Redundant Torque Security Path

• US 8,818,676 B2
• Filed: 05/02/2006
• Issued: 08/26/2014
• Est. Priority Date: 05/02/2006
• Status: Expired due to Fees

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Peng, Jinchun, Hartrey, Timothy J.
• Primary Examiner(s): Dager, Jonathan M
• Application Number:
  US11/417,310
• Publication Number:
  US 20070260389A1
• Time in Patent Office: 3,038 Days
• Field of Search: 700/48
• US Class Current: 701/84
• CPC Class Codes: F02D 2041/141 using a feed-forward control element
• CPC Class Codes: F02D 2200/501 Vehicle speed
• CPC Class Codes: F02D 2200/602 Pedal position
• CPC Class Codes: F02D 2250/18 Control of the engine output torque
• CPC Class Codes: F02D 2400/08 Redundant elements, e.g. two sensors for measuring the same parameter
• CPC Class Codes: F02D 41/1405 Neural network control
• CPC Class Codes: F02D 41/1497 With detection of the mechanical response of the engine
• CPC Class Codes: F02D 41/22 Safety or indicating devices for abnormal conditions in air/fuel ratio feedback systems F02D41/1495, in electric control linkage F02D11/107, in purge control systems F02M25/0809
• CPC Class Codes: Y02T 10/40 Engine management systems

Abstract

An engine control system includes a torque request control module to determine a first engine torque request. An artificial neural network (ANN) torque request module determines a second engine torque request using an ANN model. A torque security check module that selectively generates a malfunction signal based on the difference between the first engine torque request and the second engine torque request.

Claims

1. An engine control system comprising:

a torque request control module that determines a first engine torque request based on an accelerator pedal position, a vehicle speed, and a cruise torque request;

a torque control module that controls an engine to generate the first engine torque request;

an artificial neural network (ANN) torque request module that determines a second engine torque request using an ANN model, the determination of the second engine torque request using the ANN model including;

determining calculated values as functions of products of the accelerator pedal position, the vehicle speed, and the cruise torque request multiplied by corresponding weights; and

determining the second engine torque request based on the calculated values; and

a torque security check module that selectively generates a malfunction signal based on a difference between the first engine torque request and the second engine torque request,

wherein the torque control disables a fuel injection system of the engine when the malfunction signal is generated.

2. The engine control system of claim 1 wherein the torque security check module generates the malfunction signal when the difference is greater than a predetermined value.

3. The engine control system of claim 1 wherein the ANN torque request module updates at least one of the weights when the difference is less than a predetermined value.

4. The engine control system of claim 3 wherein the ANN torque request module updates at least one of the weights to adjust the second engine torque request toward the first engine torque request.

5. The engine control system of claim 3 wherein said ANN torque request module updates at least one of the weights using a particle swarm optimization algorithm.

6. The engine control system of claim 1 wherein the torque security check module determines the difference by subtracting one of the first and second engine torque requests from the other one of the first and second engine torque requests.

7. An engine control method comprising:

determining a first engine torque request based on an accelerator pedal position, a vehicle speed, and a cruise torque request;

controlling an engine to generate the first engine torque request;

determining a second engine torque request using an artificial neural network (ANN) model, the determination of the second engine torque request using the ANN model including;

determining calculated values as functions of products of the accelerator pedal position, the vehicle speed, and the cruise torque request multiplied by corresponding weights; and

determining the second engine torque request based on the calculated values; and

selectively generating a malfunction signal based on a difference between the first engine torque request and the second engine torque request; and

disabling a fuel injection system of the engine when the malfunction signal is generated.

8. The engine control method of claim 7 further comprising generating the malfunction signal when the difference is greater than a predetermined value.

9. The engine control method of claim 7 further comprising updating at least one of the weights when the difference is less than a predetermined value.

10. The engine control method of claim 9 further comprising updating at least one of the weights to adjust the second engine torque request toward the first engine torque request.

11. The engine control method of claim 9 further comprising updating at least one of the weights using a particle swarm optimization algorithm.

12. The engine control method of claim 7 further comprising determining the difference by subtracting one of the first and second engine torque requests from the other one of the first and second engine torque requests.