Synchronous Diagnosis of Discrete-Event Systems

In general, systems are formed by the composition of several modules, local components, or subsystems, and may exhibit a large number of states. The growth of the composed model with the number of system components leads to high-computational costs for diagnosis techniques based on the composed plant model. We propose in this article a new approach for fault diagnosis that avoids the direct use of the composed system model for the diagnoser implementation, reducing the computational cost for diagnosis. The diagnosis strategy is based on the observation of the fault-free behavior of the system components. In this regard, we introduce the definition of synchronous diagnosability of the language of a discrete-event system (DES) with respect to the languages of its components and provide a method to verify this property. An algorithm that efficiently computes the fault-free behavior model of the system components is also proposed. We extend this approach to a decentralized architecture and introduce the definition of synchronous codiagnosability. Moreover, a comparison between the classical definition of diagnosability, synchronous diagnosability, synchronous codiagnosability, and modular diagnosability of DESs is established. The verification of synchronous diagnosability for a didactic automated system is presented to show the results of the article. Note to Practitioners-In the traditional fault diagnosis approaches, in order to design a diagnoser for a discrete-event system, it is necessary to obtain its model, including both fault-free and postfault behaviors. Since, in general, complex systems are formed by several modules, components, or subsystems, then the composed system model may have a large number of states, which leads to diagnosers, obtained by using the traditional techniques, with a huge number of states, increasing the computational cost for their implementation. In order to circumvent this problem, we propose in this article the implementation of a diagnoser that is computed from the fault-free behavior models of the system components, avoiding the direct use of the composed system model for diagnosis. We also present a decentralized architecture in order to enable its use for large systems where the sensor information is distributed. The verification of the diagnosability of the system considering the fault diagnosis scheme proposed in this article is applied to a didactic automated plant.