Nonlinear dynamic transform for correction of crankshaft acceleration having torsional oscillations

• US 5,699,253 A
• Filed: 04/05/1995
• Issued: 12/16/1997
• Est. Priority Date: 04/05/1995
• Status: Expired due to Fees

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Feldkamp, Lee Albert, Puskorius, Gintaras Vincent
• Primary Examiner(s): Teska, Kevin J.
• Assistant Examiner(s): NGUYEN, TAN QUANG
• Application Number:
  US08/417,361
• Time in Patent Office: 986 Days
• Field of Search: 364/431.03, 364/431.08, 364/431.07, 123/419, 123/416, 73/117.3, 73/116
• US Class Current: 701/111
• CPC Class Codes: F02D 2041/1432 the system including a filter, e.g. a low pass or high pass filter
• CPC Class Codes: F02D 2200/1012 Engine speed gradient
• CPC Class Codes: F02D 2200/1015 Engines misfires
• CPC Class Codes: G01M 15/11 by detecting misfire

Abstract

Irregularities in crankshaft velocity introduced when measuring crankshaft rotation at a section of a crankshaft in an internal combustion engine that is less damped to torsional oscillations than is another more accessible crankshaft section are corrected by performing a nonlinear transformation via a neural network to predict rotation measurements that would have been obtained at the inaccessible section from data actually collected at the accessible crankshaft section. Thus, the effects of torsional oscillations in the crankshaft are substantially filtered away, resulting in crankshaft acceleration values that form the basis of a misfire detector having nearly maximum signal-to-noise performance.

Claims

1. A method for obtaining corrected rotation quantities in a misfire detector for an internal combustion engine, said engine having a crankshaft with a first crankshaft section being damped with respect to torsional oscillations, said engine further having a crankshaft position sensor generating position signals at predetermined rotational positions of said crankshaft, said crankshaft position sensor being juxtaposed with a second crankshaft section where torsional oscillations have a greater magnitude than at said first crankshaft section, said method comprising the steps of:

measuring rotation quantities corresponding to individual cylinder events during operation of said engine;

correcting said measured rotation quantities to remove periodic position irregularities;

applying a nonlinear transform to said corrected measured rotation quantities to estimate acceleration values occurring at said first crankshaft section; and

detecting misfire using said estimated rotation quantities.

2. The method of claim 1 wherein said rotation quantities are comprised of acceleration between successive rotation intervals of said crankshaft.

3. The method of claim 1 wherein said nonlinear transform is comprised of a neural network.

4. Engine apparatus for detecting misfires comprising:

a crankshaft with a first crankshaft section being damped with respect to torsional oscillations created during engine rotation;

a crankshaft position sensor generating position signals at predetermined rotational positions of said crankshaft, said crankshaft position sensor being juxtaposed with a second crankshaft section where torsional oscillations have a greater magnitude than at said first crankshaft section;

a timer coupled to said crankshaft position sensor measuring rotation intervals corresponding to individual cylinder events during engine rotation;

a processor coupled to said timer generating rotation quantities corrected for periodic position irregularities in said measured rotation intervals;

a transformer coupled to said processor estimating said corrected rotation quantities occurring at said first crankshaft section; and

a misfire detector coupled to said transformer for detecting misfires of said individual cylinder events in response to said estimated corrected rotation quantities.

5. The engine apparatus of claim 4 wherein a flywheel is mounted at said first crankshaft section.

6. The engine apparatus of claim 4 further comprising an engine assembly, wherein said first crankshaft section is disposed at a first end of said engine assembly and has a flywheel mounted thereto, and wherein said crankshaft position sensor includes an encoder wheel mounted at said second crankshaft section which is disposed at a second end of said engine assembly.

7. The engine apparatus of claim 4 wherein said transformer is comprised of a neural network having a predetermined configuration determined in a training procedure to model a nonlinear transformation relating the position of said second crankshaft section to the position of said first crankshaft section.

8. The engine apparatus of claim 4 wherein said rotation quantities are comprised of crankshaft acceleration.