# US 12,007,758 B2 · Process state monitoring device and process state monitoring method

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

- Number: US 12,007,758 B2
- Document ID: US12007758B2
- Status: Granted
- Kind: B2
- Application number: 17/440,267
- Filed: 2020-03-24
- Published: 2022-06-16
- Granted: 2024-06-11
- Earliest claimed: 2019-03-26
- Assignees: Jfe Steel Corporation
- Applicants: Jfe Steel Corporation
- Inventors: Takehide Hirata; Tatsuhiro Sue; Masafumi Matsushita; Yohei Harada
- Web page: https://patentgrep.com/patent/US12007758B2

## CPC

- G05B 19/41875: {characterised by quality surveillance of production}
- 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}
- G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods}
- G06F 3/14: Digital output to display device {; Cooperation and interconnection of the display device with other functional units}
- 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 20/00: Machine learning
- 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)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A process state monitoring device incudes a processor including hardware, the processor being configured to: separate two or more components from time series data of a value indicating a state of a process; compute a characteristic value from each of the separated components; and classify the state of the process on the basis of the computed characteristic values.

## Claims

### Claim 1

A process state monitoring device comprising a processor comprising hardware, the processor being configured to:
separate two or more components from time series data of a value indicating a state of a process;
compute a characteristic value from each of the separated components;
classify the state of the process on the basis of the computed characteristic values;
search a past database for an operation case similar to the process on the basis of the computed characteristic values;
determine a similarity of the computed characteristic values and characteristic values of the operation case on the basis of a distance or an angle, in a variable space composed of a plurality of characteristic values, depending on the number of characteristic values to be compared; and
compute, as a contribution, the component contributing to the similarity.

### Claim 2 (depends on 1)

The process state monitoring device according to claim 1, wherein the time series data is time series data of a difference value between a prediction value and a result value of the value.

### Claim 3 (depends on 2)

The process state monitoring device according to claim 2, wherein the processor is configured to separate the components from the time series data by filtering processing.

### Claim 4 (depends on 1)

The process state monitoring device according to claim 1, wherein the time series data is
time series data of a difference value between the value and a preset value obtained at a time at which the state of the process is normal, or
time series data of a value of a ratio of the value to the preset value obtained at the time at which the state of the process is normal.

### Claim 5 (depends on 4)

The process state monitoring device according to claim 4, wherein the processor is configured to separate the components from the time series data by filtering processing.

### Claim 6 (depends on 1)

The process state monitoring device according to claim 1, wherein the processor is configured to separate the components from the time series data by filtering processing.

### Claim 7 (depends on 1)

The process state monitoring device according to claim 1, wherein the processor is configured to compute, as the characteristic value, at least one of statistics including an average value, a maximum value, a difference value between the maximum value and a minimum value, a standard deviation, a difference value between a front half portion and a rear half portion, an average number of crossings, and a computation value based on the difference value between the maximum value and the minimum value.

### Claim 8 (depends on 1)

The process state monitoring device according to claim 1, wherein the processor is configured to classify the state of the process using a machine learning technique.

### Claim 9 (depends on 1)

The process state monitoring device according to claim claim 1, further comprising a guidance display configured to display
the similarity and the contribution of the operation case, the similarity and the contribution being computed by the processor, and
an action taken in, and an operation state of, the searched operation case.

### Claim 10

A process state monitoring method comprising:
separating two or more components from time series data of a value indicating a state of a process;
computing a characteristic value from each of the separated components;
classifying the state of the process on the basis of the computed characteristic values;
searching a past database for an operation case similar to the process on the basis of the computed characteristic values;
determining a similarity of the computed characteristic values and characteristic values of the operation case on the basis of a distance or an angle, in a variable space composed of a plurality of characteristic values, depending on the number of characteristic values to be compared; and
computing, as a contribution, the component contributing to the similarity.