# US 2025/0036120 A1 · Method, System, and Computer Program Product for Automatic Tweel Control in Molten Glass Manufacturing

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

- Number: US 2025/0036120 A1
- Document ID: US20250036120A1
- Status: Published application
- Kind: A1
- Application number: 18/783,647
- Filed: 2024-07-25
- Published: 2025-01-30
- Earliest claimed: 2023-07-28
- Assignees: Vitro Flat Glass LLC
- Applicants: Vitro Flat Glass LLC
- Inventors: Wei Xu; Alan Dum; Priyadarshi Mahapatra; Russell W. Schrier; Yu Jiao
- Web page: https://patentgrep.com/patent/US20250036120A1

## CPC

- G05B 23/0289: {Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection}
- C03B 5/24: Automatically regulating the melting process
- C03B 18/02: Forming sheets
- C03B 18/04: Changing or regulating the dimensions of the molten glass ribbon
- C03B 18/10: using electric means
- C03B 18/18: Controlling or regulating the temperature of the float bath; Composition or purification of the float bath
- G05B 23/027: {Alarm generation, e.g. communication protocol; Forms of alarm}
- G05B 23/0275: {Fault isolation and identification, e.g. classify fault; estimate cause or root of failure}
- G06T 7/0006: {using a design-rule based approach}
- G06T 7/0008: {checking presence/absence}
- G06T 7/13: Edge detection
- G06T 7/62: of area, perimeter, diameter or volume
- G06T 2207/30108: Industrial image inspection
- 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)
- C03B: MANUFACTURE, SHAPING, OR SUPPLEMENTARY PROCESSES
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems, methods, and computer program products are provided for automatic tweel control in molten glass manufacturing. An example system includes a processor configured to receive visual data from a camera positioned with a view of a molten glass flow that is spreading from a melting tank into a bath containing molten metal, wherein a flow rate of the molten glass flow is controlled by a tweel. The processor is also configured to process the visual data to determine a value of a dimension of the molten glass flow. The processor is further configured to, in response to the value of the dimension of the molten glass flow satisfying a predetermined threshold value, generate a first control pulse signal to the tweel, wherein the first control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, with at least one processor, visual data from at least one camera positioned with a view of a molten glass flow that is spreading from a melting tank into a bath containing molten metal, wherein a flow rate of the molten glass flow is controlled by a tweel associated with the bath;
processing, with at least one processor, the visual data to determine a value of at least one dimension of the molten glass flow; and
in response to the value of the at least one dimension of the molten glass flow satisfying at least one predetermined threshold value, generating, with at least one processor, at least one first control pulse signal to the tweel, wherein the at least one first control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising repeatedly executing, with at least one processor, for a duration of a glass manufacturing float line process:
receiving new visual data from the at least one camera;
processing the new visual data to determine a new value of the at least one dimension of the molten glass flow; and
in response to the new value of the at least one dimension of the molten glass flow satisfying the at least one predetermined threshold value, generating, with at least one processor, a new control pulse signal to the tweel, wherein the new control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising, before processing the visual data to determine the value of the at least one dimension of the molten glass flow:
determining, with at least one processor, a heat output of a heat source associated with the melting tank; and
adjusting, with at least one processor, at least one parameter of the visual data based on the heat output of the heat source, the at least one parameter selected from the group of: exposure; gain; and position.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
detecting, with at least one processor, a process anomaly based at least partly on the processing of the visual data; and
in response to detecting the process anomaly, activating, with at least one processor, an alarm to signal to an operator to respond to the process anomaly.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein the process anomaly comprises a presence of debris in a manufacturing area containing the molten glass flow, and wherein detecting the process anomaly based at least partly on the processing of the visual data comprises:
detecting, with at least one processor, the presence of the debris in a field of view of the at least one camera during the processing of the visual data.

### Claim 6 (depends on 4)

The computer-implemented method of claim 4, wherein the process anomaly comprises an equipment failure, and wherein detecting the process anomaly based at least partly on the processing of the visual data comprises:
comparing the value of the at least one dimension of the molten glass flow to at least one expected value of the molten glass flow, wherein the at least one expected value of the molten glass flow is associated with a prior control pulse signal sent to the tweel; and
detecting the equipment failure based on a difference between the value of the at least one dimension of the molten glass flow and the at least one expected value of the molten glass flow.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, further comprising, in response to detecting the equipment failure, changing a control mode of the tweel from an automatic mode to a semi-automatic mode or a manual mode.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one dimension is a maximum width of the molten glass flow, and wherein processing the visual data to determine the value of at least one dimension of the molten glass flow further comprises:
converting the visual data from color to grayscale;
executing an edge detection process to identify a first edge of the molten glass flow and a second edge of the molten glass flow from the visual data, wherein the first edge is opposite the second edge; and
calculating the maximum width between the first edge and the second edge.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein executing the edge detection process further comprises:
receiving an input of at least one user-defined search line; and
procedurally searching along the at least one user-defined search line until the first edge and the second edge are identified.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising determining a length of the at least one first control pulse signal that is generated based on a difference between the value of the at least one dimension of the molten glass flow and the at least one predetermined threshold value.

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, further comprising determining a number of pulse signals of the at least one first control pulse signal that are generated based on a difference between the value of the at least one dimension of the molten glass flow and the at least one predetermined threshold value.

### Claim 12

A system comprising:
at least one processor configured to:
receive visual data from at least one camera positioned with a view of a molten glass flow that is spreading from a melting tank into a bath containing molten metal, wherein a flow rate of the molten glass flow is controlled by a tweel associated with the bath;
process the visual data to determine a value of at least one dimension of the molten glass flow; and
in response to the value of the at least one dimension of the molten glass flow satisfying at least one predetermined threshold value, generate at least one first control pulse signal to the tweel, wherein the at least one first control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

### Claim 13 (depends on 12)

The system of claim 12, wherein the at least one processor is further configured to repeatedly execute for a duration of a glass manufacturing float line process:
receive new visual data from the at least one camera;
process the new visual data to determine a new value of the at least one dimension of the molten glass flow; and
in response to the new value of the at least one dimension of the molten glass flow satisfying the at least one predetermined threshold value, generate a new control pulse signal to the tweel, wherein the new control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

### Claim 14 (depends on 12)

The system of claim 12, wherein the at least one dimension is a maximum width of the molten glass flow, and wherein, when processing the visual data to determine the value of at least one dimension of the molten glass flow, the at least one processor is configured to:
convert the visual data from color to grayscale;
execute an edge detection process to identify a first edge of the molten glass flow and a second edge of the molten glass flow from the visual data, wherein the first edge is opposite the second edge; and
calculate the maximum width between the first edge and the second edge.

### Claim 15 (depends on 12)

The system of claim 12, wherein the at least one processor is further configured to determine a length of the at least one first control pulse signal that is generated based on a difference between the value of the at least one dimension of the molten glass flow and the at least one predetermined threshold value.

### Claim 16 (depends on 12)

The system of claim 12, wherein the at least one processor is further configured to determine a number of pulse signals of the at least one first control pulse signal that are generated based on a difference between the value of the at least one dimension of the molten glass flow and the at least one predetermined threshold value.

### Claim 17

A computer program product comprising at least one non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to:
receive visual data from at least one camera positioned with a view of a molten glass flow that is spreading from a melting tank into a bath containing molten metal, wherein a flow rate of the molten glass flow is controlled by a tweel associated with the bath;
process the visual data to determine a value of at least one dimension of the molten glass flow; and
in response to the value of the at least one dimension of the molten glass flow satisfying at least one predetermined threshold value, generate at least one first control pulse signal to the tweel, wherein the at least one first control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the program instructions further cause the at least one processor to repeatedly execute for a duration of a glass manufacturing float line process:
receive new visual data from the at least one camera;
process the new visual data to determine a new value of the at least one dimension of the molten glass flow; and
in response to the new value of the at least one dimension of the molten glass flow satisfying the at least one predetermined threshold value, generate a new control pulse signal to the tweel, wherein the new control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

### Claim 19 (depends on 17)

The computer program product of claim 17, wherein the program instructions further cause the at least one processor to determine a length of the at least one first control pulse signal that is generated based on a difference between the value of the at least one dimension of the molten glass flow and the at least one predetermined threshold value.

### Claim 20 (depends on 17)

The computer program product of claim 17, wherein the program instructions further cause the at least one processor to determine a number of pulse signals of the at least one first control pulse signal that are generated based on a difference between the value of the at least one dimension of the molten glass flow and the at least one predetermined threshold value.
