A control apparatus, for an internal combustion engine, detects a rotational speed parameter (time parameter) that represents a rotational speed of the internal combustion engine including a plurality of cylinders, detects a single misfire that is a misfire for every ignition for each of the plurality of cylinders, based on the rotational speed parameter that has been detected in each combustion stroke of the plurality of cylinders (steps 2 to 7 and 9), counts, as a misfire counter value, the number of times that the single misfire has been detected for each of the plurality of cylinders (steps 8 and 10), determines whether the misfire is occurring in the cylinder, based on the misfire counter value (steps 11 to 12), and corrects an ignition timing of the cylinder that has been determined that the misfire is occurring to an advance angle side (steps 25, 26, and 34).

A control apparatus, for an internal combustion engine, detects a rotational speed parameter (time parameter) that represents a rotational speed of the internal combustion engine including a plurality of cylinders, detects a single misfire that is a misfire for every ignition for each of the plurality of cylinders, based on the rotational speed parameter that has been detected in each combustion stroke of the plurality of cylinders (steps 2 to 7 and 9), counts, as a misfire counter value, the number of times that the single misfire has been detected for each of the plurality of cylinders (steps 8 and 10), determines whether the misfire is occurring in the cylinder, based on the misfire counter value (steps 11 to 12), and corrects an ignition timing of the cylinder that has been determined that the misfire is occurring to an advance angle side (steps 25, 26, and 34).

A calibration system and method for a spark ignition engine of a vehicle involve artificially weighting engine dynamometer data in high engine load regions and using it to generate training data for an artificial neutral network (ANN). A plurality of ANNs are trained using the training data and the plurality of ANNs are then filtered based on their maximum error to obtain a filtered set of trained ANNs. A statistical analysis is performed on each of the filtered set of trained ANNs including determining a set of statistical metrics for each of the filtered set of trained ANNs and then one of the filtered set of trained ANNs having a best combination of error at high engine loads and the set of statistical error metrics is then selected. Finally, an ANN calibration is generated using the selected one of the filtered set of trained ANNs.

A calibration system and method for a spark ignition engine of a vehicle involve artificially weighting engine dynamometer data in high engine load regions and using it to generate training data for an artificial neutral network (ANN). A plurality of ANNs are trained using the training data and the plurality of ANNs are then filtered based on their maximum error to obtain a filtered set of trained ANNs. A statistical analysis is performed on each of the filtered set of trained ANNs including determining a set of statistical metrics for each of the filtered set of trained ANNs and then one of the filtered set of trained ANNs having a best combination of error at high engine loads and the set of statistical error metrics is then selected. Finally, an ANN calibration is generated using the selected one of the filtered set of trained ANNs.

A calibration system and method for a spark ignition engine of a vehicle involve artificially weighting engine dynamometer data in high engine load regions and using it to generate training data for an artificial neutral network (ANN). A plurality of ANNs are trained using the training data and the plurality of ANNs are then filtered based on their maximum error to obtain a filtered set of trained ANNs. A statistical analysis is performed on each of the filtered set of trained ANNs including determining a set of statistical metrics for each of the filtered set of trained ANNs and then one of the filtered set of trained ANNs having a best combination of error at high engine loads and the set of statistical error metrics is then selected. Finally, an ANN calibration is generated using the selected one of the filtered set of trained ANNs.

A calibration system and method for a spark ignition engine of a vehicle involve artificially weighting engine dynamometer data in high engine load regions and using it to generate training data for an artificial neutral network (ANN). A plurality of ANNs are trained using the training data and the plurality of ANNs are then filtered based on their maximum error to obtain a filtered set of trained ANNs. A statistical analysis is performed on each of the filtered set of trained ANNs including determining a set of statistical metrics for each of the filtered set of trained ANNs and then one of the filtered set of trained ANNs having a best combination of error at high engine loads and the set of statistical error metrics is then selected. Finally, an ANN calibration is generated using the selected one of the filtered set of trained ANNs.

A processor (B705, B706) of a control device for an internal combustion engine 1 operates a first combustion timing (MFB 50) or a first combustion period (IG 100_1) in a cylinder of the internal combustion engine 1 from a crank angle detected by a crank angle sensor 20. A processor (B702) operates a heat generation rate based on a first combustion timing or a first combustion period. A processor (B703) operates in-cylinder pressure and in-cylinder unburned gas temperature based on the heat generation rate. A processor (B704) operates a first combustion speed (laminar flow combustion speed SL1) based on the in-cylinder pressure and the in-cylinder unburned gas temperature. A processor (B707) learns a correspondence relationship between the first combustion speed and the first combustion timing or the first combustion period.

A processor (B705, B706) of a control device for an internal combustion engine 1 operates a first combustion timing (MFB 50) or a first combustion period (IG 100_1) in a cylinder of the internal combustion engine 1 from a crank angle detected by a crank angle sensor 20. A processor (B702) operates a heat generation rate based on a first combustion timing or a first combustion period. A processor (B703) operates in-cylinder pressure and in-cylinder unburned gas temperature based on the heat generation rate. A processor (B704) operates a first combustion speed (laminar flow combustion speed SL1) based on the in-cylinder pressure and the in-cylinder unburned gas temperature. A processor (B707) learns a correspondence relationship between the first combustion speed and the first combustion timing or the first combustion period.

A processor (B705, B706) of a control device for an internal combustion engine 1 operates a first combustion timing (MFB 50) or a first combustion period (IG 100_1) in a cylinder of the internal combustion engine 1 from a crank angle detected by a crank angle sensor 20. A processor (B702) operates a heat generation rate based on a first combustion timing or a first combustion period. A processor (B703) operates in-cylinder pressure and in-cylinder unburned gas temperature based on the heat generation rate. A processor (B704) operates a first combustion speed (laminar flow combustion speed SL1) based on the in-cylinder pressure and the in-cylinder unburned gas temperature. A processor (B707) learns a correspondence relationship between the first combustion speed and the first combustion timing or the first combustion period.

A processor (B705, B706) of a control device for an internal combustion engine 1 operates a first combustion timing (MFB 50) or a first combustion period (IG 100_1) in a cylinder of the internal combustion engine 1 from a crank angle detected by a crank angle sensor 20. A processor (B702) operates a heat generation rate based on a first combustion timing or a first combustion period. A processor (B703) operates in-cylinder pressure and in-cylinder unburned gas temperature based on the heat generation rate. A processor (B704) operates a first combustion speed (laminar flow combustion speed SL1) based on the in-cylinder pressure and the in-cylinder unburned gas temperature. A processor (B707) learns a correspondence relationship between the first combustion speed and the first combustion timing or the first combustion period.