Abstract: A system and method are described for post-processing a 3D printed component. For example, support structures for the 3D printed component may be removed during post-processing. In the system and method, a first image of a component is stored in memory. A second image of a 3D printed component corresponding to the component is also captured. One or more cutting paths between the 3D printed component and the support structures is then determined based on the first image and the second image. The 3D printed component may then be autonomously separated from the support structures by cutting through the cutting path.

Abstract: A system and method are described for post-processing a 3D printed component. For example, support structures for the 3D printed component may be removed during post-processing. In the system and method, a marker is placed on the 3D printed component or on a support structure attached to the 3D printed component. The marker may be printed while the 3D printed component and the support structures are printed by a 3D printer. After printing, the marker may then be sensed to determine one or more cutting paths between the 3D printed component and the support structures. The 3D printed component may then be autonomously separated from the support structures by cutting through the cutting path.

Abstract: To generate real-time or at least near real-time predictions for a process in an industrial plant, a set of neural networks are trained to create a set of trained models. The set of trained models is then used to output the predictions, by inputting online measurement results in an original space to two trained models whose outputs are fed, as reduced space inputs and reduced space initial states, to a third trained model. The third trained model processes the reduced space inputs to reduced space predictions. They are fed to a fourth trained model, which outputs the predictions in the original space.

Abstract: A system and method are described for post-processing 3D printed components. Post-processing may include removing support structures for the 3D printed components and may also include other processes like assembling 3D printed components into finished products. In the system and method, post-processing strategies are iteratively generated and performed on 3D printed components. Performance metrics of the post-processing strategies are compared with a user-defined performance indicator in a learning process to improve the post-processing strategy over a number of 3D printed components.

Abstract: To minimize the probability of occurrences of a delayed control action of a human operator, at least the human operator's interactions, including control actions, with a process and process responses to control actions are measured and processed to determine the human operator's alertness level, and if the alertness level is low enough, an engagement session may be triggered.

Abstract: A method for actively damping oscillations in a compression process, the method being performed by a controller. The method includes acquiring process data from a compression process, performing oscillation frequency estimation of any detected oscillations in the process data, generating a damping signal based on the oscillation frequency estimation, and providing the damping signal to an electrical drive of the compression process.

Abstract: A method for actively damping oscillations in a compression process, the method being performed by a controller. The method includes acquiring process data from a compression process, performing oscillation frequency estimation of any detected oscillations in the process data, generating a damping signal based on the oscillation frequency estimation, and providing the damping signal to an electrical drive of the compression process.