Robust fault detection using consistency techniques with application to an automotive engine

Monitoring of the air intake system of an automotive engine is important to meet emission related legislative diagnosis requirements. In this paper, the problem of fault detection in the air intake system is stated as a constraint satisfaction problem over continuous domains with a big number of variables and constraints. This problem can be solved using Consistency Techniques. Consistency techniques are shown to be particularly efficient for checking the consistency of the Analytical Redundancy Relations (ARRs), dealing with uncertain measurements and parameters, and using experimental data.