Hierarchical Modelling and Diagnosis for Embedded Systems

Memory-limited model-based diagnosis

“…Measurement selection requires a measurement selection function [3,91,92] which gets a set of minimal diagnoses D as input, and outputs one system measurement such that any measurement outcome eliminates at least one spurious diagnosis in D. As measurement selection functions we adopted split-in-half (SPL) [32], which suggests a measurement with the lowest worst-case number of spurious diagnoses in D eliminated 44 , and entropy (ENT) [3], which selects a measurement with highest information gain. These functions appear to be the most commonly adopted ones in model-based diagnosis, cf., e.g., [18,32,92,93,94,95,96,97,98].…”

Iterative hybrid causal model based diagnosis: Application to automotive embedded functions

“…This paper proposes a consistency based method designed for hybrid systems that can complement an available fault dictionary based method, in our case the method of Ressencourt et al (2006) based on Modelica models, and uses the same models and simulation results. The only additional information that is required is the structure of the reference models in the form of a causal graph that we are able to derive automatically and the interpretation of the simulation results obtained for continuous variables into qualitative values and events.…”

“…Most methods are based on a dictionary of fault signatures supporting heuristic optimization techniques or the computation of the expected quantity of information for the tests. In Ressencourt et al (2006), hybrid system simulation techniques, based on the Modelica language, are used to build the dictionary of fault signatures from faulty models. Hierarchical multi-model strategies are then applied to structure the search space by articulating functional observations with low level signal measures, so that proposed tests best match expert human intuition.…”