TF3820 | TwinCAT 3 Machine Learning Server

Beckhoff offers a solution for machine learning (ML) and deep learning (DL) that is seamlessly integrated into TwinCAT 3. The TF3820 TwinCAT 3 Machine Learning Server is a high-performance execution module (inference engine) for trained ML and DL models.

The TwinCAT 3 Machine Learning Server provides a function for loading and executing trained AI models. The server's services can be called and configured from TwinCAT runtimes via PLC function blocks. A server can load multiple AI models and be called by multiple TwinCAT runtimes. Loaded AI models can be run on the CPU or on the GPU. An integrated load balancing system distributes and prioritizes requests to the server, taking the available computing resources into account. The model runs in an independent process of the operating system. There are almost no restrictions when it comes to the ML and DL models. From clustering models to image classification to object detection, the options for model selection are extremely diverse.

The ML and DL models are trained in established frameworks, e.g. scikit-learn, PyTorch, TensorFlow or MATLAB®. The information of the learned network is loaded to the inference engine as a description file. The Open Neural Network Exchange (ONNX) standardized exchange format is supported, thus seamlessly merging the worlds of automation and data science.

The TwinCAT 3 Machine Learning Server provides an inference engine with maximum flexibility in terms of models and high performance in terms of hardware. Applications can be found in predictive and prescriptive models, in the machine vision sector, and in robotics. Examples include image-based methods for sorting or evaluating products, for defect classification or defect or product localization, and for calculating gripping positions.