A dynamic routing method and apparatus for an Overhead Hoist Transport (OHT) system are disclosed. The present disclosure in some embodiments provides a dynamic routing method for an OHT system, including generating a Q table of records of at least one Q value which is a time for a vehicle to move through an edge between two adjacent nodes to a node other than the two adjacent nodes, measuring a transit time of the vehicle when assigned a destination node and passing a transit edge between a current node and next node, extracting target edges to be updated according to the transit time from a plurality of edges, and differentially updating Q values for the target edges according to distances to the transit edge partially based on the transit time, the Q values for the target edges being time values for the vehicle to move through the target edges to the destination node.

A wafer manufacturing system includes a wafer manufacturing device provided with a sensor; a host PC that is connected to the wafer manufacturing device via a data communication line; a logic controller that samples and stores an analog output signal of the sensor; and a relay PC that extracts tracking information transmitted on the data communication line for a wafer or a single crystal that is being processed by the wafer manufacturing device and sends the tracking information to the logic controller, and the logic controller stores a digital value of the analog output signal of the sensor in association with the tracking information that is sent from the relay PC.

A model learning unit learns a prediction model on the basis of learning data, a target setting unit sets a target output parameter value by interpolating between a goal output parameter value and an output parameter value which is the closest to the goal output parameter value in output parameter values in the learning data, a processing condition search unit estimates input parameter values which corresponds to the goal output parameter value and the target output parameter value, a model learning unit updates the prediction model by using a set of the estimated input parameter value and an output parameter value which is a result of processing that a processing device performs as additional learning data.

There is provided a learning method. The method includes performing preprocessing on light emission data in a chamber of a plasma processing apparatus, setting a constraint for generating a regression equation representing a relationship between an etching rate of the plasma processing apparatus and the light emission data, selecting a learning target wavelength from the light emission data subjected to the preprocessing, and receiving selection of other sensor data different from the light emission data. The method further includes generating a regression equation based on the set constraint while using, as learning data, the selected wavelength, the received other sensor data, and the etching rate, and outputting the generated regression equation.

The present disclosure provides a flow control equipment and an automatic refilling system. The flow control equipment includes: a housing, including a discharge hole in a bottom of the housing; a liquid inlet tube connecting with a top of the housing; a motor located in the housing; a flow locking blade and a plurality of flow control blades connected to the motor, where leakage holes of different sizes are formed in the flow control blades, and the motor drives the flow control blades and the flow locking blade to rotate to align the different leakage holes with the discharge hole, or to seal the discharge hole; and a liquid outlet tube connecting with the discharge hole.

A method includes receiving, from sensors, sensor data associated with processing a substrate via a processing chamber of substrate processing equipment. The sensor data includes a first subset received from one or more first sensors and a second subset received from one or more second sensors, the first subset being mapped to the second subset. The method further includes identifying model input data and model output data. The model output data is output from a physics-based model based on model input data. The method further includes training a machine learning model with data input including the first subset and the model input data, and target output data including the second subset and the model output data to tune calibration parameters of the machine learning model. The calibration parameters are to be used by the physics-based model to perform corrective actions associated with the processing chamber.

A detection method includes: determining process data of a new process; according to the process data of the new process, detecting, by a first production system, whether a wafer carrier type of the new process matches an acceptable level of a corresponding process step or not and whether the new process matches a flag of the corresponding process step or not; if not, determining that the process data does not pass the detection and outputting first detection information; or if the wafer carrier type of the new process matches the acceptable level of the corresponding process step and the new process matches the flag of the corresponding process step, detecting, by a second production system, if the second production system detects a mismatch, determining that the process data does not pass the detection and outputting second detection information.

An operating method of a vacuum processing apparatus for processing multiple wafers sequentially in a vacuum processing apparatus comprising multiple vacuum transfer containers, adjacent two of which are interlinked, a lock chamber inside which a wafer is housed. The multiple processing units are each subjected to of cleaning the interior thereof upon elapse of a predetermined period. In advance of processing multiple wafers, the operating method configures multiple sets of processing units to process each of the wafers from among the multiple processing units and starts processing of the wafers, delayed by a predetermined time in descending order of the number of processing units included in each of the multiple sets of processing units and in descending order of distance of the processing units included from the lock chamber.

An advanced process control system including a first process tool, a second process tool, and a measurement tool is provided. The first processing tool is configured to process each of a plurality of wafers by one of a plurality of first masks, and provide a first process timing data. The second processing tool is configured to process the wafer processing by the first process tool by one of a plurality of second masks to provide a plurality of works. The second process tool provides a measurement trigger signal according to the first process timing data. The measuring tool is configured to determine whether to perform a measuring operation on each works in response to the measurement trigger signal, and correspondingly provide a measurement result.

A substrate processing apparatus includes a process station for processing a substrate; a cassette station integrated with the process station; a substrate carriage equipped for transferring the substrate between said process station and the cassette station through a passage located at an interface between the process station and said cassette station; and a substrate scanner equipped at said interface between the process station and the cassette station for capturing surface image data during transportation of the substrate that passes through the passage.