Statistical framework for tool chamber matching in semiconductor manufacturing processes

A system, comprising:

• a memory;
• and
• a processor configured to perform a method for detecting mismatches among a plurality of manufacturing tools of the same type and operating on a first semiconductor wafer, the method comprising:
• receiving metrological data and time series data applicable to the first semiconductor wafer from each of the plurality of manufacturing tools;
• applying a plurality of statistical tests to the metrological data and a data mining technique to the time series data;
• assigning a score to each result from applying the plurality of statistical test and the data mining technique to the plurality of manufacturing tools, the scores indicating a degree of mismatch among the plurality of manufacturing tools;
• and
• responsive to the sum of scores exceeding a predetermined threshold,
• declaring a mismatch condition for each tool among the plurality of manufacturing tools.

A computer program product for detecting mismatches among a plurality of manufacturing tools of the same type and operating on a first semiconductor wafer, the computer program product comprising:

• a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to:
• receive metrological data and time series data applicable to the first semiconductor wafer from each of the plurality of manufacturing tools;
• apply a plurality of statistical tests to the metrological data and a data mining technique to the time series data;
• assign a score to each result from applying the plurality of statistical test and the data mining technique to the plurality of manufacturing tools, the scores indicating a degree of mismatch among the plurality of manufacturing tools
• responsive to the sum of scores exceeding a predetermined threshold,
• declaring a mismatch condition for each tool among the plurality of manufacturing tools.