A technique to generate predicted data for control or monitoring of a production process to improve a parameter of interest. Context data associated with operation of the production process is obtained. Metrology/testing is performed on the product of the production process, thereby obtaining performance data. A context-to-performance model is provided to generate predicted performance data based on labeling of the context data with performance data. This is an instance of semi-supervised learning. The context-to-performance model may include the learner that performs semi-supervised labeling. The context-to-performance model is modified using prediction information related to quality of the context data and/or performance data. Prediction information may include relevance information relating to relevance of the obtained context data and/or obtained performance data to the parameter of interest. The prediction information may include model uncertainty information relating to uncertainty of the predicted performance data.

A system for determining a processing procedure including a plurality of processes for controlling an object, the system includes a learning unit for performing a learning process for determining a processing condition of each of a plurality of processes, and the learning unit acquires a physical quantity correlating with a state of the object on which a process has been performed under a predetermined processing condition, from a device for controlling the object on the basis of the processing procedure, calculates a pseudo state corresponding to the state of the object on the basis of the physical quantity, performs a learning process using a value function, and determines a processing condition of each of the plurality of processes to achieve a target state of the object.

A system for monitoring a process step during manufacturing of an assembly sheet includes a detection camera configured to capture a first image of the assembly sheet, the first image including a locating feature of the assembly sheet, a vacuum hold-down device for selectively inhibiting advancement of the assembly sheet along a process step line for a predetermined measurement time, and a measurement camera configured to capture a second image of the assembly sheet responsive to the vacuum hold-down device inhibiting advancement of the assembly sheet, the second image including one or more features of a coupon of the assembly sheet.

In an example, a method includes operating, by a processor, on object model data and operating, on a processor, on pattern data. The object model data describes at least part of an object to be generated in additive manufacturing and the pattern data describes an object pattern intended to be formed on at least a portion of the part of the object to be generated in additive manufacturing. The method includes determining, by a processor, control data to control a print agent applicator to apply a pattern of fusing agent onto a part of a layer of build material. The pattern of fusing agent comprises a fusing agent area and a gap area that lacks fusing agent. The gap area corresponds to the object pattern such that no fusing agent is applied to a part of the layer of build material that corresponds to the object pattern.

A real time software and array control software application platform which maintains the ability to manage the synchronization between substrate alignments and image projection systems during maskless lithography patterning in a manufacturing process is disclosed. The application coordinates and controls the image projection systems such that discrepancies in and misalignments of the substrate may be determined and accounted for in real time. The image projection systems may run in parallel and may be controlled by a central processor.

A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

A system and method of shaping a film with a template on a substrate. Generating a first series of parameters from tests performed on a first series of films formed with: a set of shaping conditions; a calibration measurement parameter determined for each substrate prior to shaping; and a first scaling parameter. Generating a second series of parameters from the tests performed on a second series of films produced formed with the set of shaping conditions. The second series of films produced with the calibration measurement parameter determined for each substrate; and a second scaling parameter; or without the calibration measurement parameter. Generating a scaling parameter from: the first series of the parameters; and the second series of parameters. Generating the calibration measurement parameter prior to forming the film. Forming the film using the set of shaping conditions, the calibration measurement parameter, and the scaling parameter.

A method of determining topographical variation across a substrate on which one or more patterns have been applied. The method includes obtaining measured topography data representing a topographical variation across a substrate on which one or more patterns have been applied by a lithographic process; and combining the measured topography data with knowledge relating to intra-die topology to obtain derived topography data having a resolution greater than the resolution of the measured topography data. Also disclosed is a corresponding level sensor apparatus and lithographic apparatus having such a level sensor apparatus, and a more general method of determining variation of a physical parameter from first measurement data of variation of the physical parameter across the substrate and intra-die measurement data of higher resolution than the first measurement data and combining these.

A real time software and array control software application platform which maintains the ability to manage the synchronization between substrate alignments and image projection systems during maskless lithography patterning in a manufacturing process is disclosed. The application coordinates and controls the image projection systems such that discrepancies in and misalignments of the substrate may be determined and accounted for in real time. The image projection systems may run in parallel and may be controlled by a central processor.

A test artifact for additive manufacturing is provided. The artifact comprises an additively manufactured singular continuous body between 100 cc and 6 cc in bounding box volume and between 50 cc and 3 cc in solid body. The body comprises at least three fiducials positioned for identification of locations in cross-section after sectioning of the artifact and at least three geometries that are unique from each other when exposed in cross section.