Machine learning device, machine learning method, electronic control unit and method of production of same, learned model, and machine learning system

Abstract

A learning use data set showing relationships among an engine speed, an engine load rate, an air-fuel ratio of the engine, an ignition timing of the engine, an HC or CO concentration of exhaust gas flowing into an exhaust purification catalyst and a temperature of the exhaust purification catalyst is acquired. The acquired engine speed, engine load rate, air-fuel ratio of the engine, ignition timing of the engine, and HC or CO concentration of the exhaust gas flowing into the exhaust purification catalyst are used as input parameters of a neural network and the acquired temperature of the exhaust purification catalyst is used as training data to learn a weight of the neural network. The learned neural network is used to estimate the temperature of the exhaust purification catalyst.

1 . A machine learning apparatus for use with an internal combustion engine, the machine learning apparatus comprising:
 an electronic control unit configured to:
 acquire data showing an engine speed, an engine load rate, an air-fuel ratio of an engine, an ignition timing of the engine, an HC or CO concentration of exhaust gas flowing into an exhaust purification catalyst and a temperature of the exhaust purification catalyst from the internal combustion engine, 
 prepare a data set using the acquired engine speed, engine load rate, air-fuel ratio of the engine, ignition timing of the engine, HC or CO concentration, and exhaust purification catalyst temperature, and 
 learn a weight of the neural network by applying a temperature of the exhaust purification catalyst as training data to learn a weight of the neural network wherein, 
 the temperature of the exhaust purification catalyst of the internal combustion engine is predicted based on the learned neural network from the acquired engine speed, the engine load rate, air-fuel ratio of the engine, ignition timing of the engine, and HC or CO concentration of the exhaust gas flowing into the exhaust purification catalyst. 
   
     
     
         2 . A machine learning method for use with an internal combustion engine, the machine learning method comprising:
 acquiring data showing an engine speed, an engine load rate, an air-fuel ratio of an engine, an ignition timing of the engine, an HC or CO concentration of exhaust gas flowing into an exhaust purification catalyst and a temperature of the exhaust purification catalyst from the internal combustion engine,   preparing a data set using the acquired engine speed, engine load rate, air-fuel ratio of the engine, ignition timing of the engine, HC or CO concentration, and exhaust purification catalyst temperature, and   learning a weight of the neural network by applying a temperature of the exhaust purification catalyst as training data to learn a weight of the neural network wherein,   the temperature of the exhaust purification catalyst of the internal combustion engine is predicted based on the learned neural network from the acquired engine speed, the engine load rate, air-fuel ratio of the engine, ignition timing of the engine, and HC or CO concentration of the exhaust gas flowing into the exhaust purification catalyst.   
     
     
         3 . A non-transitory computer readable medium storing a program for use with an internal combustion engine, the program causing a computer to perform steps comprising:
 acquiring data showing an engine speed, an engine load rate, an air-fuel ratio of an engine, an ignition timing of the engine, an HC or CO concentration of exhaust gas flowing into an exhaust purification catalyst and a temperature of the exhaust purification catalyst from the internal combustion engine,   preparing a data set using the acquired engine speed, engine load rate, air-fuel ratio of the engine, ignition timing of the engine, HC or CO concentration, and exhaust purification catalyst temperature, and   learning a weight of the neural network by applying a temperature of the exhaust purification catalyst as training data to learn a weight of the neural network wherein,   the temperature of the exhaust purification catalyst of the internal combustion engine is predicted based on the learned neural network from the acquired engine speed, the engine load rate, air-fuel ratio of the engine, ignition timing of the engine, and HC or CO concentration of the exhaust gas flowing into the exhaust purification catalyst.