Dynamic Probabilistic Model Checking for Sensor Validation in Industry 4.0 Applications

Abstract

Industry 4.0 adopts Internet of Things (IoT) and service-oriented architectures to integrate Cyber-Physical Systems and Enterprise Planning into manufacturing operations. This kind of integration consists of a combination of connected sensors and run-time control algorithms. Consequential control decisions are driven by sensor-generated data. Hence, the trustworthiness of the sensor network readings is increasingly crucial to guarantee the performance and the quality of a manufacturing task. However, existing methodologies to test such systems often do not scale to the complexity and dynamic nature of today’s sensor networks. This paper proposes a novel run-time verification framework combining sensor-level fault detection and system-level probabilistic model checking. This framework can rigorously quantify the trustworthiness of sensor readings, hence enabling formal reasoning for system failure prediction. We evaluated our approach on an industrial turn-mill machine equipped with a sensor network to monitor its main components continuously. The results indicate that the proposed verification framework involving the quantified sensor’s trustworthiness enhances the accuracy of the system failure prediction.