System and method for predicting peak pressure values using knock sensor

1. A system comprising:

at least one sensor for sensing at least one of vibration, pressure, acceleration, deflection, or movement within a reciprocating engine; and

a controller configured to:

receive a raw signal from the at least one sensor;

derive a filtered signal using predictive frequency bands by applying a filter;

derive an absolute filtered signal from the filtered signal;

identify a maximum of the absolute filtered signal for each engine cycle;

predict a peak pressure value of each of one or more engine cycles using the identified maximums of the absolute filtered signal and a predictive model; and

adjust operation of the reciprocating engine based on the predicted peak pressure values, wherein the at least one sensor is disposed outside of a cylinder in which the peak pressure occurs.

2. The system of claim 1 , wherein the controller is configured to adjust operation of the reciprocating engine by adjusting one or more of an engine timing map of the reciprocating engine, a compression ratio of the reciprocating engine, an oxidant/fuel ratio of the reciprocating engine, a flow of exhaust recirculation gas of the reciprocating engine, or a position of an intake or exhaust valve of the reciprocating engine in response to the predicted peak pressure values.

3. The system of claim 1 , wherein the filter comprises a low pass or a band pass filter.

4. The system of claim 1 , wherein the filter has a range of 0-1400 Hz.

5. The system of claim 1 , wherein the predictive model is based on a Gaussian Process ensemble.

6. The system of claim 1 , wherein the at least one sensor comprises a piezoelectric sensor configured to sense vibrations and/or acoustics in a cylinder of the reciprocating engine.

7. The system of claim 1 , wherein the predictive model is a linear model, a kernel regression model, a random forest model, or a combination thereof.

8. The system of claim 1 , wherein the predictive model is trained to predict the peak firing pressure for a particular reciprocating engine.

9. The system of claim 1 , wherein the sensor comprises a knock sensor.

10. A method for training a controller to estimate a peak firing pressure of a cylinder in a reciprocating engine, comprising:

receiving a raw signal from at least one exterior sensor, wherein the raw signal comprises data corresponding to a peak firing pressure event;

receiving a true pressure signal from a pressure sensor corresponding to the true peak firing pressure;

deriving a filtered signal by applying a low pass or a band pass filter to the raw signal;

deriving an absolute filtered signal from the filtered signal;

identifying a maximum of the absolute filtered signal for each engine cycle;

identifying the true peak pressure value for each engine cycle from the true pressure signal;

mapping the maximums of the absolute filtered signal to the true peak pressure values;

deriving predictive frequency bands for the peak firing pressure; and

executing an algorithm to generate a predictive model using the maximums of the absolute filtered signal and the true pressure signal, wherein the predictive model is configured to estimate the peak firing pressure of the cylinder in the reciprocating engine during ordinary engine operation.

11. The method of claim 10 , wherein the exterior sensor comprises a knock sensor.

12. The method of claim 10 , wherein deriving predictive frequency bands comprises combining one or more sets of adjacent frequency bands until combining a pair of adjacent frequency bands does not improve predictiveness of the resulting predictive frequency bands.

13. The method of claim 10 , wherein the pressure sensor is an in-cylinder pressure sensor.

14. The method of claim 10 , wherein, the predictive model is a linear model, a kernel regression model, a random forest model, or a combination thereof.

15. The method of claim 10 , wherein the method is repeated until the predictive model estimates the peak firing pressure within 95% of the true peak firing pressure.

16. The method of claim 10 , wherein the reciprocating engine is a Waukesha VHP engine, a CFR-RON engine.

17. The method of claim 10 , wherein the exterior sensor is disposed outside of the cylinder.

18. A system, comprising:

a reciprocating engine controller configured to:

receive a raw signal from at least one sensor coupled to a reciprocating engine;

derive a filtered signal using predictive frequency bands by applying a low pass or band pass filter;

derive an absolute filtered signal from the filtered signal;

identify a maximum of the absolute filtered signal (MAFS) of each engine cycle;

predict a peak firing pressure of each engine cycle using the identified MAFS and a predictive model; and

output a control action for at least the reciprocating engine based on the predicted peak firing pressure, wherein the at least one sensor is disposed outside a cylinder.

19. The system of claim 18 , wherein the control action comprises adjusting operation of the reciprocating engine by adjusting one or more of an engine timing map of the reciprocating engine, a compression ratio, an oxidant/fuel ratio of the reciprocating engine, a flow of exhaust recirculation gas of the reciprocating engine, a position of an intake or exhaust valve of the reciprocating engine, or another operating parameter of the reciprocating engine in response to the predicted peak firing pressure.

20. The system of claim 18 , wherein the predictive model is trained to predict the peak firing pressure for a particular reciprocating engine.