公开(公告)号：US11840974B2

公开(公告)日：2023-12-12

申请号：US17245484

申请日：2021-04-30

申请人： International Engine Intellectual Property Company, LLC

发明人： Askin Minaz ,  Ravi Rayala ,  Jungme Park ,  Rahul Rajampeta Rahul Rajampeta ,  Manoj Vemuri ,  Sriram Jayachandran Raguraman

IPC分类号： F02D41/18 ,  G06N3/08 ,  F02D41/14

CPC分类号： F02D41/182 ,  F02D41/1405 ,  F02D41/187 ,  G06N3/08

摘要： The Method and Apparatus of Predicting MAF Sensor Information includes training multiple candidate Artificial Neural Network (ANN) architectures using training data, and then selecting an ANN architecture from the candidates using an automated ANN architecture selection algorithm and testing data. An intelligent engine intake MAF prediction or estimation system using the selected ANN architecture then provides an engine intake Mass Air Flow (MAF) output variable, which is used along with the output of a hot-wire type engine intake MAF sensor. The system is deployed into the engine controller. The training and testing sets of data include input variables from engine sensors and/or actuators that relate to engine intake MAF, and may be acquired by testing a target engine. Selecting the optimal ANN architecture may be based on Root Mean Squared Error (RMSE) analysis using the automated ANN architecture algorithm and the training set of data.

公开(公告)号：US20220349358A1

公开(公告)日：2022-11-03

申请号：US17245484

申请日：2021-04-30

申请人： International Engine Intellectual Property Company, LLC

发明人： Askin Minaz ,  Ravi Rayala ,  Jungme Park ,  Rahul Rajampeta Rahul Rajampeta ,  Manoj Vemuri ,  Sriram Jayachandran Raguraman

IPC分类号： F02D41/18 ,  G06N3/08 ,  G06K9/62

摘要： The Method and Apparatus of Predicting MAF Sensor Information includes training multiple candidate Artificial Neural Network (ANN) architectures using training data, and then selecting an ANN architecture from the candidates using an automated ANN architecture selection algorithm and testing data. An intelligent engine intake MAF prediction or estimation system using the selected ANN architecture then provides an engine intake Mass Air Flow (MAF) output variable, which is used along with the output of a hot-wire type engine intake MAF sensor. The system is deployed into the engine controller. The training and testing sets of data include input variables from engine sensors and/or actuators that relate to engine intake MAF, and may be acquired by testing a target engine. Selecting the optimal ANN architecture may be based on Root Mean Squared Error (RMSE) analysis using the automated ANN architecture algorithm and the training set of data.