# US 2026/0086579 A1 · Control factor calculation apparatus and operating method thereof

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

- Number: US 2026/0086579 A1
- Document ID: US20260086579A1
- Status: Published application
- Kind: A1
- Application number: 19/111,163
- Filed: 2023-09-06
- Published: 2026-03-26
- Earliest claimed: 2022-09-15
- Applicants: LG Energy Solution, Ltd.
- Inventors: Dong Min SEO; Wi Dae PARK; Min Su KIM; Jong Seok PARK; Dong Wook PARK; Seol Hee KIM; Eun Ji JO; Suk Yeong YUN; Kyung Ho HAM
- Web page: https://patentgrep.com/patent/US20260086579A1

## CPC

- G05D 7/0623: {characterised by the set value given to the control element}
- G06N 3/08: Learning methods
- G05B 13/027: {using neural networks only}
- G05B 13/04: involving the use of models or simulators
- G05D 7/0676: {by action on flow sources (G05D7/0688, G05D7/0694 take precedence)}
- G06N 20/00: Machine learning
- H01M 4/0404: {by coating on electrode collectors}
- H01M 4/0407: {by coating on an electrolyte layer}
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- 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)
- H01M: PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY

## Abstract

A control factor calculation apparatus according to an embodiment disclosed herein includes a data obtaining unit configured to periodically obtain data including a slurry loading amount and a slurry flow rate and a processor configured to learn a correlation between the slurry loading amount and the slurry flow rate based on the data, and calculate a slurry flow rate control value for achieving a target slurry loading amount based on the correlation.

## Claims

### Claim 1

A control factor calculation apparatus comprising:
a data obtaining unit configured to periodically obtain data comprising a slurry loading amount and a slurry flow rate; and
a processor configured to:
learn a correlation between the slurry loading amount and the slurry flow rate based on the data; and
calculate a slurry flow rate control value for achieving a target slurry loading amount based on the correlation.

### Claim 2 (depends on 1)

The control factor calculation apparatus of claim 1, wherein the processor is further configured to:
learn a first correlation between first data comprising a first slurry loading amount for a first period of N and a slurry flow rate for a second period of (N+1) and second data comprising the second slurry loading amount for the second period of (N+1); and
calculate the slurry flow rate control value based on the first correlation.

### Claim 3 (depends on 2)

The control factor calculation apparatus of claim 2, wherein the processor is further configured to calculate the slurry flow rate control value based on the second slurry loading amount for the second period of (N+2) corresponding to the target slurry loading amount, and the first correlation.

### Claim 4 (depends on 2)

The control factor calculation apparatus of claim 2, wherein:
the data further comprises a slurry pump revolution per minute (RPM), and
the processor is further configured to:
learn a second correlation between slurry flow rate change data associated with a period change and slurry pump RPM change data; and
calculate a slurry pump RPM control value for achieving the flow rate control value based on the second correlation.

### Claim 5 (depends on 1)

The control factor calculation apparatus of claim 1, wherein the data further comprises a gap between a slurry discharging device and a base material.

### Claim 6 (depends on 1)

The control factor calculation apparatus of claim 1, wherein the processor is further configured to learn the correlation based on a machine learning model or a deep learning model.

### Claim 7

A control factor calculation method comprising:
periodically obtaining data comprising a slurry loading amount and a slurry flow rate;
learning a correlation between the slurry loading amount and the slurry flow rate based on the data; and
calculating a slurry flow rate control value for achieving a target slurry loading amount based on the correlation.

### Claim 8 (depends on 7)

The control factor calculation method of claim 7, wherein:
learning the correlation comprises learning a first correlation between first data comprising a first slurry loading amount for a first period of N and a slurry flow rate for a second period of (N+1) and second data comprising the second slurry loading amount for the second period of (N+1), and
calculating the slurry flow rate control value comprises calculating the slurry flow rate control value based on the first correlation.

### Claim 9 (depends on 8)

The control factor calculation method of claim 8, wherein calculating of the slurry flow rate control value comprises calculating the slurry flow rate control value based on the second slurry loading amount for the second period of (N+2) corresponding to the target slurry loading amount, and the first correlation.

### Claim 10 (depends on 8)

The control factor calculation method of claim 8, wherein:
the data further comprises a slurry pump revolution per minute (RPM), and
learning the correlation comprises learning a second correlation between slurry flow rate change data associated with a period change and slurry pump RPM change data, and
calculating a slurry pump RPM control value for achieving the flow rate control value, based on the second correlation.

### Claim 11 (depends on 7)

The control factor calculation method of claim 7, wherein the data further comprises a gap between a slurry discharging device and a base material.

### Claim 12 (depends on 7)

The control factor calculation method of claim 7, wherein learning the correlation comprises learning the correlation based on a machine learning model or a deep learning model.
