Biologically based chamber matching
Abstract
The subject disclosure relates to automatically learning relationships among a plurality of manufacturing tool parameters as applied to arbitrary semiconductor manufacturing tools and a graphical user interface that is supported, at least in part, by an autonomous learning system. The graphical user interface can create one or more matrixes based on received data and can further generate additional matrices by transforming the one or more matrixes. A series of windows can be output, wherein the series of windows, provide performance analysis that comprises a matching between a focus chamber and a reference chamber. In an aspect, the focus chamber and the reference chamber can be different chambers. In another aspect, the focus chamber and the reference chamber can be the same chamber, which provides analysis of the deterioration in performance of the same chamber over time.
Claims
exact text as granted — not AI-modified1 . A system for biologically based chamber matching, comprising:
one or more tools configured for processing one or more substrates; an autonomous learning system that determines a behavior of the one or more tools by identifying tool behavior differences between the one or more tools and a reference tool; and a computer system that provides a graphical user interface that expresses an output of interest, based on the behavior, as a function of one or more tool sensors, tool maintenance counters, or other metrology data, wherein the output of interest is a performance comparison of at least one focus tool and the reference tool.
2 . The system of claim 1 , wherein the graphical user interface provides rapid analysis of chamber matching performance for the one or more tools through related components, comprising:
an importer that receives information indicative of the reference tool and the at least one focus tool; a generate component that creates at least one matrix based on the information; a transform component that generates one or more additional matrices of data by transforming the at least one matrix; and an output component that renders a progression of windows as a function of the one or more additional matrices of data, wherein the progression of windows comprises performance analysis results that compare the reference tool and the at least one focus tool.
3 . The system of claim 2 , wherein the graphical user interface imports sensor measurements, tool performance counters readings, metrology data, process recipes, system recipes, or combinations thereof.
4 . The system of claim 1 , wherein the autonomous learning system comprises:
a reference repository that stores behavioral attributes of the reference tool based on a determination that the reference tool is operating at a preferred capable performance level.
5 . The system of claim 4 , wherein the autonomous learning system further comprises:
a matching repository that compares a current performance of the reference tool with a previous performance of the reference tool.
6 . The system of claim 1 , wherein the autonomous learning system comprises:
an event generator that generates events based on a determination that performance degradation has occurred, wherein maintenance activities are performed based on the generated events and before significant loss to operations of the one or more tools.
7 . The system of claim 1 , wherein the graphical user interface is a front end for the autonomous learning system and directly connects to the one or more tools, and wherein the graphical user interface receives data, displays analysis results, or combinations thereof.
8 . The system of claim 1 , wherein the graphical user interface creates one or more matrixes and the autonomous learning system learns each column of the one or more matrixes as a function of other columns and generates a sample for each column.
9 . The system of claim 1 , wherein the graphical user interface expresses the output of interest as a progression of windows that build upon each other.
10 . The system of claim 1 , wherein the graphical user interface provides a means to drill down into details of the at least one focus tool, the reference tool, or both the at least one focus tool and the reference tool.
11 . The system of claim 1 , wherein the graphical user interface is tool independent.
12 . The system of claim 1 , wherein the reference tool and the at least one focus tool are the same tool.
13 . The system of claim 1 , wherein the reference tool and the at least one focus tool are different tools.
14 . A method, comprising:
using at least one processor, communicatively coupled to at least one memory, to perform the following acts:
processing, by a set of tools, one or more substrates;
determining a respective behavior of each tool in the set of tools;
determining a performance difference between a focus tool selected from the set of tools and a reference tool; and
displaying an output of interest based on the performance difference.
15 . The method of claim 14 , wherein the determining respective behaviors comprises determining respective tool behavior differences between the reference tool and each tool of the set of tools.
16 . The method of claim 14 , wherein the determining the performance difference comprising receiving data from a tool sensor, a tool maintenance counter, a metrology measurement device, or a combination thereof.
17 . The method of claim 14 , wherein the displaying the output of interest comprises displaying the output of interest on a graphical user interface as a progression of windows, wherein each window of the progression of windows builds upon a preceding window of the progression of windows.
18 . The method of claim 14 , wherein the displaying the output of interest comprises displaying, on a graphical user interface, the output of interest and a means to drill down into details of the focus tool, the reference tool, or both the focus tool and the reference tool.
19 . The method of claim 14 , further comprising:
providing rapid analysis of chamber matching performance for the set of tools comprising:
receiving information indicative of the reference tool and the focus tool;
generating a first matrix as a function of the received information;
generating a second matrix of data based on a transformation of the first matrix; and
outputting a progression of windows based on the second matrix, wherein the progression of windows comprises performance analysis results that compare the reference tool and the focus tool.
20 . The method of claim 14 , further comprising:
determining the reference tool is operating at a threshold level of performance; and storing behavioral attributes of the reference tool in a reference repository.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.