Credit: Google News
Software integrates machine learning and drive programming
Beckhoff has integrated a real-time machine learning (ML) capability into its TwinCat 3 automation software. It says that the ML technology is powerful enough to handle advanced tasks such as motion control, and predicts that it will open up new possibilities and optimisation potential in areas such as predictive maintenance, anomaly detection, collaborative robotics, automated quality control, and machine optimisation.
Beckhoff unveiled the ML capability at the Hannover Fair, where it was also demonstrating a plug-and-play integration technology, developed in conjunction with Danfoss Drives, that allows Danfoss’ AC drives to be programmed and commissioned directly from TwinCat. Having a single tool that can handle all aspects of programming and commissioning of these drives is expected to save time and money for systems integrators and OEMs.
Machine learning allows control algorithms to be developed by analysing process data. The models to be learned are trained in an ML framework, such as Matlab or TensorFlow, and then imported into TwinCat runtime using the Open Neural Network Exchange Format (ONNX) – a standard data exchange format used to describe trained models.
TwinCat runtime incorporates new functions to support the ML capabilities: an ML inference engine for algorithms such as support vector machine (SVM) and principal component analysis (PCA); and a neural network inference engine for deep learning and neural networks.
Beckhoff demonstrated the ability of its TwinCat software to program Danfoss drives at the recent Hannover Fair
Trained ML models can be executed in real-time with a TwinCAT TcCom object. With smaller networks, response times of less than 100µs are possible, corresponding to a TwinCat cycle time of 50µs. Models can be called via PLC, C/C++ TcCom interfaces, or a cyclical task.
TwinCat 3’s multi-core capabilities are available for machine learning applications. This means, for instance, that different tasks can access an inference engine without restricting each other. The ML technology can also access the large amounts of data available in TwinCat, allowing complex data-merging operations.
Credit: Google News