CN118032365A - PLIF-based hydrogen-doped flame state identification and flameout early warning device and method - Google Patents
PLIF-based hydrogen-doped flame state identification and flameout early warning device and method Download PDFInfo
- Publication number
- CN118032365A CN118032365A CN202410068822.7A CN202410068822A CN118032365A CN 118032365 A CN118032365 A CN 118032365A CN 202410068822 A CN202410068822 A CN 202410068822A CN 118032365 A CN118032365 A CN 118032365A
- Authority
- CN
- China
- Prior art keywords
- flame
- flameout
- plif
- image
- intensity
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 102100020760 Ferritin heavy chain Human genes 0.000 title claims abstract 14
- 101001002987 Homo sapiens Ferritin heavy chain Proteins 0.000 title claims abstract 14
- 238000002485 combustion reaction Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000007493 shaping process Methods 0.000 claims abstract description 16
- 239000007789 gas Substances 0.000 claims description 30
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 13
- 239000001257 hydrogen Substances 0.000 claims description 13
- 229910052739 hydrogen Inorganic materials 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000008033 biological extinction Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 7
- 239000000284 extract Substances 0.000 abstract 1
- 239000000446 fuel Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 125000002887 hydroxy group Chemical group [H]O* 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000009841 combustion method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000013067 intermediate product Substances 0.000 description 1
- 238000001499 laser induced fluorescence spectroscopy Methods 0.000 description 1
- 238000001307 laser spectroscopy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/14—Testing gas-turbine engines or jet-propulsion engines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
Landscapes
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses a PLIF-based hydrogen-doped flame state identification and flameout early warning device and method, wherein the device comprises a laser, a sheet light shaping system, a camera, an image processing board with an embedded FPGA and a register, and an upper computer, wherein the sheet light shaping system performs beam shaping on laser output by the laser to output sheet light beams, the sheet light beams irradiate a combustion chamber of a gas turbine to excite fluorescence, and the camera acquires a real-time flame image in the combustion chamber of the gas turbine; the FPGA carries out binarization on the flame image, extracts the flame intensity and the flame area, recognizes the flame state through a threshold comparison algorithm, judges whether the flame has flameout trend or not, and the register stores flame characteristic data at different moments; and the upper computer displays the flame state identification result in real time. The invention obtains the hydrogen-doped flame image by a non-contact method, does not change the original combustion field structure, and does not introduce external interference to the flame state.
Description
Technical Field
The invention belongs to the technical field of laser spectrum application, and relates to a gas turbine hydrogen-doped flame state identification and flameout early warning device and method based on an OH-PLIF technology.
Background
With the widespread use of hydrogen-loaded fuels, problems with the combustion process are also associated therewith. Since the adiabatic flame temperature of hydrogen is higher than natural gas, localized high temperatures are generated during combustion such that NOx pollutant emissions from a syngas gas turbine are significantly increased over conventional natural gas. In order to suppress the amount of NOx generated in the diffusion flame, the generation of NOx can be reduced by a novel combustion method. The fuel burns more fully at an equivalence ratio of about 1 and at a higher temperature, resulting in an exponential rise in NOx emissions, while combustion at a deviation from normal equivalence ratio can effectively reduce NOx production. Using this principle, lean premixed combustion is an effective method of controlling combustion temperature, reducing NOx production by cutting off the heat path. However, because the equivalence ratio of hydrogen fuel in a gas turbine is difficult to control, the occurrence of equivalence ratio deviations during lean combustion tends to cause the gas turbine to stall, which can adversely affect the safe use of the gas turbine. In the running process of the gas turbine, if flameout can be predicted timely and accurately, the fuel input end is regulated and controlled, and flameout can be avoided. The traditional gas turbine monitoring method mainly utilizes a thermocouple, a pressure sensor and other modes to acquire temperature, pressure and other information of a combustion field, and the methods can change a flow field structure and have hysteresis, so that the method has the advantage of not having rapid and efficient dynamic response in gas turbine state monitoring and flameout early warning.
PLIF (PLANAR LASER-induced fluorescence) technology is a laser spectroscopy-based technology, and is also characterized as non-invasive and is commonly used in the diagnosis of gas turbine flow fields. In the combustion process of hydrogen fuel, OH groups are important intermediate products, the distribution and concentration change condition of the OH groups can be obtained through an OH-PLIF image, the image characteristic representing the combustion state is extracted through an image processing system, so that the heat release rate change of the gas turbine and the oscillation condition of flame are indirectly obtained, the combustion state is accurately and timely identified through a threshold comparison algorithm, and the flameout of the gas turbine is early-warned through capturing flameout characteristics in the monitoring process.
Disclosure of Invention
The invention aims to provide a PLIF-based hydrogen-doped flame state identification and flameout early warning device and method.
The invention aims at realizing the following technical scheme:
a PLIF-based hydrogen-doped flame state identification and flameout early warning device comprises a PLIF measurement module, an image processing module and a display module, wherein:
The PLIF measurement module comprises a laser, a sheet light shaping system and a camera, wherein the laser outputs 283nm laser for exciting OH, the sheet light shaping system is used for carrying out beam shaping on the laser output by the laser, outputting sheet light beams with smaller thickness and uniform energy distribution, the sheet light beams irradiate a combustion chamber of the gas turbine for exciting fluorescence, and the front of the camera is provided with an optical filter for detecting 310nm wave band fluorescence so as to acquire a real-time flame image in the combustion chamber of the gas turbine;
The image processing module comprises an image processing board internally provided with FPGA (Field Programmable GateArray) and a register, the FPGA is used for binarizing a flame image acquired by a camera, extracting flame intensity and flame area, identifying flame state and judging whether flame has flameout trend or not through a threshold comparison algorithm, and the register is used for storing flame characteristic data at different moments;
the display module comprises an upper computer, and the upper computer is used for displaying the identification result of the flame state in real time.
A method for realizing hydrogen-doped flame state identification and flameout early warning by utilizing the device comprises the following steps:
Step one, acquiring a real-time flame image in a combustion chamber of a gas turbine by using a PLIF measurement module;
step two, binarizing the flame image by utilizing an image processing module and calculating the flame area and the flame intensity;
And step three, recognizing the flame state through a threshold comparison algorithm and judging whether the flame has a flameout trend or not.
Compared with the prior art, the invention has the following advantages:
the invention obtains the hydrogen-doped flame image by a non-contact method, does not change the original combustion field structure, and does not introduce external interference to the flame state. The OH-PLIF image can intuitively obtain the spatial distribution information of the groups, the flame state is identified through the threshold comparison algorithm, the response speed of the algorithm is high, real-time identification can be realized, the fastest response time of a single picture is only 25ms, and the quick response capability of the single picture enables the single picture to have the capability of capturing flameout characteristics and realizing flameout early warning.
Drawings
FIG. 1 is a flow chart of a method for identifying and pre-warning a flame condition based on OH-PLIF;
FIG. 2 is a structural frame diagram of an OH-PLIF based hydrogen loading flame condition identification and flameout warning device of the present invention;
FIG. 3 is a layout diagram of an OH-PLIF based hydrogen loading flame condition identification and flameout warning device of the present invention;
FIG. 4 is a flow chart of a threshold comparison algorithm for identifying flame status and determining flameout trend in the present invention;
FIG. 5 is a diagram of an interface between an image processing board and a system component according to the present invention.
Detailed Description
The following description of the present invention is provided with reference to the accompanying drawings, but is not limited to the following description, and any modifications or equivalent substitutions of the present invention should be included in the scope of the present invention without departing from the spirit and scope of the present invention.
The invention provides a PLIF-based gas turbine flame state identification and flameout early warning device, as shown in fig. 2 and 3, comprising a PLIF measurement module, an image processing module and a display module, wherein:
The PLIF measurement module comprises a laser, a sheet light shaping system and a camera, wherein the laser outputs 283nm laser for exciting OH, the sheet light shaping system is used for carrying out beam shaping on the laser output by the laser, outputting sheet light beams with smaller thickness and uniform energy distribution, the sheet light beams irradiate a combustion chamber of the gas turbine for exciting fluorescence, and the front of the camera is provided with an optical filter for detecting 310nm wave band fluorescence so as to acquire a real-time flame image in the combustion chamber of the gas turbine;
the image processing module comprises an image processing board internally provided with FPGA (Field Programmable GateArray) and a register, the FPGA is used for binarizing the PLIF image acquired by the camera, extracting the flame intensity and the flame area, identifying the flame state and judging whether flame has flameout trend or not through a threshold comparison algorithm, and the register is used for storing flame characteristic data at different moments;
the display module comprises an upper computer, and the upper computer is used for displaying the identification result of the flame state in real time.
In the invention, the FPGA model is XC7K325T.
In the invention, the FPGA is connected with the camera through CAMERA LINK wires, the laser is connected through an RS422 serial port, the 5V TTL level synchronous triggering (SMA) laser and the camera are connected, the result is transmitted to the upper computer through CAMERA LINK wires, and the connection diagram of the result and the component is shown in figure 5.
A method for realizing flame state identification and flameout early warning of a gas turbine by using the device is shown in fig. 1, and comprises the following steps:
Step one, acquiring a real-time flame image in a combustion chamber of a gas turbine by using a PLIF measurement module, wherein the method comprises the following specific steps of:
the laser output by the laser outputs a sheet-shaped light beam after being subjected to beam shaping by the sheet-shaped light shaping system, the sheet-shaped light beam irradiates and excites fluorescence to the combustion chamber of the gas turbine, and a camera is utilized to collect a real-time flame image in the combustion chamber of the gas turbine.
Step two, binarizing the flame image by utilizing an image processing module and calculating the flame area S and the flame intensity I, wherein the specific steps are as follows:
step two, transmitting the flame image acquired by the camera to an image processing board in real time;
and step two, the image processing board binarizes the flame image by using a preset threshold value, and the flame area S and the flame intensity I are calculated after binarizing the image.
In the invention, a threshold I th is preset in the image processing board, the threshold is a fixed threshold after pre-training in order to save calculation time, I is the calculated flame intensity, if I is larger than I th, the signal at the pixel is a flame signal, the flame area and intensity of the signal need to be counted, if I is smaller than I th, no signal or the signal at the pixel is background noise, and the flame area and intensity need not be counted. Flame area characteristics are frequently used to represent combustion heat release changes due to well-defined physical implications, and are widely used.
The image processing board is preset with a flame area calculation formula, wherein the flame area calculation formula is as follows:
where n, m are the number of pixels of the image in the horizontal and vertical directions, I ij is the gray value of the pixel in the j-th column of the I-th row, and L (x) is a step function defined as:
The step function utilizes a preset threshold value to binarize the flame image, and the flame area is calculated according to an area calculation formula after binarizing the image.
The flame intensity refers to the gray value average value of the flame area, the light intensity has a definite functional relation with the concentration of free radicals to be detected, and the higher the concentration of the free radicals is, the stronger the spectrum intensity is. The change of the concentration of the chemical reaction product can be indirectly monitored by monitoring the change of the fluorescence intensity, so that a basis is provided for the identification of the combustion state. The image processing board is preset with a flame intensity calculation formula, wherein the flame intensity calculation formula is as follows:
Step three, recognizing the flame state through a threshold comparison algorithm and judging whether the flame has a flameout trend, wherein the specific steps are as follows:
Step three, according to the extracted flame intensity and flame area, the flame state is divided into four types of ignition or extinction, stable combustion, strong combustion and weak combustion, and the specific classification method is as follows:
Thirdly, calculating to obtain the flame intensity I and the flame area S at the moment t, wherein a flame area threshold S th is set in the image processing board, and if the flame area S at the moment is smaller than the threshold S th, the flame is considered to be ignited or extinguished; if the flame area S is larger than or equal to the threshold S th, calculating the flame intensity and the flame area variation value of two adjacent frames;
The three steps are as follows: the image processing board is provided with two constants delta I and delta S with the fluctuation threshold values of the flame intensity and the flame area being larger than zero, the flame intensity I 0 and the flame area S 0 at the last moment (t 0 moment) are read from a register, if I 0-ΔI<I<I0 +delta I is used, the flame is stably burnt, otherwise, the flame area identification state is continuously utilized, if S is larger than or equal to S 0 +delta S, the burning is strong, and if S 0 is larger than or equal to S+delta S, the burning is weak;
Step three, for the flame image with weak combustion, reading the flame intensity of the 9 images before the moment t from a register, calculating the average deviation delta I of the flame intensities of the adjacent ten images, comparing the average deviation delta I with the average deviation delta I 0 preset in an image processing board, if delta I is more than or equal to delta I 0, determining that the flame of the gas turbine has a flameout trend, otherwise, determining that the flame of the gas turbine does not have a flameout trend.
Claims (9)
1. The utility model provides a hydrogen-doped flame state discernment and flameout early warning device based on PLIF, its characterized in that the device includes PLIF measurement module, image processing module and display module, wherein:
The PLIF measurement module comprises a laser, a sheet light shaping system and a camera, wherein the laser outputs 283nm laser for exciting OH, the sheet light shaping system is used for carrying out beam shaping on the laser output by the laser, outputting sheet light beams with smaller thickness and uniform energy distribution, the sheet light beams irradiate a combustion chamber of the gas turbine for exciting fluorescence, and the front of the camera is provided with an optical filter for detecting 310nm wave band fluorescence so as to acquire a real-time flame image in the combustion chamber of the gas turbine;
The image processing module comprises an image processing board with an FPGA and a register, the FPGA is used for binarizing a flame image acquired by a camera, extracting flame intensity and flame area, identifying flame state and judging whether flame has flameout trend or not through a threshold comparison algorithm, and the register is used for storing flame characteristic data at different moments;
the display module comprises an upper computer, and the upper computer is used for displaying the identification result of the flame state in real time.
2. The PLIF-based hydrogen-loaded flame condition identification and flameout pre-warning device of claim 1, wherein the FPGA model is XC7K325T.
3. The PLIF-based hydrogen-loaded flame state recognition and flameout early warning device according to claim 1 or 2, wherein the FPGA is connected to the camera through CAMERA LINK lines, connected to the laser through RS422 serial ports, and the 5V TTL level triggers the laser and the camera synchronously, and transmits the result to the host computer through CAMERA LINK lines.
4. A method for achieving PLIF-based hydrogen loading flame condition identification and flameout pre-warning using the apparatus of any one of claims 1-3, said method comprising the steps of:
Step one, acquiring a real-time flame image in a combustion chamber of a gas turbine by using a PLIF measurement module;
step two, binarizing the flame image by utilizing an image processing module and calculating the flame area and the flame intensity;
And step three, recognizing the flame state through a threshold comparison algorithm and judging whether the flame has a flameout trend or not.
5. The PLIF-based hydrogen-loaded flame condition identification and flameout pre-warning method according to claim 4, wherein the specific steps of said step one are as follows:
the laser output by the laser outputs a sheet-shaped light beam after being subjected to beam shaping by the sheet-shaped light shaping system, the sheet-shaped light beam irradiates and excites fluorescence to the combustion chamber of the gas turbine, and a camera is utilized to collect a real-time flame image in the combustion chamber of the gas turbine.
6. The PLIF-based hydrogen-loaded flame condition identification and flameout pre-warning method of claim 4, wherein the step two comprises the following specific steps:
step two, transmitting the flame image acquired by the camera to an image processing board in real time;
And step two, the image processing board binarizes the flame image by utilizing a preset threshold I th, and the flame area S and the flame intensity I are calculated after binarizing the image.
7. The PLIF-based hydrogen-doped flame condition identification and flameout pre-warning method according to claim 6, wherein in the second step, if I is greater than I th, the signal at the pixel is a flame signal, the flame area and intensity thereof need to be counted, and if I is less than I th, the signal at the pixel is no signal or the signal is background noise, and the flame area and intensity thereof do not need to be counted.
8. The PLIF-based hydrogen-loaded flame condition identification and flameout pre-warning method according to claim 6 or 7, wherein the flame area calculation formula is:
where n, m are the number of pixels of the image in the horizontal and vertical directions, I ij is the gray value of the pixel in the j-th column of the I-th row, and L (x) is a step function defined as:
The flame intensity is calculated by the following formula:
9. The PLIF-based hydrogen-loaded flame condition identification and flameout pre-warning method according to claim 4, wherein the step three comprises the following specific steps:
Step three, according to the extracted flame intensity and flame area, the flame state is divided into four types of ignition or extinction, stable combustion, strong combustion and weak combustion, and the specific classification method is as follows:
Thirdly, calculating to obtain the flame intensity I and the flame area S at the moment t, wherein a flame area threshold S th is set in the image processing board, and if the flame area S at the moment is smaller than the threshold S th, the flame is considered to be ignited or extinguished; if the flame area S is larger than or equal to the threshold S th, calculating the flame intensity and the flame area variation value of two adjacent frames;
The three steps are as follows: the fluctuation threshold values of the flame intensity and the flame area are respectively set as two constants delta I and delta S which are larger than zero, the flame intensity I 0 and the flame area S 0 at the moment t 0 at the last moment are read from a register, if I 0-ΔI<I<I0 +delta I, the flame is stably burnt, otherwise, the flame area identification state is continuously utilized, if S is larger than or equal to S 0 +delta S, the burning is strong, and if S 0 is larger than or equal to S+delta S, the burning is weak;
Step three, for the flame image with weak combustion, reading the flame intensity of the 9 images before the moment t from a register, calculating the average deviation delta I of the flame intensities of the adjacent ten images, comparing the average deviation delta I with the average deviation delta I 0 preset in an image processing board, if delta I is more than or equal to delta I 0, determining that the flame of the gas turbine has a flameout trend, otherwise, determining that the flame of the gas turbine does not have a flameout trend.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410068822.7A CN118032365A (en) | 2024-01-17 | 2024-01-17 | PLIF-based hydrogen-doped flame state identification and flameout early warning device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410068822.7A CN118032365A (en) | 2024-01-17 | 2024-01-17 | PLIF-based hydrogen-doped flame state identification and flameout early warning device and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118032365A true CN118032365A (en) | 2024-05-14 |
Family
ID=90983350
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410068822.7A Pending CN118032365A (en) | 2024-01-17 | 2024-01-17 | PLIF-based hydrogen-doped flame state identification and flameout early warning device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118032365A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104374755A (en) * | 2014-10-23 | 2015-02-25 | 哈尔滨工业大学 | Method for quantitatively measuring transient concentration distribution of OH radicals of turbulent combustion field by utilizing bi-directional optical path-based laser-induced fluorescence imaging technology |
CN105678295A (en) * | 2016-01-04 | 2016-06-15 | 武汉科技大学 | Method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis |
CN109614908A (en) * | 2018-12-04 | 2019-04-12 | 西安理工大学 | A kind of flame combustion state detection system and detection method |
CN116771519A (en) * | 2023-06-20 | 2023-09-19 | 哈尔滨工业大学 | PLIF-based fuel engine equivalence ratio identification and regulation device and method |
CN116977727A (en) * | 2023-07-27 | 2023-10-31 | 上海理工大学 | Image processing-based gas combustion flame real-time monitoring method and system |
CN117315563A (en) * | 2023-08-29 | 2023-12-29 | 浙江工业大学 | Vision-based rapid detection boiler internal flame and control algorithm |
-
2024
- 2024-01-17 CN CN202410068822.7A patent/CN118032365A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104374755A (en) * | 2014-10-23 | 2015-02-25 | 哈尔滨工业大学 | Method for quantitatively measuring transient concentration distribution of OH radicals of turbulent combustion field by utilizing bi-directional optical path-based laser-induced fluorescence imaging technology |
CN105678295A (en) * | 2016-01-04 | 2016-06-15 | 武汉科技大学 | Method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis |
CN109614908A (en) * | 2018-12-04 | 2019-04-12 | 西安理工大学 | A kind of flame combustion state detection system and detection method |
CN116771519A (en) * | 2023-06-20 | 2023-09-19 | 哈尔滨工业大学 | PLIF-based fuel engine equivalence ratio identification and regulation device and method |
CN116977727A (en) * | 2023-07-27 | 2023-10-31 | 上海理工大学 | Image processing-based gas combustion flame real-time monitoring method and system |
CN117315563A (en) * | 2023-08-29 | 2023-12-29 | 浙江工业大学 | Vision-based rapid detection boiler internal flame and control algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109614908A (en) | A kind of flame combustion state detection system and detection method | |
Wang et al. | Pattern recognition for measuring the flame stability of gas-fired combustion based on the image processing technology | |
CN102538000B (en) | Combustion flame diagnostic method | |
CN113390569B (en) | Wide wavelength infrared imaging gas leakage detection system and method based on photo-thermal excitation | |
CN101750152A (en) | Method for representing and diagnosing combustion instability | |
CN103256620A (en) | Multi-information-fusion intelligent flame detecting device and detecting method thereof | |
Gallo et al. | A study of in-cylinder soot oxidation by laser extinction measurements during an EGR-sweep in an optical diesel engine | |
Memon et al. | U-bend evanescent wave plastic optical fibre sensor for minute level concentration detection of ethanol corresponding to biofuel production rate | |
CN118032365A (en) | PLIF-based hydrogen-doped flame state identification and flameout early warning device and method | |
CN110702699B (en) | Rolled glass defect detection device and method | |
Han et al. | A hybrid deep neural network model for NOx emission prediction of heavy oil-fired boiler flames | |
CN113506285A (en) | Boiler furnace three-dimensional temperature field detection method and device and computer equipment | |
Compais et al. | Promoting the valorization of blast furnace gas in the steel industry with the visual monitoring of combustion and artificial intelligence | |
Compais et al. | Detection of slight variations in combustion conditions with machine learning and computer vision | |
CN201440127U (en) | Defect detection device for solar cells and modules | |
CN203489237U (en) | Embedded type flame monitoring and combusting diagnosis system | |
CN117989559A (en) | Method and system for monitoring flame combustion state of heating furnace | |
CN113155844B (en) | Automatic judging device for flame state of burner | |
CN211825761U (en) | Rolled glass defect detection device | |
CN113485262A (en) | SVM-based fault analysis method for fuel system of thermal power plant | |
Xie et al. | Study on statistical invariance of probability processing and fluctuation characteristics of consecutive images of horizontal spray flame under low-pressure | |
Sawicki et al. | Monitoring combustion process using image classification | |
Chen et al. | A novel AI-based combustion diagnostic technology for the identification of chemical source information via flame images: Fuel type and reaction condition | |
CN118090618B (en) | Hydrogen blending combustion tempering detection system and method based on optical fiber sensing | |
CN111586372B (en) | Boiler flame high-temperature intelligent industrial television system with self-warning function |
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 |