Editor’s choice
To avoid latency issues, the AI system is integrated at the edge, instead of the cloud, resulting in quicker machine shutdown and a reduced likelihood of product damage. This principle also applies to process performance optimisation, including the speed or movement of a machine. An AI system situated at the edge can transmit directives to equipment for performance improvements faster than from the cloud. For instance, imagine a manufacturing facility where every machine communicates its health status, productivity metrics and potential maintenance needs in real time, allowing for predictive and preventive actions that significantly reduce downtime.
Or a smart energy grid that optimises power distribution based on real-time consumption patterns, enhancing efficiency and sustainability. These scenarios, once the stuff of science fiction, are swiftly becoming reality thanks to the merging of edge IoT and AIoT.
INTEGRATING THE AIOT To incorporate AIoT on the edge, plant managers need to develop an offline AI model. This model should subsequently undergo
Instrumentation Monthly October 2023
training, by employing pre-existing datasets to enhance its performance and ensure alignment with predetermined standards and criteria. Once satisfied, plant managers can export the model and implement it online, where it interfaces with fresh, real time data streams. Testing the model on stored data, which has already passed the training stage, is a completely different matter compared to applying it online. This is because real time data has not been filtered or categorised and each set, that arrives at different times, creates an information mess for the AIoT. Therefore, technologies that facilitate the integration of AI into industrial processes and machinery are required before the model can be used by the AIoT. Programmable logic controllers (PLCs) and industrial PCs are feasible options, as they can serve as edge computing devices. These edge devices can host AI models and algorithms, allowing data analysis and decision making at the edge of the network, without the need to rely solely on centralised cloud resources. In fact, Beckhoff’s TwinCAT software platform is commonly used for programming and configuring their PLCs and industrial PCs. This platform
supports the development and deployment of AI and machine learning algorithms, enabling the creation of AI-powered applications within industrial environments.
As the demand for real-time data processing intensifies, this allows companies to harness the potential of edge IoT and AIoT in their applications - be it for predictive maintenance, quality control or the optimisation of production process purposes.
Beckhoff Automation
www.beckhoff.co.uk
13
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82
