Method for diagnosing life of manufacturing equipment using rotary machine

• US 20030154052A1
• Filed: 08/27/2002
• Published: 08/14/2003
• Est. Priority Date: 08/31/2001
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Nakao, Takashi, Samata, Shuichi, Ishii, Ken, Ushiku, Yukihiro
• Granted Patent: US 6,766,275 B2
• Time in Patent Office: Days
• US Class Current: 702/184
• CPC Class Codes: F04D 19/04 specially adapted to the production of a high vacuum, e.g. molecular pumps
• CPC Class Codes: F04D 27/001 Testing thereof; Determination or simulation of flow characteristics; Stall or surge detection, e.g. condition monitoring
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06

Abstract

A method for diagnosing life of manufacturing equipment having a rotary machine, includes: measuring reference time series data for characteristics before deterioration of the manufacturing equipment occurs; finding a reference auto covariance function based on the reference time series data; extracting a reference variation caused by variations of the process condition and power supply from the reference auto covariance function, and calculating a cycle of the reference variation; measuring diagnostic time series data for the characteristics in a sequence to be measured of the manufacturing equipment; finding a diagnostic auto covariance function based on the diagnostic time series data; and determining the life of the manufacturing equipment from the diagnostic auto covariance function using a component with a cycle shorter than a cycle of the reference variation.

Claims

1. A method for diagnosing life of manufacturing equipment having a rotary machine, comprising:

measuring reference time series data representing characteristics in a state before deterioration of the manufacturing equipment occurs;

finding a reference auto covariance function based on the reference time series data;

extracting a reference variation caused by variations of the process condition and power supply from the reference auto covariance function, and calculating a cycle of the reference variation;

measuring diagnostic time series data representing the characteristics in a sequence to be measured of the manufacturing equipment;

finding a diagnostic auto covariance function based on the diagnostic time series data; and

determining the life of the manufacturing equipment from the diagnostic auto covariance function using a component with a cycle shorter than a cycle of the reference variation.

2. The method of claim 1, wherein the characteristics include at least one of a motor current, a motor power, a pressure, a vibration, and a gas temperature in relation to the rotary machine of the manufacturing equipment.

3. The method of claim 1, wherein the manufacturing equipment is semiconductor manufacturing equipment.

4. The method of claim 3, wherein the characteristics include at least one of a motor current, a motor power, a pressure, a vibration, and a gas temperature in relation to the semiconductor manufacturing equipment.

5. The method of claim 4, wherein the characteristics are associated with behavior of a dry pump serving as the rotary machine used in the semiconductor manufacturing equipment.

6. The method of claim 3, wherein the semiconductor manufacturing equipment is LPCVD equipment.

7. The method of claim 6, wherein the characteristics include at least one of a motor current, a motor power, a pressure, a vibration, and a gas temperature in relation to a dry pump serving as the rotary machine used in the LPCVD equipment.

8. The method of claim 6, wherein the reference time series data is measured immediately after maintenance operation on a dry pump serving as the rotary machine used in the LPCVD equipment.

9. The method of claim 6, wherein the sequence to be measured is a deposition sequence using the LPCVD equipment.

10. The method of claim 6, wherein the diagnostic time series data for the characteristics is measured at intervals of between 0.5 seconds and 10 minutes.

11. The method of claim 6, wherein the characteristics include a motor current of a dry pump serving as the rotary machine used in the LPCVD equipment.

12. The method of claim 6, wherein the characteristics include a frequency distribution of casing vibration of a dry pump serving as the rotary machine used in the LPCVD equipment.

13. A method for diagnosing life of manufacturing equipment having a rotary machine, comprising:

measuring reference time series data before starting measurement of diagnostic time series data for characteristics of the manufacturing equipment;

setting a Mahalanobis space from the reference time series data;

measuring the diagnostic time series data;

calculating a time variation of a Mahalanobis distance of the diagnostic time series data by using the diagnostic time series data and the Mahalanobis space;

setting a new Mahalanobis space from the diagnostic time series data when the Mahalanobis distance reaches a threshold value; and

determining the life of the manufacturing equipment by comparing a new Mahalanobis distance corresponding to the new Mahalanobis space with the threshold value.

14. The method of claim 13, wherein the characteristics include at least one of a motor current, a motor power, a pressure, a vibration, and a gas temperature relating to a rotary machine of the manufacturing equipment.

15. The method of claim 13, wherein the manufacturing equipment is semiconductor manufacturing equipment.

16. The method of claim 15, wherein the characteristics include one of a motor current, a motor power, a pressure, a vibration, and a gas temperature relating to the semiconductor manufacturing equipment.

17. The method of claim 16, wherein the characteristics are associated with behavior of a dry pump serving as the rotary machine used in the semiconductor manufacturing equipment.

18. The method of claim 15, wherein the semiconductor manufacturing equipment is LPCVD equipment.

19. The method of claim 18, wherein the characteristics include at least one of a motor current, a motor power, a pressure, a vibration, and a gas temperature in relation to a dry pump serving as the rotary machine used in the LPCVD equipment.

20. The method of claim 18, wherein a deposition sequence has the same process condition as the diagnosis.

21. The method of claim 18, wherein the predetermined threshold value for the Mahalanobis distance falls within a range of 5 through 10.

22. The method of claim 18, wherein the diagnostic time series data for the characteristics is measured at intervals of between 0.5 seconds and 10 minutes.

23. The method of claiml8, wherein the Mahalanobis space is formed by a group of characteristics of a motor current, an inner pressure of a pump, and a vibration on a casing of a dry pump serving as the rotary machine used in the LPCVD equipment.