中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.021 seconds)

    MAINTAINING A SET OF PROCESS FINGERPRINTS
    2.
    发明申请
    MAINTAINING A SET OF PROCESS FINGERPRINTS 审中-公开

    公开(公告)号：WO2018192789A1

    公开(公告)日：2018-10-25

    申请号：PCT/EP2018/058997

    申请日：2018-04-09

    Applicant: ASML NETHERLANDS B.V.

    Inventor： YPMA, Alexander ,  BASTANI, Vahid ,  SONNTAG, Dag ,  NIJE, Jelle ,  CEKLI, Hakki, Ergun ,  TSIROGIANNIS, Georgios ,  VAN WIJK, Robert Jan

    IPC: G03F7/20

    Abstract: A method of maintaining a set of fingerprints (316) representing variation of one or more process parameters across wafers, has the steps: (a) receiving measurement data (324) of one or more parameters measured on wafers; (b) updating (320) the set of fingerprints based on an expected evolution (322) of the one or more process parameters; and (c) evaluation of the updated set of fingerprints based on decomposition of the received measurement data in terms of the updated set of fingerprints. Each fingerprint may have a stored likelihood of occurrence (316), and the decomposition may involve: estimating, based the received measurement data (324), likelihoods of occurrence of the set of fingerprints in the received measurement data; and updating the stored likelihoods of occurrence based on the estimated likelihoods.

    METHOD AND APPARATUS FOR DETERMINING FEATURE CONTRIBUTION TO PERFORMANCE
    3.
    发明申请
    METHOD AND APPARATUS FOR DETERMINING FEATURE CONTRIBUTION TO PERFORMANCE 审中-公开

    公开(公告)号：WO2021001114A1

    公开(公告)日：2021-01-07

    申请号：PCT/EP2020/065619

    申请日：2020-06-05

    Applicant: ASML NETHERLANDS B.V.

    Inventor： BASTANI, Vahid ,  SONNTAG, Dag ,  SAHRAEIAN, Reza ,  GKOROU, Dimitra

    IPC: G03F7/20 ,  G05B19/418 ,  H01L21/66

    Abstract: A method of determining a contribution of a process feature to the performance of a process of patterning substrates. The method may comprise obtaining a first model trained on first process data and first performance data. One or more substrates may be identified based on a quality of prediction of the first model when applied to process data associated with the one or more substrates. A second model may be trained on second process data and second performance data associated with the identified one or more substrates. The second model may be used to determine the contribution of a process feature of the second process data to the second performance data associated with the one or more substrates.

    METHOD TO LABEL SUBSTRATES BASED ON PROCESS PARAMETERS
    4.
    发明申请
    METHOD TO LABEL SUBSTRATES BASED ON PROCESS PARAMETERS 审中-公开

    公开(公告)号：WO2019149562A1

    公开(公告)日：2019-08-08

    申请号：PCT/EP2019/051424

    申请日：2019-01-22

    Applicant: ASML NETHERLANDS B.V.

    Inventor： BASTANI, Vahid ,  YPMA, Alexander ,  SONNTAG, Dag ,  MOS, Everhardus, Cornelis ,  CEKLI, Hakki, Ergun ,  LIN, Chenxi

    IPC: G06N5/00 ,  G03F7/20

    Abstract: Substrates to be processed (402) are partitioned based on pre-processing data (404) that is associated with substrates before a process step. The data is partitioned using a partition rule (410, 412, 414) and the substrates are partitioned into subsets (G1-G4) in accordance with subsets of the data obtained by the partitioning. Corrections (COR1-COR4) are applied, specific to each subset. The partition rule is obtained (Fig 5) using decision tree analysis on a training set of substrates (502). The decision tree analysis uses pre-processing data (256, 260) associated with the training substrates before they were processed, and post-processing data (262) associated with the training substrates after being subject to the process step. The partition rule (506) that defines the decision tree is selected from a plurality of partition rules (512) based on a characteristic of subsets of the post-processing data. The associated corrections (508) are obtained implicitly at the same time.

Patent Agency Ranking