Early warning system for stochastic preignition
AssigneeGM Global Technology Operations LLC
InventorsAlok Warey, Ronald O. Grover, Jr., Balakrishna Chinta, Elana M. Chapman, John O. Waldman, Hugh W. Miller
Life of this patent
Estimating the term…
Abstract
A method for early detection of a stochastic preignition (SPI) in an internal combustion engine includes monitoring sensor data from a sensor that is coupled to the internal combustion engine of a vehicle, determining whether a SPI event will occur using the sensor data and a Hankel Alternative View of Koopman (HAVOK) model, and commanding the vehicle to take a corrective action before the SPI event occurs to prevent the SPI event from happening in response to determining that the SPI event will occur.
Claims12
A method for early detection of a stochastic preignition (SPI) in an internal combustion engine, comprising:
- monitoring sensor data from a sensor that is coupled to the internal combustion engine of a vehicle;
- determining whether a SPI event will occur using the sensor data and a Hankel Alternative View of Koopman (HAVOK) model;
- commanding the vehicle to take a corrective action before the SPI event occurs to prevent the SPI event from happening in response to determining that the SPI event will occur;
- wherein the sensor data includes a peak cylinder pressure in the internal combustion engine of the vehicle;
- wherein determining whether the SPI event will occur using the sensor data and the HAVOK model includes determining, in real time, a forcing term using the sensor data, wherein the forcing term is based on the peak cylinder pressure in the internal combustion engine of the vehicle;
- wherein determining whether the SPI event will occur using the sensor data and the HAVOK model includes:
- determining whether the forcing term is greater than a predetermined threshold;
- and
- in response to determining whether the forcing term is greater than the predetermined threshold, determining that the SPI event will occur.
A tangible, non-transitory, machine-readable medium, comprising machine-readable instructions, that when executed by a processor, cause the processor to:
- monitor sensor data from a sensor that is coupled to an internal combustion engine of a vehicle;
- determine whether a stochastic preignition (SPI) event will occur using the sensor data and a Hankel Alternative View of Koopman (HAVOK) model;
- and
- commanding the vehicle to take a corrective action before the SPI event occurs to prevent the SPI event from happening in response to determining that the SPI event will occur;
- wherein the sensor data includes a peak cylinder pressure in the internal combustion engine of the vehicle;
- wherein the tangible, non-transitory, machine-readable medium, further comprises machine-readable instructions, that when executed by the processor, causes the processor to:
- determine whether the SPI event will occur using the sensor data and the HAVOK model includes determining, in real time, a forcing term using the sensor data, wherein the forcing term is based on the peak cylinder pressure in the internal combustion engine of the vehicle;
- wherein the tangible, non-transitory, machine-readable medium, further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
- determining whether the forcing term is greater than a predetermined threshold;
- and
- in response to determining whether the forcing term is greater than the predetermined threshold, determining that the SPI event will occur.
A system, comprising:
- an internal combustion engine;
- a sensor coupled to the internal combustion engine;
- a controller in communication with the sensor, wherein the controller is programmed to:
- monitor sensor data from the sensor that is coupled to the internal combustion engine of a vehicle;
- determine whether a stochastic preignition (SPI) event will occur using the sensor data and a Hankel Alternative View of Koopman (HAVOK) model;
- and
- commanding the vehicle to take a corrective action before the SPI event occurs to prevent the SPI event from happening in response to determining that the SPI event will occur;
- wherein the sensor data includes a peak cylinder pressure in the internal combustion engine of the vehicle;
- wherein the controller is programmed to determine whether a SPI event will occur using the sensor data and the HAVOK model includes determining, in real time, a forcing term using the sensor data, wherein the forcing term is based on the peak cylinder pressure in the internal combustion engine of the vehicle;
- wherein the controller is programmed to:
- determining whether the forcing term is greater than a predetermined threshold;
- and
- in response to determining whether the forcing term is greater than the predetermined threshold, determining that the SPI event will occur.
Dependencies are inferred from the claim text.