Decentralized fault diagnosis of discrete-event systems with unreliable sensors using linear temporal logic

In this paper, we investigate a decentralized diagnosis problem of a discrete-event system (DES) subject to unreliable sensors, where the sensor observations of local diagnosers may be non-deterministic as a result of possible failures. Existing studies on decentralized robust diagnosis can only deal with different types of sensor failures separately, e.g., all sensors suffer from the same type of sensor failures such as intermittent sensor failures or permanent sensor failures. However, since sensors of different local diagnosers may face different external environments and have different internal characteristics, sensors corresponding to different local diagnosers may also have their own fault features. In this paper, we propose a flexible framework of decentralized diagnosis for DES subject to unreliable sensors such that sensors of different local diagnosers are permitted to have different types of sensor failures. To this end, we extend the existing decentralized diagnosis framework to the case where there exist common sensors broadcasting their observations to all local diagnosers. We apply linear temporal logic (LTL) to constrain infinite behaviors of private sensors of local diagnosers and common sensors. Then, a new notion of φ-codiagnosability is proposed as the necessary and sufficient condition for the existence of a decentralized diagnoser that works correctly under sensors satisfying LTL-based sensor constraints. Finally, we provide an effective approach to verify the φ-codiagnosability.