Machine learning system for estimating a temperature of an exhaust purification catalyst

Patent metadata

Field	Value
Publication number	US-10635976-B2
Application number	US-201815987172-A
Country	US
Kind code	B2
Filing date	May 23, 2018
Priority date	Apr 5, 2018
Publication date	Apr 28, 2020
Grant date	Apr 28, 2020

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.

First claim

The invention claimed is:

1. A machine learning system for use with a vehicle, the machine learning system comprising:
a vehicle-mounted 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 vehicle; and

a server configured to:
acquire the data from the vehicle-mounted electronic control unit, including acquiring: (i) the engine speed, (ii) the engine load rate, (iii) the air-fuel ratio of the engine, (iv) the ignition timing of the engine, (v) the HC or CO concentration of exhaust gas flowing into the exhaust purification catalyst, and (vi) the temperature of the exhaust purification catalyst,
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,
determine the temperature of the exhaust purification catalyst in accordance with the prepared data set,
generate a learned model based on 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 as input parameters of a neural network,
learn a weight of the neural network by applying a received temperature of the exhaust purification catalyst as training data, and
transmit the generated learned model to the vehicle, wherein:

the temperature of the exhaust purification catalyst of the internal combustion engine is predicted based on the learned model 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 in the vehicle.

Assignees

• Toyota Motor Co Ltd

Inventors

• Nagasaka Keisuke
• Oyagi Hiroshi
• Takasu Yusuke
• Kaneko Tomohiro

Classifications

• F01N9/00

  Electrical control of exhaust gas treating apparatus (monitoring or diagnostic devices for exhaust-gas treatment apparatus F01N11/00; conjoint electrical control of two or more combustion engine functions F02D43/00) · CPC title

• F01N2900/1402

  Exhaust gas composition · CPC title

• F01N2900/0402

  using adaptive learning · CPC title

• G06N3/02

  Neural networks · CPC title

• F01N2560/022

  for measuring or detecting CO or CO2 · CPC title