A method includes processing a substrate in a process chamber according to a recipe, wherein the substrate comprises at least one of a film or a feature after the processing. The method further includes generating a profile map of the first substrate. The method further includes processing data from the profile map using a first model, wherein the first model outputs at least one of an estimated mesa condition of a substrate support for the process chamber, an estimated lift pin location condition of the substrate support an estimated seal band condition of the substrate support, or an estimated process kit ring condition for a process kit ring for the process chamber. The method further includes outputting a notice as a result of the processing.

A substrate processing system includes a process chamber, one or more robot, a substrate measurement system, and a computing device. The process chamber may process a substrate that will comprise a film and/or feature after the processing. The one or more robot, to move the substrate from the process chamber to a substrate measurement system. The substrate measurement system may measure the film and/or feature on the substrate and generate a profile map of the film and/or feature. The computing device may process data from the profile map using a first trained machine learning model, wherein the first trained machine learning model outputs a first chamber component condition estimation for a first chamber component of the process chamber. The computing device may then determine whether to perform maintenance on the first chamber component of the process chamber based at least in part on the first chamber component condition estimation.

A substrate processing system includes: an acquiring unit configured to acquire process data of each step when each step included in a predetermined process is executed under different control conditions; an extracting unit configured to divide each step into a first section in which the process data fluctuates and a second section in which the process data is converged, and extract first data belonging to the first section and second data belonging to the second section from the process data; and a monitoring unit configured to monitor the process data by comparing one or both of an evaluation value that evaluates the first data and an evaluation value that evaluates the second data with corresponding upper and lower limit values.

A gas delivery apparatus is provided, comprising a system controller configured to collect valve position information and sensor information from at least a plurality of the sensors and valves, store the valve position information and sensor information into the monitored gas delivery process data, and execute the discriminative classifier including a first artificial intelligence (AI) model configured to extract features in a first input image of the monitored gas delivery process; a second AI model configured to extract features in a second input image of a golden gas delivery process; and a contrastive loss function configured to calculate a similarity between the first input image and the second input image based on outputs of the first AI model and the second AI model, and output a repeatability confidence value based on a similarity index between the first input image and the second input image.

A method of generating a simulation model based on simulation data and measurement data of a target includes classifying weight parameters, included in a pre-learning model learned based on the simulation data, as a first weight group and a second weight group based on a degree of significance, retraining the first weight group of the pre-learning model based on the simulation data, and training the second weight group of a transfer learning model based on the measurement data, wherein the transfer learning model includes the first weight group of the pre-learning model retrained based on the simulation data.

The program code, when executed by a processor, causes the processor to input fabrication data including a plurality of parameters associated with a semiconductor fabricating process to a framework to generate a first class for analyzing the fabrication data, to extract a first parameter targeted for analysis and a second parameter associated with the first parameter from the plurality of parameters and generate a second class for analyzing the first parameter as a sub class of the first class, to modify the first parameter and the second parameter into a data structure having a format appropriate to store in the second class, so as to be stored in the second class, to perform data analysis on the first parameter and the second parameter, to transform the first parameter and the second parameter into corresponding tensor data, and to input the tensor data to the machine learning model.

The present disclosure provides a semiconductor manufacturing process control method and apparatus, a device, and a storage medium. The method includes: analyzing wafer lot information and determining a current product lot of a current product; obtaining historical measurement data within a specified period; when determining that the historical measurement data does not include first measurement data of the current product lot, if determining, based on preset configuration information, that the historical measurement data includes second measurement data of a target product lot, determining a target regulatory data based on the preset configuration information and the second measurement data; and controlling a production parameter of the current product based on the target regulatory data.

In one embodiment, a system includes a wafer handling system, processing components, a controller, a virtual assistant, a natural language processing (NLP) engine, and a data-analytics engine. The wafer handling system is configured to hold one or more wafers for processing. The processing components is configured to physically treat the one or more wafers. The controller is configured to operate the processing components. The virtual assistant, in communication with the NLP engine, is configured to receive a user query from a user, understand an intent or context of the user query, and provide a context-specific response to the user query. The data-analytics engine is configured to generate and provide analytical data relating to the user query based on data collected from a plurality of data sources via one or more communication protocols.

A semiconductor machine system comprises a plurality of working chambers, wherein the working chambers process materials separately; a control host coupled to the plurality of working chambers, comprising: a main control module coupled to the plurality of working chambers; an analog control module coupled to the plurality of working chambers, and the analog control module is detachably coupled to one or more external devices by serial interface coupling; a digital control module coupled to the plurality of working chambers, and the main control module, the analog control module and the digital control module are coupled to each other; and a plurality of operating units coupled to at least one of the main control module, the analog control module and the digital control module, respectively, to control the plurality of working chambers for processing the materials by the main control module, the analog control module and the digital control module.

The current disclosure describes techniques for managing vertical alignment or overlay in semiconductor manufacturing using machine learning. Alignments of interconnection features in a fan-out WLP process are evaluated and managed through the disclosed techniques. Big data and neural networks system are used to correlate the overlay error source factors with overlay metrology categories. The overlay error source factors include tool related overlay source factors, wafer or die related overlay source factors and processing context related overlay error source factors.