Attack Tolerant Fault Detection for CPSs: An Unknown Input Interval Observer Approach

The interval observer, recognized as a potent tool for fault detection (FD), diverges from the adoption of fixed thresholds to enhance the timeliness and precision of detection. This study endeavors to design an FD mechanism for fuzzy cyber-physical systems (CPSs) subjected to adversarial influences based on improved attack tolerant interval observer. Specifically, the proposed frequency-information-based unknown input interval observer (UIIO) not only enables a more precise estimation of the interval range under the influence of attack signals but also isolates unknown decoupled inputs. Furthermore, it facilitates specific performance design for signals within a particular frequency range. Following the stability analysis of the system, linear solvable conditions are presented to ensure the robustness, fault sensitivity of the augmented system, as well as non-negativity of the augment system matrix. Finally, the proposed attack-tolerant FD mechanism is validated through simulation examples, including the influence of the prior attack information to detection interval width and the detection performance for small-amplitude faults or faults with specific frequency characteristics. Note to Practitioners-CPSs constitute the core of the next-generation manufacturing industry, applicable in areas like unmanned autonomous systems, smart grids, and intelligent healthcare, capitalizing on wide-ranging cyber space utilization. Nonetheless, this breadth also exposes them to elevated risks, including the threat of actuator attacks. The novel fault detection scheme developed in this paper is capable of operating in real-time when the system is confronted with various threats such as disturbances, faults, and actuator attacks. This approach obviates the requirement for knowledge about the nature of actuator attack signals, while enabling the generation of a system state estimation interval with a tunable error range. Leveraging frequency-dependent techniques, the developed scheme, even in the presence of potential actuator attack and disturbance, is particularly well-suited for the detection of fault signals with specific frequency domain characteristics.