# US 2019/0095812 A1 · Automated control of circumferential variability of blast furnace

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

- Number: US 2019/0095812 A1
- Document ID: US20190095812A1
- Status: Published application
- Kind: A1
- Application number: 15/712,255
- Filed: 2017-09-22
- Published: 2019-03-28
- Earliest claimed: 2017-09-22
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Young Min Lee; Kyong Min Yeo
- Web page: https://patentgrep.com/patent/US20190095812A1

## CPC

- G06N 20/00: Machine learning
- C21B 5/006: {Automatically controlling the process}
- C21B 7/00: Blast furnaces
- C21B 7/24: Test rods or other checking devices
- F27B 1/26: Arrangements of controlling devices
- F27D 19/00: Arrangements of controlling devices
- G05B 19/4155: characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- C21B 2300/04: Modeling of the process, e.g. for control purposes; CII
- F27D 2019/0003: {Monitoring the temperature or a characteristic of the charge and using it as a controlling value}
- F27D 2019/0006: {Monitoring the characteristics (composition, quantities, temperature, pressure) of at least one of the gases of the kiln atmosphere and using it as a controlling value}
- F27D 2019/0034: {through control of a heating quantity such as fuel, oxidant or intensity of current}
- G05B 2219/42058: General predictive controller GPC
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- C21B: MANUFACTURE OF IRON OR STEEL (preliminary treatment of ferrous ores or scrap C22B1/00)
- F27B: FURNACES, KILNS, OVENS OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
- F27D: DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- 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)

## Abstract

Controlling circumferential variability in a blast furnace may include generating a predictive model that sets up a relationship between a standard deviation of a selected state variable, state variables and one or more control variables in blast furnace operation for predicting the standard deviation. A number of circumferential sections of the blast furnace is defined, and the predictive model associated with the selected state variable for each of the circumferential sections is trained based on process data of the blast furnace. A plurality trained predictive models is generated associated with different circumferential sections and different selected state variables. One or more future control variable set points that minimize a sum of the plurality of predictive models, is determined. One or more future control variable set points is transmitted to a control system to control the blast furnace operation.

## Claims

### Claim at position 1

-9. (canceled)

### Claim 10

A computer readable storage medium storing a program of instructions executable by a machine to perform a method of controlling circumferential variability in a blast furnace, the method comprising:
generating a predictive model that sets up a relationship between a standard deviation of a selected state variable, state variables and one or more control variables in blast furnace operation for predicting the standard deviation;
defining a number of circumferential sections of the blast furnace;
receiving process data associated with the blast furnace operation;
training the predictive model associated with the selected state variable for each of the circumferential sections based on the process data, wherein a plurality trained predictive models is generated associated with different circumferential sections and different selected state variables, the different selected state variables comprising temperature and pressure;
determining one or more future control variable set points that minimize a sum of the plurality of predictive models that are trained; and
transmitting the one or more future control variable set points to a control system to control the blast furnace operation.

### Claim 11 (depends on 10)

The computer readable storage medium of claim 10, wherein the blast furnace operation is a continuous operation.

### Claim 12 (depends on 10)

The computer readable storage medium of claim 10, wherein the determining one or more future control variable set points that minimize a sum of the plurality of predictive models that are trained, comprises determining one or more future control variable set points that minimize a weighted sum of the plurality of predictive models that are trained.

### Claim 13 (depends on 10)

The computer readable storage medium of claim 10, wherein the one or more future control variable set points comprise control variable set points associated with a plurality of future time points.

### Claim 14 (depends on 10)

The computer readable storage medium of claim 10, wherein the determining one or more future control variable set points that minimize a sum of the plurality of predictive models that are trained and a regularization term that controls value fluctuations of the one or more future control variable set points between future time points.

### Claim 15 (depends on 10)

The computer readable storage medium of claim 10, wherein the state variables include temperature and pressure.

### Claim 16 (depends on 10)

The computer readable storage medium of claim 10, wherein the one or more control variables include one or more of a dumping rate of input material, a flow rate of blast air, moisture content of blast air, an oxygen enrichment amount of blast air, or a flow rate of pulverized coal, or combinations thereof.

### Claim 17 (depends on 10)

The computer readable storage medium of claim 10, wherein the predictive model's relationship between a standard deviation of a selected state variable, state variables and one or more control variables in blast furnace operation defines a future standard deviation value of the selected state variable as a function of past standard deviations of the selected state variable, past values of the state variables, past values of the one or more control variables and future values of the one or more control variables.

### Claim 18 (depends on 10)

The computer readable storage medium of claim 10, wherein the predictive model comprises a deep learning model comprising long short-term memory.

### Claim 19

A system of controlling circumferential variability in a blast furnace, comprising:
at least one hardware processor operable to generate a predictive model that sets up a relationship between a standard deviation of a selected state variable, state variables and one or more control variables in blast furnace operation for predicting the standard deviation, the at least one hardware processor further operable to define a number of circumferential sections of the blast furnace;
a storage device storing process data associated with the blast furnace operation and coupled to the at least one hardware processor;
the at least one hardware processor further operable to receive the process data associated with the blast furnace operation, train the predictive model associated with the selected state variable for each of the circumferential sections based on the process data, wherein a plurality trained predictive models is generated associated with different circumferential sections and different selected state variables, the different selected state variables comprising temperature and pressure, the at least one hardware processor further operable to determine one or more future control variable set points that minimize a sum of the plurality of predictive models that are trained;
the at least one hardware processor coupled to a control system, and operable to transmit the one or more future control variable set points to control the blast furnace operation.

### Claim 20 (depends on 19)

The system of claim 19, wherein the at least one hardware processor determines one or more future control variable set points that minimize a sum of the plurality of predictive models that are trained by determining one or more future control variable set points that minimize a weighted sum of the plurality of predictive models that are trained, wherein a weight is associated with a section of the circumferential sections.
