# US 2006/0230821 A1 · Method and a relative device for diagnosing misfire or partial combustion conditions in an internal combustion engine

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2006/0230821 A1
- Document ID: US20060230821A1
- Status: Published application
- Kind: A1
- Application number: 11/367,806
- Filed: 2006-03-03
- Published: 2006-10-19
- Earliest claimed: 2005-03-04
- Assignees: STMicroelectronics S.r.I.
- Inventors: Ferdinando Taglialatela-Scafati; Nicola Cesario; Giovanni Di Lorenzo
- Web page: https://patentgrep.com/patent/US20060230821A1

## CPC

- G01M 15/11: by detecting misfire
- G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR

## Abstract

A method of diagnosing misfire or partial combustion conditions in an internal combustion engine without using a phonic wheel discriminates the combustion conditions with soft-computing techniques directly exploiting a combustion pressure signal generated by a common pressure sensor installed in the cylinder. There exists an exploitably close correlation between the instantaneous values of the internal cylinder pressure and the occurrence of misfire or partial combustion conditions, and thus the cylinder pressure signal may be reliably used for diagnosing misfires or partial combustions in functioning conditions of the engine.

## Claims

### Claim 1

A method of diagnosing misfire or partial combustion conditions in an internal combustion engine, comprising the steps of:
sensing the pressure in at least a cylinder of the engine and generating a pressure signal;
extracting at least an operation parameter from the generated pressure signal;
producing a signal representative of a misfire condition or of a partial combustion condition in function of the value of said parameter.

### Claim 2 (depends on 1)

The method of claim 1, wherein said parameter is the instantaneous value of the ratio
P(θ)/P(−θ)
where P is the pressure in the combustion chamber of the cylinder and θ is the angular position of the engine from the Top Dead Center, for pre-established angular positions.

### Claim 3 (depends on 2)

The method of claim 2, comprising the steps of:
grouping sets of values of said characteristic parameters in a certain number of clusters by processing the sets with a clustering algorithm;
estimating an ideal clustering performance index of said clustering algorithm for each set;
calculating a clustering factor as the ratio between said performance index and said ideal performance index;
choosing the best value of said certain number as the value corresponding to the execution of the clustering algorithm for which the clustering factor is the largest.

### Claim 4 (depends on 3)

The method of claim 3, comprising the steps of:
pre-establishing three disjoint ranges, first, second and third, of positive real numbers;
locating the center of gravity of each cluster;
for each center of gravity, calculating the arithmetic mean of the components thereof;
asserting that misfire conditions have occurred if at least one of said arithmetic means is contained in the first pre-established range;
asserting that partial combustion conditions have occurred if at least one of said arithmetic means is contained in the second pre-established range;
asserting that normal combustion conditions have occurred if at least one of said arithmetic means is contained in the third pre-established range.

### Claim 5

A device for diagnosing misfire or partial combustion conditions in an internal combustion engine, comprising:
a pressure sensor generating a signal representative of the pressure in at least a cylinder of the engine;
an off-line trained learning machine input with said pressure signal, extracting the values of said parameter and thereof and generating in function of said characteristic parameters a signal representative of a misfire condition or of a partial combustion condition.

### Claim 6 (depends on 5)

The device of claim 5, wherein said off-line trained learning machine comprises an identification block (C2) that selects the parameter of said pressure signal, and a core (C1) that generates said signal representative of the engine functioning condition, namely normal combustion, partial burning or misfire, in function only of the value of said parameter.

### Claim at position 7

7-8. (canceled)
