Fault Detection and Identification of Automotive Engines using Neural Networks
| Authors: | Gomm James Barry, Liverpool John Moores University, United Kingdom
Sangha Mahavir, Liverpool John Moores University, United Kingdom
Yu Dingli, Liverpool John Moores University, United Kingdom
Page George, Liverpool John Moores University, United Kingdom |
|---|
| Topic: | 7.1 Automotive Control |
|---|
| Session: | Automotive Control |
|---|
| Keywords: | fault diagnosis and isolation, radial basis function networks, classification, artificial intelligence, neural networks, engine systems |
|---|
Abstract
Fault detection and isolation (FDI) in dynamic data from an automotive engine air path using artificial neural networks is investigated. A generic SI mean value engine model is used for experimentation. Several faults are considered, including leakage, EGR valve and sensor faults, with different fault intensities. RBF neural networks are trained to detect and diagnose the faults, and also to indicate fault size, by recognising the different fault patterns occurring in the dynamic data. Three dynamic cases of fault occurrence are considered with increasing generality of engine operation. The approach is shown to be successful in each case.
