A state detection system for an internal combustion engine includes: a memory configured to store mapping data, the mapping data being data that defines a detection mapping, the detection mapping being a mapping between an input and an output, the input being a rotation waveform variable and a drive system rotation speed variable and the output being a value of a combustion state variable, and the detection mapping including a joint operation of the rotation waveform variable and the drive system rotation speed variable based on a parameter learned by machine learning; and a processor configured to execute an acquisition process and a determination process, the acquisition process being configured to acquire a value of the drive system rotation speed variable, the determination process being configured to determine whether or not the internal combustion engine is in a predetermined operating state.

The disclosure provides a combustion abnormality detecting device, a combustion abnormality detecting method, and a non-transitory computer-readable storage medium, a misfire detection accuracy is increased by increasing a piezoelectric detection accuracy. A charge amplifier (210) outputting a voltage signal corresponding to a charge generated by a piezoelectric element (35) in response to a received pressure, a drift component extracting part (230) extracting a drift component of the piezoelectric element (35), a drift correcting part (250) generating a correction signal for removing the drift component based on the extracted drift component and feeding back the correction signal to an input side of the charge amplifier (210), and a misfire detecting part (400) performing misfire detection based on the correction signal are included.

The disclosure provides a combustion abnormality detecting device, a combustion abnormality detecting method, and a non-transitory computer-readable storage medium, a misfire detection accuracy is increased by increasing a piezoelectric detection accuracy. A charge amplifier (210) outputting a voltage signal corresponding to a charge generated by a piezoelectric element (35) in response to a received pressure, a drift component extracting part (230) extracting a drift component of the piezoelectric element (35), a drift correcting part (250) generating a correction signal for removing the drift component based on the extracted drift component and feeding back the correction signal to an input side of the charge amplifier (210), and a misfire detecting part (400) performing misfire detection based on the correction signal are included.

A vehicle controller is provided. An update process updates a relationship defining data by inputting, to a predetermined update map, a state of a vehicle, a value of an action variable used to operate an electronic device, and a reward corresponding to that electronic device. A reward calculating process provides, based on the state of the vehicle obtained by an obtaining process, a greater reward when a characteristic of the vehicle meets a standard than when the characteristic of the vehicle does not meet the standard. A loosening process loosens the standard to a larger extent when the degree of deterioration is large than when the degree of deterioration is small.

Engine combustion phasing control techniques utilize a trained feedforward artificial neural network (ANN) to model both base and maximum brake torque (MBT) spark timing based on six inputs: intake and exhaust camshaft positions, mass and temperature of an air charge being provided to each cylinder of the engine, engine speed, engine coolant temperature. The selected target spark timing could be adjusted based on a two-dimensional surface having engine speed and air charge mass as inputs. The target spark timing adjustment could be performed only during an initial period when the trained ANN is immature. The ANN could also be trained using dynamometer data for the engine that is artificially weighted for high load regions where accuracy of spark timing is critical.

Engine combustion phasing control techniques utilize a trained feedforward artificial neural network (ANN) to model both base and maximum brake torque (MBT) spark timing based on six inputs: intake and exhaust camshaft positions, mass and temperature of an air charge being provided to each cylinder of the engine, engine speed, engine coolant temperature. The selected target spark timing could be adjusted based on a two-dimensional surface having engine speed and air charge mass as inputs. The target spark timing adjustment could be performed only during an initial period when the trained ANN is immature. The ANN could also be trained using dynamometer data for the engine that is artificially weighted for high load regions where accuracy of spark timing is critical.

A method for programming an internal combustion engine control unit includes operating a test internal combustion engine at a first speed and a first torque while simulating a condition of the test internal combustion engine by restricting a flow of air to the test internal combustion engine to simulate altitude variations of the test internal combustion engine or elevating a temperature of the flow of air to simulate ambient temperature variations of the test internal combustion engine. The method also includes measuring engine performance information while operating the test internal combustion engine at the first speed and first torque and while simulating the condition of the test internal combustion engine, and programming the internal combustion engine control unit by storing the measured engine performance information in a memory associated with the internal combustion engine control unit.

A big data-based driving information provision system may include a sensor configured to measure and collect state monitoring data of an engine, vehicle monitoring data, and vibration data; an engine electronic control unit (ECU) configured to generate a combustion characteristic index (CCI) data of the engine; and a graphic controller configured to generate a primary deep learning model which classifies the big data including the state monitoring data, the vehicle monitoring data, the vibration data, and the CCI into at least two categories.

A big data-based driving information provision system may include a sensor configured to measure and collect state monitoring data of an engine, vehicle monitoring data, and vibration data; an engine electronic control unit (ECU) configured to generate a combustion characteristic index (CCI) data of the engine; and a graphic controller configured to generate a primary deep learning model which classifies the big data including the state monitoring data, the vehicle monitoring data, the vibration data, and the CCI into at least two categories.

A vehicle controller is provided. An update process updates a relationship defining data by inputting, to a predetermined update map, a state of a vehicle, a value of an action variable used to operate an electronic device, and a reward corresponding to that electronic device. A reward calculating process provides, based on the state of the vehicle obtained by an obtaining process, a greater reward when a characteristic of the vehicle meets a standard than when the characteristic of the vehicle does not meet the standard. A loosening process loosens the standard to a larger extent when the degree of deterioration is large than when the degree of deterioration is small.