# US 2021/0082673 A1 · Plasma processing apparatus and prediction method of the condition of plasma processing apparatus

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0082673 A1
- Document ID: US20210082673A1
- Status: Published application
- Kind: A1
- Application number: 17/108,383
- Filed: 2020-12-01
- Published: 2021-03-18
- Earliest claimed: 2017-09-20
- Assignees: Hitachi High-Tech Corporation
- Applicants: Hitachi High-Tech Corporation
- Inventors: Yoshito Kamaji; Masahiro Sumiya
- Web page: https://patentgrep.com/patent/US20210082673A1

## CPC

- H01J 37/32926: {Software, data control or modelling}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06N 3/048: Activation functions
- G06N 7/00: Computing arrangements based on specific mathematical models
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- H01J 37/24: Circuit arrangements not adapted to a particular application of the tube and not otherwise provided for
- H01J 37/32: Gas-filled discharge tubes (heating by discharge H05B)
- H01J 37/32082: {Radio frequency generated discharge (H01J37/32357, H01J37/32366, H01J37/32394 and H01J37/32403 take precedence)}
- H01J 37/32192: {Microwave generated discharge (H01J37/32357, H01J37/32366, H01J37/32394, H01J37/32403 take precedence)}
- H01J 37/32449: {Gas control, e.g. control of the gas flow}
- H01J 37/32972: {Spectral analysis}
- H01J 37/3299: {Feedback systems}
- G05B 13/00: Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion (G05B19/00 takes precedence)
- G05B 13/04: involving the use of models or simulators
- H01J 2237/1825: Evacuating means
- H01J 2237/334: Etching
- H01J 2237/335: Cleaning
- H05H 13/005: {Cyclotrons}
- H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- H05H: PLASMA TECHNIQUE (apparatus or processes specially adapted for producing X-rays H05G2/00); PRODUCTION OF ACCELERATED ELECTRICALLY-CHARGED PARTICLES OR OF NEUTRONS; PRODUCTION OR ACCELERATION OF NEUTRAL MOLECULAR OR ATOMIC BEAMS

## Abstract

A system that predicts an apparatus state of a plasma processing apparatus including a processing chamber in which a sample is processed is configured to have a data recording unit that records emission data of plasma during processing of the sample and electrical signal data obtained from the apparatus during the plasma processing, an arithmetic unit that includes a first calculation unit for calculating a first soundness index value of the plasma processing apparatus and a first threshold for an abnormality determination using a first algorithm with respect to the recorded emission data and a second calculation unit for calculating a second soundness index value of the plasma processing apparatus and a second threshold for the abnormality determination using a second algorithm with respect to the electrical signal data recorded in the data recording unit, and a determination unit that determines soundness of the plasma processing apparatus using the calculated first soundness index value and the first threshold and the calculated second soundness index value and the second threshold.

## Claims

### Claim at position 1

1-4. (canceled)

### Claim 5

A plasma processing apparatus state prediction method of predicting a state of a plasma processing apparatus including a processing chamber in which a sample is subjected to plasma processing, the method comprising:
predicting the state of the plasma processing apparatus based on a first soundness index value obtained by analyzing a first data obtained from the plasma processing apparatus using a first algorithm and a second soundness index value obtained by analyzing a second data obtained from the plasma processing apparatus using a second algorithm,
wherein the second algorithm is an algorithm in which a second time of the plasma processing in which the state is determined as abnormal by the second soundness index value is a time within a range of a time obtained by subtracting a predetermined time from a first time of the plasma processing in which the state is determined as abnormal by the first soundness index value to a time obtained by adding the predetermined time to the first time.

### Claim 6 (depends on 5)

The plasma processing apparatus state prediction method according to claim 5,
wherein the first data is emission data obtained from plasma during the plasma processing, and
wherein the second data is data different from the first data.

### Claim 7 (depends on 6)

The plasma processing apparatus state prediction method according to claim 6,
wherein principal component analysis (PCA) is used as the first algorithm, and
wherein auto associative kernel regression (AAKR) is used as the second algorithm.

### Claim 8 (depends on 6)

The plasma processing apparatus state prediction method according to claim 6,
wherein a radio frequency component is removed from the second data, and then the radio frequency component removed second data is analyzed using the second algorithm.
