Abstract: A method detects a suspension position of a supporting bar in a pallet, having supporting bars along a longitudinal direction, each with multiple supporting bar tips along a main direction of extent. The supporting bar tips define a supporting plane. A two-dimensional contrast-image dataset of the pallet is created, its pixels being assigned a pixel value and a pixel-area unit of the supporting plane. The contrast-image dataset has regions that are assigned to the supporting bar tips as local pixel-value extremes in a uniform pixel-value background. A longitudinal position is determined in the contrast-image dataset of the regions that are assigned to the supporting bar tips a supporting bar using the local pixel-value extremes. The suspension position of the supporting bar in the pallet is deduced based on the longitudinal position in the contrast-image dataset and an extent of the pixel-area unit in the longitudinal direction.

Abstract: A method for optimizing production of sheet-metal parts, the production comprising cutting out and singularizing the sheet-metal parts and bending the sheet-metal parts, wherein the method includes: (A) training a neural network, which is executed on a Monte Carlo tree search framework, by means of supervised learning and self-play with reinforcement learning; (B) recording constraints for the sheet-metal parts, the constraints comprising geometric data of the sheet-metal parts; (C) creating an optimized production schedule by way of the neural network; and (D) outputting the production schedule.

Abstract: A method for optimizing production of sheet-metal parts, the production comprising cutting out and singularizing the sheet-metal parts and bending the sheet-metal parts, wherein the method includes: (A) training a neural network, which is executed on a Monte Carlo tree search framework, by means of supervised learning and self-play with reinforcement learning; (B) recording constraints for the sheet-metal parts, the constraints comprising geometric data of the sheet-metal parts; (C) creating an optimized production schedule by way of the neural network; and (D) outputting the production schedule.

Abstract: A method determines an actual state of a supporting bar for supporting a plate-like workpiece on a machine tool for a cutting the workpiece. The method includes: determining a geometry of supporting projections on the supporting bar by a light section method, which includes: projecting a longitudinal line of light onto a longitudinal side of the supporting bar; with the line of light, scanning the longitudinal side over a height region assigned to the supporting projections in the direction of the height of the supporting bar, detecting the scanned extent of the longitudinal side of the supporting bar to generate an image of the longitudinal side of the supporting bar, and determining the geometry of the supporting projections based on the generated image; and comparing the determined geometry of the supporting projections with the defined intended geometry of the supporting projections.

Abstract: A method for cutting machining of a plate-shaped workpiece, including determining the position of the support points either by measuring or inferring the position of the support points and/or the relative position of the workpiece, establishing starting-point-free regions, establishing end-point-free regions, establishing starting-point-free and end-point-free regions depending on the inferred or measured position of the support points and/or the relative position of the workpiece, establishing a grid of possible starting points and end points, omitting the starting-point-free and end-point-free regions determined in advance, either calculating a torque in a stabilizing and/or tilting direction or calculating a tilt height and/or a tilt depth for each of the points on the grid, setting a priority of points on the grid, transmitting the priority of points to a route planning means of the cutting head, and selecting one of the points on the grid and carrying out the cutting machining.

Abstract: A method generates a nesting plan for controlling a cutting process of a flatbed machine tool for cutting workpieces from a material sheet. The nesting plan includes an overlap-free arrangement of sub-spaces corresponding to the workpieces in a two-dimensional planning space as well as a spatial arrangement of predetermined supported spaces. After each new insertion of a sub-space during nesting, a packing density evaluation and at least one evaluation incorporating the position data of the respective initial position of the newly inserted sub-space in a local search space are performed.