Abstract: An ignition timing control device includes a storage device that stores a normal signal generation model configured to output, upon receiving an output value of a knocking sensor, a noise-removed output value therefrom which an unlearned noise component value has been removed, and a first learned neural network pre-learned to output, upon receiving one of the output value of the knocking sensor and the noise-removed output value, an estimated value of a knocking intensity representative value, and a processor that acquires the estimated value by inputting the output value of the knocking sensor to the normal signal generation model and inputting the noise-removed output value to the first learned neural network, and executes retarding control of an ignition timing based on the acquired estimated value.

Abstract: An ignition timing control device includes a storage device that stores a normal signal generation model configured to output, upon receiving an output value of a knocking sensor, a noise-removed output value therefrom which an unlearned noise component value has been removed, and a first learned neural network pre-learned to output, upon receiving one of the output value of the knocking sensor and the noise-removed output value, an estimated value of a knocking intensity representative value, and a processor that acquires the estimated value by inputting the output value of the knocking sensor to the normal signal generation model and inputting the noise-removed output value to the first learned neural network, and executes retarding control of an ignition timing based on the acquired estimated value.

Abstract: A knocking sensor detecting vibration of an engine body and a pressure sensor detecting a pressure of a combustion chamber are provided. A value representing the knocking strength is acquired from output values of the pressure sensor. Weights of a neural network are learned using a value representing the vibration of the engine body detected by the knocking sensor as an input value of the neural network and using the acquired value representing the knocking strength as training data. The value representing the knocking strength is estimated from the output values of the knocking sensor by using the learned neural network.

Abstract: An ignition timing control device includes bandpass filters each configured to pass and output only a specific frequency band for the output value of a knocking sensor, a storage device storing first learned neural networks configured to receive the output values of the bandpass filters in respective frequency band, and a processor. Each of the first learned neural networks is pre-learned to output an estimated value for a value representing knocking intensity when receiving the filtered output value of the bandpass filter. The processor calculates an optimal estimated value using a part of acquired estimated values for the value excluding a unique estimated value, and executes retarding control of an ignition timing based on the calculated optimal estimated value.

Abstract: An ignition timing control device includes bandpass filters each configured to pass and output only a specific frequency band for the output value of a knocking sensor, a storage device storing first learned neural networks configured to receive the output values of the bandpass filters in respective frequency band, and a processor. Each of the first learned neural networks is pre-learned to output an estimated value for a value representing knocking intensity when receiving the filtered output value of the bandpass filter. The processor calculates an optimal estimated value using a part of acquired estimated values for the value excluding a unique estimated value, and executes retarding control of an ignition timing based on the calculated optimal estimated value.

Abstract: An ignition timing control device includes a storage device that stores a normal signal generation model configured to output, upon receiving an output value of a knocking sensor, a noise-removed output value therefrom which an unlearned noise component value has been removed, and a first learned neural network pre-learned to output, upon receiving one of the output value of the knocking sensor and the noise-removed output value, an estimated value of a knocking intensity representative value, and a processor that acquires the estimated value by inputting the output value of the knocking sensor to the normal signal generation model and inputting the noise-removed output value to the first learned neural network, and executes retarding control of an ignition timing based on the acquired estimated value.

Abstract: A knocking sensor (18) detecting vibration of an engine body (1) and a pressure sensor (19) detecting a pressure of a combustion chamber (5) are provided. A value representing the knocking strength is acquired from output values of the pressure sensor (19). Weights of a neural network are learned using a value representing the vibration of the engine body (1) detected by the knocking sensor (18) as an input value of the neural network and using the acquired value representing the knocking strength as training data. The value representing the knocking strength is estimated from the output values of the knocking sensor (18) by using the learned neural network.

Abstract: A fuel injection control device is applied to an internal combustion engine that includes a port injection valve and a direct injection valve. The fuel injection control device includes a port warm-up judgment section, which judges whether the intake port has been warmed up, and an injection mode determination section, which determines the injection mode based on the engine speed and a predicted load rate. When determining the injection mode at the cold operation of the internal combustion engine, the injection mode determination section sets the range of the operation region of the internal combustion engine in which the direct-injection-only mode is selected as the injection mode to be broader in a case in which the port warm-up judgment section has judged that the port has not been warmed up than in a case in which the port warm-up judgment section has judged that the port has been warmed up.

Abstract: A fuel injection amount control device controls a fuel injection amount of an injector in an internal combustion engine including a blow-by gas ventilation system. The fuel injection amount control device includes a reflection rate setting section, a dilution correction section, and a dilution learning section. The reflection rate setting section sets a reflection rate proportional to the amount of a blow-by gas discharged to an intake air. The dilution correction section corrects a fuel injection amount by using, as a correction value, the product obtained by multiplying a reflection rate by a dilution learning value. The dilution learning section updates the dilution learning value such that an air-fuel ratio F/B correction value approaches 0 on the condition that a fuel dilution amount of engine oil is equal to or greater than a predetermined value.

Abstract: A cold-time fuel increasing section calculates, as increase correction values for a required injection amount, an increase-after-startup correction value, which attenuates with an increment of the number of times of combustion carried out after startup of the internal combustion engine, and a basic warmup increase correction value, which attenuates with an increase in a temperature of coolant in the internal combustion engine. The cold-time fuel increasing section calculates the increase correction values such that the increase-after-startup correction value when the port injection mode is selected is greater than the increase-after-startup correction value when the single direct injection mode is selected, and that the basic warmup increase correction value when the port injection mode is selected is less than the basic warmup increase correction value when the single direct injection mode is selected.

Abstract: A cold-time fuel increasing section calculates, as increase correction values for a required injection amount, an increase-after-startup correction value, which attenuates with an increment of the number of times of combustion carried out after startup of the internal combustion engine, and a basic warmup increase correction value, which attenuates with an increase in a temperature of coolant in the internal combustion engine. The cold-time fuel increasing section calculates the increase correction values such that the increase-after-startup correction value when the port injection mode is selected is greater than the increase-after-startup correction value when the single direct injection mode is selected, and that the basic warmup increase correction value when the port injection mode is selected is less than the basic warmup increase correction value when the single direct injection mode is selected.

Abstract: A fuel injection control device is applied to an internal combustion engine that includes a port injection valve and a direct injection valve. The fuel injection control device includes a port warm-up judgment section, which judges whether the intake port has been warmed up, and an injection mode determination section, which determines the injection mode based on the engine speed and a predicted load rate. When determining the injection mode at the cold operation of the internal combustion engine, the injection mode determination section sets the range of the operation region of the internal combustion engine in which the direct-injection-only mode is selected as the injection mode to be broader in a case in which the port warm-up judgment section has judged that the port has not been warmed up than in a case in which the port warm-up judgment section has judged that the port has been warmed up.

Abstract: A fuel injection amount control device controls a fuel injection amount of an injector in an internal combustion engine including a blow-by gas ventilation system. The fuel injection amount control device includes a reflection rate setting section, a dilution correction section, and a dilution learning section. The reflection rate setting section sets a reflection rate proportional to the amount of a blow-by gas discharged to an intake air. The dilution correction section corrects a fuel injection amount by using, as a correction value, the product obtained by multiplying a reflection rate by a dilution learning value. The dilution learning section updates the dilution learning value such that an air-fuel ratio F/B correction value approaches 0 on the condition that a fuel dilution amount of engine oil is equal to or greater than a predetermined value.