System for monitoring and controlling a semiconductor manufacturing apparatus using prediction model equation

• US 7,343,217 B2
• Filed: 05/24/2006
• Issued: 03/11/2008
• Est. Priority Date: 09/06/2001
• Status: Expired due to Term

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Tanaka, Junichi, Shiraishi, Daisuke, Ikuhara, Shoji, Yamamoto, Hideyuki, Kitsunai, Hiroyuki, Masuda, Toshio, Kagoshima, Akira
• Primary Examiner(s): Jarrett; Ryan A.
• Application Number:
  US11/439,265
• Publication Number:
  US 20060212156A1
• Time in Patent Office: 657 Days
• Field of Search: 700/108, 700/121
• US Class Current: 700/121
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 19/41865 characterised by job scheduling, process planning, material flow
• CPC Class Codes: G05B 2219/31357 Observer based fault detection, use model
• CPC Class Codes: G05B 2219/32058 Execute program as function of deviation from predicted state, result
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: H01L 21/67276 Production flow monitoring, e.g. for increasing throughput program-control systems per se G05B19/00, e.g. total factory control G05B19/418
• CPC Class Codes: H01L 22/20 Sequence of activities consisting of a plurality of measurements, corrections, marking or sorting steps
• CPC Class Codes: H01L 2924/00 Indexing scheme for arrangements or methods for connecting or disconnecting semiconductor or solid-state bodies as covered by H01L24/00
• CPC Class Codes: H01L 2924/0002 Not covered by any one of groups H01L24/00, H01L24/00 and H01L2224/00
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A semiconductor processing apparatus for processing a semiconductor wafer includes a plurality of sensors for monitoring a processing state, a processing result input unit, a model equation generation unit to generate a model equation for predicting a processing result, a processing result prediction unit which predicts a processing result, and a process recipe control unit. Further, a system is provided which comprises the model equation generation unit is provided at a remote location, and transmits the generated prediction model equation to the semiconductor processing apparatus through a network to control the processing condition of the semiconductor processing apparatus by the process recipe control unit.

Claims

1. A semiconductor processing system, comprising:

a semiconductor processing apparatus for processing a semiconductor wafer;

a plurality of sensors each for monitoring a processing state of said semiconductor processing apparatus;

a processing result input unit which inputs measured values for processing results of a semiconductor wafer processed by said semiconductor processing apparatus;

a model equation storage unit which stores a prediction model equation for predicting a processing result;

a processing result prediction unit which predicts a processing result based on said prediction model equation stored in said model equation storage unit and sensed data acquired by said sensors; and

a process recipe control unit which compares said predicted processing result with a previously set value to control a processing condition of said semiconductor processing apparatus such that a deviation between said predicted processing result and said previously set value is corrected;

wherein a model equation generation unit relying on said sensed data and said measured values to generate said prediction model equation usinq said sensed data as an explanatory variable is provided at a remote location at least with respect to a location of said model equation storage unit, and said model equation generation unit transmits said generated prediction model equation to said model equation storage unit through a network to control the processing condition of said semiconductor processing apparatus by said process recipe control unit using said generated prediction model equation from said model equation storage unit.

2. A semiconductor processing system according to claim 1, wherein said model equation unit generates the model equation using a partial least square (PLS) method.

3. A semiconductor processing system according to claim 1, wherein said model equation unit generates the model equation using robust regression for measured data in which any abnormal measured data is removed.

4. A semiconductor processing system according to claim 1, wherein a plurality of different performances are controlled, and said plurality of different performances include different etching performances.

5. A semiconductor processing system according to claim 4, wherein the etching performance includes vertical etching or selectivity.