CN118190887A - Aviation kerosene detection method with fluorescence spectrum and vision fused - Google Patents
Aviation kerosene detection method with fluorescence spectrum and vision fused Download PDFInfo
- Publication number
- CN118190887A CN118190887A CN202410293541.1A CN202410293541A CN118190887A CN 118190887 A CN118190887 A CN 118190887A CN 202410293541 A CN202410293541 A CN 202410293541A CN 118190887 A CN118190887 A CN 118190887A
- Authority
- CN
- China
- Prior art keywords
- detection
- spectrum
- fluorescence
- detection system
- aviation kerosene
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 187
- 239000003350 kerosene Substances 0.000 title claims abstract description 52
- 238000002189 fluorescence spectrum Methods 0.000 title claims abstract description 39
- 238000001228 spectrum Methods 0.000 claims abstract description 69
- 238000013528 artificial neural network Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims description 19
- 238000007689 inspection Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 4
- 238000004445 quantitative analysis Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000001069 Raman spectroscopy Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 239000005416 organic matter Substances 0.000 claims description 3
- 238000004451 qualitative analysis Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 abstract 1
- 239000003921 oil Substances 0.000 description 42
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 239000002480 mineral oil Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 239000010779 crude oil Substances 0.000 description 3
- 239000003344 environmental pollutant Substances 0.000 description 3
- 238000001917 fluorescence detection Methods 0.000 description 3
- 235000010446 mineral oil Nutrition 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 231100000719 pollutant Toxicity 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- UFWIBTONFRDIAS-UHFFFAOYSA-N Naphthalene Chemical compound C1=CC=CC2=CC=CC=C21 UFWIBTONFRDIAS-UHFFFAOYSA-N 0.000 description 2
- MWPLVEDNUUSJAV-UHFFFAOYSA-N anthracene Chemical compound C1=CC=CC2=CC3=CC=CC=C3C=C21 MWPLVEDNUUSJAV-UHFFFAOYSA-N 0.000 description 2
- 230000005494 condensation Effects 0.000 description 2
- 238000009833 condensation Methods 0.000 description 2
- 239000000295 fuel oil Substances 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000003973 paint Substances 0.000 description 2
- YNPNZTXNASCQKK-UHFFFAOYSA-N phenanthrene Chemical compound C1=CC=C2C3=CC=CC=C3C=CC2=C1 YNPNZTXNASCQKK-UHFFFAOYSA-N 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 150000001335 aliphatic alkanes Chemical class 0.000 description 1
- 150000001491 aromatic compounds Chemical class 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001924 cycloalkanes Chemical class 0.000 description 1
- 239000002283 diesel fuel Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000295 emission spectrum Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001506 fluorescence spectroscopy Methods 0.000 description 1
- 239000003502 gasoline Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 238000001499 laser induced fluorescence spectroscopy Methods 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003305 oil spill Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention relates to the field of oil stain detection methods in oil reservoir areas, in particular to an aviation kerosene detection method with fluorescence spectrum and vision integrated, which comprises the following steps: system calibration of the visual equipment and the spectrum detection system is finished in advance; acquiring a detection area image through visual equipment; positioning a target area on the detection area image based on the target detection model, and obtaining a target position coordinate; acquiring parameters calibrated by the system under the current distance and the target position coordinates, calculating the angle information of the turntable of the spectrum detection system, which is required to rotate, corresponding to the target position coordinates by the working end of the spectrum detection system, and controlling the turntable to rotate according to the angle information so that the working end of the spectrum detection system is corresponding to the target position coordinates; performing aviation kerosene oil film detection operation on a target area through a spectrum detection system to obtain detection information; detection analysis is performed on the probe information based on the neural network. The method can realize rapid detection and detection identification of the local aviation kerosene film in the oil reservoir area.
Description
Technical Field
The invention relates to a detection method for detecting oil stains, in particular to a detection method for detecting oil stains in an oil reservoir area.
Background
All enterprises and units for receiving, storing and dispensing crude oil or crude oil products are called oil reservoirs, some of which mainly store combustible crude oil and petroleum products, some of which store light oil such as gasoline and diesel oil, and some of which store heavy oil such as lubricating oil and fuel oil. The larger the oil storage capacity of the oil depot is, the more light oil materials are, the wider the service range is, and the greater the danger is; in case of fire or explosion, the influence range is large, and the loss of lives and properties of enterprises and people is also large.
The accurate detection and effective treatment of oil pollutants in an oil reservoir area are unprecedented work at present, and the detection and identification of the oil pollutants are work foundation and precondition for treating the oil pollutants in the oil reservoir area. In the daily operation of oil reservoir area, frequent small-size oil leakage accident has the characteristics of strong burst nature, high concealment, various oil leakage types, and because the reservoir area is huge, inspection personnel are difficult to carry out accurate, quick floor drain oil detection to the reservoir area through naked eyes or a mode of limbs touching. Therefore, a technology for realizing the rapid detection and identification of the oil film aiming at a specific local area is urgently needed.
Aiming at the problem of oil leakage, the detection and identification technology commonly used internationally at present mainly comprises two major types of chemical detection and analysis methods and remote sensing identification technologies. The chemical detection analysis method can accurately acquire the composition of the detected oil sample, is commonly called oil fingerprint detection, can realize quantitative analysis and identification of the oil sample, but often needs a series of processes such as sample configuration, instrument detection and the like, and has poor real-time performance. The remote sensing detection method is mainly used for rapidly judging the position of spilled oil and the severity of spilled oil after an oil spill accident happens, and further monitoring a detection area for 24 hours through modern means.
Disclosure of Invention
The invention aims to provide an aviation kerosene detection method integrating fluorescence spectrum and vision, which can realize rapid detection and detection identification of local aviation kerosene films in oil reservoir areas.
In order to achieve the above purpose, the technical scheme of the invention is as follows: the utility model provides a fluorescence spectrum and vision fused aviation kerosene detection method adopts the robot of patrolling and examining to carry out the operation of patrolling and examining, the robot of patrolling and examining carries on detection module, detection module includes vision equipment and passes through the revolving stage installation and connects the spectrum detecting system on the robot of patrolling and examining, and vision equipment and revolving stage relative position are fixed, and its method steps are as follows:
s1, completing system calibration of a visual device and a spectrum detection system in advance;
S2, acquiring a detection area image of an area to be detected through a visual device;
S3, positioning a target area on the detection area image based on the target detection model, and obtaining target position coordinates of the target area;
S4, acquiring parameters of system calibration of the visual equipment and the spectrum detection system under the current distance and the target position coordinate, calculating angle information of a turntable of the spectrum detection system, which is required to rotate, corresponding to the target position coordinate by the working end of the spectrum detection system, and controlling the turntable to rotate according to the angle information so that the working end of the spectrum detection system is corresponding to the target position coordinate;
S5, performing aviation kerosene oil film detection operation on the target area through a spectrum detection system to obtain detection information;
and S6, detecting and analyzing the detection information based on the neural network.
The system calibration method in the step S1 is that the working end of the initial vision equipment and the spectrum detection system face to the right front, the inspection robot moves to the detection distance d between the vision equipment and the area to be detected, the detection area image of the area to be detected is obtained, when the target area is located in the central area of the detection area image, the spectrum detection system carried by the inspection robot rotates to an angle r corresponding to the target area and needing rotation of a turntable of the target area, the relation between the change of the angle r of the turntable and the change of the position of the target area in the detection area image is recorded, the angle change of the turntable when the target area is located at any position in the detection area image is calculated, and the relation between the coordinate of the target area in the detection area image and the change of the rotation angle r of the turntable is recorded when the detection distance d between the vision equipment and the area to be detected is changed, so that the system calibration of the vision equipment and the spectrum detection system is completed.
In the step S5, when the spectrum detection system detects the aviation kerosene film, ultraviolet laser is adopted to focus and emit to a target area to induce fluorescent substances in the target area to emit fluorescence so as to generate a fluorescent spectrum; the detection and analysis method in the step S6 is that the method comprises the steps of pre-constructing BP neural network and carrying out qualitative and quantitative analysis on the organic matter components in the target area by analyzing fluorescence spectrum and Raman scattering; in a pre-constructed BP neural network, a spectrum detection system performs aviation kerosene oil film detection, in a specific range, fluorescent intensity values at n characteristic wavelengths are used as network characteristic input parameters of the BP neural network, the number of hidden layers and the number of hidden nodes are set, and output results are classified according to the content of kerosene on the surface of an object, so that the construction of the BP neural network is completed; and (3) taking the fluorescence intensity value in the detection information obtained by the spectrum detection system in the detection analysis of the step (S6) as a network characteristic input parameter of the BP neural network, and judging the corresponding class of aviation kerosene leakage conditions in classification in the target area through training and testing of the BP neural network.
In the pre-constructed BP neural network, the spectrum detection system performs aviation kerosene oil film detection, in the range of 300 nm-400 nm, takes one characteristic wavelength from each 1nm, takes the fluorescence intensity value of the characteristic wavelength as the input value of the BP neural network, takes 100 characteristic wavelengths as a total, takes 1 hidden layer number as a hidden node number as 16, and divides the output result into non-leakage 0 class, micro-leakage 1 class, small leakage 2 class and large leakage 3 class according to the kerosene content on the surface of an object.
In step S5, the spectrum detection system uses a high-energy laser to emit ultraviolet laser light for focusing, and separates fluorescence generated from the target area from back scattered light in the atmosphere medium by a range gating technique.
The spectrum detection system in step S5 selects fluorescence at different detection moments by a time-lapse gating technique to generate a fluorescence spectrum.
By adopting the technical scheme, the invention has the beneficial effects that: according to the method, manual inspection work is replaced by the inspection robot, the inspection robot generates fluorescence spectrum through a spectrum detection system laser induction technology, the laser induction technology is an active remote sensing optical detection technology, accuracy and anti-interference capability are better than those of other technologies, kerosene leakage conditions of a target area can be rapidly detected through the fluorescence spectrum, and the method is particularly based on special fluorescent substances contained in aviation kerosene, and can classify petroleum in various complex backgrounds such as water, soil, ice and snow according to the characteristic of the fluorescence spectrum. The vision equipment can accurately position the target area to be detected in the detection area image through the trained target detection model, such as an oil depot valve, an oil depot pipeline and the like. According to the method, fluorescence spectrum and visual detection are integrated, so that fast and accurate detection of aviation kerosene in a specific area can be realized, and important functions can be played in emergency treatment and daily monitoring of oil leakage accidents in a reservoir area. Thereby achieving the above object of the present invention.
Drawings
FIG. 1 is a flow chart of a fluorescence spectrum and vision fusion aviation kerosene detection method related to the invention;
fig. 2 and fig. 3 are schematic diagrams of a system calibration method in an aviation kerosene detection method integrating fluorescence spectrum and vision according to the invention;
FIG. 4 is a schematic diagram of a positioning target area in an aviation kerosene detection method integrating fluorescence spectrum and vision according to the present invention;
fig. 5 is a schematic diagram of a BP neural network in an aviation kerosene detection method with fluorescence spectrum and vision fusion according to the present invention;
FIG. 6 is a schematic representation of energy level transitions of fluorescent molecules in accordance with the present invention;
FIG. 7 is a schematic diagram of a range gating technique in accordance with the present invention;
FIG. 8 is a schematic diagram of a possible energy level distribution of a plasma according to the present invention;
FIG. 9 is a schematic diagram of the spectral time evolution of a system according to the present invention;
Fig. 10 is a schematic diagram of a spectroscopic detection system according to the present invention.
Detailed Description
In order to further explain the technical scheme of the invention, the invention is explained in detail by specific examples.
The utility model provides a fluorescence spectrum and vision fused aviation kerosene detection method adopts the robot of patrolling and examining to carry out the operation of patrolling and examining, the robot of patrolling and examining carries on detection module, detection module includes vision equipment and passes through the revolving stage and installs the spectral detection system who connects on the robot of patrolling and examining, and vision equipment and revolving stage relative position are fixed, and the flow chart of its method step is as shown in figure 1, and the method step is as follows:
s1, system calibration of the vision equipment and the spectrum detection system is finished in advance.
The method for calibrating the system in this embodiment is that the working end of the initial vision device and the spectrum detection system face to the right front, the inspection robot moves to the detection distance d between the vision device and the area to be detected, the detection area image of the area to be detected is obtained, when the target area is located in the central area of the detection area image, the spectrum detection system carried by the inspection robot rotates to an angle r corresponding to the target area and needing rotation of a turntable of the target area, the relation between the change of the angle r of the turntable and the change of the position of the target area in the detection area image is recorded, the angle change of the turntable when the target area is located at any position in the detection area image is calculated, and the relation between the coordinate of the target area in the detection area image and the change of the rotation angle r of the turntable is recorded, so that the system calibration of the vision device and the spectrum detection system is completed, as shown in fig. 2 and 3.
S2, acquiring a detection area image of the area to be detected through a visual device.
S3, positioning a target area on the detection area image based on the target detection model, and obtaining target position coordinates of the target area; the object detection model may use, for example yolo, ssd, faster-cnn, to learn the object detection model in depth, detect the object region, and obtain the position coordinate information of the object region in the image from the object detection model, as shown in fig. 4.
S4, acquiring parameters of system calibration of the visual equipment and the spectrum detection system under the current distance and the target position coordinate, calculating angle information of the turntable of the spectrum detection system, which is required to rotate, corresponding to the target position coordinate of the working end of the spectrum detection system, and controlling the turntable to rotate according to the angle information so that the working end of the spectrum detection system is corresponding to the target position coordinate.
S5, performing aviation kerosene oil film detection operation on the target area through a spectrum detection system to obtain detection information; the aviation kerosene oil film detection work is to adopt ultraviolet laser to gather and emit to a target area to induce fluorescent substances in the target area to emit fluorescence so as to generate a fluorescence spectrum.
And S6, detecting and analyzing the detection information based on the neural network.
The detection and analysis method in the step S6 is that the method comprises the steps of pre-constructing BP neural network and carrying out qualitative and quantitative analysis on the organic matter components in the target area by analyzing fluorescence spectrum and Raman scattering; in a pre-constructed BP neural network, a spectrum detection system performs aviation kerosene oil film detection, in a specific range, fluorescent intensity values at n characteristic wavelengths are used as network characteristic input parameters of the BP neural network, the number of hidden layers and the number of hidden nodes are set, and output results are classified according to the content of kerosene on the surface of an object, so that the construction of the BP neural network is completed; and (3) taking the fluorescence intensity value in the detection information obtained by the spectrum detection system in the detection analysis of the step S6 as a network characteristic input parameter of the BP neural network, and judging the corresponding class of aviation kerosene leakage conditions in classification in the target area through training and testing of the BP neural network as shown in fig. 5.
In the test process of the technical scheme of the embodiment of the invention, in the pre-constructed BP neural network, the spectrum detection system performs aviation kerosene oil film detection, in the range of 300 nm-400 nm, each 1nm is used for taking a characteristic wavelength, the fluorescence intensity value of the characteristic wavelength is taken as an input value of the BP neural network, 100 characteristic wavelengths are combined, the hidden layer number is 1 layer, the hidden node number is 16, the output result is divided into non-leakage 0 class, micro-leakage 1 class, small leakage 2 class and large leakage 3 class according to the kerosene content on the surface of an object, the predicted value gradually converges to be close to the true value through network training, and the detection effect of a model is verified through the test. The fluorescence of aviation kerosene is excited by adopting 262nm deep ultraviolet laser light condensation, trace aviation kerosene at a pipeline joint is detected, and a result shows a fluorescence spectrum with obvious characteristics; then, the non-contact fluorescence spectrum is adopted to detect the aviation kerosene oil films coated with red paint and white paint on the surface of the stainless steel valve, and the fluorescence spectra are obvious in characteristics, so that the detection results of the kerosene fluorescence spectra under different materials are different in the range of 300-400 nm, the spectrum data of kerosene on the surfaces of different media have obvious differences, and the spectrum data of the wave bands can be analyzed, thereby analyzing the kerosene leakage degree.
The structure of fluorescent molecules affects the fluorescence intensity and spectrum characteristics to a certain extent, and the relationship between the spectrum and the molecular structure can be established by utilizing the phenomenon, so that the organic matters such as mineral oil and the like can be effectively analyzed and detected, and the energy level transition diagram of the fluorescent molecules is shown in fig. 6. Mineral oils are generally composed of a large number of alkanes, cycloalkanes, and aromatics, and their molecular structures have a strong ability to absorb light; meanwhile, the mineral oil contains huge unsaturated conjugated pi bonds such as anthracene, naphthalene, phenanthrene and the like, and the structures ensure that the mineral oil can generate stronger fluorescence. The essence of the detection of greasy dirt by adopting a fluorescence spectrum method is that organic matters contain nondegradable or difficultly degradable aromatic compounds, and the types and the concentrations of the organic matters are distinguished by the characteristics of curve shapes, fluorescence intensity and the like in the fluorescence spectrum. Therefore, the method for detecting the greasy dirt has rationality and feasibility.
In step S5, when the spectrum detection system performs remote oil stain detection, a high-energy laser is required to emit ultraviolet laser light for condensation, if the target fluorescence is directly received, a large amount of near back-scattered light is introduced, so that the result (including the result in the test) is affected, for this purpose, the fluorescence generated from the target area is separated from the back-scattered light in the atmosphere medium by the distance gating technology, because the distance gating technology is an effective technology for solving the back-scattering of the atmosphere and improving the signal-to-noise ratio of detection, it uses the advantages of the laser, such as intensity, directivity, pulse width, and the like, to separate the fluorescence of the sample to be detected from the back-scattered light of the medium, such as the atmosphere, in time, as shown in fig. 7, when the back-scattered light reaches the receiving system, the control of the image enhancement and the CCD is not enabled, and when the fluorescence of the sample to be detected reaches the receiving system, such time control of the image enhancement and the CCD is enabled, such that only the fluorescence of the sample to be detected can enter the data processing system, so that the influence of most of the back-scattered light is eliminated, thereby facilitating remote oil stain detection. Also, the interaction between the laser pulse and the sample to be measured is a complex process, and the high energy laser pulse is focused on the sample to be measured, which generates a high temperature plasma. All substances melt into small particles under such high temperature system, decompose into molecules or atoms, then further collide with each other to ionize into ions, the particles are distributed at various energy levels, and then the particles located at high energy levels transition toward low energy levels, thereby generating a strong emission spectrum, as shown in fig. 8. In addition, in step S5, the spectrum detection system selects fluorescence at different detection moments through a delay gating technology to generate a fluorescence spectrum, that is, different delay gating controls are added to the detection system, so that the influence of the background radiation spectrum can be weakened, and the characteristic spectral lines of elements are mainly detected, so that the detection purpose is achieved, and the spectrum time evolution of the system is shown in fig. 9.
The spectrum detection system is introduced below, as shown in fig. 10, and mainly comprises four parts of laser emission, fluorescence detection, signal control and an upper computer, wherein the laser emission part comprises a laser and a collimation light path, and generates laser under the action of a trigger signal to excite a target to generate fluorescence; the fluorescence detection part comprises an optical system such as collimation, light splitting, focusing and the like, an image intensifier, a CCD and the like, converts signals such as fluorescence and the like into spectrum data under the action of a trigger signal, and communicates with an upper computer; the signal control part receives a control instruction of the upper computer, gives a trigger signal T1 of the laser or a trigger input signal T1' of the received laser, and gives trigger signals T2 and T3 of the image intensifier and the CCD; the upper computer is used for completing the functions of collecting, processing, displaying, analyzing and the like of related communication, fluorescence and other spectrum data. The whole detection system comprises the following working processes: the upper computer sends a control instruction through the USB; for a portable system, a signal control part receives an instruction and generates three trigger signals of a laser, an image intensifier and a CCD; for a radar system, a signal control part receives a trigger input signal after photoelectric conversion and generates two paths of trigger signals of an image intensifier and a CCD; the laser generates laser and excites the target to be measured to generate fluorescence; the fluorescence detection part receives signals such as fluorescence under the action of a trigger signal, firstly passes through an optical system such as collimation, light splitting and focusing, then converts the signals into spectrum data through an image intensifier and a CCD, and finally transmits the data to an upper computer through a USB; the upper computer processes the data and displays and analyzes the spectrum data.
According to the laser-induced fluorescence technology, the radiation fluorescence of a fluorescence spectrometry is strong, and meanwhile, a sample is not required to be contacted with the laser and the radar detection technology, so that the remote fluorescence spectrum detection can be realized by combining the high-energy laser with the radar detection technology, the fluorescence spectrum detection and the visual target positioning technology are fused, the oil leakage detection of a specific target area can be realized, the analysis of the oil leakage degree can be realized through a constructed BP neural network, the rapid detection of an aviation kerosene oil film of a local specific target can be realized, the rapid and accurate classification of the aviation kerosene fluorescence matrix spectrum can be realized, and the technical support and responsibility basis can be provided for monitoring the oil pollution of a reservoir area.
The above examples and drawings are not intended to limit the form or form of the present invention, and any suitable variations or modifications thereof by those skilled in the art should be construed as not departing from the scope of the present invention.
Claims (7)
1. The aviation kerosene detection method integrating fluorescence spectrum and vision is characterized in that an inspection robot is adopted for inspection operation, the inspection robot is provided with a detection module, the detection module comprises vision equipment and a spectrum detection system which is installed and connected on the inspection robot through a turntable, the relative positions of the vision equipment and the turntable are fixed, and the method comprises the following steps:
s1, completing system calibration of a visual device and a spectrum detection system in advance;
S2, acquiring a detection area image of an area to be detected through a visual device;
S3, positioning a target area on the detection area image based on the target detection model, and obtaining target position coordinates of the target area;
S4, acquiring parameters of system calibration of the visual equipment and the spectrum detection system under the current distance and the target position coordinate, calculating angle information of a turntable of the spectrum detection system, which is required to rotate, corresponding to the target position coordinate by the working end of the spectrum detection system, and controlling the turntable to rotate according to the angle information so that the working end of the spectrum detection system is corresponding to the target position coordinate;
S5, performing aviation kerosene oil film detection operation on the target area through a spectrum detection system to obtain detection information;
and S6, detecting and analyzing the detection information based on the neural network.
2. The aviation kerosene detection method based on fluorescence spectrum and vision fusion is characterized in that the method of system calibration in the step S1 is characterized in that the working end of an initial vision device and a spectrum detection system faces to the front, a patrol robot moves to a detection distance d between the vision device and a region to be detected, a detection region image of the region to be detected is obtained, when a target region is located in the center region of the detection region image, the spectrum detection system carried by the patrol robot rotates to an angle r corresponding to the target region and requiring rotation of a turntable of the target region, the relation between the change of the angle r of the turntable and the position change of the target region in the detection region image is recorded, the angle change of the turntable when the target region is located at any position in the detection region image is calculated, and the relation between the coordinate of the target region in the detection region image and the rotation angle r of the turntable when the detection distance d between the vision device and the region to be detected is changed is recorded, so that the calibration of the vision device and the spectrum detection system is completed.
3. The aviation kerosene detection method with integrated fluorescence spectrum and vision according to claim 1 or 2, wherein the spectrum detection system in step S5 uses ultraviolet laser to collect light and emit the light to a target area to induce fluorescent substances in the target area to emit fluorescence to generate fluorescence spectrum when performing aviation kerosene film detection work; the detection and analysis method in the step S6 is that the method comprises the steps of pre-constructing BP neural network and carrying out qualitative and quantitative analysis on the organic matter components in the target area by analyzing fluorescence spectrum and Raman scattering; in a pre-constructed BP neural network, a spectrum detection system performs aviation kerosene oil film detection, in a specific range, fluorescent intensity values at n characteristic wavelengths are used as network characteristic input parameters of the BP neural network, the number of hidden layers and the number of hidden nodes are set, and output results are classified according to the content of kerosene on the surface of an object, so that the construction of the BP neural network is completed; and (3) taking the fluorescence intensity value in the detection information obtained by the spectrum detection system in the detection analysis of the step (S6) as a network characteristic input parameter of the BP neural network, and judging the corresponding class of aviation kerosene leakage conditions in classification in the target area through training and testing of the BP neural network.
4. The aviation kerosene detection method integrating fluorescence spectrum and vision as claimed in claim 3, wherein in the pre-constructed BP neural network, the spectrum detection system performs aviation kerosene oil film detection work, in the range of 300 nm-400 nm, each 1nm is taken as a characteristic wavelength, the fluorescence intensity value is taken as an input value of the BP neural network, 100 characteristic wavelengths are taken as a total, the hidden layer number is 1, the hidden node number is 16, and the output result is divided into non-leakage 0 class, micro-leakage 1 class, small-leakage 2 class and large-leakage 3 class according to the kerosene content on the surface of an object.
5. The aviation kerosene detection method of fusion of fluorescence spectrum and vision according to claim 1 or 2, wherein in step S5, the spectrum detection system emits ultraviolet laser light to collect light when long-distance oil stain detection is performed, and fluorescence generated from a target area is separated from back scattered light in an atmospheric medium by a distance gating technology; and/or, the spectrum detection system selects fluorescence at different detection moments through a time-delay gating technology to generate a fluorescence spectrum in step S5.
6. The method for detecting aviation kerosene by combining fluorescence spectrum and vision according to claim 3, wherein in step S5, the spectrum detection system emits ultraviolet laser light to collect light when detecting oil stains at a long distance, and separates fluorescence generated from a target area from back scattered light in an atmosphere medium by a distance gating technique; and/or, the spectrum detection system selects fluorescence at different detection moments through a time-delay gating technology to generate a fluorescence spectrum in step S5.
7. The method for detecting aviation kerosene by combining fluorescence spectrum and vision according to claim 4, wherein in step S5, the spectrum detection system emits ultraviolet laser light to collect light when detecting oil stains at a long distance, and separates fluorescence generated from a target area from back scattered light in an atmosphere medium by a distance gating technique; and/or, the spectrum detection system selects fluorescence at different detection moments through a time-delay gating technology to generate a fluorescence spectrum in step S5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410293541.1A CN118190887A (en) | 2024-03-14 | 2024-03-14 | Aviation kerosene detection method with fluorescence spectrum and vision fused |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410293541.1A CN118190887A (en) | 2024-03-14 | 2024-03-14 | Aviation kerosene detection method with fluorescence spectrum and vision fused |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118190887A true CN118190887A (en) | 2024-06-14 |
Family
ID=91406131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410293541.1A Pending CN118190887A (en) | 2024-03-14 | 2024-03-14 | Aviation kerosene detection method with fluorescence spectrum and vision fused |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118190887A (en) |
-
2024
- 2024-03-14 CN CN202410293541.1A patent/CN118190887A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rosenwasser et al. | Development of a method for automated quantitative analysis of ores using LIBS | |
| CN102374979B (en) | Petroleum-type pollutant detection system and detection method | |
| Gallais et al. | Optimized metrology for laser-damage measurement: application to multiparameter study | |
| CN104483292B (en) | A kind of method that use multiline ratio method improves laser microprobe analysis accuracy | |
| KR20080081192A (en) | Method for determining the identity, absence and concentration of a chemical compound in a medium | |
| CN109827946A (en) | Soil constituent in-situ analysis system and method | |
| CN109001207A (en) | The detection method and detection system of a kind of transparent material surface and internal flaw | |
| US10203283B2 (en) | Fluorescent substance detection system | |
| CN109444092B (en) | Test system and method for identifying oil product types by combining terahertz and laser | |
| CN201233392Y (en) | Real time on-line detection device for multi metallic elements in waste water | |
| CN114897812A (en) | Infrared detection method for oil gas leakage | |
| CN113189082B (en) | Trace organic pollutant analytical spectrometer based on double-pulse-width laser and detection method | |
| CN110487774A (en) | Laser induced breakdown spectroscopy (LIBS) water quality quality evaluation system | |
| Tian et al. | Rapid evaluation method based on DOM for water quality by microlaser fluorescence spectrometer | |
| CN110057850A (en) | A kind of the X-ray non-destructive testing device and method of metal component surface holiday | |
| CN118190887A (en) | Aviation kerosene detection method with fluorescence spectrum and vision fused | |
| Dyachenko et al. | Laser systems for the pollutants control in the oil and gas industry | |
| Ullom et al. | A simple optical patternator for evaluating spray symmetry | |
| Panne | Laser remote sensing | |
| CN110231319A (en) | The laser induced fluorescence system of petroleum hydrocarbon class pollutant in field quick detection soil | |
| US20170299516A1 (en) | Characterizing petroleum product contamination using fluorescence signal | |
| CN104330387A (en) | Liquid-level oil contamination measurement system | |
| WO2017163065A1 (en) | Portable optical analysis apparatus for universal application | |
| CN109270004B (en) | Atmospheric analysis detection system and detection method based on DOAS and LIBS technologies | |
| Koechler et al. | Determination of aquatic parameters by a time-resolved laser fluorosensor operating from a helicopter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |