Method and system for managing semiconductor manufacturing equipment

• US 7,076,318 B2
• Filed: 11/14/2003
• Issued: 07/11/2006
• Est. Priority Date: 09/30/1998
• Status: Expired due to Fees

• Current Assignee: LAPIS Semiconductor Co., Ltd. (ROHM Co., Ltd.)
• Original Assignee: OKI Electric Industry Company Limited
• Inventors: Hayashi, Shunji
• Primary Examiner(s): Bahta, Kidest
• Application Number:
  US10/712,100
• Publication Number:
  US 20040098161A1
• Time in Patent Office: 970 Days
• Field of Search: 702/182, 702/185, 702/183, 702/83, 702/84, 700/73, 700/110, 700/112, 700/117, 700/32, 700/78, 700/79, 700/95, 700/109, 700/108, 382/278, 382/309, 382/115, 382/118
• US Class Current: 700/121
• 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: H01J 37/32935 Monitoring and controlling tubes by information coming from the object and/or discharge
• CPC Class Codes: H01L 21/02 Manufacture or treatment of semiconductor devices or of parts thereof

Abstract

A management method capable of making an accurate decision about a malfunction of the semiconductor manufacturing equipment includes sampling a plurality of data of at least one parameter under normal operating conditions of the semiconductor manufacturing equipment; generating a Mahalanobis space A from a group of sampled data; calculating a Mahalanobis distance from measured values of the parameter under ordinary operating conditions of the semiconductor manufacturing equipment; and deciding that a malfunction occurred in the semiconductor manufacturing equipment when the value of the Mahalanobis distance exceeds a predetermined value.

Claims

1. A method of controlling semiconductor manufacturing equipment, comprising:

sampling a plurality of data;

generating a correlation matrix based on the plurality of data;

generating an inverse matrix of the correlation matrix in order to generate a Mahalanobis space;

generating a Mahalanobis distance based on the Mahalanobis space; and

generating a control signal which indicates that an operation of the semiconductor manufacturing equipment should be stopped when the Mahalanobis distance exceeds a threshold value.

2. The method of controlling semiconductor manufacturing equipment of claim 1, wherein the plurality of data is plasma emission intensity.

3. The method of controlling semiconductor manufacturing equipment of claim 1, further comprising generating an alarm when the Mahalanobis distance exceeds the threshold value.

4. The method of controlling semiconductor manufacturing equipment of claim 1, further comprising:

standardizing the plurality of data obtained by said sampling to provide standardized data used during said generating a correlation matrix,

wherein said standardizing uses an equation

Y<sub>n·

m</sub>=(Y′

<sub>n·

m</sub>−

Ave_n)/σ

_n,

wherein Y′

<sub>n·

m</sub> is a sample data at an appointed time X_n in m time sampling, Ave_n is an average of a group of sample data measured at time X_n, σ

_n is a standard deviation of data at time X_n, and Y_n,m is a standardized sample value at X_n,

whereby n is an integer from 1 to n and m is an integer from 1 to m.

5. The method of controlling semiconductor manufacturing equipment of claim 4, wherein said generating a correlation matrix uses an equation

$r_{\mathrm{ij}}=r_{\mathrm{ji}}=\frac{1}{m}$

∑

p = 1 m ⁢

⁢

Y i ·

p ⁢

Y jp ,

wherein r_ij and r_ji are matrix elements and i and j are integers from 1 to n.

6. The method of controlling semiconductor manufacturing equipment of claim 5, wherein said generating a Mahalanobis distance uses an equation

$D^2$

= 1 n ⁢

∑

i = 1 n ⁢

⁢

∑

j = 1 n ⁢

⁢

a ij ⁢

Y i ⁢

Y j ,

wherein D is the Mahalanobis distance and a_ij are matrix elements of the inverse matrix.

7. The method of controlling semiconductor manufacturing equipment of claim 1, wherein the threshold value is within a range of 2 to 4.

8. The method of controlling semiconductor manufacturing equipment according to claim 1, wherein the plurality of data are sampled based on a light intensity of plasma in a reaction chamber.

9. The method of controlling semiconductor manufacturing equipment according to claim 1, wherein the plurality of data are sampled based on a change in an impedance of a reaction chamber.

10. The method of controlling semiconductor manufacturing equipment according to claim 9, wherein the change in the impedance is based on a change in a voltage of a high frequency to be supplied to an electrode in the reaction chamber.

11. The method of controlling semiconductor manufacturing equipment according to claim 1, wherein the plurality of data are sampled based on a voltage, a current and a phase of a supplied high frequency electric power.

12. A semiconductor device produced in accordance with the method of claim 1.