Methods and systems for controlling a semiconductor fabrication process
View Patent ↗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.
1. A computer program product comprising computer executable code embodied on a non-transitory computer readable medium that, when executing on one or more computing devices, performs the steps of:
creating a data structure for a workpiece in a memory of the one or more computing devices, the data structure including an identity of the workpiece and one or more fields for storing workpiece processing data;
receiving the workpiece processing data from a semiconductor manufacturing system that includes a plurality of interconnected process modules that provide workpiece processing data for storage in the data structure while the workpiece is processed by the semiconductor manufacturing system and updating the data structure to provide substantially real time workpiece processing data in the data structure, wherein the workpiece processing is controlled by a neural network and a finite state machine scheduler; and
storing the received workpiece processing data in one of the one or more fields of the data structure where the neural network and the finite state machine scheduler adjust throughput of the semiconductor manufacturing system where the neural network is responsive to inputs that include the workpiece processing data and is configured to generate outputs so that, in combination with the finite state machine scheduler, throughput of the semiconductor manufacturing system is adjusted substantially in real time based on the workpiece processing data.
2. The computer program product of claim 1 , wherein the data structure is an object oriented data structure.
3. The computer program product of claim 1 , wherein the data structure is embodied in a relational database.
4. The computer program product of claim 1 , wherein the code further performs the step of creating a plurality of data structures for a plurality of workpieces.
5. The computer program product of claim 1 , wherein the workpiece processing data includes a measured property of the workpiece.
6. The computer program product of claim 5 , wherein the measured property includes at least one of a location of the workpiece, a process time of the workpiece, a temperature of the workpiece.
7. The computer program product of claim 1 , wherein the workpiece processing data includes an estimated temperature of the workpiece.
8. The computer program product of claim 7 , further comprising code that performs the step of updating the estimated temperature according to a thermal model for the workpiece.
9. The computer program product of claim 7 , further comprising code that performs the step of storing a time of attaining the estimated temperature.
10. The computer program product of claim 1 , wherein the workpiece includes a semiconductor wafer.
11. The computer program product of claim 1 , wherein the semiconductor manufacturing system includes a robotic semiconductor wafer handler that provides workpiece processing data for storage in the data structure.
12. The computer program product of claim 1 , further comprising code that performs the step of associating a time with the workpiece processing data in one of the one or more fields of the data structure.
13. The computer program product of claim 1 , further comprising code that performs the step of storing an attribute of the workpiece processing data in one of the one or more fields of the data structure.
14. The computer program product of claim 13 , wherein the attribute identifies at least one of a source of the workpiece processing data, and a time that the workpiece processing data was acquired.
15. The computer program product of claim 1 , further comprising code that performs the step of retrieving workpiece processing data from at least one of the one or more fields of the data structure and using the retrieved workpiece processing data to control processing of the workpiece.
16. The computer program product of claim 1 wherein the workpiece processing data includes at least one of a recipe for processing the workpiece, a particle map for the workpiece that identifies a location of one or more particles on the workpiece, and a process history for the workpiece.
17. A method comprising:
creating a data structure for a workpiece in a memory of a device, the data structure including an identity of the workpiece and one or more fields for storing workpiece processing data;
receiving, through a processor of the device, the workpiece processing data from a semiconductor manufacturing system including a plurality of interconnected process modules that provide the workpiece processing data for storage in the data structure while the workpiece is processed by the semiconductor manufacturing system and updating the data structure to provide substantially real time workpiece processing data in the data structure, wherein the workpiece processing is controlled by a neural network and a finite state machine scheduler; and
storing the workpiece processing data in one of the one or more fields of the data structure where the neural network and the finite state machine scheduler adjust throughput of the semiconductor manufacturing system where the neural network is responsive to inputs that include the workpiece processing data and is configured to generate outputs so that, in combination with the finite state machine scheduler, throughput of the semiconductor manufacturing system is adjusted substantially in real time based on the workpiece processing data.
18. The method of claim 17 , wherein the workpiece processing data includes a measured property of the workpiece.