A MAS-based architecture for IIoT safety applications

Abstract

The Internet of Things (IoT), and in particular, the concept of an Industrial Internet of Things (IIoT), is one of the key technological pillars of the Fourth Industrial Revolution, also known as Industry 4.0. In this context, an area of considerable interest is safety, whereby multiple intelligent sensors may be permanently connected to a central system to autonomously or semi-autonomously identify safety hazards. Vision systems emerged as popular sensors leveraged in such safety domain as they can simultaneously monitor many different safety concerns. However, the continuous video stream transmission and the increasing number of intelligent devices in IIoT networks introduce additional demand for network resources. There is a risk that the network may fail in the timely handling of video traffic in the case of large scenarios. This work proposes and discusses a reference architecture for the IIoT. It has been based on Multi-Agent Systems and is primarily intended to identify and manage safety risks. The architecture allows the simultaneous insertion of multiple sensors into the system. Input from the different sensors is then dynamically examined and weighed accordingly to estimate the risk level for any given situation. The architecture explores sensor-level intelligence (at the edge layer) to mitigate the network overloading problem. Edge agents quickly assess the risk, deciding whether or not to forward their signals to a local cloud agent for further processing. The cloud agent can then selectively request more information from other distributed edge agents. The architecture is tested in a use case for assessing operators’ safety in the assembly of aircraft components and uses intelligent vision systems as safety monitoring devices. In the selected use case, the accuracy of the system and its impact on the network load are evaluated. The results show that the proposed architecture allows and benefits from the distribution of the processing to the edge. It reduces the load in the network by avoiding the transmission in the absence of risks, without losing accuracy, compared to when using centralized continuous and direct transmissions from the distributed sensors.