Trained neural network engine idle speed control system

• US 6,092,018 A
• Filed: 02/05/1996
• Issued: 07/18/2000
• Est. Priority Date: 02/05/1996
• Status: Expired due to Term

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Puskorius, Gintaras Vincent, Davis, Leighton Ira, Feldkamp, Lee Albert
• Primary Examiner(s): Cuchlinski, Jr., William A.
• Application Number:
  US08/597,095
• Time in Patent Office: 1,625 Days
• Field of Search: 364/423.098, 364/431.07, 364/431.01, 364/431.03, 364/431.04, 364/431.12, 364/424.058, 364/431.051, 364/424.034, 123/416, 123/492, 123/693, 123/339.23, 123/417, 123/480, 123/339.11, 395/22, 395/905, 395/911, 395/913, 701/102, 701/103, 701/110, 706/20, 706/21, 706/25, 706/10
• US Class Current: 701/110
• CPC Class Codes: F02D 31/005 by controlling a throttle by-pass
• CPC Class Codes: F02D 37/02 one of the functions being ignition
• CPC Class Codes: F02D 41/1405 Neural network control

Abstract

A electronic engine control (EEC) module executes a neural network processing program to control the idle speed of an internal combustion engine by controlling the bypass air (throttle duty cycle) and the engine'"'"'s ignition timing. The neural network is defined by a unitary data structure which defmes the network architecture, including the number of node layers, the number of nodes per layer, and the interconnections between nodes. To achieve idle speed control, the neural network processes input signals indicating the current operating state of the engine, including engine speed, the intake mass air flow rate, a desired engine speed, engine temperature, and other variables which influence engine speed, including loads imposed by power steering and air conditioning systems. The network definition data structure holds weight values which determine the manner in which network signals, including the input signals, are combined. The network definition data structures are created by a network training system which utilizes an external training processor which employ dynamic gradient methods to derive network weight values in accordance with a cost function which quantitatively defines system objectives and an identification network which is pretined to provide gradient signals representative of the behavior of the physical plant. The training processor executes training cycles asynchronously with the operation of the EEC module in a representative test vehicle.

Claims

1. Apparatus for controlling the idle speed of an internal combustion engine, said engine including an ignition timing control and a throttle, said apparatus comprising, in combination:

sensing means coupled to said engine for producing a plurality of input signal values, each of which is indicative of a corresponding one of a plurality of engine operation conditions, said conditions including engine speed and the rate at which intake air is being delivered to said engine.

data storage means for storing a neural network definition data structure which defines a neural network, said structure including;

signal value data defining said input signal values and the values of signals being processed by said neural network, and

weight values governing the manner in which signals are combined within said neural network, and

processing means consisting of an electronic engine control microprocessor and program storage means for storing instructions executable by said processor, said processing means including;

means responsive to said signal value data in said data structure for performing a generic neural network routine for combining selected signal values to produce and store new signal values in said data structure in accordance with said weight values in said data structure,

output means coupled to said throttle and responsive to one or more of said now signal values for controlling the speed of said engine,

second output means coupled to said ignition timing control and responsive to one or more of said new signals for generating, a second output signal for controlling the ignition timing of said engine, and

an independently operating training processor external to said electronic engine control microprocessor.

2. Apparatus as set forth in claim 1 wherein at least a portion said data storage means a sharable memory coupled to and accessible by both said electronic engine control microprocessor and said training processor.

3. Apparatus as set forth in claim 2 further including second program storage means for storing a training program executable by said training processor for monitoring the changes in the data stored in said definition data structure during the operation of said engine and said electronic engine control microprocessor for modify said weight values in said data structure.

4. Apparatus for developing a neural network for controlling the idle speed of an internal combustion engine, said apparatus comprising, in combination:

sensing means coupled to said engine for producing a plurality of input signal values, each of which is indicative of one of a plurality of particular engine operation conditions including engine speed and the rate at which intake air is delivered to said engine,

data storage means for storing a neural network definition data structure, said structure including;

data defining the values of signals being processed by said neural network, and

weight values governing the manner in which signals are combined within said neural network,

program storage means for storing instructions executable by said electronic engine control microprocessor, said instructions including a generic neural network routine for combining at least selected ones of said input signal values to produce and store new signal values in said particular data structure in accordance with said weight values in said particular data structure,

a training processor external to and operating independently of said electronic engine control microprocessor, said training processor being coupled to said data storage means and including means for monitoring changes in the values stored in a selected one of said data structures, and means for altering the values of weight values stored in said data structure to alter the new signal values produced within said structure by the operation of said neural network routine,

output means responsive to one or more of said new signal values for generating a first output signal, and

a throttle responsive to said output signal for controlling the speed of said engine.

5. Apparatus as set forth in claim 4 wherein said means for altering said weight values comprises determining the dynamic gradient of said weight values with respect to changes in the operating speed of a representative test engine subjected to a range of typical operating conditions.

6. The method of training a neural network to control the idle speed of an internal combustion engine, said neural network being implemented by an electronic engine control processor connected to receive input signal values indicative of the operating speed of said engine and the rate at which intake air is being delivered to said engine, and being further connected to supply output signals to control the speed of said engine, said method comprising the steps of:

interconnecting an external training processor to said electronic engine control processor such that said external training processor can access said input signal values,

generating and storing a data structure consisting of an initial set of neural network weight values,

operating a representative internal combustion engine and its connected electronic engine control processor over a range of operating conditions,

concurrently with the operation of said engine, executing a generic neural network control program on said electronic engine control processor to process said input signal values into output control values in accordance with the values stored in said data structures,

concurrently with the operation of said engine, varying said output signals in accordance with said output control values to control the operation of said engine,

concurrently with the operation of said engine, executing a neural network training program on said external training processor to progressively alter at least selected ones of said neural network weight values in said data structure to modify the results produced during the execution of said neural network training program,

evaluating the operation of said engine to indicate deviations in the operating speed of said engine from a desired idle speed is achieved, and

utilizing the values in said data structure determined to minimize said deviations to control the execution of said neural network control program on said EEC to control production engines corresponding to said representative engine.

7. The method set forth in claim 6 wherein said step of interconnecting an external training processor to said electronic engine control processor such that said external training processor can access said input signal values consists of the step of coupling a shared memory device for storing said data structure to both said training processor and electronic engine control processor such that information within said data structure can be manipulated independently by both said training processor and said electronic engine control processor.

8. The method as set forth in claim 6 wherein said step of executing a neural network training program on said external training processor to progressively alter at least selected ones of said neural network weight values means includes the step of determining the dynamic gradient of said selected weight values with respect to changes in the operating speed of a representative test engine subjected to a range of typical operating conditions.

9. The method as set forth in claim 6 wherein said step of executing a neural network training program on said external training processor to progressively alter at least selected ones of said neural network weight values means includes the step of determining the dynamic gradient of said selected weight values with respect to changes in the operating speed and in the throttle duty cycle of a representative test engine subjected to a range of typical operating conditions.