US 11,940,785 B2
Method for predicting maintenance for components used in substrate treatments, and predictive maintenance device
Taku Omori, Akishima (JP)
Assigned to ASM IP Holding B.V., Almere (NL)
Filed by ASM IP Holding B.V., Almere (NL)
Filed on Oct. 12, 2021, as Appl. No. 17/498,999.
Claims priority of provisional application 63/092,222, filed on Oct. 15, 2020.
Prior Publication US 2022/0121196 A1, Apr. 21, 2022
Int. Cl. G05B 23/02 (2006.01); H01L 21/67 (2006.01)
CPC G05B 23/0283 (2013.01) [G05B 23/0235 (2013.01); G05B 23/0272 (2013.01); H01L 21/67017 (2013.01); H01L 21/67253 (2013.01); H01L 21/67011 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A predictive maintenance method comprising:
providing a system with a plurality of modules and that is configured to run a plurality of recipes, wherein each of the plurality of modules has a different output data, wherein each of the plurality of recipes has a plurality of output data corresponding to the different output data of each of the plurality of modules, wherein the system is configured to measure and record the plurality of output data from the plurality of modules of the system while running each of the plurality of recipes;
determining a plurality of allowable thresholds for each of the plurality of output data for each of the plurality of recipes, wherein determining an allowable threshold for each of the plurality of output data comprises:
obtaining an average value for each of the plurality of output data for each of the plurality of modules in treatment of a plurality of dummy wafers; and
determining the allowable threshold for each of the plurality of output data on the basis of the average value;
after determining the plurality of allowable thresholds for each of the plurality of output data, performing a substrate treatment using a first recipe of a first substrate and measuring a first set of data in a substrate treating, wherein the first set of data comprises the plurality of output data for each of the plurality of modules measured while running the first recipe;
determining whether any data of the first set of data measured in a substrate treatment that has used the first recipe exceeds the allowable threshold for each of the plurality of output data for the first recipe;
calculating a degree of safety for each of the plurality of output data for the first recipe, wherein calculating a degree of safety comprises calculating the margin between the measured data and the allowable threshold;
notifying, in a case where it is determined that any data of the first set of data exceeds the allowable threshold in the determination, a user that the module associated with the data that has exceeded the allowable threshold has deteriorated,
specifying whether the first recipe is a high-load recipe for the system, wherein the high-load recipe is a recipe which provides a lower degree of safety than that of a predetermined criterion, and
changing, suppressing a frequency of use of, or restricting from the system the high-load recipe.