A method includes identifying at least one of historical data associated with historical substrate lots processed by substrate processing tools in a substrate processing facility or simulated data for simulated substrate lots processed by simulated substrate processing tools. The method further includes generating features from the at least one of the historical data for the historical substrate lots or the simulated data for the simulated substrate lots. The method further includes training a machine learning model with data input comprising the features to generate a trained machine learning model. The trained machine learning model is capable of generating one or more outputs indicative of one or more corrective actions to be performed in the substrate processing facility.

The object is to provide a vehicle system capable of suppressing a decrease in article transport efficiency while ensuring a route of an operator. The vehicle system includes a grid-patterned rail, a vehicle traveling on the rail, a controller that controls the vehicle, a work terminal that transmits identification information indicating an actual location to the controller, and a scaffold for allowing an operator carrying the work terminal to walk below the rail, the scaffold being provided below the rail. If entry permission to one or more cells formed by the rail is obtained from the controller, the vehicle enters the one or more cells. If entry permission to the one or more cells is not obtained from the controller, the vehicle does not enter the one or more cells. The controller performs blocking so as not to grant the vehicle the entry permission at least to a cell corresponding to the actual location indicated by the identification information transmitted from the work terminal, among a plurality of cells corresponding to a route of the operator from the entrance to the scaffold to the destination.

At least one laser sensor and a controller are embedded into a substrate processing system communicating with a remote big data and machine learning server receiving/sending data from/to a fleet of substrate processing systems for autonomous process control and optimization. The laser sensor is arranged proximate to a region of the substrate processing system and is configured to capture first data from at least one of an edge coupling ring and a semiconductor substrate transported from/to the processing chamber to/from the region. The controller is configured to receive the first data from the laser sensor, process the first data to generate second data, transmit the second data to a remote server via a network, receive third data from the remote server via the network in response to sending the second data to the remote server, and operate the substrate processing system based on the third data for process optimization.

A mobile stocker described herein is configured to be easily installed and relocated to various locations in a semiconductor fabrication facility. The mobile stocker is capable of being programmed with, and/or autonomously learning, the layout of a semiconductor fabrication facility, and automatically relocating to a new location based on the layout using a navigation system. Accordingly, the mobile stocker is capable of being flexibly relocated in the semiconductor fabrication facility to dynamically support changes in demand and production capacity. Moreover, the capability to quickly assign a location identifier to the mobile stocker and to automatically interface with transport systems in the semiconductor fabrication facility reduces downtime of the mobile stocker, which increases productivity in the semiconductor fabrication facility.

A reference cost and a variable cost are included in a link cost for setting a set route for causing a setting vehicle to travel to a destination on a travelable route. A controller obtains an adjusted variable cost by adjusting a variable cost using a priority adjustment value set higher as a priority for arriving more quickly at a destination decreases, determines a link cost for each link in a candidate route, which is a candidate for a set route for a setting vehicle, based on the adjusted variable cost and the reference cost, obtains a route cost for each candidate route based on the link costs, and sets the set route based on the route costs of the candidate routes.

Article transport vehicles have, as operation states, a first state of traveling toward a transport destination that is a destination set for receiving an article or delivering an article, and a second state in which a transport destination has not been set. A controller divides the entirety of a travelable route into a plurality of set areas and executes imbalance reduction control to arrange standby transport vehicles such that imbalance of the densities of standby transport vehicles present in the areas is within a predetermined range, the standby transport vehicles being article transport vehicles in the second state.

A method and apparatus for controlling wafer preparation are provided. The method includes that: in response to first work-in-process preparation dispatching instruction, the number of first available devices corresponding to preparation process of first work-in-process at a current site is acquired from wafer preparation information base and based on real-time dispatching system for wafer preparation, and a maximum loading capacity of first available devices is acquired, wafer preparation information base including the number of available devices and the maximum loading capacity of available devices corresponding to preparation process of multiple work-in-process at the current site; when the number of first available devices is greater than or equal to preset number of available devices, and the maximum loading capacity of first available devices is greater than or equal to preset maximum loading capacity, a preparation instruction of first work-in-process is issued based on real-time dispatching system.

The disclosure relates to a dimension measurement apparatus that reduces time required for dimension measurement and eliminates errors caused by an operator. Therefore, the dimension measurement apparatus uses a first image recognition model that extracts a boundary line between a processed structure and a background over the entire cross-sectional image and/or a boundary line of an interface between different kinds of materials, and a second image recognition that output information for dividing the boundary line extending over the entire cross-sectional image obtained from the first image recognition model for each unit pattern constituting a repetitive pattern, obtains coordinates of a plurality of feature points defined in advance for each unit pattern, and measures a dimension defined as a distance between two predetermined points of the plurality of feature points.

A method for process control in the manufacture of semiconductor devices including performing metrology on at least one Design of Experiment (DOE) semiconductor wafer included in a lot of semiconductor wafers, the lot forming part of a batch of semiconductor wafer lots, generating, based on the metrology, one or more correctables to a process used to manufacture the lot of semiconductor wafers and adjusting, based on the correctables, the process performed on at least one of; other semiconductor wafers included in the lot of semi-conductor wafers, and other lots of semiconductor wafers included in the batch.

Embodiments disclosed herein include a method for auto-tuning a system. In an embodiment, the method comprises determining if the system is in a steady state. Thereafter, the method includes exciting the system. In an embodiment, the method comprises storing process feedback measurements from the excited system to provide a set of stored data. In an embodiment, the set of stored data is a subset of all available data generated by the excited system. In an embodiment, the method further comprises determining when the excited system returns to the steady state, and tuning the system using the set of stored data.