Interval model-based diagnosis using constraint programming

In engineering applications many models are based on constraints with interval parameters and variables. The model is based on the knowledge of the behavior of the system to diagnose. Inputs and outputs of components are represented as variables in the constraints, and they can be observable and non-observable depending on the Situation of the sensors in the system. In this work, we propose a new approach to automate the determination of the minimal diagnosis. This approach has two phases. In the first phase, we determine components Clusters in the system in order to reduce drastically the number of components to consider. This is specially necessary in high density systems where components compose independent sets in themselves. In the second phase, we construct a constraint satisfaction diagnosis problem. In this phase we use interval variables (based on the domain of the variables). The results obtained in the Studied cases are very promising.