Fault detection, isolation and identification for hybrid systems with unknown mode changes and fault patterns

This article presents a solution to the problem of multiple fault detection, isolation and identification for hybrid systems without information on mode change and fault patterns. Multiple faults of different patterns are considered in a complex hybrid system and these faults can happen either in a detectable mode or in a non-detectable mode. A method for multiple fault isolation is introduced for situation of lacking information on fault pattern and mode change. The nature of faults in a monitored system can be classified as abrupt faults and incipient faults. Under abrupt fault assumption, i.e. constant values for fault parameters, fault identification is inappropriate to handle cases related to incipient fault. Without information on fault nature, it is difficult to achieve fault estimation. Situation is further complicated when mode change is unknown after fault occurrence. In this work, fault pattern is represented by a binary vector to reduce computational complexity of fault identification. Mode change is parameterized as a discontinuous function. Based on these new representations, a multiple hybrid differential evolution algorithm is developed to identify fault pattern vector, abrupt fault parameter/incipient fault dynamic coefficient, and mode change indexes. Simulation and experiment results are reported to validate the proposed method.

► We propose a method for multiple fault isolation for hybrid systems with unknown mode change and fault pattern. ► Mode change will make those faults occurring at a non-detectable mode to be detected. ► Fault pattern is represented by a binary vector to reduce computational complexity of fault identification. ► Multiple faults with parametric and nonparametric nature are considered and they can develop either abruptly or incipiently. ► A hybrid differential evolution algorithm is developed to deal with the identification problem.