October 2019

www.smartmachinesandfactories.com October 2019 | 31 | | APPLICATIONS | the Extensible Authentication Protocol (EAP) and strong encryption, while meeting strict latency requirements. While the standards are not expected to be ready until 2020 at the earliest, in the UK, the Worcestershire 5G consortium project is already exploring ways to increase productivity using robotics, big data analytics and augmented reality with 5G in a manufacturing setting. Promising application areas range from logistics - for supply and inventory management, through robot and motion control applications, to operations control and the localisation of devices and items. 5G is likely to support various Industrial Ethernet and Time Sensitive Networking (TSN) features, thereby enabling it to be integrated easily into the existing (wired) infrastructure, and in-turn enabling applications to exploit the full potential of 5G with ease. AI is taking Industry 4.0 further Like 5G, AI is also expected to accelerate and enhance the implementation of Industry 4.0, and connectivity is vital for AI to succeed. But what is AI in the context of industrial automation? AI can be defined as the concept of improvement and gaining insights through smart analytics and modelling, it is a collective term that incorporates a number of steps as shown in figure 2. AI can take place in all three locations shown in figure 3: in the cloud, where large quantities of data can be evaluated easily, on-premise, which is on the system at production network level, or on-edge, which is on the component at field level. Machinery will be increasingly autonomous and is expected to use AI to organise cooperation among themselves, sharing data with the supply / delivery chains and with users: creating ad hoc networks as the need arises. The data produced from the manufacturing process is analysed and actioned through AI to create dynamic self-learning production environments that are able to provide increasingly higher levels of productivity, operating with higher quality in a safer working environment. Some are concerned that AI will dramatically decrease or even eliminate the need for human interaction on the factory floor. However, AI needs human involvement, to define the objective and refine the output. AI does not provide a definitive ‘yes / no’, but rather gives a suggestion with a probability score against it. AI gradually improves the accuracy of the probability score based on the human feedback, refining its algorithm model. Manufacturing production and the digital world are merging, making factory automation more flexible, increasing energy efficiency, linking logistics processes more closely and optimising the value chain. 5G networks and the emergence of AI are key enablers for the digital future and will offer manufacturers the chance to build smart, digital factories using Industry 4.0 principles. applications with very demanding requirements in terms of end-to-end (E2E) latency (down to the millisecond level <1 ms), reliability and availability. This is a clear requirement for industrial automation and control applications. mMTC provides wide-area coverage and deep indoor penetration for hundreds of thousands of IoT devices per square kilometre. In addition, mMTC is designed to provide ubiquitous connectivity with low software and hardware requirements from the devices, and will support battery-saving, low-energy operation. eMBB provides extremely high data rates (of up to several Gb/s) and offers enhanced coverage, well beyond that of 4G. Security concerns are also being addressed with 5G. In a recent survey conducted by Festo 67% of respondents voted security as one of the main barriers to Industry 4.0 adoption, as shown in table 1, and it is frequently cited as a key challenge to overcome in implementing Industry 4.0. 5G can be characterised as a modular communication system, with in-built privacy and security, which is based upon the cloud approach and can be flexibly configured to meet different service requirements. 5G includes strong E2E security. In particular, mutual authentication between the device and the network is supported. All transmitted data is encrypted E2E between the device and the network. 5G also supports a flexible authentication framework with Fig 3. Where AI takes place

RkJQdWJsaXNoZXIy MjQ0NzM=