Diagnosis apparatus, plasma processing apparatus and diagnosis method

Patent metadata

Field	Value
Publication number	US-12040167-B2
Application number	US-201916971255-A
Country	US
Kind code	B2
Filing date	Jul 30, 2019
Priority date	Jul 30, 2019
Publication date	Jul 16, 2024
Grant date	Jul 16, 2024

Abstract

In a diagnosis apparatus for diagnosing a state of a plasma processing apparatus, prior distribution information including a probability distribution function is previously obtained for each of first sensors by using first sensor values obtained by the first sensors in a first plasma processing apparatus, a probability distribution in each of second sensors corresponding to each of the first sensors is estimated based on the previously obtained prior distribution information and second sensor values obtained by the second sensors in a second plasma processing apparatus different from the first plasma processing apparatus, and a state of the second plasma processing apparatus is diagnosed by using the estimated probability distribution.

First claim

The invention claimed is:

1. A diagnosis apparatus for diagnosing a state of a plasma processing apparatus, comprising:
a computer configured to be operatively coupled via a network to at least a first group comprising a plurality of first plasma processing apparatuses and a second group comprising a plurality of second plasma processing apparatuses,
wherein the computer is configured to
obtain, via said network, prior distribution information comprising plasma processing histories stored by at least one of said first plasma processing apparatuses, said prior distribution information including a probability distribution function for each of a plurality of first sensors by using first sensor values obtained by the first sensors of at least one of said first plasma processing apparatuses;
calculate a plurality of probability distribution functions for each of a plurality of second sensors corresponding to each of the plurality of first sensors, wherein the plurality of probability distribution functions comprises a normal distribution, a distortion normal distribution, a mixed normal distribution, and a Cauchy distribution;
calculate an estimated probability for each of the plurality of calculated probability distribution functions for each of the plurality of second sensors corresponding to each of the plurality of first sensors based on the obtained prior distribution information and second sensor values obtained by the second sensors of a second plasma processing apparatus different from the first plasma processing apparatus;
calculate a plurality of log likelihood values for a degree of fit of the estimated probability for each of the plurality of calculated probability distribution functions for each of the plurality of second sensors;
select, by said computer, one of said plurality of calculated probability distribution functions for each of the plurality of second sensors;
store, for each of the plurality of second sensors, the selected calculated probability distribution function and the normal distribution;
extract one of said plurality of calculated probability distribution functions having a maximum commonality for the plurality of second plasma processing apparatuses; and
cause a state of one of said second plasma processing apparatuses to be diagnosed using the extracted probability distribution function.

2. The diagnosis apparatus according to claim 1 , wherein
the plurality of first plasma processing apparatuses comprises two or more of said first plasma processing apparatuses, and
the probability distribution function previously obtained in each of the first sensors is a most frequent probability distribution function obtained for the first plasma processing apparatus among probability distribution functions obtained for the first plasma processing apparatuses.

3. A diagnosis apparatus for diagnosing a state of a plasma processing apparatus, comprising:
a computer configured to be operatively coupled via a network to at least a first group comprising a plurality of first plasma processing apparatuses and a second group comprising a plurality of second plasma processing apparatuses,
wherein the computer is configured to
obtain, via said network, prior distribution information comprising plasma processing histories stored by at least one of said first plasma processing apparatuses, said prior distribution information including a probability distribution function for each of a plurality of first sensors by using first sensor values obtained by first sensors of at least one of said first plasma processing apparatuses;
calculate a plurality of probability distribution functions for each of a plurality of second sensors corresponding to each of the plurality of first sensors, wherein the plurality of probability distribution functions comprises a normal distribution, a distortion normal distribution, a mixed normal distribution, and a Cauchy distribution;
calculate an estimated probability for each of the plurality of calculated probability distribution functions for each of the plurality of second sensors corresponding to each of the plurality of first sensors based on the obtained prior distribution information and second sensor values obtained by the second sensors of a second plasma processing apparatus different from the first plasma processing apparatus;
calculate a plurality of log likelihood values for a degree of fit of the estimated probability for each of the plurality of calculated probability distribution functions for each of the plurality of second sensors;
select, by said computer, one of said plurality of calculated probability distribution functions for each of the plurality of second sensors;
store, for each of the plurality of second sensors, the selected calculated probability distribution function and the normal distribution;
compare a first of the plurality of log likelihood values that is a likelihood of the estimated probability distribution and a second of the plurality of log likelihood values that is a likelihood of a normal distribution;
when the first log likelihood value is higher than the second log likelihood value, cause a state of the second plasma processing apparatus to be diagnosed using an estimated probability distribution function other than the normal distribution; and
when the second log likelihood value is higher than the first log likelihood value, cause the state of the second plasma processing apparatus to be diagnosed using the normal distribution.

4. The diagnosis apparatus according to claim 1 , wherein
the probability distribution is estimated by using a Markov chain Monte Carlo method.

5. The diagnosis apparatus according to claim 1 , wherein the computer is further configured to
output a difference in the probability distribution between the plasma processing apparatuses is output as a diagnosis value of the state of the second plasma processing apparatus, and
output a transition width over time of the probability distribution.

6. A plasma processing apparatus comprising:
a processing chamber in which a sample is plasma-processed; and
a diagnosis apparatus comprising a computer configured to diagnose a state of the plasma processing apparatus,
wherein the computer is configured to
obtain, via said network, prior distribution information comprising plasma processing histories stored by at least one of said first plasma processing apparatuses, said prior distribution information including a probability distribution function for each of a plurality of first sensors by using first sensor values obtained by the first sensors of at least one of said first plasma processing apparatuses;
calculate a plurality of probability distribution functions for each of a plurality of second sensors corresponding to each of the plurality of first sensors, wherein the plurality of probability distribution functions comprises a normal distribution, a distortion normal distribution, a mixed normal distribution, and a Cauchy distribution;
calculate an estimated probability for each of the plurality of calculated probability distribution functions for each of the plurality of second sensors corresponding to each of the plurality of first sensors based on the obtained prior distribution information and second sensor values obtained by the second sensors of a second plasma processing apparatus different from the first plasma processing apparatus;
calculate a plurality of log likelihood values for a degree of fit of the estimated probability for each of the plurality of calculated probability distribution functions for each of the plurality of second sensors;
select, by said computer, one of said plurality of calculated probability distribution functions for each of the plurality of second sensors;
store, for each of the plural

Assignees

• Hitachi High Tech Corp

Inventors

• Umeda Shota
• Tamaki Kenji
• Sumiya Masahiro
• Ishiguro Masaki

Classifications

• H10P50/242

  of Group IV materials · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• H01J2237/24578

  Spatial variables, e.g. position, distance · CPC title

• G01M99/005

  Testing of complete machines, e.g. washing-machines or mobile phones (testing of machine parts G01M13/00; testing of electric apparatus or components G01R31/50) · CPC title

• G05B23/0243

  model based detection method, e.g. first-principles knowledge model · CPC title