Abstract: Various embodiments include a computer-implemented method for determining a level of wear of a tool. The method includes: obtaining an image data set mapping a wear-relevant region of the tool; allocating, using a computing unit and an artificial neural network, one class of a predetermined quantity of classes to each image point of a plurality of image points of the image data set; and determining a characteristic value based on a result of the allocation for the level of wear. The quantity of classes includes at least one wear class.

Abstract: Various embodiments of the teachings herein include a method for subtractive machining of a workpiece using a tool. The method may include: detecting at least two process variables of a machining process; and using the process variables to infer a wear on the tool. The process variables are passed on to a neural network which assigns each process variable a respective degree of wear independently of the other. The wear is inferred by means of a logic on the basis of the respective degrees of wear. The process variables are each selected from the group consisting of: a shape of the tool, an operating current, an operating voltage, maintenance and servicing information, and interruption information of the machining. Detecting the shape of the tool includes imaging using a camera and/or a scanner.

Abstract: At least one example embodiment relates to an apparatus, machine-readable program code, a storage medium and computer-implemented method for the automatic classification of emitter structures embodied to emit electrons for the generation of X-rays, wherein the classification takes place on the basis of a reference image of an emitter structure, wherein the classification comprises a first class and at least one second class, wherein the first class corresponds to a substantially defect-free emitter structure and the at least one second class corresponds to a defective emitter structure. Since, for the classification, an image embodied as a fusion image from a bright-field image and a dark-field image is referred to and the classification of the emitter structure into the first and the second class takes place on the basis of this image, improved defect checking of emitter structures can be provided.

Abstract: In a method for training a neural network to recognize a tool condition based on image data, the neural network is trained to recognize the tool condition of a first tool type, and image data of a second tool type is applied. The image data is subjected to image processing. Via this, the image data of the second tool type is converted into image data of the first tool type. The neural network is trained based on the converted image data. In a method for machining and/or production via the first tool type, the tool condition of the first tool type is recognized via a neural network that is trained in accordance with such a method.