For etching tools, a neural network model is trained to predict optimum scheduling parameter values. The model is trained using data collected from preventive maintenance operations, recipe times, and wafer-less auto clean times as inputs. The model is used to capture underlying relationships between scheduling parameter values and various wafer processing scenarios to make predictions. Additionally, in tools used for multiple parallel material deposition processes, a nested neural network based model is trained using machine learning. The model is initially designed and trained offline using simulated data and then trained online using real tool data for predicting wafer routing path and scheduling. The model improves accuracy of scheduler pacing and achieves highest tool/fleet utilization, shortest wait times, and fastest throughput.

The feedback control device takes information regarding a control deviation between a measured value and a target value of a controlled object as input, and outputs a control amount for the controlled object; comprising: a first control unit that takes information regarding the control deviation as input, and outputs a first control amount for the controlled object; a second control unit that takes information regarding the control deviation as input and outputs a second control amount for the controlled object, and in which a parameter for calculating the second control amount is determined by machine learning; an operation unit that operates the controlled object using the first control amount output from the first control unit and the second control amount output from the second control unit; and a sampling unit for thinning out at a predetermined period information regarding the control deviation input to the second control unit.

The feedback control device takes information regarding a control deviation between a measured value and a target value of a controlled object as input, and outputs a control amount for the controlled object; comprising:

a first control unit that takes information regarding the control deviation as input, and outputs a first control amount for the controlled object; a second control unit that takes information regarding the control deviation as input and outputs a second control amount for the controlled object, and in which a parameter for calculating the second control amount is determined by machine learning;

an operation unit that operates the controlled object using the first control amount output from the first control unit and the second control amount output from the second control unit; and a sampling unit for thinning out at a predetermined period information regarding the control deviation input to the second control unit.

Disclosed herein are methods and systems for semiconductor fabrication. In one embodiment, a method for fabricating semiconductors utilizing a semiconductor fabrication system includes performing a semiconductor fabrication process on a first lot of unprocessed semiconductor substrates with a semiconductor fabrication equipment unit to form a first lot of processed substrates and communicating processing data regarding the first lot of processed substrates from the semiconductor fabrication equipment unit to a just-in-time (JIT) module of the semiconductor fabrication system. The method further includes determining a processing priority of the first lot of processed substrates and a processing priority of a second lot of unprocessed substrates at the JIT module and scheduling removal of the first lot of processed substrates from the semiconductor fabrication equipment unit and delivery of the second lot of unprocessed substrates to the semiconductor fabrication equipment unit by the JIT module based on the processing data and the priority of one or both of the first lot of processed substrates and the second lot of unprocessed substrates.