# US 2013/0155227 A1 · Computer vision-based valve control system and method

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

- Number: US 2013/0155227 A1
- Document ID: US20130155227A1
- Status: Published application
- Kind: A1
- Application number: 13/332,001
- Filed: 2011-12-20
- Published: 2013-06-20
- Earliest claimed: 2011-12-20
- Assignees: King Fahd University of Petroleum and Minerals
- Inventors: SAMI EL FERIK; MUSTAFA EL-SHAFEI; MOHAMMAD SHAQURA; ATEF BOUCHRIT
- Web page: https://patentgrep.com/patent/US20130155227A1

## CPC

- G01B 11/00: Measuring arrangements characterised by the use of optical techniques
- G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS

## Abstract

The computer vision-based valve control system and method includes a camera mounted on a pneumatic control valve in such a way that the camera periodically observes positioning of the valve stem. An image processor is applied to the output of the camera to determine percentage opening of the valve. The valve opening percentage of the image processor is fed to a PID controller that uses the valve opening percentage in its process control calculations.

## Claims

### Claim 1

A computer vision-based valve control system, comprising:
a camera having a lens, the camera producing a video output;
a valve having an actuator stem, the camera being mounted on a stationary portion of the valve with the lens oriented to observe positioning of the valve actuator stem;
an image processor including a controller, the video output of the camera being connected to the image processor, the image processor having means for processing the video output to determine percentage opening of the valve from images of the valve actuator stem and means for communicating the percentage opening of the valve to the controller, the controller having means for generating a control signal for opening and closing the valve in response to the percentage opening of the valve; and
means for receiving the control signal and for opening and closing the valve in response to the control signal;
whereby the camera functions as a feedback element in a closed loop control circuit for opening and closing the valve.

### Claim 2 (depends on 1)

The computer vision-based valve control system according to claim 1, further comprising a plurality of light emitting diodes mounted on camera in concentric relation to the lens, the light emitting diodes uniformly illuminating an aiming point on the valve stem.

### Claim 3 (depends on 1)

The computer vision-based valve control system according to claim 1, further comprising a substantially opaque cap surrounding said valve actuator stem, the cap isolating said valve actuator stem from variations of ambient light intensity, the cap having a hole formed therein, said camera being inserted through the hole in the cap for unimpeded line-of-sight to said valve actuator stem.

### Claim 4 (depends on 1)

The computer vision-based valve control system according to claim 1, wherein said camera further comprises a USB port for connection of the camera video output to said image processor.

### Claim 5 (depends on 1)

The computer vision-based valve control system according to claim 1, wherein said means for processing the video output to determine percentage opening of the valve further comprises means for detection of positioning and motion of an edge of a reference body directly connected to said valve actuator stem, the positioning and motion of the reference body edge being linearly related to the percentage opening of the valve according to the relation:
Percentage opening=C1*Pixel position−C2,
wherein Pixel position represents the edge positioning relative to a field of view of said camera, and C1 and C2 are constants determined by calibration of said valve control system.

### Claim 6 (depends on 5)

The computer vision-based valve control system according to claim 5, further comprising means for automatically calibrating said camera.

### Claim 7 (depends on 5)

The computer vision-based valve control system according to claim 5, further comprising means for adaptively processing images of said valve stem in the field of view of said camera according to light intensity proximate said valve actuator stem.

### Claim 8

A computer implemented computer vision-based valve control method, comprising the steps of:
transmitting video frames from a camera positioned to make observations of a valve stem position;
receiving the video frames for image processing of the camera observations;
image processing the video frames to determine percentage opening of the valve based on the valve stem position;
outputting the percentage opening to a process controller input; and
sending a process controller signal control opening and closing the valve based on the percentage opening of the valve determined in the image processing step.

### Claim 9 (depends on 8)

The computer implemented valve control method according to claim 8, further comprising the step of illuminating a region of interest including said valve stem, thereby facilitating details of said valve stem position observations transmitted via said video frames.

### Claim 10 (depends on 8)

The computer implemented valve control method according to claim 8, wherein said image processing step further comprises the step of detecting positioning and motion of an edge of a reference body on said valve stem, the positioning and motion of the reference body edge being linearly related to percentage opening of the valve according to the relation:
Percentage opening=C1*Pixel position−C2,
where Pixel position represents edge positioning relative to a field of view of said camera, and C1 and C2 are constants determined by calibration of said camera.

### Claim 11 (depends on 10)

The computer implemented valve control method according to claim 10, wherein said calibration comprises the step of automatically calibrating said camera.

### Claim 12 (depends on 10)

The computer implemented valve control method according to claim 10, further comprising the step of adaptively processing images of said valve stem in the field of view of said camera according to light intensity proximate said valve actuator stem.

### Claim 13

A computer software product, comprising a medium readable by a processor, the medium having stored thereon a set of instructions for computer vision-based valve control in a process control system, the set of instructions including:
(a) a first sequence of instructions which, when executed by the processor, causes said processor to initiate transmission of video frames from a camera positioned to make observations of a valve stem position;
(b) a second sequence of instructions which, when executed by the processor, causes said processor to receive said video frames for image processing of said camera observations;
(c) a third sequence of instructions which, when executed by the processor, causes said processor to perform image processing on said video frames to determine % open information of said valve based on said valve stem position;
(d) a fourth sequence of instructions which, when executed by the processor, causes said processor to output said % open information to a process controller input; and
wherein said process controller utilizes said % open information to output control signals to said valve.

### Claim 14 (depends on 13)

The computer software product according to claim 13, further comprising a fifth sequence of instructions which, when executed by the processor, causes said processor to activate a source of illumination trained on said valve stem thereby illuminating a region of interest including said valve stem to facilitate details of said valve stem position observations transmitted via said video frames.

### Claim 15 (depends on 13)

The computer software product according to claim 13, further comprising a sixth sequence of instructions which, when executed by the processor, causes said processor to detect positioning and motion of an edge of a reference body on said valve stem, said positioning and motion of said reference body edge being linearly related to said valve open percent according to the relation:
Percentage opening=C1*Pixel position−C2,
where Pixel position represents edge positioning relative to a field of view of said camera, and C1 and C2 are constants determined by calibration of said process control system.

### Claim 16 (depends on 15)

The computer software product according to claim 15, further comprising a seventh sequence of instructions which, when executed by the processor, causes said processor to automatically calibrate said camera to derive said open percent relation including substitution of real valued numbers for said C1 and C2 constants.

### Claim 17 (depends on 15)

The computer software product according to claim 15, further comprising an eighth sequence of instructions which, when executed by the processor, causes said processor to adaptively process images of said valve stem in said field of view of said camera according to light intensity proximate said valve actuator stem.
