Process change detection through the use of evolutionary algorithms
View Patent ↗The present invention provides a method for creating a process change detection algorithm. An evolutionary computing technique is applied to at least one process dataset containing at least one known process change. The evolutionary computing technique will generate a process state function (or a scaling coefficient set for use with an existing process state function) that optimizes detection of the known process changes. The generated process state function or coefficients can then be applied thereafter to future datasets (either in real-time or after processing) to detect process changes.
1. A method for improving the detection of a process change, the method comprising:
placing a substrate in a chamber;
exposing the substrate to a process with at least one known process change;
acquiring at least one dataset during a process;
generating a first random population of process state functions;
applying at least one dataset to each member of the first generated population;
evaluating the ability of each member of the first generated population to detect at least one known process change;
recombining the most successful members of the first generated population to generate a second population;
applying at least one dataset to each member of the second generated population; and
evaluating the ability of each member of the second generated population to detect at least one known process change.
2. The method according to claim 1 wherein said process is a plasma etch process.
3. The method according to claim 1 wherein said substrate is a photomask.
4. The method according to claim 1 wherein said substrate is a semiconductor material.
5. The method according to claim 1 wherein said substrate is a dielectric material.
6. The method according to claim 1 wherein said substrate is an electrically conductive material.
7. The method according to claim 1 wherein said process change is a material transition in the substrate.
8. The method according to claim 1 wherein said dataset further comprising plasma emission spectra data.
9. The method according to claim 1 wherein said dataset further comprising residual gas analysis data.
10. The method according to claim 1 wherein said process state functions are a set of scaling coefficients.
11. The method according to claim 1 wherein said successful members are the top 20 percent of the population.
12. The method according to claim 11 wherein the remaining 80 percent of the population is eliminated from further consideration.
13. The method according to claim 1 further comprising a set number of generated populations.
14. The method according to claim 1 further comprising terminating the generation of populations when at least one member of a population meets a set criteria.
15. The method according to claim 1 wherein said dataset further comprising at least one plasma processing parameter.
16. The method according to claim 14 wherein said plasma processing parameter comprises measurements of the plasma condition, substrate condition, or processing apparatus condition.