Methods and systems for controlling a semiconductor fabrication process
AssigneeBrooks Automation, Inc.
InventorsPatrick D. Pannese, Vinaya Kavathekar, Peter van der Meulen
Life of this patent
Estimating the term…
Abstract
Software for controlling processes in a heterogeneous semiconductor manufacturing environment may include a wafer-centric database, a real-time scheduler using a neural network, and a graphical user interface displaying simulated operation of the system. These features may be employed alone or in combination to offer improved usability and computational efficiency for real time control and monitoring of a semiconductor manufacturing process. More generally, these techniques may be usefully employed in a variety of real time control systems, particularly systems requiring complex scheduling decisions or heterogeneous systems constructed of hardware from numerous independent vendors.
Claims19
A system comprising:
- a state machine that controls operation of a semiconductor manufacturing system to schedule processing of one or more workpieces, the state machine including a plurality of states associated by a plurality of transitions, each one of the plurality of transitions having a weight assigned thereto, wherein when the state machine is operating within one of the plurality of states, a selection of a transition from the one of the plurality of states to another one of the plurality of states is determined by evaluating the weight assigned to each one of a number of possible transitions from the one of the plurality of states;
- and
- a plurality of sensors for sensing aspects of the semiconductor manufacturing system;
- a neural network that receives as inputs data from the plurality of sensors and provides as outputs the weights for one or more of the plurality of transitions;
- a graphical user interface that displays a three-dimensional model of the semiconductor manufacturing system, wherein the three-dimensional model includes one or more objects that are correlated to an inventory containing data about a physical inventory of system components, the graphical user interface being configured to graphically present the one or more of the plurality of transitions in the three-dimensional model based on the weights from the neural network output in response to the data from the plurality of sensors.
A method comprising:
- controlling operation of a semiconductor manufacturing system with a state machine to schedule processing of one or more workpieces, the state machine including a plurality of states associated by a plurality of transitions, each one of the plurality of transitions having a weight assigned thereto, wherein when the state machine is operating within one of the plurality of states, a selection of a transition from the one of the plurality of states to another one of the plurality of states is determined by evaluating the weight assigned to each one of a number of possible transitions from the one of the plurality of states;
- and
- sensing aspects of the semiconductor manufacturing system;
- calculating, with a neural network, the weight assigned to each one of a number of possible transitions from a current state of the plurality of states by applying data representing the sensed aspects as inputs to the neural network;
- selecting a transition from the current state of the plurality of states by evaluating the weight assigned to each one of the number of possible transitions from the current state;
- and
- displaying a three-dimensional model on a graphical user interface of the semiconductor manufacturing system, wherein the three-dimensional model includes one or more objects that are correlated to an inventory containing data about a physical inventory of system components, the three-dimensional model being configured to graphically present one or more of the plurality of transitions on the display based on the weights calculated by the neural network in response to applying the data representing the sensed aspects.
Dependencies are inferred from the claim text.