Virtual cylinder pressure sensor with individual estimators for pressure-related values

• US 20050251322A1
• Filed: 04/20/2005
• Published: 11/10/2005
• Est. Priority Date: 04/20/2004
• Status: Active Grant

• Current Assignee: Southwest Research Institute
• Original Assignee: Southwest Research Institute
• Inventors: Wang, Junmin, Roberts, Charles E. Jr., Roecker, Ryan C.
• Granted Patent: US 7,142,975 B2
• Time in Patent Office: Days
• US Class Current: 701/114
• CPC Class Codes: F02D 2200/0406 Intake manifold pressure
• CPC Class Codes: F02D 35/024 using an estimation
• CPC Class Codes: F02D 41/1405 Neural network control
• CPC Class Codes: G01M 15/08 by monitoring pressure in cylinders

Abstract

A virtual cylinder pressure sensor for use with an internal combustion engine. The sensor has one or more independent modules, each used to estimate a different cylinder pressure variable. Each module is trained using measurement data from a physical cylinder pressure sensor and a real engine. After the modules are trained, they can be embedded into the engine control unit of the same engine type, and used to estimate and predict the values for which they were trained.

Claims

1. A virtual cylinder pressure sensor for an internal combustion engine, comprising:

at least one estimator module, operable to receive engine operating data and to output estimated cylinder pressure data;

wherein the estimator module is operable to provide model data representing the relationship between measurement data extracted from a physical pressure sensor and data representing at least one engine operating condition associated with the measurement data, and to use to the model data to provide the estimated cylinder pressure data in response to engine operating condition data.

2. The sensor of claim 1, wherein the estimated cylinder pressure data is combustion timing data.

3. The sensor of claim 1, wherein the estimated cylinder pressure data is peak value data.

4. The sensor of claim 1, wherein the estimated cylinder pressure data is maximum pressure data.

5. The sensor of claim 1, wherein the estimated cylinder pressure data is maximum rising rate value.

6. The sensor of claim 1, wherein the estimated cylinder pressure data is pressure inflection value.

7. The sensor of claim 1, wherein the estimated cylinder pressure data is pressure inflection position.

8. The sensor of claim 1, wherein the estimated cylinder pressure data is second peak value.

9. The sensor of claim 1, wherein the estimated cylinder pressure data is second peak value position.

10. The sensor of claim 1, wherein the sensor has one or more modules of the following type:

a combustion timing data module, a peak value data module, and maximum pressure data module.

11. The sensor of claim 1, wherein the engine operating conditions are at least one or more from the group comprising:

intake manifold pressure, intake manifold temperature, coolant temperature, and exhaust gas recirculation (EGR) rate.

12. The sensor of claim 1, wherein the engine operating conditions are at least one or more from the group comprising:

injection timing, injection fuel mass, and injection pressure.

13. The sensor of claim 1, wherein the sensor is implemented with programming integrated into the programming of an engine control unit for the engine.

14. A method of providing cylinder pressure data to an engine control system of an internal combustion engine, comprising:

training at least one estimator module, using measurement data extracted from a physical pressure sensor and data representing at least one engine operating condition associated with the measurement data to establish a model of the relationship between the measurement data and engine operating condition data;

embedding the module into engine control programming; and

during operation of the engine, using the module to receive engine operating data, to access the model data, and to output the cylinder pressure data.

15. The method of claim 14, wherein the estimated cylinder pressure data is combustion timing data.

16. The method of claim 14, wherein the estimated cylinder pressure data is peak value data.

17. The method of claim 14, wherein the estimated cylinder pressure data is maximum pressure data.

18. The method of claim 14, wherein the training step is performed using a neural network.

19. The method of claim 14, wherein the step of using the module is performed by receiving current engine operating data and estimating pressure data associated with the current engine conditions.

20. The method of claim 14, wherein the step of using the module is performed by receiving current engine operating data and predicting pressure data associated with future engine operating conditions.