CN114594060A - Hyperspectral image-based hybrid sensitization detection method and device - Google Patents
Hyperspectral image-based hybrid sensitization detection method and device Download PDFInfo
- Publication number
- CN114594060A CN114594060A CN202210210789.8A CN202210210789A CN114594060A CN 114594060 A CN114594060 A CN 114594060A CN 202210210789 A CN202210210789 A CN 202210210789A CN 114594060 A CN114594060 A CN 114594060A
- Authority
- CN
- China
- Prior art keywords
- sensitization
- colloid
- value
- mixed
- density
- 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.)
- Granted
Links
- 206010070834 Sensitisation Diseases 0.000 title claims abstract description 235
- 230000008313 sensitization Effects 0.000 title claims abstract description 235
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 239000000084 colloidal system Substances 0.000 claims abstract description 134
- 239000000463 material Substances 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000005187 foaming Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 26
- 238000002156 mixing Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 66
- 238000001228 spectrum Methods 0.000 claims description 39
- 238000006243 chemical reaction Methods 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 31
- 238000012937 correction Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 23
- 230000000875 corresponding effect Effects 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 17
- 230000003595 spectral effect Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 239000000853 adhesive Substances 0.000 claims description 7
- 230000001070 adhesive effect Effects 0.000 claims description 7
- 238000003491 array Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000701 chemical imaging Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000005086 pumping Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 4
- 238000012843 least square support vector machine Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 229910052736 halogen Inorganic materials 0.000 claims description 3
- 150000002367 halogens Chemical class 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000010238 partial least squares regression Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 239000002360 explosive Substances 0.000 abstract description 23
- 239000000839 emulsion Substances 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 12
- 238000004880 explosion Methods 0.000 abstract description 5
- 230000001235 sensitizing effect Effects 0.000 description 15
- 239000004816 latex Substances 0.000 description 4
- 229920000126 latex Polymers 0.000 description 4
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Natural products NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009191 jumping Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- LPXPTNMVRIOKMN-UHFFFAOYSA-M sodium nitrite Substances [Na+].[O-]N=O LPXPTNMVRIOKMN-UHFFFAOYSA-M 0.000 description 3
- NBIIXXVUZAFLBC-UHFFFAOYSA-N Phosphoric acid Chemical compound OP(O)(O)=O NBIIXXVUZAFLBC-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005422 blasting Methods 0.000 description 2
- 238000005474 detonation Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- UMGDCJDMYOKAJW-UHFFFAOYSA-N thiourea Chemical compound NC(N)=S UMGDCJDMYOKAJW-UHFFFAOYSA-N 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- PAWQVTBBRAZDMG-UHFFFAOYSA-N 2-(3-bromo-2-fluorophenyl)acetic acid Chemical compound OC(=O)CC1=CC=CC(Br)=C1F PAWQVTBBRAZDMG-UHFFFAOYSA-N 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- FBPFZTCFMRRESA-FSIIMWSLSA-N D-Glucitol Natural products OC[C@H](O)[C@H](O)[C@@H](O)[C@H](O)CO FBPFZTCFMRRESA-FSIIMWSLSA-N 0.000 description 1
- 230000002378 acidificating effect Effects 0.000 description 1
- 229910000147 aluminium phosphate Inorganic materials 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 239000004202 carbamide Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001804 emulsifying effect Effects 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 239000004088 foaming agent Substances 0.000 description 1
- -1 foaming promoter Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000004005 microsphere Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000010451 perlite Substances 0.000 description 1
- 235000019362 perlite Nutrition 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 235000010288 sodium nitrite Nutrition 0.000 description 1
- 239000000600 sorbitol Substances 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Images
Classifications
-
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a mixed sensitization detection method and a device based on hyperspectral images, which can utilize a hyperspectral imager to monitor the colloid state of a mixed material in a sensitizer in real time, process hyperspectral images with multiple wavelengths, calculate to obtain a mixed sensitization density to further detect whether a sensitization material is uniformly dispersed in the colloid, and detect the content of a residual foaming material in a explosive body, thereby achieving the technical effects of judging the mixing effect in the sensitization process and the explosion performance of an emulsion explosive.
Description
Technical Field
The invention relates to the technical field of emulsion explosive sensitization, in particular to a hyperspectral image-based hybrid sensitization detection method and device.
Background
The emulsion explosive is emulsion-like water-containing industrial explosive prepared by an emulsion technology, has the advantages of wide raw material sources, high detonation velocity, high waterproofness, high detonation sensitivity and the like, and is widely applied to various industrial and civil blasting works in recent years. However, the production process of the emulsion explosive is complex, the influence factors are more, and a plurality of potential safety hazards exist in production and management. The mixing sensitization is an important link in the production process, and the device and the method can directly influence the quality performance and the blasting effect of the emulsion explosive.
The mixed sensitization is a process of introducing initiation and detonation-propagation hot spots by introducing uniform micro-bubbles into an emulsion matrix so as to adjust the initiation elasticity sensitivity of the emulsion matrix. At present, the existing sensitization technology is mainly divided into two modes, one mode is physical sensitization, and the mode is that light plastic microsphere materials or perlite and the like are fully mixed to mix bubbles into a latex matrix; the other is chemical sensitization, using chemical materials such as NaNO2And NH4NO4Carrying out chemical reaction under an acidic condition to release gas, and forming bubbles which are uniformly distributed in the emulsified matrix; the combination of the two methods is called composite sensitization technology. However, all of the above sensitization techniques are difficultThe technical problems that the mixing effect of the foaming agent and the latex matrix is difficult to control and the like exist when the sensitizing material is uniformly dispersed in the colloid or not are monitored. If excessive foaming materials exist in the stored emulsion explosive product, the explosive body can continue to react to release gas under the conditions of proper temperature and concentration, so that the explosive body expands, bubbles gather to enlarge and escape, and the phenomena of 'after effect' such as explosive cartridge bursting, explosive property reduction, effluent thinning and the like occur.
Disclosure of Invention
In view of the limitation of the existing methods, the invention aims to provide a mixed sensitization detection method and a device based on a hyperspectral image, which can utilize a hyperspectral imager to monitor the colloid state of a mixed material in a sensitization device in real time, process hyperspectral images with multiple wavelengths, calculate to obtain a mixed sensitization density to further detect whether the sensitization material is uniformly dispersed in the colloid, and detect the content of the residual foaming material in a explosive body, thereby achieving the technical effects of judging the mixing effect in the sensitization process and the explosion performance of emulsion explosives.
In order to achieve the above object, according to an aspect of the present disclosure, there is provided a method for hybrid sensitization detection based on hyperspectral images, the method including the steps of:
s100, obtaining a mixed colloid image sequence of the mixed material by using a hyperspectral imager;
s200, calculating to obtain a sensitization density matrix and a mixed sensitization density according to the mixed colloid image sequence;
s300, calculating to obtain a dynamic sensitization balance threshold value according to the sensitization density matrix;
s400, judging whether the mixed sensitization density is greater than or equal to a dynamic sensitization balance threshold value, and if so, skipping to the step S500; otherwise, marking the mixed sensitization process as not meeting the standard, and skipping to the step S600;
s500, if the content of the foaming material in the mixed material exceeds 5 percent of the mixed material, marking the mixed sensitization process as exceeding the standard, and jumping to the step S600; otherwise, marking that the mixed sensitization process reaches the standard;
s600, pumping a foaming promoter and an adhesive into the mixed material, and skipping to the step S100; if the mark exceeds the standard, pumping the emulsified base into the mixed material, and skipping to the step S100.
Optionally, the amount of the foaming promoter and the adhesive accounts for 0.1-0.2% of the amount of the mixed material, and the mixed sensitization reaction is promoted by keeping the temperature at 50-60 ℃; the content of the foaming material accounts for 0.07-0.08 percent of the dosage of the emulsified substrate, and the temperature is kept at 50-60 ℃ to promote the mixing sensitization reaction.
Further, in S200, the method for calculating the sensitization density matrix and the mixed sensitization density according to the mixed colloid image sequence includes:
s201, setting the resolution of a mixed colloid image in the mixed colloid image sequence to be M multiplied by N pixel sizes, and selecting and collecting L wavelengths; each corresponding pixel point is represented by coordinates (x, y, z) and represents a pixel point with coordinates (x, y) on the mixed colloid image with the wavelength serial number z; the value range of x is [1, M ], the value range of y is [1, N ], the value range of z is [1, L ], the initialization x is 1, y is 1, and z is 1;
s202, filtering and smoothing the environment interference and noise error of the hyperspectral data by the mixed colloid image sequence to obtain a de-noised colloid image sequence;
s203, sequentially traversing corresponding pixel point coordinates in the value ranges of x and y values of the de-noised colloid image sequence in the de-noised colloid image with the wavelength sequence number of z, and calculating to obtain a multi-wavelength corrected colloid image sequence;
whereinCorr (x, y, z) represents a correction value of a sequence of multi-wavelength correction colloid images having pixel coordinates (x, y) at the z-th wavelength; spect (x, y, z) is expressed as a gray value of a de-noised colloid image with pixel coordinates (x, y) at the z-th wavelength; k is a radical ofzThe spectral correlation coefficient of the de-noised colloid image corresponding to the z-th wavelength is obtained; bzThe spectral error mean value of the de-noised colloid image at the z-th wavelength is obtained;
expressed as the mean value of the gray scale of the de-noised colloid image at the z-th wavelength;
s204, obtaining the quality of the mixed material in the sensitizing device by adopting an electronic automatic metering pump; measuring the volume of the mixed colloid in the sensitizing device by adopting an electronic meter, and calculating the difference value between the volume of the mixed colloid and the volume of the mixed material which is automatically metered and pumped before the mixing reaction as the volume increment of the mixed colloid, namely the volume of the gas generated in the mixing, sensitizing and foaming process;
s205, calculating to obtain a sensitized density matrix according to the multi-wavelength corrected colloid image sequence by combining the mass of the mixed material and the volume increment of the mixed colloid;
s206, establishing a regression model of the spectral data and the mixed sensitization density by combining a least square support vector machine according to the sensitization density matrix;
and S207, taking the mixed colloid image sequence as an input of a mixed sensitization regression model, and outputting to obtain a mixed sensitization density.
In S205, the method for obtaining the sensitized density matrix by calculation according to the multi-wavelength calibration colloid image sequence and by combining the mixed material mass and the volume increment of the mixed colloid includes:
s2051, setting the wavelength number of the multi-wavelength calibration colloid image sequence to be z, setting the value range of z to be [1, L ], and initializing z to be 1; representing the sensitization density matrix as Sens (m, n), which is composed of L maximum correlation sensitization operators; initial Sens (M, N) ═ 0, the value range of M is [1, L ], the value range of N is [1, mxn ], and initialization M ═ N is 1;
s2052, traversing the value range of the z value in the multi-wavelength correction colloid image sequence, converting the value range into a two-dimensional array with the size of Lx (Mx N) by utilizing the transposition and reshape functions, obtaining a correction colloid spectrum array under the z-th wavelength, and recording the correction colloid spectrum array as Calz(i) 1,2., mxn, z ═ 1,2., L; obtaining a set of corrected colloid spectrum arrays by the corrected colloid spectrum arrays under the total L wavelengths; the reshape function is a function for transforming a specified matrix into a matrix with a specific bit number in Matlab, and the size of an array dimension can be reconstructed;
s2053, dividing the mass of the mixed material by the volume increment of the mixed colloid to obtain the density of the mixed colloid;
s2054, traversing the value range of the z value, establishing a linear regression model of the average spectral value of diffuse reflection under the total L wavelengths and the mixed colloid density for the corrected colloid spectrum array set by adopting a partial least squares regression method, calculating the regression correlation coefficient of the corrected colloid spectrum array set, selecting the corrected colloid spectrum array with the maximum corresponding regression correlation coefficient as a reference sensitization vector, and recording the reference sensitization vector as Refk(i) 1,2., mxn; k is a sensitization related wavelength serial number, and the value of k is equal to the wavelength serial number corresponding to the correction colloid spectrum array with the maximum regression correlation coefficient in the correction colloid spectrum array set;
s2055, sequentially calculating related sensitization operators of the corrected colloidal spectrum array at the z-th wavelength in the value range of z according to the reference sensitization vector;
wherein, Pz(i) Expressed as the ith value in the correlation sensitization operator of the calibration colloid spectrum array at the z-th wavelength; the correlation sensitization operator is formed by Pz(i) The formed vector, i ═ 1,2](ii) a The correlation sensitization operator at total L wavelengths forms the correlation sensitization algorithmA subset;
s2056, calculating the arithmetic mean value of the correlation sensitization operator set at each wavelength, searching the correlation sensitization operator at the wavelength corresponding to the maximum value of the arithmetic mean value, and recording the correlation sensitization operator as the maximum correlation sensitization operator; making the k value equal to the wavelength serial number of the maximum correlation sensitization operator, and re-marking the correction colloid spectrum array under the corresponding wavelength as a reference sensitization vector; let the m-th row vector of sensitization density matrix equal to the maximum correlation sensitization operator, i.e. Sens (m, n) ═ MaxPz(i)，i＝1,2,...,M×N；MaxPz(i) Expressed as the ith value in the maximum correlation sensitization operator, and Sens (m, n) represents the value with the coordinate (m, n) in the sensitization density matrix;
s2057, judging whether the m value is equal to the L value, if so, obtaining the sensitization density matrix; otherwise, the value m is increased by 1, and the process goes to step S2055.
Further, in S300, the method for calculating the dynamic sensitization balance threshold according to the sensitization density matrix includes:
s301, dividing L wavelengths into floor (L/Nl) wave bands for calculation, wherein a floor function is rounded by Gaussian, Nl is the length of the wave band, the serial number of the wave band is set to be j, the numeric area of the j value is set to be [1, floor (L/Nl) ], and j is initialized to be 1; setting the size of a reaction window to be Ns multiplied by Ns pixel points, wherein Ns is the length of the reaction window, the moving sequence number of the reaction window is p, w is the moving unit distance, and the value range of w is [0.05Ns,0.6Ns ]; the value range of the p value is [1, floor (min (M, N)/w) ], the floor function is Gaussian integer, the min function is the minimum value, and p is initialized to 1;
s302, calculating the sensitization density matrix in the value range of the j value to obtain an average sensitization density matrix;
wherein, the first and the second end of the pipe are connected with each other,
expressed as the jth bandQuantizing the nth value of the density matrix; sens (m, n) is expressed as a numerical value with coordinates (m, n) in the sensitization density matrix;
s303, converting the average sensitization density matrix into a three-dimensional array with the size of M multiplied by N multiplied by L by utilizing a reshape function to obtain an average sensitization density image sequence, wherein the average sensitization density image sequence is recorded as Dens (j, x1, y1) and is expressed as a numerical value of the average sensitization density image under the j wave band at the pixel coordinate of (x1, y 1); the value range of x1 is [1, M ], the value range of y1 is [1, N ], and j is initialized to x1 to y1 to 1;
s304, traversing the average sensitization density image sequence in the value range of the j value, moving the reaction window by taking the pixel coordinate (0,0) as a starting point in the average sensitization density image under the j wave band, and calculating to obtain a dynamic sensitization density sequence;
wherein, Limit (p) is a numerical value of the dynamic sensitization density in the reaction window of the p-th movement; ns is the length of the reaction window, len is the moving distance, len ═ wx (p-1) +1, w is the moving unit distance, and p is the moving times of the reaction window;
and S305, averaging according to the dynamic sensitization density sequence to obtain a dynamic sensitization equilibrium threshold value.
The invention also provides a mixed sensitization detection device based on the hyperspectral image, which comprises: high spectral imaging collection system, central processing unit, storage module and power module, wherein:
the hyperspectral imaging acquisition system comprises a hyperspectral imager, a halogen lamp light source and an electric control scanning moving support; the hyperspectral imager is fixed by an electric control scanning movable bracket and is arranged above the sensitizer, and any reaction area of mixed materials in the sensitizer can be moved;
optionally, the spectrum acquisition range is 600-1400 nm, the set exposure time is 4.00ms, the scanning speed is 15mm/s, the hyperspectral imager acquires hyperspectral images of diffuse reflection of the mixed materials in the sensitizer under various wavelengths, the image pixel resolution is mxn, and analog signals are converted into digital signals through analog-to-digital conversion and then enter the central processing unit;
the central processing unit comprises a computer and a microprocessor, wherein common microprocessors comprise a microcontroller, an embedded CPU or a field programmable gate array and the like, can control the electric control scanning movable support, or are used for digital signal processing, task scheduling and the like;
the storage module is controlled by a central processing unit and comprises a memory and a computer program which is stored in the memory and can run on the central processing unit, the central processing unit realizes the steps of the hyperspectral image-based hybrid sensitization detection method in claim 1 when executing the computer program, and the central processing unit realizes the steps of the hyperspectral image-based hybrid sensitization detection method in any one of claims 1 to 4 when executing the computer program; in the hybrid sensitization detection apparatus based on the hyperspectral image, the central processing unit executing the computer program can be operated in computing devices such as a desktop computer, a notebook, a palm computer, a cloud data center and the like, and an operable system can include, but is not limited to, a processor, a memory and a server cluster.
As described above, the hybrid sensitization detection method and device based on the hyperspectral image have the following beneficial effects: (1) monitoring the colloid state of the mixed material in the sensitizing device in real time, detecting the mixed sensitizing density and judging whether the sensitizing process is complete or not; (2) detecting whether the emulsion explosive contains excessive foaming materials or not, and avoiding the phenomenon of 'after effect' of the explosive body; (3) the explosive property of the emulsion explosive is ensured to a certain extent.
Drawings
The foregoing and other features of the present disclosure will become more apparent from the detailed description of the embodiments shown in conjunction with the drawings in which like reference characters designate the same or similar elements throughout the several views, and it is apparent that the drawings in the following description are merely some examples of the present disclosure and that other drawings may be derived therefrom by those skilled in the art without the benefit of any inventive faculty, and in which:
FIG. 1 is a flow chart of a hybrid sensitization detection method based on hyperspectral images in an embodiment;
fig. 2 is a flowchart of a computer program of a hybrid sensitization detection apparatus based on hyperspectral images in an embodiment.
Detailed Description
The conception, specific structure and technical effects of the present disclosure will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, aspects and effects of the present disclosure. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than the number, shape and layout of the components in actual implementation, and the types, the numbers and the proportions of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.
In the description of the present invention, a plurality of means is one or more, a plurality of means is two or more, and greater than, less than, more than, etc. are understood as excluding the present numbers, and greater than, less than, more than, etc. are understood as including the present numbers, and outer and inner are understood as relative inside-outside relationships. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
The mixed sensitization detection method and device based on the hyperspectral image can efficiently optimize the sensitization efficiency of a mixed sensitization process in the emulsion explosive preparation process, and the sensitization density is calculated through multispectral detection and fitting; the technical difficulty of judging whether the sensitizing material is uniformly dispersed in the colloid is realized; the detection of the excessive materials in the stored product is combined, so that the explosion performance of the emulsion explosive is guaranteed, and the method is suitable for being applied to the field of emulsion explosive sensitization detection.
Fig. 1 is a flow chart of a hybrid sensitization detection method based on hyperspectral images according to the present invention, and a hybrid sensitization detection method based on hyperspectral images according to an embodiment of the present invention is described below with reference to fig. 1.
The disclosure provides a hyperspectral image-based hybrid sensitization detection method, which specifically comprises the following steps:
s000, pumping the latex, the foaming material, the foaming accelerant and the emulsion matrix into a sensitizing device to form a mixed material, and carrying out mixing sensitization;
s100, acquiring a mixed colloid image sequence of the mixed materials in the sensitizing device by using a hyperspectral imager;
s200, calculating to obtain a sensitization density matrix and a mixed sensitization density according to the mixed colloid image sequence;
s300, calculating to obtain a dynamic sensitization balance threshold value according to the sensitization density matrix;
s400, judging whether the mixed sensitization density is greater than or equal to a dynamic sensitization balance threshold value, and if so, skipping to the step S500; otherwise, marking the mixed sensitization process as not meeting the standard, and skipping to the step S600;
s500, detecting the content of the foaming material of the mixed material in the sensitizing device, if the content of the foaming material exceeds 5 percent of the total amount of all the components of the mixed material, marking that the mixed sensitizing process exceeds the standard, and skipping to the step S600; otherwise, marking that the mixed sensitization process reaches the standard;
s600, judging the mark of the mixed sensitization process, if the mark does not meet the standard, automatically metering and pumping a foaming promoter and an adhesive into the sensitization device, and jumping to the step S100; if the mark is over the standard, automatically metering and pumping the emulsified matrix into the sensitizing device, and jumping to the step S100.
Preferably, in the embodiment, the mixed materials comprise latex, foaming material, foaming promoter, emulsion matrix and the like, and the mixed sensitization reaction is carried out in a sensitizing device; the foaming material is a mixture of sodium nitrite, water, ammonium nitrate and phosphoric acid; the foaming accelerant can be one of thiourea, 0.3-2.0% of urea and the like, and can achieve the foaming effect of accelerating the mixed sensitization reaction; the adhesive can be sorbitol, can play a role in viscosity, entrains and coats a certain amount of tiny bubbles, namely generates hot spots, and is beneficial to promoting the explosion effect of the emulsion explosive. Therefore, the foaming promoter and the adhesive are added to play a good foaming and foam stabilizing role, so that micro bubbles are not easy to escape and disperse, and the explosion performance and the storage life of the emulsion explosive are improved.
Optionally, the amount of the foaming promoter and the adhesive accounts for 0.1-0.2% of the amount of the mixed material, and the mixed sensitization reaction is promoted by keeping the temperature at 50-60 ℃; the content of the residual foaming material accounts for 0.07-0.08 percent of the dosage of the pumped emulsifying matrix, and the temperature is kept at 50-60 ℃ to promote the mixing sensitization reaction.
Further, in S200, the method for calculating the sensitization density matrix and the mixed sensitization density according to the mixed colloid image sequence includes:
s201, setting the resolution of a mixed colloid image in the mixed colloid image sequence to be M multiplied by N pixel sizes, and selecting and collecting L wavelengths; each corresponding pixel point is represented by coordinates (x, y, z) and represents a pixel point with coordinates (x, y) on the mixed colloid image with the wavelength serial number z; the value range of x is [1, M ], the value range of y is [1, N ], the value range of z is [1, L ], the initialization x is 1, y is 1, and z is 1;
s202, filtering and smoothing the environment interference and noise error of the hyperspectral data by the mixed colloid image sequence to obtain a de-noised colloid image sequence;
s203, sequentially traversing corresponding pixel point coordinates in the value ranges of x and y values of the de-noised colloid image sequence in the de-noised colloid image with the wavelength sequence number of z, and calculating to obtain a multi-wavelength corrected colloid image sequence;
wherein Corr (x, y, z) represents the correction value of the multi-wavelength correction colloid image sequence with pixel coordinate (x, y) at the z-th wavelength; spect (x, y, z) is expressed as a gray value of a de-noised colloid image with pixel coordinates (x, y) at the z-th wavelength; k is a radical of formulazThe spectral correlation coefficient of the de-noised colloid image corresponding to the z-th wavelength is obtained; bzThe spectral error mean value of the de-noised colloid image at the z-th wavelength is obtained;
expressed as the mean value of the gray scale of the de-noised colloid image at the z-th wavelength;
s204, obtaining the quality of the mixed material in the sensitization device by adopting an electronic automatic metering pump; measuring the volume of the mixed colloid in the sensitization device by adopting an electronic meter, and calculating the difference value between the volume of the mixed colloid and the volume of the mixed material which is automatically metered and pumped before the mixing reaction as the volume increment of the mixed colloid, namely the volume of the gas generated in the mixing sensitization foaming process;
s205, calculating to obtain a sensitized density matrix according to the multi-wavelength corrected colloid image sequence by combining the mass of the mixed material and the volume increment of the mixed colloid;
s206, establishing a regression model of the spectral data and the mixed sensitization density by combining a least square support vector machine according to the sensitization density matrix;
and S207, taking the mixed colloid image sequence as an input of a mixed sensitization regression model, and outputting to obtain a mixed sensitization density.
In S205, the method for obtaining the sensitized density matrix by calculation according to the multi-wavelength calibration colloid image sequence and by combining the mixed material mass and the volume increment of the mixed colloid includes:
s2051, setting the wavelength number of the multi-wavelength calibration colloid image sequence to be z, setting the value range of z to be [1, L ], and initializing z to be 1; representing the sensitization density matrix as Sens (m, n), which is composed of L maximum correlation sensitization operators; initial Sens (M, N) ═ 0, the value range of M is [1, L ], the value range of N is [1, mxn ], and initialization M ═ N is 1;
s2052, traversing the value range of the z value in the multi-wavelength correction colloid image sequence, converting the value range into a two-dimensional array with the size of Lx (Mx N) by utilizing the transposition and reshape functions, obtaining a correction colloid spectrum array under the z-th wavelength, and recording the correction colloid spectrum array as Calz(i) 1,2., mxn, z ═ 1,2., L; obtaining a set of corrected colloid spectrum arrays by the corrected colloid spectrum arrays under the total L wavelengths; the reshape function is a function for transforming a specified matrix into a matrix with a specific bit number in Matlab, and the size of an array dimension can be reconstructed;
s2053, dividing the mass of the mixed material by the volume increment of the mixed colloid to obtain the density of the mixed colloid;
s2054, traversing the value range of the z value, establishing a linear regression model of the average spectral value of diffuse reflection under the total L wavelengths and the mixed colloid density for the corrected colloid spectrum array set by adopting a partial least squares regression method, calculating the regression correlation coefficient of the corrected colloid spectrum array set, selecting the corrected colloid spectrum array with the maximum corresponding regression correlation coefficient as a reference sensitization vector, and recording as Refk(i) 1,2., mxn; k is a sensitization related wavelength serial number, and the value of k is equal to the wavelength serial number corresponding to the correction colloid spectrum array with the maximum regression correlation coefficient in the correction colloid spectrum array set;
s2055, sequentially calculating related sensitization operators of the corrected colloidal spectrum array at the z-th wavelength in the value range of z according to the reference sensitization vector;
wherein, Pz(i) Expressed as the ith value in the correlation sensitization operator of the calibration colloid spectrum array at the z-th wavelength; the correlation sensitization operator is formed by Pz(i) The formed vector, i ═ 1,2](ii) a The correlated sensitization operators under the total L wavelengths form a correlated sensitization operator set;
s2056, calculating the arithmetic mean value of the correlation sensitization operator set at each wavelength, searching the correlation sensitization operator at the wavelength corresponding to the maximum value of the arithmetic mean value, and recording the correlation sensitization operator as the maximum correlation sensitization operator; making the k value equal to the wavelength serial number of the maximum correlation sensitization operator, and re-marking the correction colloid spectrum array under the corresponding wavelength as a reference sensitization vector; let the m-th row vector of sensitization density matrix equal to the maximum correlation sensitization operator, i.e. Sens (m, n) ═ MaxPz(i)，i＝1,2,...,M×N；MaxPz(i) Expressed as the ith value in the maximum correlation sensitization operator, and Sens (m, n) represents the value with the coordinate (m, n) in the sensitization density matrix;
s2057, judging whether the m value is equal to the L value, if so, obtaining the sensitization density matrix; otherwise, the value m is increased by 1, and the process goes to step S2055.
Further, in S300, the method for calculating the dynamic sensitization balance threshold according to the sensitization density matrix includes:
s301, dividing L wavelengths into floor (L/Nl) wave bands for calculation, wherein a floor function is rounded by Gaussian, Nl is the length of the wave band, the serial number of the wave band is set to be j, the numeric area of the j value is set to be [1, floor (L/Nl) ], and j is initialized to be 1; setting the size of a reaction window to be Ns multiplied by Ns pixel points, wherein Ns is the length of the reaction window, the moving sequence number of the reaction window is p, w is the moving unit distance, and the value range of w is [0.05Ns,0.6Ns ]; the value range of the p value is [1, floor (min (M, N)/w) ], a floor function is a Gaussian integer, a min function is a minimum value, and p is initialized to be 1;
s302, calculating the sensitization density matrix in the value range of the j value to obtain an average sensitization density matrix;
wherein the content of the first and second substances,
expressing the nth value of the average sensitization density matrix at the jth wave band; sens (m, n) is expressed as a numerical value with coordinates (m, n) in the sensitization density matrix;
s303, converting the average sensitization density matrix into a three-dimensional array with the size of M multiplied by N multiplied by L by utilizing a reshape function to obtain an average sensitization density image sequence, wherein the average sensitization density image sequence is recorded as Dens (j, x1, y1) and is expressed as a numerical value of the average sensitization density image under the j wave band at the pixel coordinate of (x1, y 1); the value range of x1 is [1, M ], the value range of y1 is [1, N ], and j is initialized to x1 to y1 to 1;
s304, traversing the average sensitization density image sequence in the value range of the j value, moving the reaction window by taking the pixel coordinate (0,0) as a starting point in the average sensitization density image under the j wave band, and calculating to obtain a dynamic sensitization density sequence;
wherein, Limit (p) is expressed as a numerical value of the dynamic sensitization density in the p reaction window; ns is the reaction window length, len is the displacement distance, len ═ wx (p-1) +1, and w is the displacement unit distance;
and S305, obtaining a dynamic sensitization balance threshold value by taking the mean value according to the dynamic sensitization density sequence.
The mixed sensitization detection device based on the hyperspectral image provided by the embodiment of the disclosure comprises: high spectrum imaging acquisition system, central processing unit, storage module and power module, wherein:
the hyperspectral imaging acquisition system comprises a hyperspectral imager, a halogen lamp light source and an electric control scanning movable bracket; the hyperspectral imager is fixed by an electric control scanning movable support and is arranged above the sensitizer, and any reaction area of mixed materials in the sensitizer can be moved;
optionally, the spectrum acquisition range is 600-1400 nm, the exposure time is set to be 4.00ms, and the scanning speed is 15 mm/s; the hyperspectral imager acquires hyperspectral images of diffuse reflection of the mixed materials in the sensitizer under various wavelengths, the pixel resolution of the images is 512 x 512pixels in the specific embodiment, and analog signals are converted into digital signals through analog-to-digital conversion and then enter a central processing unit;
the central processing unit comprises a computer and a microprocessor, wherein common microprocessors comprise a microcontroller, an embedded CPU or a field programmable gate array and the like, can control the electric control scanning movable support, or are used for digital signal processing, task scheduling and the like;
a storage module controlled by a central processing unit, comprising a memory and a computer program stored in the memory and operable on the central processing unit, wherein the central processing unit implements the steps of the hyperspectral image based hybrid sensitization detection method according to claim 1 when executing the computer program, the central processing unit executes the computer program to operate in the units of the following system, and the flow chart of the computer program is shown in fig. 2:
the filtering and smoothing unit is used for filtering and smoothing the environment interference and the noise error of the hyperspectral data of the mixed colloid image sequence to obtain a de-noised colloid image sequence;
the multi-wavelength correction processing unit is used for calculating the de-noised colloid image sequence to obtain a multi-wavelength correction colloid image sequence;
the automatic metering and storing unit is used for recording and storing the mass of the mixed material and the volume of the mixed colloid in the sensitizing device measured by the electronic automatic metering pump, and the volume increment of the mixed colloid;
the sensitization density calculating unit is used for calculating the multi-wavelength correction colloid image sequence to obtain a sensitization density matrix by combining the mass of the mixed materials and the volume increment of the mixed colloid;
the mixed sensitization density regression model unit is used for establishing a regression model for the sensitization density matrix by adopting a least square support vector machine; inputting the mixed colloid image sequence to obtain mixed sensitization density;
the dynamic sensitization balance threshold unit is used for calculating the sensitization density matrix to obtain a dynamic sensitization balance threshold;
a sensitization process judging and marking unit for judging the mixed sensitization process to be three states of not meeting the standard, meeting the standard and exceeding the standard and marking;
the central processing unit in the hybrid sensitization detection apparatus based on the hyperspectral image executes the computer program, and the computer program can be run in computing devices such as a desktop computer, a notebook, a palm computer, a cloud data center and the like, and the system which can run can include, but is not limited to, a processor, a memory and a server cluster.
The hyperspectral image-based hybrid sensitization detection device is a movable hyperspectral imaging detection device, and can comprise a hyperspectral imager, a processor and a memory. It will be understood by those skilled in the art that the example is merely an example of a hybrid sensitization detection apparatus based on hyperspectral images, and does not constitute a limitation of a hybrid sensitization detection apparatus based on hyperspectral images, and may include more or less components than the other, or combine some components, or different components, for example, the hybrid sensitization detection apparatus based on hyperspectral images may further include a mobile support, an analog-to-digital conversion module, a wireless network interface, and the like.
The processor may be a Central Processing Unit (CPU), other general purpose processor, a Field-Programmable Gate Array (FPGA), or other Programmable logic device. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the hybrid sensitization detection device based on the hyperspectral image, and various interfaces and lines are utilized to connect all parts of the whole hybrid sensitization detection device based on the hyperspectral image.
The memory can be used for storing the computer program and/or the module, and the processor realizes various functions of the hybrid sensitization detection device based on the hyperspectral image by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store a main program, an application program (such as a filtering smoothing processing unit, a multi-wavelength correction processing unit and the like) required by at least one function, and the like; the storage data area may store data buffered by the processor, clock data, and the like.
Although the description of the present disclosure has been rather exhaustive and particularly described with respect to several illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiments, so as to effectively encompass the intended scope of the present disclosure. Furthermore, the foregoing describes the disclosure in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the disclosure, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (5)
1. A hybrid sensitization detection method based on hyperspectral images is characterized by comprising the following steps:
s100, obtaining a mixed colloid image sequence of the mixed material by using a hyperspectral imager;
s200, calculating to obtain a sensitization density matrix and a mixed sensitization density according to the mixed colloid image sequence;
s300, calculating to obtain a dynamic sensitization balance threshold value according to the sensitization density matrix;
s400, judging whether the mixed sensitization density is greater than or equal to a dynamic sensitization balance threshold value, and if so, skipping to the step S500; otherwise, marking the mixed sensitization process as not meeting the standard, and skipping to the step S600;
s500, if the content of the foaming material in the mixed material exceeds 5% of the mixed material, marking the mixed sensitization process as exceeding the standard, and skipping to the step S600; otherwise, marking that the mixed sensitization process reaches the standard;
s600, pumping a foaming promoter and an adhesive into the mixed material, and skipping to the step S100; if the mark is over the standard, the emulsified base is pumped into the mixture and the process jumps to step S100.
2. The hyperspectral image-based hybrid sensitization detection method according to claim 1 is characterized in that in S200, the method for calculating a sensitization density matrix and a hybrid sensitization density according to the hybrid colloidal image sequence comprises the following steps:
s201, setting the resolution of a mixed colloid image in the mixed colloid image sequence to be M multiplied by N pixel sizes, and selecting and collecting L wavelengths; each corresponding pixel point is represented by coordinates (x, y, z) and represents a pixel point with coordinates (x, y) on the mixed colloid image with the wavelength serial number z; the value range of x is [1, M ], the value range of y is [1, N ], the value range of z is [1, L ], the initialization x is 1, y is 1, and z is 1;
s202, filtering and smoothing the environment interference and noise error of the hyperspectral data by the mixed colloid image sequence to obtain a de-noised colloid image sequence;
s203, sequentially traversing corresponding pixel point coordinates in the value ranges of x and y values of the de-noised colloid image sequence in the de-noised colloid image with the wavelength sequence number of z, and calculating to obtain a multi-wavelength corrected colloid image sequence;
wherein Corr (x, y, z) represents the correction value of the multi-wavelength correction colloid image sequence with pixel coordinate (x, y) at the z-th wavelength; spect (x, y, z) is expressed as a gray value of a de-noised colloid image with pixel coordinates (x, y) at the z-th wavelength; k is a radical ofzThe spectral correlation coefficient of the de-noised colloid image corresponding to the z-th wavelength is obtained; bzThe spectral error mean value of the de-noised colloid image at the z-th wavelength is obtained;
expressed as the mean value of the gray scale of the de-noised colloid image at the z-th wavelength;
s204, obtaining the quality of the mixed material by adopting an electronic automatic metering pump; measuring the volume of the mixed colloid by using an electronic meter, and calculating the difference value between the volume of the mixed colloid and the volume of the mixed material pumped before the mixing reaction as the volume increment of the mixed colloid, namely the volume of the gas generated in the mixing sensitization foaming process;
s205, calculating to obtain a sensitized density matrix according to the multi-wavelength corrected colloid image sequence by combining the mass of the mixed material and the volume increment of the mixed colloid;
s206, establishing a regression model of the spectral data and the mixed sensitization density by combining a least square support vector machine according to the sensitization density matrix;
and S207, taking the mixed colloid image sequence as an input of a mixed sensitization regression model, and outputting to obtain a mixed sensitization density.
3. The hybrid sensitization detection method based on the hyperspectral image according to claim 2 is characterized in that in S205, according to the multi-wavelength correction colloid image sequence, the method for obtaining the sensitization density matrix by calculation by combining the mass of the mixed material and the volume increment of the mixed colloid comprises the following steps:
s2051, setting the wavelength number of the multi-wavelength calibration colloid image sequence to be z, setting the value range of z to be [1, L ], and initializing z to be 1; representing the sensitization density matrix as Sens (m, n), which is composed of L maximum correlation sensitization operators; initial Sens (M, N) ═ 0, the value range of M is [1, L ], the value range of N is [1, mxn ], and initialization M ═ N is 1;
s2052, traversing the value range of the z value in the multi-wavelength correction colloid image sequence, converting the value range into a two-dimensional array with the size of Lx (Mx N) by utilizing the transposition and reshape functions, obtaining a correction colloid spectrum array under the z-th wavelength, and recording the correction colloid spectrum array as Calz(i) 1,2., mxn, z ═ 1,2., L; obtaining a set of corrected colloid spectrum arrays by the corrected colloid spectrum arrays under the total L wavelengths; the reshape function is a function for transforming a specified matrix into a matrix with a specific bit number in Matlab, and the size of an array dimension can be reconstructed;
s2053, dividing the mass of the mixed material by the volume increment of the mixed colloid to obtain the density of the mixed colloid;
s2054, traversing the value range of the z value, establishing a linear regression model of the average spectral value of diffuse reflection under the total L wavelengths and the mixed colloid density for the corrected colloid spectrum array set by adopting a partial least squares regression method, calculating the regression correlation coefficient of the corrected colloid spectrum array set, selecting the corrected colloid spectrum array with the maximum corresponding regression correlation coefficient as a reference sensitization vector, and recording the reference sensitization vector as Refk(i) 1,2., mxn; k is a sensitization related wavelength serial number, and the value of k is equal to the wavelength serial number corresponding to the correction colloid spectrum array with the maximum regression correlation coefficient in the correction colloid spectrum array set;
s2055, sequentially calculating related sensitization operators of the corrected colloidal spectrum array at the z-th wavelength in the value range of z according to the reference sensitization vector;
wherein, Pz(i) Expressed as corrected colloidal light at the z-th wavelengthThe ith numerical value in the correlation sensitization operator of the spectrum array; the correlation sensitization operator is formed by Pz(i) The formed vector, i ═ 1,2](ii) a The correlated sensitization operators under the total L wavelengths form a correlated sensitization operator set;
s2056, calculating the arithmetic mean value of the correlation sensitization operator set at each wavelength, searching the correlation sensitization operator at the wavelength corresponding to the maximum value of the arithmetic mean value, and recording the correlation sensitization operator as the maximum correlation sensitization operator; making the k value equal to the wavelength serial number of the maximum correlation sensitization operator, and re-marking the correction colloid spectrum array under the corresponding wavelength as a reference sensitization vector; let the m-th row vector of sensitization density matrix equal to the maximum correlation sensitization operator, i.e. Sens (m, n) ═ MaxPz(i)，i＝1,2,...,M×N；MaxPz(i) Expressed as the ith value in the maximum correlation sensitization operator, and Sens (m, n) represents the value with the coordinate (m, n) in the sensitization density matrix;
s2057, judging whether the m value is equal to the L value, if so, obtaining the sensitization density matrix; otherwise, the value m is increased by 1, and the process goes to step S2055.
4. The hyperspectral image-based hybrid sensitization detection method according to claim 1, wherein in S300, the method for calculating the dynamic sensitization balance threshold according to the sensitization density matrix comprises the following steps:
s301, dividing L wavelengths into floor (L/Nl) wave bands for calculation, wherein a floor function is rounded by Gaussian, Nl is the length of the wave band, the serial number of the wave band is set to be j, the numeric area of the j value is set to be [1, floor (L/Nl) ], and j is initialized to be 1; setting the size of a reaction window to be Ns multiplied by Ns pixel points, wherein Ns is the size of the reaction window, the moving sequence number of the reaction window is p, w is the moving unit distance, and the numeric area of w is [0.05Ns,0.6Ns ]; the value range of the p value is [1, floor (min (M, N)/w) ], the floor function is Gaussian integer, the min function is the minimum value, and p is initialized to 1;
s302, calculating the sensitization density matrix in the value range of the j value to obtain an average sensitization density matrix;
wherein the content of the first and second substances,
expressing the nth value of the average sensitization density matrix at the jth wave band; sens (m, n) is expressed as a numerical value with coordinates (m, n) in the sensitization density matrix;
s303, converting the average sensitization density matrix into a three-dimensional array with the size of M multiplied by N multiplied by L by utilizing a reshape function to obtain an average sensitization density image sequence, wherein the average sensitization density image sequence is recorded as Dens (j, x1, y1) and is expressed as a numerical value of the average sensitization density image under the j wave band at the pixel coordinate of (x1, y 1); the value range of x1 is [1, M ], the value range of y1 is [1, N ], and j is initialized to x1 to y1 to 1;
s304, traversing the average sensitization density image sequence in the value range of the j value, moving the reaction window by taking the pixel coordinate (0,0) as a starting point in the average sensitization density image under the j wave band, and calculating to obtain a dynamic sensitization density sequence;
wherein, Limit (p) is a numerical value of the dynamic sensitization density in the reaction window of the p-th movement; ns is the length of the reaction window, len is the moving distance, len ═ wx (p-1) +1, w is the moving unit distance, and p is the moving times of the reaction window;
and S305, obtaining a dynamic sensitization balance threshold value by taking the mean value according to the dynamic sensitization density sequence.
5. The utility model provides a mix sensitization detection device based on hyperspectral image which characterized in that, a mix sensitization detection device based on hyperspectral image includes: high spectral imaging collection system, central processing unit module, storage module and power module, wherein:
the hyperspectral imaging acquisition system comprises a hyperspectral imager, a halogen lamp light source and an electric control scanning moving support; the hyperspectral imager is fixed by an electric control scanning movable support and is arranged above the sensitizer, and any reaction area of mixed materials in the sensitizer can be moved; the hyperspectral imager collects hyperspectral images of diffuse reflection of the mixed materials in the sensitizer under various wavelengths, the resolution of image pixels is MxN, and analog signals are converted into digital signals through analog-to-digital conversion and then enter a central processing unit;
the central processing unit comprises a computer and a microprocessor, wherein common microprocessors comprise a microcontroller, an embedded CPU or a field programmable gate array and the like, can control the electric control scanning movable support, or are used for digital signal processing, task scheduling and the like;
the storage module is controlled by a central processing unit and comprises a memory and a computer program which is stored in the memory and can run on the central processing unit, the central processing unit realizes the steps of the hyperspectral image-based hybrid sensitization detection method in claim 1 when executing the computer program, and the central processing unit realizes the steps of the hyperspectral image-based hybrid sensitization detection method in any one of claims 1 to 4 when executing the computer program; in the hybrid sensitization detection apparatus based on the hyperspectral image, the central processing unit executing the computer program can be operated in computing devices such as a desktop computer, a notebook, a palm computer, a cloud data center and the like, and an operable system can include, but is not limited to, a processor, a memory and a server cluster.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210210789.8A CN114594060B (en) | 2022-03-04 | 2022-03-04 | Hyperspectral image-based hybrid sensitization detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210210789.8A CN114594060B (en) | 2022-03-04 | 2022-03-04 | Hyperspectral image-based hybrid sensitization detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114594060A true CN114594060A (en) | 2022-06-07 |
| CN114594060B CN114594060B (en) | 2022-09-09 |
Family
ID=81808172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210210789.8A Active CN114594060B (en) | 2022-03-04 | 2022-03-04 | Hyperspectral image-based hybrid sensitization detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114594060B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103543149A (en) * | 2013-10-23 | 2014-01-29 | 安徽江南化工股份有限公司 | Method for detecting emulsifying agent for emulsion explosive |
| CN104515843A (en) * | 2014-12-23 | 2015-04-15 | 中煤科工集团淮北***技术研究院有限公司 | On-line emulsified explosive product quality monitoring method |
| WO2019237135A1 (en) * | 2018-06-04 | 2019-12-12 | Selwyn Peter Pearton | Pumpable explosives density measurement |
| CN112881306A (en) * | 2021-01-15 | 2021-06-01 | 吉林大学 | Hyperspectral image-based method for rapidly detecting ash content of coal |
| CN113588571A (en) * | 2021-09-29 | 2021-11-02 | 广东省农业科学院动物科学研究所 | Hyperspectral imaging-based method and system for identifying fishy smell of aquatic product |
-
2022
- 2022-03-04 CN CN202210210789.8A patent/CN114594060B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103543149A (en) * | 2013-10-23 | 2014-01-29 | 安徽江南化工股份有限公司 | Method for detecting emulsifying agent for emulsion explosive |
| CN104515843A (en) * | 2014-12-23 | 2015-04-15 | 中煤科工集团淮北***技术研究院有限公司 | On-line emulsified explosive product quality monitoring method |
| WO2019237135A1 (en) * | 2018-06-04 | 2019-12-12 | Selwyn Peter Pearton | Pumpable explosives density measurement |
| CN112881306A (en) * | 2021-01-15 | 2021-06-01 | 吉林大学 | Hyperspectral image-based method for rapidly detecting ash content of coal |
| CN113588571A (en) * | 2021-09-29 | 2021-11-02 | 广东省农业科学院动物科学研究所 | Hyperspectral imaging-based method and system for identifying fishy smell of aquatic product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114594060B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3971684A1 (en) | Vision-based tactile measurement method, apparatus, chip and storage medium | |
| Dunson et al. | Bayesian latent variable models for mixed discrete outcomes | |
| CN1666113A (en) | Error estimate concerning a target device's location operable to move in a wireless environment | |
| CN1595192A (en) | Rtk positioning system and positioning method therefor | |
| Rüdisüli et al. | Monte Carlo simulation of the bubble size distribution in a fluidized bed with intrusive probes | |
| CN107064068A (en) | A kind of remote sensing inversion method of turbid water body particulate organic carbon concentration | |
| Takoutsing et al. | Comparing the prediction performance, uncertainty quantification and extrapolation potential of regression kriging and random forest while accounting for soil measurement errors | |
| CN109163878B (en) | Vegetation dragging force coefficient measuring method and device, computer equipment and storage medium | |
| US10088411B2 (en) | Method and device for performing colorimetric analysis of a test fluid to evaluate physiological parameters | |
| Konishi | Three-parameter lognormal distribution ubiquitously found in cDNA microarray data and its application to parametric data treatment | |
| CN114594060B (en) | Hyperspectral image-based hybrid sensitization detection method and device | |
| CA3129730A1 (en) | Systems and methods for formulating or evaluating a construction composition | |
| US11796530B2 (en) | Simulation and optimization of concrete recipe | |
| Augugliaro et al. | dglars: an R package to estimate sparse generalized linear models | |
| CN110824496B (en) | Motion estimation method, motion estimation device, computer equipment and storage medium | |
| CN113987690A (en) | Method, system, equipment and storage medium for analyzing fatigue stress of aircraft landing gear | |
| CN115685129A (en) | FPGA chip radar signal processing equipment based on artificial intelligence | |
| Veilleux et al. | Pressure sensor calibrations of acoustic telemetry transmitters | |
| Goel et al. | EnergyNN: Energy estimation for neural network inference tasks on DPU | |
| CN113567369A (en) | Forest environment monitoring method and system based on multispectral remote sensing | |
| CN114356538A (en) | Model deployment method, device, equipment and computer readable storage medium | |
| CN114591121B (en) | Emulsion explosive preparation method and system based on near infrared spectrum | |
| CN104112045A (en) | Thruster local optimum configuration method based on dynamic positioning capacity comprehensive standards | |
| CN202096218U (en) | B ultrasonic diagnosis instrument with textural feature quantifying function | |
| CN104049243B (en) | A kind of method and system of diameter radar image emulation |
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 |