiplier.
Claim 5
Dependent Claim
34 words
The vehicle fuel control system of claim 3 wherein said neural network means further comprises a bias layer for providing a reference value to each of the two hidden nodes and the output node.
Claim 6
Dependent Claim
92 words
A vehicle fuel control method for controlling fuel flow to an engine of a motor vehicle operating in a transient mode, comprising the steps of: determining engine speed, manifold absolute pressure, throttle position, AIS motor position, oxygen, and spark advance position using a plurality of sensors, thereby determining an engine state; determining a fuel multiplier using a neural network having as inputs engine speed, manifold absolute pressure, throttle position, AIS motor position, oxygen, and spark advance position; and using the fuel multiplier to control fuel flow in the vehicle fuel control system.
Claim 7
Dependent Claim
92 words
A vehicle fuel control method for controlling fuel flow to an engine of a motor vehicle operating in a transient mode, comprising the steps of: determining engine speed, manifold absolute pressure, throttle position, AIS motor position, oxygen, and spark advance position using a plurality of sensors, thereby determining an engine state; determining a fuel multiplier using a neural network having as inputs engine speed, manifold absolute pressure, throttle position, AIS motor position, oxygen, and spark advance position; and using the fuel multiplier to control fuel flow in the vehicle fuel control system.
Claim 8
Dependent Claim
33 words
The vehicle fuel control method of claim 5 wherein the step of using the fuel multiplier further comprises adjusting a fuel actuator to control the fuel flow into the engine of the vehicle.
Claim 9
Dependent Claim
59 words
The vehicle fuel control method of claim 5 further comprising the step of training said neural network using input data from each of said plurality of sensors and a desired fuel multiplier, where the desired fuel multiplier is determined by measuring an actual fuel/air ratio which corresponds to the input data from each of said plurality of input sensors.
Claim 10
Dependent Claim
29 words
The vehicle fuel control method of claim 5 further comprising the step of normalizing each input from said plurality of sensors prior to being input into said neural network.
Claim 11
Dependent Claim
123 words
The vehicle fuel control method of claim 5 wherein said neural network includes: an input node for each of said input sensors for multiplying each of said inputs by an input weight; two hidden nodes receiving and summing the output from each of said input nodes into an intermediate output; a hyperbolic tangent function for each hidden node receiving said intermediate output and transmitting a hidden layer output; an output node receiving the hidden layer output from each of said hidden nodes, multiplying each of said hidden layer outputs by an output weight resulting in a weighted output, and summing said weighted output into a summed output; and a output hyperbolic tangent function receiving said summed output, and transmitting an output layer output.
Claim 12
Dependent Claim
40 words
The vehicle fuel control method of claim 9 further comprising the step of denormalizing said output layer output into said fuel multiplier, and multiplying said fuel multiplier by a steady state fuel control value resulting in a final fuel value.
Claim 13
Dependent Claim
33 words
The vehicle fuel control method of claim 9 wherein said neural network further comprises a bias layer for providing a reference value to each of the two hidden nodes and the output node.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-08-01 | 2004-01-31 | 2004-08-01 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-08-01 | 2008-01-31 | 2008-08-01 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-08-01 | 2012-01-31 | 2012-08-01 | $7700.00 | Window Closed / Lapsed |