Abstract: To generate a decision logic for a controller of an Industrial Automation Control System, IACS, an iterative process is performed in which a decision logic candidate for the decision logic is generated, and a performance of the decision logic candidate in response to scenarios is computed.

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: A model generation system includes input and output units. The input unit receives a plurality of input value trajectories comprising operational input value trajectories and simulation input value trajectories relating to an industrial process. The processing unit implements a simulator of the industrial process and generates behavioral data for at least some of the plurality of input value trajectories. The processing unit further implements a machine learning algorithm that models the industrial process, and trains the machine learning algorithm.

Abstract: A method and computer program product including training a machine learning model by means of input data and score data, wherein the machine learning model is an artificial neural net, ANN; running the trained machine learning model by applying the first time-series to the trained machine learning model; and outputting, by the trained machine learning model, an output value, comprising at least a second criticality value of the at least one predicted observable process-value indicative of the abnormal behaviour of the industrial process in a predefined temporal distance.

Abstract: Performance of a decision-making logic (35) of a controller (31) of an industrial automation control system is monitored during field operation of the controller (31). A supervisory system (20) receives operational data collected during field operation of the controller (31). The supervisory system performs an analysis of the operational data to assess performance of the decision-making logic (35), using pre-operational data generated prior to field operation of the controller (31) and/or a performance assessment logic (27) generated prior to field operation of the controller (31).

Abstract: Machine learning, ML, using labeled data is performed to thereby train a ML model to generate decision logic for a controller of an IACS, in particular a power system controller. The ML model has ML model inputs and ML model outputs. The ML model is decomposed into a plurality of computational sub-processes, wherein intermediate signals output by one of the computational sub-processes are input into a consecutive one of the computational sub-processes. Information on the trained ML model is generated based on the intermediate signals and is output for interpretation, verification, visualization, and/or inspection of at least one of the computational sub-processes.

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.