PROCESS CONTROL TECHNIQUES FOR SEMICONDUCTOR MANUFACTURING PROCESSES
First Claim
Patent Images
1. A method, comprising:
- receiving real-time inputs of a current production run of semiconductor wafers from a lithography process and at least one upstream process into an overlay measurement model stored in a data processing apparatus, wherein the overlay measurement model is configured to determine a multi-variate relationship of a plurality of input data to overlay measurement, the input data is obtained from the lithography process and the upstream process in previous production runs;
generating a predicted overlay measurement from the real-time inputs using the overlay measurement model; and
adjusting the lithography process or the upstream process such that the predicted overlay measurement correlates with an actual overlay measurement.
1 Assignment
0 Petitions
Accused Products
Abstract
Techniques for measuring and/or compensating for process variations in a semiconductor manufacturing processes. Machine learning algorithms are used on extensive sets of input data, including upstream data, to organize and pre-process the input data, and to correlate the input data to specific features of interest. The correlations can then be used to make process adjustments. The techniques may be applied to any feature or step of the semiconductor manufacturing process, such as overlay, critical dimension, and yield prediction.
76 Citations
20 Claims
-
1. A method, comprising:
-
receiving real-time inputs of a current production run of semiconductor wafers from a lithography process and at least one upstream process into an overlay measurement model stored in a data processing apparatus, wherein the overlay measurement model is configured to determine a multi-variate relationship of a plurality of input data to overlay measurement, the input data is obtained from the lithography process and the upstream process in previous production runs; generating a predicted overlay measurement from the real-time inputs using the overlay measurement model; and adjusting the lithography process or the upstream process such that the predicted overlay measurement correlates with an actual overlay measurement. - View Dependent Claims (2)
-
-
3. A method, comprising:
-
obtaining a plurality of overlay measurements from a plurality of wafers in a plurality of production runs of a lithography process, wherein each overlay measurement indicates an offset between a first set of features formed on a first layer and a second set of features formed on a second layer above the first layer; collecting a set of input data from each production run including data obtained from the lithography process and data obtained from upstream processes; analyzing the sets of input data to determine a multi-variate relationship of the input data to the overlay measurements; generating a predicted overlay measurement for each set of input data; and adjusting the lithography process or the upstream processes such that the predicted overlay measurements correlate with an actual overlay measurement. - View Dependent Claims (4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16)
-
-
17. A non-transitory machine-readable medium having stored thereon one or more sequences of instructions, which instructions, when executed by one or more processors, cause the one or more processors to carry out the steps of:
-
obtaining a plurality of overlay measurements from a plurality of wafers in a plurality of production runs of a lithography process, wherein each overlay measurement indicates an offset between a first set of features formed on a first layer and a second set of features formed on a second layer above the first layer; collecting a set of input data from each production run including data obtained from the lithography process and data obtained from upstream processes; analyzing the sets of input data to determine a multi-variate relationship of the input data to the overlay measurements; generating a predicted overlay measurement for each set of input data; and adjusting the lithography process or the upstream processes such that the predicted overlay measurements correlate with an actual overlay measurement. - View Dependent Claims (18)
-
-
19. A system, comprising:
-
at least one processor; and a memory coupled to the processor comprising instructions executable by the processor, the instructions, when executed by the processor, cause the processor to; obtain a plurality of overlay measurements from a plurality of wafers in a plurality of production runs of a lithography process, wherein each overlay measurement indicates an offset between a first set of features formed on a first layer and a second set of features formed on a second layer above the first layer; collect a set of input data from each production run including data obtained from the lithography process and data obtained from upstream processes; analyze the sets of input data to determine a multi-variate relationship of the input data to the overlay measurements; generate a predicted overlay measurement for each set of input data; and adjust the lithography process or the upstream processes such that the predicted overlay measurements correlate with an actual overlay measurement. - View Dependent Claims (20)
-
Specification