Method and associated device for sensing the air/fuel ratio of an internal combustion engine

• US 8,131,450 B2
• Filed: 05/17/2011
• Issued: 03/06/2012
• Est. Priority Date: 03/04/2005
• Status: Active Grant

• Current Assignee: STMicroelectronics SRL (STMicroelectronics NV)
• Original Assignee: STMicroelectronics SRL (STMicroelectronics NV)
• Inventors: Cesario, Nicola, Amato, Paolo, Di Meglio, Maurizio, Pirozzi, Francesco, Moselli, Giovanni, Taglialatela-Scafati, Ferdinando, Carpentieri, Francesco
• Primary Examiner(s): HUYNH, HAI H
• Application Number:
  US13/109,027
• Publication Number:
  US 20110218727A1
• Time in Patent Office: 294 Days
• Field of Search: 701/106, 701103-105, 706 2- 6, 706 20- 23, 706 26- 27, 706/31, 706/41, 706/905, 73/350.7, 73/350.8, 73/351.2, 731/140.8, 731/140.9, 731/141.6, 731/141.8, 731/146.2, 123/480, 123/435, 123/436
• US Class Current: 701/106
• CPC Class Codes: F02D 2041/141 using a feed-forward control element
• CPC Class Codes: F02D 35/023 by determining the cylinder pressure
• CPC Class Codes: F02D 41/1401 characterised by the control or regulation method F02D41/1473, F02D41/1477 take precedence
• CPC Class Codes: F02D 41/1404 Fuzzy logic control
• CPC Class Codes: F02D 41/1405 Neural network control
• CPC Class Codes: F02D 41/1458 with determination means using an estimation
• CPC Class Codes: F02D 41/187 using a hot wire flow sensor
• CPC Class Codes: F02D 41/2454 Learning of the air-fuel ratio control
• CPC Class Codes: G06F 18/23213 with fixed number of clusters, e.g. K-means clustering

Abstract

A method of sensing the air/fuel ratio in a combustion chamber of an internal combustion engine that may be easily implemented by a respective low-cost device includes a pressure sensor and a learning machine that generates a sensing signal representing the air/fuel ratio by processing the waveform of the pressure in at least one cylinder of the engine. In practice, the learning machine extracts characteristic parameters of the waveform of the pressure and as a function of a certain number of them generates the sensing signal.

Claims

1. An apparatus comprising:

at least one input device; and

a classifier coupled to said at least one input device and configured to implement a probabilistic neural network comprising

a hidden layer of neurons, each neuron computing respective membership matrix elements for an input vector based upon a respective radial basis function defined by a respective spread factor and according to a distance of the input vector from a respective constant vector,

said hidden layer comprising a plurality of neurons having different spread factors.

2. The apparatus of claim 1 wherein the radial basis function comprises a Gaussian function.

3. The apparatus of claim 1 wherein said at least one input device comprises at least one sensor.

4. The apparatus of claim 1 wherein said at least one input device comprises at least one internal combustion engine sensor.

5. The apparatus of claim 1 wherein said at least one input device comprises at least one cylinder pressure sensor for an internal combustion engine.

6. The apparatus of claim 1 wherein said classifier is configured to output a virtual air/fuel ratio value for internal combustion engine control.

7. An apparatus comprising:

at least one sensor; and

a classifier coupled to said at least one sensor and configured to implement a probabilistic neural network comprising

a hidden layer of neurons, each neuron computing respective membership matrix elements for an input vector based upon a respective radial basis function defined by a respective spread factor and according to a distance of the input vector from a respective constant vector,

said hidden layer comprising a plurality of neurons having different spread factors,

the radial basis function comprising a Gaussian function.

8. The apparatus of claim 7 wherein said at least one sensor comprises at least one internal combustion engine sensor.

9. The apparatus of claim 7 wherein said at least one sensor comprises at least one cylinder pressure sensor for an internal combustion engine.

10. The apparatus of claim 7 wherein said classifier is configured to output a virtual air/fuel ratio value for internal combustion engine control.

11. A method for internal combustion engine control comprising:

sensing at least one parameter of the internal combustion engine using at least one sensor; and

implementing a probabilistic neural network in a classifier coupled to the at least one sensor, the probabilistic neural network comprising

a hidden layer of neurons, each neuron computing respective membership matrix elements for an input vector of the neural network based upon a respective radial basis function defined by a respective spread factor and according to a distance of the input vector from a respective constant vector,

the hidden layer comprising a plurality of neurons having different spread factors; and

controlling at least one engine parameter of the internal combustion engine based upon the probabilistic neural network.

12. The method of claim 11 wherein the radial basis function comprises a Gaussian function.

13. The method of claim 11 wherein sensing comprises sensing at least one cylinder pressure.

14. The method of claim 11 further comprising generating a virtual air/fuel ratio value for the internal combustion engine using the probabilistic neural network.

15. The method of claim 14 wherein controlling comprises controlling an air/fuel mixture for the internal combustion engine based upon the virtual air/fuel ratio value.