Techniques for inspection of articles having multiple features of one or more types are disclosed. Input data indicative of one or more selected features of interest is used for inspection by a given inspection system characterized by associated imaging configuration data. The input data is analyzed to extract information regarding one or more inspection tasks, and an inspection plan data is generated, to be used as a recipe data for operation of the given inspection system to provide measured data in accordance with the one or more inspection tasks. Selected inspection mode data corresponding to the inspection task data may be retrieved from a database system and utilized to generate the inspection plan data.

The present disclosure relates to the automatic generation of characterized image data. For this purpose, a visual representation of a component is computed on the basis of existent structure data for the component, wherein the surface properties of the visual representation of the component may be varied based on predefined characteristic properties. Because, in the computation of such visual representations, both the component itself and the underlying characteristic surface properties are known, this information may be used for characterizing the corresponding parts in the visual representation in order to achieve automatic characterization of the computed visual representation.

A shape evaluation method according to the present invention comprises: a shape error calculation step that calculates a shape error, which is an error between a designed shape and a shape to be evaluated; and a visible error detection step that detects visible shape errors on the basis of the shape error and predetermined visual characteristic data.

Various embodiments enable batch inspection of a plurality of workpieces by and inspection instrument such as a coordinate measuring machine. Some embodiments present user interfaces, including graphical user interfaces, to enable an operator to configure a batch inspection system and a batch inspection job, and to monitor and control execution of a batch inspection job.

A method for quality control in industrial manufacturing for one or more production processes for producing at least one workpiece and/or product includes creating a learning model for at least one production process for the at least one workpiece and/or product. The learning model is trained and initialized using a meta-learning algorithm, and the learning model is calibrated using normalized data of the at least one production process for the at least one workpiece and/or product. Currently generated data of the at least one production process for at least one currently produced workpiece/product is forwarded to the learning model. The data is generated by sensors. The learning model compares the currently generated data with the normalized data and finds deviations. The learning model scales the deviations between the currently generated data and the normalized data, and the learning model communicates presence of an anomaly for the currently produced workpiece/product.

Various embodiments enable batch inspection of a plurality of workpieces by and inspection instrument such as a coordinate measuring machine. Some embodiments present user interfaces, including graphical user interfaces, to enable an operator to configure a batch inspection system and a batch inspection job, and to monitor and control execution of a batch inspection job.

Assembly-level properties defined by a manufactured product’s assembly tree analyzed as trigger predicates to assist identification (i.e., selection and/or preparation) of inspection requirements for the manufactured product. Particular emphasis is placed on hierarchical relationships-assembly identification, effects of manufacturing on the visibility/accessibility of an assembly to inspection, and using assembly-level semantics to trigger inspection requirements. The identified inspection requirements are optionally open (semantic) or closed. In some embodiments, identified inspection requirements are provided to an automatic inspection planning system configured to generate an inspection plan, the actions of which said plan fulfill the inspection requirements.

The present disclosure provides systems and methods for controlling a semiconductor manufacturing equipment. The control system includes an inspection unit capturing a set of images of the semiconductor manufacturing equipment, a sensor interface receiving the set of images and generating at least one input signal for a database server, and a control unit. The control unit includes a front end subsystem, a calculation subsystem, and a message and feedback subsystem. The calculation subsystem receives the data signal from the front end subsystem, wherein the calculation subsystem performs an artificial intelligence analytical process to determine, according to the data signal, whether a malfunction has occurred in the semiconductor manufacturing equipment and to generate an output signal. The message and feedback subsystem generates an alert signal and a feedback signal according to the output signal, and the alert signal is transmitted to a user of the semiconductor manufacturing equipment.

Provided is a computer-implemented method for determining at least one quality attribute for at least one defect of interest, including the steps: a. providing an input data set including the at least one defect of interest; b. determining the at least one quality attribute for the at least one defect of interest using a classification algorithm based on the input data set; and c. providing the determined at least one quality attribute and/or additional output information as output. Further, a computing unit and a computer program product are provided.

An initial inspection or critical dimension measurement can be made at various sites on a wafer. The location, design clips, process tool parameters, or other parameters can be used to train a deep learning model. The deep learning model can be validated and these results can be used to retrain the deep learning model. This process can be repeated until the predictions meet a detection accuracy threshold. The deep learning model can be used to predict new probable defect location or critical dimension failure sites.