Fault diagnosis for spark ignition engine based on multi-sensor data fusion

Abstract

In data fusion approaches, Dempster-Shafer (D-S) evidence theory offers an interesting tool to combine data from multi-sensor. The decision-level fusion based on Dempster-Shafer (D-S) evidence theory can process non-commensurate data and has robust operational performance, reduces ambiguity, increases confidence, and improves system reliability. This paper describes mainly a decision-level data fusion technique for fault diagnosis for electronically controlled spark ignition engines. A D-S evidence theory fault diagnosis model is founded, and the feature selection and extraction of fault signal is conducted. Experiments on a 462 mini engine show that the data fusion technique provides good engine fault diagnosis method.