Schwarz + Kollegen

The patent application pertains to a method for determining control commands for driving an electrical drive of a laser processing machine. The method involves receiving specifications from a cutting plan, including an intended trajectory, and providing a machine model that represents the dynamic behavior of the electrical drive. An adapted model predictive control (MPC) algorithm is applied based on the provided machine model and the received specifications to predict the future dynamic behavior of the electrical drive, particularly a predicted trajectory, within a pre-determined prediction horizon. The predicted trajectory is compared with the intended trajectory to determine control commands for the electrical drive. These determined control commands are then provided on a control interface. The machine model is generated in a preparation phase using measurement data from the machine, particularly a position feedback signal. The MPC algorithm is adapted to include constraints on the parameters of the differential equations, particularly on the motor current, and to have a prediction horizon equal to the control horizon. The method allows for precise and repeatable movements of the laser beam along predetermined paths, improving the quality of the processed material.

Beschichtungszusammensetzung, umfassend eine wasserbasierte Polyester- aliphatische Polyurethan-Dispersion, enthaltend isocyanatfreie Polyurethane (NIPU), dadurch gekennzeichnet, dass der Feststoffgehalt (d.h. die aliphatischen Polyester-Polyurethane) der Dispersion im Bereich von 50 bis 95 Gew.-% liegt und dass diese durch Trocknung aushärtet.

The invention pertains to a detection method for identifying anomalies on a material intended for laser processing. The method involves the acquisition of image data of the material via an input interface connected to an optical sensor system. This image data is then processed using a classification algorithm that is embedded within a trained neural network. The outcome of this process is a classification result, which is made available through an output interface. This method provides an efficient and accurate means of detecting irregularities on materials before they undergo laser processing, thereby enhancing the overall quality and efficiency of the laser processing operation.

The invention relates to a technique for pre-training a principal encoder and a concept head. A method comprises receiving, at a principal encoder (302), a medical image (502) and processing it for obtaining a principal latent representation (504), which is provided to a concept head (306) and to a style head (310) to obtain a first vector of discretized anatomical concepts and an associated further first vector of continuous styles per discretized anatomical concept in the medical image (502), respectively. An auxiliary feature decoder determines, based on the obtained first vector of discretized anatomical concepts, an auxiliary latent representation (10), based on which an auxiliary image decoder (316) performs a reconstruction (512) of the medical image (502). The principal encoder (302) and concept head (306) are pre-trained based a reconstruction loss between the received medical image (502) and the first reconstruction (512).

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …