Reticle design inspection system

• US 6,466,314 B1
• Filed: 09/17/1998
• Issued: 10/15/2002
• Est. Priority Date: 09/17/1998
• Status: Expired due to Fees

• Current Assignee: Applied Materials Incorporated
• Original Assignee: Applied Materials Incorporated
• Inventors: Lehman, Yonatan
• Primary Examiner(s): Font, Frank G.
• Assistant Examiner(s): Nguyen, Sang H.
• Application Number:
  US09/156,572
• Time in Patent Office: 1,489 Days
• Field of Search: 356/237.1, 356/237.3, 356/237.4, 356/237.5, 356/390, 356/391, 356/392, 356/393, 356/394, 250/548, 250/561, 382/1, 382/8, 982/145
• US Class Current: 356/237.1
• CPC Class Codes: G01N 21/95607 using a comparative method
• CPC Class Codes: G03F 1/44 Testing or measuring features, e.g. grid patterns, focus monitors, sawtooth scales or notched scales
• CPC Class Codes: G03F 1/84 Inspecting
• CPC Class Codes: G03F 7/70433 Layout for increasing efficiency or for compensating imaging errors, e.g. layout of exposure fields for reducing focus errors; Use of mask features for increasing efficiency or for compensating imaging errors

Abstract

A method of reticle inspection, comprising generating a test reticle comprising a plurality of test pattern-features thereon; manufacturing a wafer using the reticle; and determining a transfer of at least one of said plurality of pattern features from said reticle to said wafer. Preferably, a neural network is trained using the determination. Preferably, a reticle is inspected by running detected defects through the neural network to determine if the detected defect has a consequence.

Claims

1. A reticle inspection system comprising:

a training engine receiving data of known test defects produced on a test reticle and data of defects detected on a test wafer, and outputting training results correlating said defects detected on said test wafer to said test defects, thereby identifying test defects which have been transferred to the test wafer and test defects which have not been transferred to the test wafer;

an inspection result module receiving manufacturing defect data of defects detected on a production reticle by an inspection system;

a print/no print module receiving an input from said inspection result module and the training results, and

a defect reporter which receives an input from said print/no print module and identifies which of the manufacturing defects is transferred to a manufactured wafer.

2. A system according to claim 1, further comprising a neural network.

3. A system according to claim 1, further comprising a pattern matching computer.

4. The reticle inspection system of claim 1, further comprising a defect review stage and a re-train feedback loop connected between said defect review stage and said training engine.