Abstract: A control device of an internal combustion engine is configured to output a predicted value of an output parameter by using a learning model if actually measured values of input parameters are input, control the internal combustion engine based on the predicted value of the output parameter, learn the learning model by using a gradient method and by using a combination of actually measured values of the input parameters and an actually measured value of the output parameter as teacher data, and adjust the learning rate so that the learning is performed by a smaller learning rate when an amount of noise superposed on an actually measured value of at least one parameter among the input parameters and the output parameter is relatively large compared with when the amount of noise superposed on the actually measured value of the parameter is relatively small.

Abstract: A control device of an internal combustion engine using a neural network, wherein an output value obtained by experiments is made training data for a value of an operating parameter of the engine in a presumed usable range, while an output value obtained by prediction without relying on experiments is made training data for a value of the operating parameter of the engine outside of the presumed usable range. The training data obtained by experiments and the training data obtained by prediction are used to learn the weights and the biases of the neural network so that an output value which changes in accordance with a value of an operating parameter of the engine matches the training data, and thereby even outside of the presumed usable range of the operating parameter, the output value can be suitably estimated.

Abstract: A machine learning system using a neural network to output an output value corresponding to values of operating parameters of the machine. When the value of an operating parameter of a machine is outside a preset range, the number of nodes of the hidden layer one layer before the output layer of the neural network is increased and training data obtained by actual measurement for a newly acquired value of an operating parameter of the machine is used to learn the weights of the neural network so that the difference between the output value changing in accordance with the values of the operating parameters of the machine and training data corresponding to the values of the operating parameters of the machine becomes smaller.

Abstract: First ECUs and second ECU of a control system of an internal combustion engine is configured to: output a predicted value of an output parameter by using a learning model if actually measured values of input parameters are input; and control an internal combustion engine based on this predicted value, the first ECUs is configured to: learn a learning model; and transmit first vehicle information including a usage environment and usage state of the first vehicle and the learned learning model linked with each other, and the second ECU is configured to receive the learned learning models, and wherein the second ECU is configured to use a learned learning model linked with the first vehicle information closest to the usage environment and usage state of the second vehicle.

Abstract: A model aggregation device includes a communication device able to communicate with a plurality of vehicles in which neural network models are learned, a storage device storing a part of the neural network models sent from the plurality of vehicles, and a control device. The neural network model outputs at least one output parameter from a plurality of input parameters. The control device is configured to, if receiving a new neural network model from one vehicle among the plurality of vehicles through the communication device, compare ranges of the plurality of input parameters which were used for learning the new neural network model and ranges of the plurality of input parameters which were used for learning a current neural network model stored in the storage device to thereby determine whether to replace the current neural network model with the new neural network model.

Abstract: A machine learning system comprises a learning planning part 81 configured to create a learning plan of a neural network model, a data set creating part 82 configured to create training data sets, a learning part 83 configured to perform learning of the neural network model using the training data sets when the vehicle is stopped, and a stopping period predicting part 84 configured to predict stopping periods of the vehicle. The data set creating part is configured to allocate the training data sets to a plurality of learning regions determined based on respective ranges of the plurality of input parameters. The learning part is configured to perform learning of the neural network model for each learning region. The learning planning part is configured to allocate the plurality of learning regions to the stopping periods so that learning of the neural network model is not suspended during the stopping periods.

Abstract: A machine learning system using a neural network to output an output value corresponding to values of operating parameters of the machine. When the value of an operating parameter of a machine is outside a preset range, the number of nodes of the hidden layer one layer before the output layer of the neural network is increased and training data obtained by actual measurement for a newly acquired value of an operating parameter of the machine is used to learn the weights of the neural network so that the difference between the output value changing in accordance with the values of the operating parameters of the machine and training data corresponding to the values of the operating parameters of the machine becomes smaller.

Abstract: First ECUs and second ECU of a control system of an internal combustion engine is configured to: output a predicted value of an output parameter by using a learning model if actually measured values of input parameters are input; and control an internal combustion engine based on this predicted value, the first ECUs is configured to: learn a learning model; and transmit first vehicle information including a usage environment and usage state of the first vehicle and the learned learning model linked with each other, and the second ECU is configured to receive the learned learning models, and wherein the second ECU is configured to use a learned learning model linked with the first vehicle information closest to the usage environment and usage state of the second vehicle.

Abstract: A control device mounted in a vehicle in which at least one controlled part is controlled based on an output parameter obtained by inputting input parameters to a learned model using a neural network, provided with a parked period predicting part predicting future parked periods of the vehicle and a learning plan preparing part preparing a learning plan for performing relearning of the learned model during the future parked periods based on results of prediction of the future parked periods.

Abstract: A control support device for supporting control of a vehicle using a learned model obtained by machine learning, includes: a data acquisition unit acquiring sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning; a learning unit generating a learned model by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit and is data including input parameters and an output parameter of the learned model; and a transmission unit Transmitting at least one of the generated learned model and an output parameter calculated by inputting sensor information of the vehicle, control of which is supported, to the generated learned model as an input parameter.

Abstract: A control device of an internal combustion engine using a neural network. When a value of an operating parameter of the engine is outside a preset range, the number of nodes of a hidden layer one layer before an output layer of the neural network is increased and training data obtained by actual measurement with respect to a newly acquired value of an operating parameter of the engine is used to learn a weight of the neural network so that a difference between the output value changing corresponding to the value of the operating parameter of the engine and training data corresponding to the value of the operating parameter of the engine becomes smaller.

Abstract: A control device of an internal combustion engine is configured to output a predicted value of an output parameter by using a learning model if actually measured values of input parameters are input, control the internal combustion engine based on the predicted value of the output parameter, learn the learning model by using a gradient method and by using a combination of actually measured values of the input parameters and an actually measured value of the output parameter as teacher data, and adjust the learning rate so that the learning is performed by a smaller learning rate when an amount of noise superposed on an actually measured value of at least one parameter among the input parameters and the output parameter is relatively large compared with when the amount of noise superposed on the actually measured value of the parameter is relatively small.

Abstract: A control device of an internal combustion engine using a neural network. When a value of an operating parameter of the engine is outside a preset range, the number of nodes of a hidden layer one layer before an output layer of the neural network is increased and training data obtained by actual measurement with respect to a newly acquired value of an operating parameter of the engine is used to learn a weight of the neural network so that a difference between the output value changing corresponding to the value of the operating parameter of the engine and training data corresponding to the value of the operating parameter of the engine becomes smaller.

Abstract: A control device of an internal combustion engine using a neural network, wherein an output value obtained by experiments is made training data for a value of an operating parameter of the engine in a presumed usable range, while an output value obtained by prediction without relying on experiments is made training data for a value of the operating parameter of the engine outside of the presumed usable range. The training data obtained by experiments and the training data obtained by prediction are used to learn the weights and the biases of the neural network so that an output value which changes in accordance with a value of an operating parameter of the engine matches the training data, and thereby even outside of the presumed usable range of the operating parameter, the output value can be suitably estimated.

Abstract: A control device for an internal combustion engine includes an in-cylinder pressure sensor, a crank angle sensor, and an electronic control unit. The electronic control unit is configured to calculate a correlation index value showing a degree of a correlation between a actually measured data of a combustion mass ratio and reference data of the combustion mass ratio based on an operating condition of the internal combustion engine. The electronic control unit is configured to, in a case where the correlation index value is lower than a determination value, prohibit the actually measured value of the specific ratio combustion point pertaining to a combustion cycle in which the correlation index value is calculated from being reflected in the engine control or reduce a degree of the reflection in the engine control compared to a case where the correlation index value is equal to or higher than the determination value.

Abstract: Feedback control is executed based on a measured CA10 and a measured CA50 that are calculated based on measured data for MFB. During steady operation a correlation index value IRA that shows a degree of correlation between the measured data and reference data corresponding thereto is calculated. During transient operation, a correlation index value IAA that shows a degree of correlation between the measured data and measured data that is measured immediately prior to the measured data is calculated. If the correlation index value IRA or the correlation index value IAA is less than a determination value Ith, control is performed to prohibit reflection in the aforementioned feedback control of each of the measured CA10 and the measured CA50 which are measured in the combustion cycle in which the relevant correlation index value is calculated.

Abstract: A control apparatus for an internal combustion engine is configured to: calculate measured data for MFB in synchrony with crank angle based on in-cylinder pressure detected by an in-cylinder pressure sensor; execute SA-CA10 feedback control and CA50 feedback control based on a measured CA10 and a measured CA50 that are calculated based on the measured data; execute engine control based on a degree of correlation between the MFB measured data and the reference data that corresponds thereto; and generate reference data for a combustion period by linear interpolation and linear extrapolation based on a target CA50 and a specified CA10.

Abstract: A control device for an internal combustion engine includes an in-cylinder pressure sensor, a crank angle sensor, and an electronic control unit. The electronic control unit is configured to calculate a correlation index value showing a degree of a correlation between a actually measured data of a combustion mass ratio and reference data of the combustion mass ratio based on an operating condition of the internal combustion engine. The electronic control unit is configured to, in a case where the correlation index value is lower than a determination value, prohibit the actually measured value of the specific ratio combustion point pertaining to a combustion cycle in which the correlation index value is calculated from being reflected in the engine control or reduce a degree of the reflection in the engine control compared to a case where the correlation index value is equal to or higher than the determination value.

Abstract: A control apparatus for an internal combustion engine is configured to: calculate measured data of MFB based on in-cylinder pressure detected by an in-cylinder pressure sensor; execute engine control based on a measured value of a specified fraction combustion point that is calculated based on the measured data of MFB; and calculate a first correlation index value for the measured data (current data) and the reference data of MFB and a second correlation index value for the current data and the immediately preceding past data. The engine control is suspended that uses the measured data of the specified fraction combustion point based on the current data when both of the first correlation index value and the second correlation index value are less than a determination value.

Abstract: A control apparatus for an internal combustion engine is configured to: calculate measured data of MFB based on in-cylinder pressure detected by an in-cylinder pressure sensor; execute engine control based on a measured value of a specified fraction combustion point that is calculated based on the measured data of MFB; and calculate a first correlation index value for the measured data (current data) and the reference data of MFB and a second correlation index value for the current data and the immediately preceding past data. The engine control is suspended that uses the measured data of the specified fraction combustion point based on the current data when both of the first correlation index value and the second correlation index value are less than a determination value.