Techniques for determining print quality for a 3D printer are disclosed. An example method includes obtaining an image of a stream of material jetted from a nozzle of the 3D printer, and binarizing the image to distinguish background features from foreground features contained in the image. The method also includes identifying elements of jetted material in the foreground features, and computing statistical data characterizing the identified elements. The method also includes generating a quality score of jetting quality based on the statistical data and controlling the 3D printer based on the quality score. The quality score indicates a degree to which the elements of jetted material form droplets of a same size, shape, alignment, and jetting frequency.

A machining program generation support device includes: a CAD data analysis unit which analyzes the CAD data so as to obtain CAD shape information; a machining program analysis unit which. analyzes the machining program in the middle of being produced so as to obtain machining shape information in the middle of being produced; a shape matching unit which performs matching of shapes of the CAD shape information and the machining shape information in the middle of being produced so as to obtain. matching shape information; and a candidate shape program generation unit that predicts, based on the CAD shape information, a candidate shape following the matching shape information, and that thereby predicts a candidate shape following the machining shape information in the middle of being produced so as to automatically generate a machining program for the candidate shape following the machining program in the middle of being produced.

A machine learning apparatus includes a first information acquiring unit that acquires first information including at least one of a shape of a workpiece, a material of the workpiece, a cutting path of a cutting process, a type of a tool, and an amount of wear of the tool; a second information acquiring unit that acquires second information correlated with an evaluation of a burr occurring on the workpiece due to the cutting process; and a learning unit that executes learning processing using a plurality of pieces of the first information and a plurality of pieces of the second information, and generates a learning model that outputs a cutting condition, according to another piece of first information that is different from the plurality of pieces of first information.

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.

A machine tool for performing a cutting process on a workpiece with a cutting tool, includes: a pre-machining shape acquisition unit configured to acquire the shape of the workpiece before cutting, as a pre-machining shape; a target shape acquisition unit configured to acquire a target shape of the workpiece after cutting; a differential shape acquisition unit configured to acquire a differential shape between the pre-machining shape and the target shape; and a machining path setting unit configured to set machining paths so as to perform the cutting process on the differential shape only.

A machine tool controller according to an aspect of the present disclosure controls a machine tool having a plurality of drive axes, the machine tool controller including: an input processing unit which displays an input screen including a schematic projection drawing of a driven body that is driven by the plurality of drive axes and an input box that allows for a positional relationship of the driven body in the schematic projection drawing to be inputted, and stores a numerical value inputted to the input box; a drawing information management unit which stores decoding information indicating a relationship between the numerical value inputted to the input box and a position or drive amount of the drive axis; and a parameter processing unit which converts the numerical value inputted to the input box into a drive parameter of the plurality of drive axes, based on the decoding information.

A system and a method is provided in which a CAD system receives a solid model and receives user input to select points on the surface of the solid model, to create a wire part program file based on the selected points, and to transmit the wire part program file to a bending machine. The wire part program files is configured such that the bending machine will manufacture a wire based on the wire part program file.

Methods aim to reduce and/or eliminate the need for shims in manufacturing assemblies, such as in manufacturing of aircraft wings. Exemplary methods include predicting a set of predicted manufacturing dimensions within a range of predetermined allowances for a first part, manufacturing the first part, scanning the first part to determine a set of actual manufacturing dimensions for the first part, and at least beginning manufacturing a second part before the scanning the first part is completed. The second part may be manufactured based on the set of predicted manufacturing dimensions for the first part. Once the scan of the first part is completed, the set of predicted manufacturing dimensions may be compared to a set of actual manufacturing dimensions to check for any non-compliant deviances between the predicted and actual manufacturing dimensions. Repairs and local re-scans may be performed in the areas of the non-compliant deviances, which may streamline manufacturing.

Methods aim to reduce and/or eliminate the need for shims in manufacturing assemblies, such as in manufacturing of aircraft wings. Exemplary methods include predicting a set of predicted manufacturing dimensions within a range of predetermined allowances for a first part, manufacturing the first part, scanning the first part to determine a set of actual manufacturing dimensions for the first part, and at least beginning manufacturing a second part before the scanning the first part is completed. The second part may be manufactured based on the set of predicted manufacturing dimensions for the first part. Once the scan of the first part is completed, the set of predicted manufacturing dimensions may be compared to a set of actual manufacturing dimensions to check for any non-compliant deviances between the predicted and actual manufacturing dimensions. Repairs and local re-scans may be performed in the areas of the non-compliant deviances, which may streamline manufacturing.

A sewn product making apparatus such as a sewing robot can be used to produce a variety of products over a broad range of sizes, shapes or materials. Various examples are provided related to the automation of sewing robots, and the making of sewn products. In one example, among others, a system can generate a product making path using a product construction file, and instruct a sewing device and fabric mover(s) to automatically sew the product based upon the product making path. The product making path can be modified when a deviation is detected, and the sewing adjusted based upon the modified product making path. The product construction file can be generated using information from a computer aided design associated with the product.