Technology
TwinCAT software solutions for networked machine control SOURCE: BECKHOFF
New automation and machine control networking solutions include direct integration of OPC UA Pub/Sub for real-time communication, a server inference engine for increasing machine learning requirements and a TwinCAT/BSD Hypervisor that increases availability through integrated virtual machine environments. SOFTWARE AND HARDWARE INNOVATIONS ARE the heart of advances and new capabilities for automation and control applications. New TwinCAT solutions from Beckhoff including direct integration of OPC UA Pub/ Sub, a server inference engine for increasing machine learning requirements and TwinCAT/ BSD Hypervisor as a new system feature that increases availability through integrated virtual machine environments.
OPC UA Pub/Sub
With PC-based control and TwinCAT 3, Beckhoff supports the extension of OPC UA to include publisher/ subscriber communication. second transport path. With the new TwinCAT 3 function OPC UA Pub/Sub (TF6105), Beckhoff provides a package that can be used to configure and use both OPC UA Pub/ Sub UDP and MQTT Publisher and Subscriber directly in TwinCAT 3.
transport via an MQTT message broker primarily, but not exclusively, supports cloud scenarios. As an early adopter, Beckhoff implemented an initial prototype implementation of the UDP transport path back in 2016. Now, the implementation of MQTT adds a SOURCE: BECKHOFF
Direct integration of OPC UA Pub/Sub communication into the TwinCAT 3 runtime paves the way for straightforward realization of machine-to-machine (M2M) and device-tocloud (D2C) scenarios based on the OPC UA Pub/Sub specification. With a new extension of the OPC UA specification, which Beckhoff played a prominent role in helping develop, the publisher/subscriber principle is being introduced into the established and standardized OPC UA communication protocol. Two different transport paths can be defined for data transmission: UDP and MQTT. UDP enables efficient and real-time-capable data exchange in a local network between machines or machine components, whereas
TwinCAT Machine Learning Server is a high-performance execution module (inference engine) for trained machine and deep learning models.
32
TwinCAT Machine Learning
With TwinCAT Machine Learning Server as an additional inference engine, TwinCAT Machine Learning also meets the increasingly growing requirements of machine learning (ML) or deep learning for industrial applications. This is because ML models are becoming more and more complex, the execution speed is expected to increase, and greater flexibility of inference engines is demanded with respect to ML models. TwinCAT Machine Learning Server is a standard TwinCAT PLC library and a so-called near-real-time inference engine, i.e., in contrast to the two previous engines, it is not executed in hard real time, but in a separate process on the IPC. In return, basically all AI models can be executed in the server engine and this with full support of the standardized exchange format Open Neural Network Exchange (ONNX). Furthermore, there are AI-optimized hardware options for this TwinCAT product that enable scalable
in d u s t r ial et h er ne t b o o k
02.2022
