Beckhoff Automation announced a new machine-learning (ML) solution that is integrated into TwinCAT 3 software. Building on established standards, TwinCAT 3 Machine Learning offers ML applications the same advantages of system openness familiar from PC-based control technology while supporting real-time ML, allowing it to simultaneously handle tasks like motion control, according to Beckhoff. These capabilities provide machine-builders and manufacturers a foundation to enhance machine performance through predictive maintenance, process self-optimization and autonomous detection of process anomalies.
Beckhoff notes that the automation controller can learn the desired algorithms from exemplary process data. With this alternative approach, powerful ML models can be trained and used to deliver superior, higher-performing solutions. In automation technology, this opens up new possibilities in many areas, including predictive maintenance and process control, anomaly detection, collaborative robotics, automated quality control and machine optimization.
The models to be learned are trained in an ML framework, such as MATLAB or TensorFlow, and then imported into the TwinCAT runtime via the Open Neural Network Exchange Format (ONNX), a standardized data-exchange format used to describe trained models. According to Beckhoff, the TwinCAT runtime incorporates the following new functions for this purpose:
- TwinCAT 3 Machine Learning Inference Engine for classic ML algorithms, such as support vector machine (SVM) and principal component analysis (PCA)
- TwinCAT 3 Neural Network Inference Engine for deep learning and neural networks, such as multilayer perceptrons (MLPs) and convolutional neural networks (CNNs)