Methods and systems for detection of an endpoint of a substrate process are provided. A set of machine learning models are trained to provide a metrology measurement value associated with a particular type of metrology measurement for a substrate based on spectral data collected for the substrate. A respective machine learning model is selected to be applied to future spectral data collected during a future substrate process for a future substrate in view of a performance rating associated with the particular type of metrology measurement. Current spectral data is collected during a current process for a current substrate and provided as input to the respective machine learning model. An indication of a respective metrology measurement value corresponding to the current substrate is extracted from one or more outputs of the trained machine learning model. In response to a determination that the respective metrology measurement satisfies a metrology measurement criterion, an instruction including a command to terminate the current process is generated.

A management apparatus manages works to supply components to component mounting devices in a component mounting line. The management apparatus includes a component remaining number information acquisition portion that acquires, from each of the component mounting devices, a remaining number of components stored in the component mounting device, a worker information storage portion that stores worker information including a working range of each of workers in the component mounting line, a work sequence decision portion that generates work sequence information indicating a work sequence of component supply works for each of the workers based on the worker information and component remaining number information about a plurality of components within a predetermined period of time, and an information transmission portion that transmits the work sequence information to the workers who should perform the works.

A feedback control device that takes information regarding a control deviation between a measured value and a desired value of a controlled object as input, and outputs a manipulated variable for the controlled object, includes: a first control unit that takes information regarding the control deviation as input, and outputs a manipulated variable for the controlled object; a second control unit that takes information regarding the control deviation as input, and that includes a learning control unit in which a parameter for outputting a manipulated variable for the controlled object is determined by machine learning; and an adder that adds a first manipulated variable output from the first control unit and a second manipulated variable output from the second control unit. A manipulated variable from the adder is output to the controlled object, and the second control unit includes a limiter that limits the second manipulated variable.

According to one embodiment, a processing information management system includes: an abnormality analyzer configured to generate abnormality occurrence data of a target wafer based on processing location information, the processing location information collected based on a first sensor outputting a first sensor signal according to a detected processing state, the first sensor provided in a wafer processing apparatus; and an integration system configured to integrate the abnormality occurrence data into wafer map data corresponding to the target wafer.

Provided is a prediction apparatus including: a data acquisition unit configured to acquire setting value data indicating a setting value of a controlled object and physical quantity data indicating a physical quantity of a product obtained by controlling the controlled object; a prediction unit configured to calculate, using the setting value data and the physical quantity data, a plurality of prediction values obtained by predicting a plurality of physical quantities in the product on a basis of a setting value used for control of the controlled object; an evaluation unit configured to evaluate the plurality of prediction values on a basis of a predefined reference; and an output unit configured to output a setting value recommended according to a result of the evaluation.

The present disclosure relates to a machine control method, a machine control system, a computer-readable storage medium, and an electronic device. The machine control method includes: matching, based on input information of a machine, a plurality of corresponding sites that the machine needs to pass through and expected pass-through time of the machine in each of the plurality of corresponding sites; determining, based on actual time at which the machine arrives at a current site and the expected pass-through time of the machine in each of the plurality of corresponding sites, expected time at which the machine arrives at a subsequent site; and sending the expected time at which the machine arrives at the subsequent site.

The inventive concept provides a substrate treating apparatus. The substrate treating apparatus includes a plurality of treating chambers performing a respective treatment on a substrate therein; a transfer chamber having a robot transferring the substrate between the plurality of treating chambers; a detection unit mounted on the robot and configured to detect a substrate state; and a controller for controlling the detection unit, wherein the detection unit comprises: an imaging member for imaging the substrate; and a driving member for moving the imaging member, and wherein the controller controls the detection unit to image and store an image of the substrate at an optimal position and determines whether an image of the substrate is a normal state based on the image obtained in the optimal position, the optimal position determined based on a process variable of the treating chamber.

Wafers that begin as flat surfaces during a semiconductor manufacturing process may become warped or bowed as layers and features are added to an underlying substrate. This warpage may be detected between manufacturing processes by rotating the wafer adjacent to a displacement sensor. The displacement sensor may generate displacement data relative to a baseline measurement to identify areas of the wafer that bow up or down. The displacement data may then be mapped to locations on the wafer relative to an alignment feature. This mapping may then be used to adjust parameters in subsequent semiconductor processes, including adjusting how a carrier head on a polishing process holds or applies pressure to the wafer as it is polished. A model may be trained to provide control signals for a polishing/cleaning process, or to generate metrology data.

A method for manufacturing a semiconductor device, includes receiving a first layout including patterns for the manufacturing of the semiconductor device, generating a second layout by performing machine learning-based process proximity correction (PPC) based on features of the patterns of the first layout, generating a third layout by performing optical proximity correction (OPC) on the second layout, and performing a multiple patterning process based on the third layout. The multiple patterning process includes patterning first-type patterns, and patterning second-type patterns. The machine learning-based process proximity correction is performed based on features of the first-type patterns and features of the second-type patterns.

A method for correcting a robot is provided. The method includes: providing a correction device, wherein the correction device comprises a jig wafer; grabbing and/or transferring the jig wafer by using the robot to obtain collected data; determining, based on the collected data, whether the robot needs to be corrected; and in response to that the robot needs to be corrected, obtaining a compensation value according to the collected data, and correcting the robot based on the compensation value.