CN111369474B - Visual identification method for detecting flame of ladle baking device - Google Patents
Visual identification method for detecting flame of ladle baking device Download PDFInfo
- Publication number
- CN111369474B CN111369474B CN202010223678.1A CN202010223678A CN111369474B CN 111369474 B CN111369474 B CN 111369474B CN 202010223678 A CN202010223678 A CN 202010223678A CN 111369474 B CN111369474 B CN 111369474B
- Authority
- CN
- China
- Prior art keywords
- flame
- contour
- array
- current frame
- queue
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000000007 visual effect Effects 0.000 title claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000002485 combustion reaction Methods 0.000 claims description 13
- 238000003491 array Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 2
- 238000009847 ladle furnace Methods 0.000 claims 1
- 230000006378 damage Effects 0.000 abstract description 2
- 238000009434 installation Methods 0.000 abstract description 2
- 230000003647 oxidation Effects 0.000 abstract description 2
- 238000007254 oxidation reaction Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22D—CASTING OF METALS; CASTING OF OTHER SUBSTANCES BY THE SAME PROCESSES OR DEVICES
- B22D41/00—Casting melt-holding vessels, e.g. ladles, tundishes, cups or the like
- B22D41/005—Casting melt-holding vessels, e.g. ladles, tundishes, cups or the like with heating or cooling means
- B22D41/01—Heating means
- B22D41/015—Heating means with external heating, i.e. the heat source not being a part of the ladle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention is used for the visual recognition method of the ladle baking device flame detection, collect the flame image data of the current frame at first; performing high-brightness contour calculation on the acquired flame image data of the current frame to obtain a flame contour array; then, calculating the contour similarity of the flame contour array of the current frame and the flame contour array calculated by the previous frame; and finally, carrying out similarity calculation result processing. The method is adopted to ensure that the instrument is not in direct contact with flame, so that the damage factors such as high temperature, high impact, chemical oxidation and the like of industrial flame cannot influence the instrument; and the instrument is simple and convenient to install, the installation mode is consistent, and the field process structure is not changed.
Description
Technical Field
The invention belongs to the technical field of embedded visual identification, in particular to a method for detecting flame of a ladle baking device in the metallurgical industry, which adopts a visual identification technology to judge the flame combustion state.
Background
The ladle baking device is main production equipment in the metallurgical production process and is used for baking the ladle, long-time continuous operation is required, the flame state (burning/extinguishing) of the ladle baking device directly influences the production rhythm and the production safety, and the flame detection device is a key component part in a ladle baking device control system.
The existing visual identification method for detecting the flame of the ladle baking device adopts temperature difference detection or plasma detection as the basis for judging the flame state, the two detection methods need to be in close contact with the flame, the detection element is easy to fail, and the maintenance workload is large.
Disclosure of Invention
Aiming at the problems, the invention provides a visual identification method for detecting the flame of a ladle baking device, which judges the flame state through the video stream shot by a camera.
The invention discloses a visual identification method for detecting flame of a ladle baking device, which comprises the following specific steps:
Step 1: and acquiring flame image data of the current frame.
Step 2: and (3) performing high-brightness contour calculation on the flame image data of the current frame acquired in the step (1) to obtain a flame contour array.
Step 3: and calculating the contour similarity of the flame contour array of the current frame and the flame contour array calculated in the previous frame.
Step 4: and (5) processing a similarity calculation result.
Storing the similarity calculation result obtained in the step3 into a queue, and when the record length of the queue reaches 24, replacing the oldest data by new data to keep the length of the queue to be 24; when the queue record reaches the length 24, each time a new similarity calculation result data is stored, the flame state is judged according to the following method:
a. judging whether the current flame is in a burning state or not; if the combustion state is the combustion state, performing the step b; otherwise, step c is performed.
B. If the number of the similarity calculation result data which is larger than the threshold value a in the queue is smaller than 7, the obvious contour jitter is not found in the past 24 similarity judgments, so that the current state is turned off; otherwise, the combustion state is maintained.
C. If the number of the similarity calculation result data which is larger than a is more than 16 in the queue, changing the current state into combustion; otherwise, the extinguishing state is maintained.
The invention has the advantages that:
1. The visual identification method for detecting the flame of the ladle baking device is adopted to ensure that the instrument is not in direct contact with the flame, so that the instrument cannot be influenced by the destruction factors such as high temperature, high impact, chemical oxidation and the like of industrial flame.
2. The visual identification method for detecting the flame of the ladle baking device is adopted to enable the instrument to be installed simply and conveniently, and meanwhile, the installation mode is consistent, and the on-site process structure is not changed.
Drawings
FIG. 1 is a flow chart of a visual identification method for detecting the flame of a ladle baking device according to the invention;
FIG. 2 is a flow chart of the high brightness profile calculation of the present invention;
FIG. 3 is a flow chart of flame status determination according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings.
The ladle baking device flame is in an open space, and has more peripheral visual interference factors such as sunlight, travelling shadows, high-temperature ladles and the like, but the ladle baking device flame has a characteristic which is obviously different from environmental interference, namely high-frequency contour shaking, because the gas pressure is higher, the flame is in a jet shape, and the contour of the flame rapidly shakes at a frequency of more than 30 Hz.
The invention judges the flame state (burning/extinguishing) based on the flame characteristics of the ladle baking device, as shown in fig. 1, the specific steps are as follows:
step 1: and (5) flame video image data acquisition.
And shooting a flame video by adopting a camera to obtain flame image data of the current frame, and transmitting the flame image data into the recognition main board in a YUY2 format to serve as an input signal of a flame recognition module running on the recognition main board.
Step 2: high brightness profile calculation as shown in fig. 2.
A. And (3) performing Gaussian filtering on the flame video image data stream of the current frame acquired in the step (1) to remove camera noise, so that a detection result is more stable.
B. and (3) performing binarization processing on the filtered data to convert the color image into a black-and-white image with only 0 and 1 values. The binarization processing adopts a fixed threshold value, and the fixed threshold value is set by a field engineer during debugging.
C. and c, taking the image subjected to binarization processing in the step b as input, and calculating a flame profile array by adopting a [ Suzuki85] profile tracking algorithm.
Step 3: and calculating the contour similarity.
Taking the flame profile array of the current frame and the flame profile array calculated in the previous frame as inputs, and directly outputting 0 if null values exist in the flame profile array and the flame profile array (the arrays are not assigned).
Otherwise, the following procedure is performed:
First, i hu moments of the two flame profile arrays A and B are calculated Wherein i=1, 2, 3, … …, 7.
Then, the similarity of two flame profile arrays is calculated, and the formula is as follows:
Where I (a, B) is the result of similarity calculation between the flame profile arrays a and B, and a value of 0 indicates that the two profiles are identical, and a larger value indicates a larger profile difference.
Step 4: similarity calculation result processing
And (3) saving the similarity calculation result obtained in the step (3) to a queue, and when the record length of the queue reaches 24, replacing the oldest data by new data to keep the length of the queue at 24. When the queue record reaches the length 24, each time a new similarity calculation result data is stored, the flame state is judged as follows, as shown in fig. 3:
a. judging whether the current flame is in a burning state or not; if the combustion state is the combustion state, performing the step b; otherwise, step c is performed.
B. If the number of similarity calculation result data in the queue is less than 7, which means that no obvious contour jitter is found in the past 24 similarity judgments, the current state is changed to be extinguished. Otherwise, the combustion state is maintained. The value range of the threshold value a is 0.1-0.6, and the threshold value a can be modified according to actual conditions by a field engineer, and the value of the threshold value a is 0.2 in the invention.
C. If the number of similarity calculation result data greater than a in the queue is more than 16, this means that in the past 24 similarity judgments, a significant contour jitter is found, and thus the current state is changed to combustion. Otherwise, the extinguishing state is maintained.
Claims (2)
1. The visual identification method for detecting the flame of the ladle baking device is characterized by comprising the following steps of: the method comprises the following specific steps:
Step 1: acquiring flame image data of a current frame;
Step 2: performing high-brightness contour calculation on the flame image data of the current frame acquired in the step 1 to obtain a flame contour array;
a. Carrying out Gaussian filtering on the flame video image data stream of the current frame acquired in the step 1;
b. Performing binarization processing on the filtered data;
c. B, taking the image subjected to binarization in the step b as input, and calculating a flame profile array by adopting a [ Suzuki85] profile tracking algorithm;
Step 3: performing contour similarity calculation on the flame contour array of the current frame and the flame contour array calculated in the previous frame;
Step 4: similarity calculation result processing;
storing the similarity calculation result obtained in the step3 into a queue, and when the record length of the queue reaches 24, replacing the oldest data by new data to keep the length of the queue to be 24; when the queue record reaches the length 24, each time a new similarity calculation result data is stored, the flame state is judged according to the following method:
a. judging whether the current flame is in a burning state or not; if the combustion state is the combustion state, performing the step b; otherwise, carrying out the step c;
b. If the number of the similarity calculation result data which is larger than the threshold value a in the queue is smaller than 7, the obvious contour jitter is not found in the past 24 similarity judgments, so that the current state is turned off; otherwise, maintaining the combustion state;
c. If the number of the similarity calculation result data which is larger than a is more than 16 in the queue, changing the current state into combustion; otherwise, the extinguishing state is maintained.
2. The visual identification method for ladle furnace flame detection as recited in claim 1 wherein: the specific method for calculating the contour similarity in the step 3 is as follows:
Taking the flame profile array of the current frame and the flame profile array calculated in the previous frame as inputs, and directly outputting 0 if null values exist in the flame profile array of the current frame and the flame profile array calculated in the previous frame;
Otherwise, the following procedure is performed:
First, i hu moments of the two flame profile arrays A and B are calculated Wherein i=1, 2, 3, … …, 7;
then, the similarity of two flame profile arrays is calculated, and the formula is as follows:
Where I (a, B) is the result of similarity calculation between the flame profile arrays a and B, and a value of 0 indicates that the two profiles are identical, and a larger value indicates a larger profile difference.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010223678.1A CN111369474B (en) | 2020-03-26 | 2020-03-26 | Visual identification method for detecting flame of ladle baking device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010223678.1A CN111369474B (en) | 2020-03-26 | 2020-03-26 | Visual identification method for detecting flame of ladle baking device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111369474A CN111369474A (en) | 2020-07-03 |
CN111369474B true CN111369474B (en) | 2024-04-19 |
Family
ID=71209188
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010223678.1A Active CN111369474B (en) | 2020-03-26 | 2020-03-26 | Visual identification method for detecting flame of ladle baking device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111369474B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010230232A (en) * | 2009-03-26 | 2010-10-14 | Tokyo Electric Power Co Inc:The | Flame detection system |
CN101930541A (en) * | 2010-09-08 | 2010-12-29 | 大连古野软件有限公司 | Video-based flame detecting device and method |
CN107633212A (en) * | 2017-08-30 | 2018-01-26 | 清华大学苏州汽车研究院(吴江) | A kind of firework detecting method and device based on video image |
-
2020
- 2020-03-26 CN CN202010223678.1A patent/CN111369474B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010230232A (en) * | 2009-03-26 | 2010-10-14 | Tokyo Electric Power Co Inc:The | Flame detection system |
CN101930541A (en) * | 2010-09-08 | 2010-12-29 | 大连古野软件有限公司 | Video-based flame detecting device and method |
CN107633212A (en) * | 2017-08-30 | 2018-01-26 | 清华大学苏州汽车研究院(吴江) | A kind of firework detecting method and device based on video image |
Non-Patent Citations (2)
Title |
---|
严云洋 等.融合色彩和轮廓特征的火焰检测.《微电子学与计算机》.2011,第28卷(第10期),第137-141,145页. * |
王江安 等.基于队列流水线的弱点目标轨迹跟踪算法.《光电工程》.2007,第34卷(第9期),第1-4,9页. * |
Also Published As
Publication number | Publication date |
---|---|
CN111369474A (en) | 2020-07-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4705090B2 (en) | Smoke sensing device and method | |
US10151006B2 (en) | Method of detecting abnormality at blast furnace and method of operating blast furnace | |
CN102881106B (en) | Dual-detection forest fire identification system through thermal imaging video and identification method thereof | |
CN108399359B (en) | Real-time fire detection early warning method under video sequence | |
CN101908142A (en) | Feature analysis-based video flame detecting method | |
CN103324910A (en) | Fire alarming method based on video detection | |
CN111369474B (en) | Visual identification method for detecting flame of ladle baking device | |
CN107729913A (en) | A kind of boiler furnace Situation Awareness method based on multiple features fusion cluster | |
CN109035676A (en) | The flame detecting recognition methods of low operand | |
KR101044903B1 (en) | Fire detecting method using hidden markov models in video surveillance and monitoring system | |
JP4930612B2 (en) | Combustion state detection device for internal combustion engine | |
CN108830161A (en) | Smog recognition methods based on video stream data | |
CN117373196B (en) | Electrical fire alarm method and system | |
CN112070072B (en) | Prefabricated cabin fire control system based on image recognition and control method thereof | |
CN112067239A (en) | Method for automatically judging establishment of supersonic wind tunnel flow field based on schlieren video | |
CN111429434B (en) | Visual identification method for detecting flame of alloy furnace | |
JP5935828B2 (en) | Unmelted ore detection method and blast furnace operation method | |
Chen et al. | Flame recognition in video images with color and dynamic features of flames | |
CN213920843U (en) | Intelligent driving behavior detection safety auxiliary system | |
CN112396101A (en) | Intelligent image analysis and decision-making method based on firepower plant hearth flame television | |
CN110097735A (en) | A kind of cable production safety method for early warning and system | |
KR101017410B1 (en) | Apparatus and method for Tunnel fire detection based on image processing | |
CN202795630U (en) | Thermal imagery video double-identification forest fire recognition system | |
CN103956016B (en) | A kind of smog flame combined type automatic testing method based on video image | |
WO2024111237A1 (en) | Smoke monitoring system, gas fluctuation monitoring system, smoke monitoring method, gas fluctuation monitoring method, smoke monitoring program, and gas fluctuation monitoring program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |