CN108458989A - A kind of Coal-rock identification method based on Terahertz multi-parameter spectrum - Google Patents
A kind of Coal-rock identification method based on Terahertz multi-parameter spectrum Download PDFInfo
- Publication number
- CN108458989A CN108458989A CN201810403512.0A CN201810403512A CN108458989A CN 108458989 A CN108458989 A CN 108458989A CN 201810403512 A CN201810403512 A CN 201810403512A CN 108458989 A CN108458989 A CN 108458989A
- Authority
- CN
- China
- Prior art keywords
- coal
- spectrum
- terahertz
- rock
- sample
- 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
- 238000001228 spectrum Methods 0.000 title claims abstract description 157
- 239000011435 rock Substances 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000003245 coal Substances 0.000 claims abstract description 149
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 51
- 238000001328 terahertz time-domain spectroscopy Methods 0.000 claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000010521 absorption reaction Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 230000009467 reduction Effects 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 16
- 238000005065 mining Methods 0.000 claims abstract description 16
- 230000003287 optical effect Effects 0.000 claims abstract description 13
- 238000000411 transmission spectrum Methods 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 5
- 239000000523 sample Substances 0.000 claims description 85
- 239000000843 powder Substances 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000003595 spectral effect Effects 0.000 claims description 18
- 239000000463 material Substances 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 10
- 238000000862 absorption spectrum Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- RHZUVFJBSILHOK-UHFFFAOYSA-N anthracen-1-ylmethanolate Chemical compound C1=CC=C2C=C3C(C[O-])=CC=CC3=CC2=C1 RHZUVFJBSILHOK-UHFFFAOYSA-N 0.000 claims description 4
- 239000003830 anthracite Substances 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 239000003077 lignite Substances 0.000 claims description 4
- 241001269238 Data Species 0.000 claims description 3
- 229910001218 Gallium arsenide Inorganic materials 0.000 claims description 3
- 230000008033 biological extinction Effects 0.000 claims description 3
- 239000002802 bituminous coal Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 229920000573 polyethylene Polymers 0.000 claims description 3
- 229910052710 silicon Inorganic materials 0.000 claims description 3
- 239000010703 silicon Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 229910052594 sapphire Inorganic materials 0.000 claims description 2
- 239000010980 sapphire Substances 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims 1
- 238000012706 support-vector machine Methods 0.000 description 6
- 239000002817 coal dust Substances 0.000 description 3
- 238000001035 drying Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000004575 stone Substances 0.000 description 2
- 239000004698 Polyethylene Substances 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 239000003818 cinder Substances 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000010117 shenhua Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
- G01N21/3586—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation by Terahertz time domain spectroscopy [THz-TDS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Toxicology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of coal-rock interface identification methods based on terahertz time-domain spectroscopy, and suitable for Coal-Rock Interface Recognition, coalcutter is independently turned up and unmanned, Intelligentized mining technical field.The terahertz time-domain spectroscopy that coal petrography sample is acquired using terahertz light spectrometer, Terahertz frequency domain spectra is converted to using Fast Fourier Transform (FFT) by terahertz time-domain spectroscopy；Optical transmission spectra, refractive index spectra and absorption coefficient spectrum are extracted from Terahertz frequency domain spectra；Dimensionality reduction and feature extraction are carried out to detection spectroscopic data using LDA technologies, deep neural network analysis modeling is carried out to optical parameter spectrum；Tested region coal petrography makes sample is acquired, the terahertz time-domain spectroscopy of coal petrography sample is obtained, is brought into step 3 and 4 established models after step 2 processing, carries out Coal-Rock Interface Recognition.Its detect quickly, efficiently, accurately identify coal rock medium, accurately identifying for the cutting state of coalcutter may be implemented, solve the problems, such as automatic lifting of shearer.
Description
Technical field
The present invention relates to it is a kind of based on Terahertz multi-parameter spectrum coal-rock interface identification method, belong to Coal-Rock Interface Recognition,
Coalcutter is independently turned up and unmanned, Intelligentized mining technical field.
Background technology
Unmanned, intelligent working face mining technology is a kind of efficient safe working mode, can effectively reduce people
Member's accident, it is ensured that safety of coal mines is exploited and the developing direction and trend of colliery industry.Coal science and technology " 13 " explicitly points out
Innovation driving development strategy is implemented in full, the related key technical in Intelligent mine is captured, intelligent control technology is brought into
Into the main production link of coal.Reach this purpose, first has to solve the problems, such as coal petrography intelligent recognition, this is also restricting current
The great difficult problem of intelligence coal mining equipment.
Coal-Rock Interface Recognition should be exploited along the interface of coal seam and rock stratum as possible when referring to coalcutter cutting coal seam, to
Ensure maximum output, to adjust coal mining machine roller height in time when cutting to rock stratum and avoid causing cutting so that in raw coal
Being mixed into a large amount of spoils reduces coal quality and output capacity, and causes coal mining machine roller pick impaired.
The other problem of coal petrography stone is always research hotspot both domestic and external, and many scholars also proposed many representative grind
Study carefully method, such as image analytical method, cutting data method, radar detection system.Above-mentioned method achieves certain effect still
There are some disadvantages.Such as when coal petrography hardness property is suitable, it is difficult to judge cutting for coalcutter by the cutting data of coalcutter
Cut state；On the other hand, it for different mining areas, mining environment and equipment, needs to choose different sensors, and adjustment
Discrimination model.
Invention content
Place in order to overcome the above-mentioned deficiencies of the prior art, the present invention provide to solve the above-mentioned problems, it is proposed that a kind of
Coal-rock interface identification method based on Terahertz spectrum.Since Terahertz is a more special frequency range, Terahertz photon energy
Grade is suitable with the vibration level of many dielectrics and material, therefore its photon energy can be inhaled after THz wave irradiates coal petrography
It receives, light intensity will will produce variation to form tera-hertz spectra, and detection substance will be obtained by studying tera-hertz spectra
Physical message (such as absorption spectrum and spectrum of refractive index), judges coal petrography character, to instruct shearer drum height adjustment.Relatively
For coal petrography nonhomogeneous hardness, terahertz light modal data can change with the variation of frequency, and it is larger can to find out otherness
Frequency point.Relative to other spectral techniques, tera-hertz spectra can directly obtain the phase of electric field, without utilizing
Kramers-Kronig equation solutions phase angle, greatly reduces calculation amount and complexity.Even if when coal petrography characteristic close, leading to
It crosses and coal petrography Terahertz transmission spectrum, absorption spectra, spectrum of refractive index and reasonably can also be efficient using depth learning technology is used in combination
" foreign matter with compose " when solving the problems, such as coal petrography characteristic close, realize that the inaccessiable identification of support vector machines (SVM) institute is accurate
Degree.The present invention is achieved through the following technical solutions：A kind of coal-rock interface identification method based on terahertz time-domain spectroscopy,
It is characterized in that, the method includes：
1. a kind of coal-rock interface identification method based on Terahertz multi-parameter spectrum, uses terahertz time-domain spectroscopy instrument, terahertz
Hereby time-domain spectroscopy instrument includes transmitting antenna (1), the sample for generating the femto-second laser of light source (3), generating terahertz pulse
The time difference prolongs between detection storehouse (4), the reception antenna (2) for receiving terahertz pulse and adjustment femtosecond laser and terahertz pulse
When (5) five parts of line；The pattern detection position in storehouse (4) is between transmitting antenna (1) and reception antenna (2), transmitting antenna
In terahertz light perpendicular acting to the coal petrography sample of pattern detection storehouse (4)；It is characterized in that steps are as follows：
Step 1, coal petrography sample is selected and made from the coal petrography of different cultivars respectively, is adopted using terahertz time-domain spectroscopy instrument
Collect the terahertz time-domain spectroscopy data of reference signal and coal petrography sample, the coal petrography sample includes：Anthracite, bituminous coal, lignite,
Sandstone and several classes of shale；
Step 2, terahertz time-domain spectroscopy is converted into Terahertz frequency domain spectra using Fast Fourier Transform (FFT)；From Terahertz
The optical transmission spectra, refractive index spectra and absorption coefficient spectrum of each coal petrography sample are extracted in frequency domain spectra；And to transmitance light
Spectrum, refractive index spectra and absorption coefficient spectrum carry out the pretreatment of smooth and adding window respectively, choose transmitance respectively after relatively
The spectroscopic data of 0.4-1.0THz frequency ranges in spectrum, refractive index spectra and absorption coefficient spectrum；
Step 3, the spectroscopic data that will transmit through rate spectrum, refractive index spectra and absorption coefficient spectrum is labeled as the light of coal and rock
Modal data carries out dimensionality reduction and feature extraction using linear discriminent analytical technology to spectroscopic data；
Step 4, joint point is carried out to optical transmission spectra, refractive index spectra and absorption coefficient spectrum using deep neural network
Analysis modeling；
Step 5, acquisition such as different cultivars coal petrography in step 1 and makes sample, obtain coal, rock sample sheet terahertz time-domain light
Spectrum brings step 3 and step 4 into after step 2 processing, in institute's established model, carries out Coal-Rock Interface Recognition.
The femto-second laser hertz time-domain spectroscopy harvester is the system equipment that University Of Tianjin is set up, wherein cardiac wave
Long 800nm, band are wider than 70nm, repetition rate 80MHz；The material of the transmitting antenna is high resistant GaAs, and described connects
Receipts antenna material is silicon on sapphire, system frequency range：0.1-3.5THz；Polyethylene material is selected in the pattern detection storehouse
Material.
3-5 different points are chosen when the terahertz time-domain spectroscopy of acquisition coal petrography sample every time to be acquired, Mei Gedian
Position 3-4 spectrum of repeated acquisition.
The step 1, using the transmission scan module of terahertz time-domain spectroscopy system, is obtained with drying in detection process
Air is the terahertz time-domain spectroscopy of the reference signal time-domain spectroscopy and coal petrography sample of background, and the dry air humidity is less than
5%.
Terahertz spectral range after the step 2 is fourier transformed is 0.1~3.5THz；
Based on Terahertz frequency domain spectra extraction transmitted spectrum T (ω), refractive index spectra n (ω) and absorption coefficient spectrum α
(ω) uses THz optical parameter extraction models, calculation formula as follows：
T (ω)=Esam(ω)/Eref(ω)
Wherein, transmission coefficient is T (ω), Eref(ω) and Esam(ω) be respectively reference signal Terahertz frequency spectrum and sample too
The thickness of hertz frequency spectrum, sample is d, and c is the light velocity, and n (ω) is the refractive index of sample, and α (ω) is the absorption coefficient of sample, ρ
(ω) item is the ratio of test sample signal and reference signal amplitude,Item is the phase of test sample signal and reference signal
Potential difference, k (ω) are the imaginary part of test sample complex refractivity index, also referred to as extinction coefficient.
The step 2 carries out transmitted spectrum, refractive index spectra and absorption spectrum by window adding technology preferred, extraction noise
Relatively high 0.4-1THz frequency range spectroscopic datas, and the curve of spectrum is handled using Savitzky-Golay smoothing methods, eliminate system
System and ambient noise.
Use linear discriminent analysis method to spectroscopic data carry out dimensionality reduction and extract spectrum characteristic parameter step for：To own
Absorption spectrum, transmitted spectrum, the refraction spectrum of coal sample merge the multi-parameter spectrum X1 of structure coal and mark, by all rock sample sheets
Absorption spectrum, transmitted spectrum, refraction spectrum merge structure rock multi-parameter spectrum X2 and mark；The wherein multiparameter light of coal
The matrix structure of multi-parameter spectrum of spectrum X1 and rock is：Wherein n indicate different coal/
Rock kind, p indicate that the spectroscopic data dimension of same coal/rock, x indicate all sample datas, indicated here with matrix form；
The multi-parameter spectrum of coal, rock sample sheet is subjected to dimensionality reduction and feature extraction by linear discriminent analysis/LDA, relatively
For monochromatic light modal data, combined spectral can obtain higher discrimination after linear discriminent analysis method.
In step 3, the dimensionality reduction flow of linear discriminent analysis method is：
1) from the mean vector of coal petrography spectroscopic data centralized calculation variety classes coal petrography spectroscopic data, wherein vector dimension is set
For 200 dimensions；
2) formula is utilized：Calculate class scatter matrix Sb, wherein NjIndicate mark
Number for j classes sample number, μ be all samples mean vector, μjFor the mean vector of all samples in classification j；
3) formula is utilized：Calculate Scatter Matrix S in classw, wherein XjFor
The spectral data set of jth class coal/rock, NjFor the number of the sample marked as j classes；
4) characteristic value and feature vector in class scatter and class corresponding to divergence are calculated, wherein characteristic value is λ1,
λ2..., λk, feature vector is respectively W1, W2 ..., Wk；
5) characteristic value is arranged in descending order, the feature vector before choosing corresponding to d characteristic value constitutes matrix W；
6) utilize matrix W by raw coal rock spectroscopic data X1/X2 projection mappings to newly spatially, obtain new coal spectrum number
It is reduced to 80 according to collection Y1 and the dimension of new rock spectroscopic data collection Y2, wherein coal spectroscopic data collection Y1 and rock spectroscopic data collection Y2
Dimension greatly reduces data volume and calculates the time.
Different types of coal and rock are labeled respectively, then utilize the coal spectrum number after linear discriminent is analyzed
It is modeled using deep neural network method as input according to collection Y1 and rock spectroscopic data collection Y2, modeling dimension is 80 dimensions, god
It is 500 through first number, output dimension is 2 dimensions, maximum iteration 100, learning rate 0.001, dropout reservation node ratios
It is set as 0.9, loss function uses AdamOptimizer optimizers, it is determined as cross entropy loss reduction.
When coalcutter works, coal mining machine roller cuts coal seam, rock stratum, will produce blocky and powdery coal petrography sample, utilizes
Powder harvester acquires the material powder of current coalcutter cutting, and pattern detection storehouse is collected at by powder by Transfer pipe
It is interior, the terahertz time-domain spectroscopy of unknown powder is obtained by tera-hertz spectra acquisition probe.
Advantageous effect：The present invention acquires the terahertz time-domain light of reference signal and coal petrography using terahertz time-domain spectroscopy instrument
Spectrum；Coal petrography terahertz time-domain spectroscopy is converted into frequency domain spectra using Fast Fourier Transform (FFT)；It is carried from Terahertz frequency domain spectra
Take out transmitted spectrum, refractive index spectra and the absorption coefficient spectrum of coal petrography.Using technologies such as adding window, smooth and LDA to spectrum number
According to being pre-processed, followed by deep neural network, to treated, coal petrography spectrum carries out classification model construction and identification, to real
Coal-Rock Interface Recognition now based on terahertz light spectral technology.
Different coal petrographys are distinguished using terahertz light spectral technology and mode identification method, it is proposed that are based on terahertz time-domain spectroscopy
Coal-rock identification method, relative to it is traditional based on the detection method of coal petrography nonhomogeneous hardness for, terahertz light modal data can be with
The variation of frequency and change, when can efficiently solve coal petrography characteristic close by using depth learning technology " foreign matter is same
Spectrum " problem solves the problem of that current methods decline in recognition accuracy after coal and rock quantity/type increase, identification
Effect is good, has used deep neural network as deep learning method, has solved prior art recognition accuracy as quantity increases
The problem of more declining, the i.e. bad problem of model robustness autgmentability, the present invention have better robustness and autgmentability, carry
High recognition accuracy.This method can quickly, efficiently, accurately identify coal rock medium, applied unmanned/intelligent
Exploitation field.
Description of the drawings
Fig. 1 is the coal-rock interface identification method flow chart based on terahertz time-domain spectroscopy of the embodiment of the present invention；
Fig. 2 is the structural schematic diagram of the terahertz time-domain spectroscopy acquisition system of the present invention；
Fig. 3 a are the part Terahertz frequency spectrums of the present invention；
Fig. 3 b are the fractional transmission spectrum of the present invention；
Fig. 3 c be the present invention partially absorb spectrum；
Fig. 3 d are the fractional index spectrum of the present invention；
Fig. 4 be combined spectral after LDA feature extractions with after single spectrum LDA feature extractions to the influence curve of accuracy rate
Figure；
Fig. 5 is the contrast curve of a variety of coal petrography classification results and existing svm methods tested of the present invention.
In figure：1, transmitting antenna, 2, reception antenna, 3, femto-second laser, 4, pattern detection storehouse, 5, delay line, 6, beam splitting
Mirror.
Specific implementation mode
Such as a kind of coal-rock interface identification method based on terahertz time-domain spectroscopy of Fig. 1 and Fig. 2, which is characterized in that described
Method includes：
Terahertz time-domain spectroscopy instrument includes the transmitting day for generating the femto-second laser 3 of light source, generating terahertz pulse
Time difference between line 1, pattern detection storehouse 4, the reception antenna 2 for receiving terahertz pulse and adjustment femtosecond laser and terahertz pulse
5 five parts of delay line, and light beam is mutually transmitted by beam splitter 6；The pattern detection position in storehouse 4 is in transmitting antenna 1
Between reception antenna 2, on the coal petrography sample of transmitting antenna terahertz light perpendicular acting to pattern detection storehouse 4；The femtosecond
The system equipment that laser hertz time-domain spectroscopy harvester is set up for University Of Tianjin, centre wavelength 800nm, band are wider than
70nm, repetition rate 80MHz；The material of the transmitting antenna is high resistant GaAs, and the reception antenna material is blue precious
Silicon on stone, system frequency range：0.1-3.5THz；Polythene material is selected in the pattern detection storehouse；Acquisition coal petrography sample every time
It chooses 3-5 different points when the terahertz time-domain spectroscopy of product to be acquired, each 3-4 spectrum of point repeated acquisition.
Its step are as follows：
Step 1, coal petrography sample is selected and made from the coal petrography of different cultivars respectively, makes coal petrography sample, it is used
Coal petrography sample mining area from various parts of the country, by the coal cinder of bulk and sillar by spontaneously drying, being crushed, by 80 mesh sieve after,
It is put into sample detection storehouse 4；Or directly using the coal dust in mining area and rock powder after drying, sample inspection is put into after being sieved by 80 mesh
Survey storehouse；The terahertz time-domain spectroscopy data of reference signal and coal petrography sample, the coal are acquired using terahertz time-domain spectroscopy instrument
Rock sample product include：Anthracite, bituminous coal, lignite, sandstone and several classes of shale；In detection process, using terahertz time-domain spectroscopy system
Transmission scan module, obtain using dry air as the terahertz time-domain light of the reference signal time-domain spectroscopy of background and coal petrography sample
Spectrum, the dry air humidity are less than 5%；
Step 2, terahertz time-domain spectroscopy is converted into Terahertz frequency domain spectra using Fast Fourier Transform (FFT)；From Terahertz
The optical transmission spectra, refractive index spectra and absorption coefficient spectrum of each coal petrography sample are extracted in frequency domain spectra；And to transmitance light
Spectrum, refractive index spectra and absorption coefficient spectrum carry out the pretreatment of smooth and adding window respectively, choose transmitance respectively after relatively
The spectroscopic data of 0.4-1.0THz frequency ranges in spectrum, refractive index spectra and absorption coefficient spectrum；By window adding technology to transmitted light
Spectrum, refractive index spectra and absorption spectrum carry out preferred, the extraction higher 0.4-1THz frequency ranges spectroscopic data of signal-to-noise ratio, and utilize
Savitzky-Golay smoothing methods handle the curve of spectrum, eliminate system and ambient noise；
Terahertz spectral range after the step 2 is fourier transformed is 0.1~3.5THz；
Based on Terahertz frequency domain spectra extraction transmitted spectrum T (ω), refractive index spectra n (ω) and absorption coefficient spectrum α
(ω) uses THz optical parameter extraction models, calculation formula as follows：
T (ω)=Esam(ω)/Eref(ω)
Wherein, transmission coefficient is T (ω), Eref(ω) and Esam(ω) be respectively reference signal Terahertz frequency spectrum and sample too
The thickness of hertz frequency spectrum, sample is d, and c is the light velocity, and n (ω) is the refractive index of sample, and α (ω) is the absorption coefficient of sample, ρ
(ω) item is the ratio of test sample signal and reference signal amplitude,Item is the phase of test sample signal and reference signal
Potential difference, k (ω) are the imaginary part of test sample complex refractivity index, also referred to as extinction coefficient；
Step 3, the spectroscopic data that will transmit through rate spectrum, refractive index spectra and absorption coefficient spectrum is labeled as the light of coal and rock
Modal data carries out dimensionality reduction and feature extraction using linear discriminent analytical technology to spectroscopic data；
Use linear discriminent analysis method to spectroscopic data carry out dimensionality reduction and extract spectrum characteristic parameter step for：To own
Absorption spectrum, transmitted spectrum, the refraction spectrum of coal sample merge the multi-parameter spectrum X1 of structure coal and mark, by all rock sample sheets
Absorption spectrum, transmitted spectrum, refraction spectrum merge structure rock multi-parameter spectrum X2 and mark；The wherein multiparameter light of coal
The matrix structure of multi-parameter spectrum of spectrum X1 and rock is：Wherein n indicate different coal/
Rock kind, p indicate that the spectroscopic data dimension of same coal/rock, x indicate all sample datas, indicated here with matrix form；
The multi-parameter spectrum of coal, rock sample sheet is subjected to dimensionality reduction and feature extraction by linear discriminent analysis/LDA, relatively
For monochromatic light modal data, combined spectral can obtain higher discrimination after linear discriminent analysis method；
The dimensionality reduction flow of linear discriminent analysis method is：
1) from the mean vector of coal petrography spectroscopic data centralized calculation variety classes coal petrography spectroscopic data, wherein vector dimension is set
For 200 dimensions；
2) formula is utilized：Calculate class scatter matrix Sb, wherein NjIndicate mark
Number for j classes sample number, μ be all samples mean vector, μjFor the mean vector of all samples in classification j；
3) formula is utilized：Calculate Scatter Matrix S in classw, wherein XjFor
The spectral data set of jth class coal/rock, NjFor the number of the sample marked as j classes；
4) characteristic value and feature vector in class scatter and class corresponding to divergence are calculated, wherein characteristic value is λ1,
λ2..., λk, feature vector is respectively W1, W2 ..., Wk；
5) characteristic value is arranged in descending order, the feature vector before choosing corresponding to d characteristic value constitutes matrix W；
6) utilize matrix W by raw coal rock spectroscopic data X1/X2 projection mappings to newly spatially, obtain new coal spectrum number
It is reduced to 80 according to collection Y1 and the dimension of new rock spectroscopic data collection Y2, wherein coal spectroscopic data collection Y1 and rock spectroscopic data collection Y2
Dimension greatly reduces data volume and calculates the time；
Different types of coal and rock are labeled respectively, then utilize the coal spectrum number after linear discriminent is analyzed
It is modeled using deep neural network method as input according to collection Y1 and rock spectroscopic data collection Y2, modeling dimension is 80 dimensions, god
It is 500 through first number, output dimension is 2 dimensions, maximum iteration 100, learning rate 0.001, dropout reservation node ratios
It is set as 0.9, loss function uses AdamOptimizer optimizers, it is determined as cross entropy loss reduction；
Fig. 4 be combined spectral after LDA feature extractions with the influence to accuracy rate after single spectrum LDA feature extractions,
Middle LDA (11) is combined spectral, remaining is single spectrum.Abscissa is sample size in figure, and totally 200 samples, include 15 kinds
Coal and 5 kinds of rocks, 10 samples of each type, it is clear that for opposite monochromatic light modal data, combined spectral can obtain after LDA
Higher discrimination；
Step 4, joint point is carried out to optical transmission spectra, refractive index spectra and absorption coefficient spectrum using deep neural network
Analysis modeling；
Step 5, acquisition such as different cultivars coal petrography in step 1 and makes sample, obtain coal, rock sample sheet terahertz time-domain light
Spectrum brings into step 3 and step 4 established model after step 2 processing, carries out Coal-Rock Interface Recognition.
Such as the spectroscopic data in Fig. 3 a, Fig. 3 b, Fig. 3 c and Fig. 3 d, the original spectral data of coal and rock simultaneously can not be by direct area
Point, but by adding window selection data and smoothing processing and after LDA Data Dimensionality Reductions and feature extraction, the spy of coal petrography sample
Value indicative has significant difference, is modeled to combined spectral by deep neural network, can accurately realize to a variety of coals
The identification of rock.This is also indicated that, " foreign matter is with spectrum " when coal petrography characteristic close can be efficiently solved the problems, such as by this method, is improved
Recognition accuracy.
When coalcutter works, above-mentioned coal mining machine roller is cut into coal seam, rock stratum, will produce blocky and powdery coal petrography
Sample acquires the material powder of current coalcutter cutting using powder harvester, and sample is collected at by powder by Transfer pipe
It detects in storehouse, the terahertz time-domain spectroscopy of unknown powder is obtained by tera-hertz spectra acquisition probe.
Terahertz time-domain spectroscopy instrument is placed near coal mining machine roller, when coalcutter is started to work, with the rotation of roller
Turn, coal seam/rock stratum is cut by roller pick, forms coal/rock powder or coal/sillar, and coal/rock powder collector is mounted below roller and adopts
On coal machine fuselage, the coal dust and rock powder generated when collecting coal mining machine roller cutting coal seam/rock stratum in such a way that timing sucks, coal
Powder is sent into the filling that sample is realized in pattern detection storehouse 4 by pipe passage.Pattern detection storehouse 4 can be fallen by way of timing rotation
Go out original powder, then resets and be packed into new coal petrography powder.The pattern detection storehouse 4 is located in terahertz sources light path,
Make in terahertz light perpendicular acting to sample.
In steps of 5, using LDA treated spectroscopic datas as input, it is sent into established deep neural network model
In, model exports result；When result is true, illustrate that current powder is that coal dust namely coalcutter are currently cutting coal seam；When
Output result is fictitious time, illustrates that current powder is that rock powder namely coalcutter are currently cutting rock stratum, inclines in conjunction with rocker arm of coal mining machine
Angle can determine whether current tangible cutting top plate or bottom plate, and adjustment roller height downwards is needed at once when cutting top plate, works as cutting
When bottom plate, need to adjust upward roller height at once.
Fig. 5 for a variety of coal petrography classification results and existing svm methods tested comparison.Wherein case1 is this method,
Case2 is the method for SVM.Abscissa is sample size, totally 80 samples, includes 15 kinds of coals and 5 kinds of rocks, each type 4
A sample, the comparison using this method and SVM methods to the classification results of a variety of different coal petrography samples, wherein coal petrography sample come
From in Shandong Yanzhou Mining Group Xinglongzhuang Mine, Lenovo Group's Guo Zhuan coal mines, Huaibei mines group Mount Tai He Kuang, the black Dai Gou of Shenhua Group
The ground such as mine, Xingtai mines group east Pang Kuang, type include packsand, shale and middle sandstone and anthracite, meager coal, 1/3/
More parts of the coal samples such as coking coal, bottle coal, dross coal, jet coal and lignite；The sample of acquisition is subjected to testing experiment, knot according to step 5
Fruit shows that, when coal and smaller rock kind quantity, the method for this method and SVM can keep higher discrimination, but work as
When coal petrography type increases, the discrimination of SVM declines, and this method still can accurately identify a variety of coal petrographys, to precisely
The cutting state for judging coalcutter, provide foundation for automatic lifting of shearer.
Claims (10)
1. a kind of coal-rock interface identification method based on Terahertz multi-parameter spectrum, using terahertz time-domain spectroscopy instrument, when Terahertz
Domain spectrometer includes for generating the femto-second laser of light source (3), the transmitting antenna (1) for generating terahertz pulse, pattern detection
The delay line of time difference between storehouse (4), the reception antenna (2) for receiving terahertz pulse and adjustment femtosecond laser and terahertz pulse
(5) five parts；The pattern detection position in storehouse (4) is between transmitting antenna (1) and reception antenna (2), transmitting antenna terahertz
Hereby in light perpendicular acting to the coal petrography sample of pattern detection storehouse (4)；It is characterized in that steps are as follows：
Step 1, coal petrography sample is selected and made from the coal petrography of different cultivars respectively, is acquired and is joined using terahertz time-domain spectroscopy instrument
The terahertz time-domain spectroscopy data of signal and coal petrography sample are examined, the coal petrography sample includes：Anthracite, bituminous coal, lignite, sandstone
With several classes of shale；
Step 2, terahertz time-domain spectroscopy is converted into Terahertz frequency domain spectra using Fast Fourier Transform (FFT)；From Terahertz frequency domain
The optical transmission spectra, refractive index spectra and absorption coefficient spectrum of each coal petrography sample are extracted in spectrum；And to optical transmission spectra, folding
Penetrate rate spectrum and absorption coefficient spectrum and carry out the pretreatment of smooth and adding window respectively, after relatively respectively selection optical transmission spectra,
The spectroscopic data of 0.4-1.0THz frequency ranges in refractive index spectra and absorption coefficient spectrum；
Step 3, the spectroscopic data that will transmit through rate spectrum, refractive index spectra and absorption coefficient spectrum is labeled as the spectrum number of coal and rock
According to using linear discriminent analytical technology to spectroscopic data progress dimensionality reduction and feature extraction；
Step 4, Conjoint Analysis is carried out to optical transmission spectra, refractive index spectra and absorption coefficient spectrum using deep neural network to build
Mould；
Step 5, acquisition such as different cultivars coal petrography in step 1 and makes sample, obtain coal, rock sample sheet terahertz time-domain spectroscopy,
Step 3 and step 4 are brought into after step 2 processing, in institute's established model, carry out Coal-Rock Interface Recognition.
2. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that：It is described
Femto-second laser hertz time-domain spectroscopy harvester be University Of Tianjin set up system equipment, centre wavelength 800nm, bandwidth
More than 70nm, repetition rate 80MHz；The material of the transmitting antenna is high resistant GaAs, and the reception antenna material is
Silicon on sapphire, system frequency range：0.1-3.5THz；Polythene material is selected in the pattern detection storehouse.
3. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that：Every time
It chooses 3-5 different points when acquiring the terahertz time-domain spectroscopy of coal petrography sample to be acquired, each point repeated acquisition 3-4
Secondary spectrum.
4. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that：It is described
Step 1, using the transmission scan module of terahertz time-domain spectroscopy system, is obtained using dry air as background in detection process
The terahertz time-domain spectroscopy of reference signal time-domain spectroscopy and coal petrography sample, the dry air humidity are less than 5%.
5. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that：It is described
Terahertz spectral range after step 2 is fourier transformed is 0.1~3.5THz；
It is adopted based on Terahertz frequency domain spectra extraction transmitted spectrum T (ω), refractive index spectra n (ω) and absorption coefficient spectrum α (ω)
With THz optical parameter extraction models, calculation formula is as follows：
T (ω)=Esam(ω)/Eref(ω)
Wherein, transmission coefficient is T (ω), Eref(ω) and Esam(ω) is respectively reference signal Terahertz frequency spectrum and sample Terahertz
The thickness of frequency spectrum, sample is d, and c is the light velocity, and n (ω) is the refractive index of sample, and α (ω) is the absorption coefficient of sample, ρ (ω) item
For the ratio of test sample signal and reference signal amplitude,Item is the phase difference of test sample signal and reference signal, k
(ω) is the imaginary part of test sample complex refractivity index, also referred to as extinction coefficient.
6. a kind of coal-rock interface identification method based on Terahertz multi-parameter spectrum according to claim 1, it is characterised in that：
The step 2 carries out preferably transmitted spectrum, refractive index spectra and absorption spectrum by window adding technology, and extraction signal-to-noise ratio is higher
0.4-1THz frequency range spectroscopic datas, and the curve of spectrum is handled using Savitzky-Golay smoothing methods, eliminate system and environment
Noise.
7. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that use
Linear discriminent analysis method carries out dimensionality reduction and extracts spectrum characteristic parameter step to spectroscopic data：By the absorption of all coal samples
Spectrum, transmitted spectrum, refraction spectrum merge the multi-parameter spectrum X1 of structure coal and mark, by the absorption light of all rock sample sheets
Spectrum, transmitted spectrum, refraction spectrum merge the multi-parameter spectrum X2 of structure rock and mark；The wherein multi-parameter spectrum X1 of coal and rock
The matrix structure of multi-parameter spectrum is：Wherein n indicates that different coal/rock kinds, p indicate
The spectroscopic data dimension of same coal/rock, x indicate all sample datas, are indicated here with matrix form；
The multi-parameter spectrum of coal, rock sample sheet is subjected to dimensionality reduction and feature extraction, opposite monochromatic light by linear discriminent analysis/LDA
For modal data, combined spectral can obtain higher discrimination after linear discriminent analysis method.
8. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that step 3
In, the dimensionality reduction flow of linear discriminent analysis method is：
1) from the mean vector of coal petrography spectroscopic data centralized calculation variety classes coal petrography spectroscopic data, wherein vector dimension is set as
200 dimensions；
2) formula is utilized：Calculate class scatter matrix Sb, wherein NjIt indicates marked as j
The number of the sample of class, μ are the mean vector of all samples, μjFor the mean vector of all samples in classification j；
3) formula is utilized：Calculate Scatter Matrix S in classw, wherein XjFor jth
The spectral data set of class coal/rock, NjFor the number of the sample marked as j classes；
4) characteristic value and feature vector in class scatter and class corresponding to divergence are calculated, wherein characteristic value is λ1, λ2..., λk,
Feature vector is respectively W1, W2 ..., Wk；
5) characteristic value is arranged in descending order, the feature vector before choosing corresponding to d characteristic value constitutes matrix W；
6) utilize matrix W by raw coal rock spectroscopic data X1/X2 projection mappings to newly spatially, obtain new coal spectroscopic data collection
Y1 and the dimension of new rock spectroscopic data collection Y2, wherein coal spectroscopic data collection Y1 and rock spectroscopic data collection Y2 have been reduced to 80 dimensions,
It greatly reduces data volume and calculates the time.
9. the coal-rock interface identification method based on Terahertz multi-parameter spectrum according to claim 1 or 8, it is characterised in that：
Different types of coal and rock are labeled respectively, then utilize the coal spectroscopic data collection Y1 after linear discriminent is analyzed and
Rock spectroscopic data collection Y2 is modeled as input using deep neural network method, and modeling dimension is 80 dimensions, neuron number
It is 500, output dimension is tieed up for 2, maximum iteration 100, learning rate 0.001, and dropout retains node ratio and is set as 0.9,
Loss function uses AdamOptimizer optimizers, it is determined as cross entropy loss reduction.
10. the coal-rock interface identification method according to claim 1 based on Terahertz multi-parameter spectrum, it is characterised in that：When
When coalcutter works, coal mining machine roller cuts coal seam, rock stratum, will produce blocky and powdery coal petrography sample, is acquired and is filled using powder
It sets, acquires the material powder of current coalcutter cutting, be collected in pattern detection storehouse by powder by Transfer pipe, pass through terahertz
Hereby spectra collection probe obtains the terahertz time-domain spectroscopy of unknown powder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810403512.0A CN108458989B (en) | 2018-04-28 | 2018-04-28 | Terahertz multi-parameter spectrum-based coal rock identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810403512.0A CN108458989B (en) | 2018-04-28 | 2018-04-28 | Terahertz multi-parameter spectrum-based coal rock identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108458989A true CN108458989A (en) | 2018-08-28 |
| CN108458989B CN108458989B (en) | 2020-10-09 |
Family
ID=63236397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810403512.0A Active CN108458989B (en) | 2018-04-28 | 2018-04-28 | Terahertz multi-parameter spectrum-based coal rock identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108458989B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632693A (en) * | 2018-12-10 | 2019-04-16 | 昆明理工大学 | A kind of tera-hertz spectra recognition methods based on BLSTM-RNN |
| CN109765191A (en) * | 2019-01-18 | 2019-05-17 | 中国矿业大学 | A kind of movement coal petrography parallel-moving type tracking EO-1 hyperion identification device |
| CN109886421A (en) * | 2019-01-08 | 2019-06-14 | 浙江大学 | Colony intelligence coalcutter cut mode identifying system based on integrated study |
| CN110068544A (en) * | 2019-05-08 | 2019-07-30 | 广东工业大学 | Material identification network model training method and tera-hertz spectra substance identification |
| CN110068543A (en) * | 2019-03-26 | 2019-07-30 | 昆明理工大学 | A kind of tera-hertz spectra recognition methods based on transfer learning |
| CN110080766A (en) * | 2019-04-30 | 2019-08-02 | 中国矿业大学 | Fully-mechanized mining working coal petrography identification device and method |
| CN110082307A (en) * | 2019-04-30 | 2019-08-02 | 中国矿业大学 | Simulate the coal petrography reflectance spectrum identification experimental provision and method of underground coal mine environment |
| CN110749566A (en) * | 2019-10-23 | 2020-02-04 | 深圳市太赫兹科技创新研究院有限公司 | Detection method and detection device for Chinese medicinal material year and terminal equipment |
| CN110751230A (en) * | 2019-10-30 | 2020-02-04 | 深圳市太赫兹科技创新研究院有限公司 | Substance classification method, substance classification device, terminal device and storage medium |
| CN111337883A (en) * | 2020-04-17 | 2020-06-26 | 中国矿业大学(北京) | Intelligent detection and identification system and method for mine coal rock interface |
| CN111982838A (en) * | 2020-08-25 | 2020-11-24 | 吉林大学 | Hyperspectrum-based coal rock identification and detection method |
| CN113029995A (en) * | 2021-03-10 | 2021-06-25 | 太原理工大学 | Linear frequency modulation coal rock radiation detection device and method |
| CN113295673A (en) * | 2021-04-29 | 2021-08-24 | 中国科学院沈阳自动化研究所 | Laser-induced breakdown spectroscopy weak supervision feature extraction method |
| CN113569664A (en) * | 2021-07-08 | 2021-10-29 | 太原理工大学 | Acoustic-electric signal fused coal rock identification method |
| CN114937190A (en) * | 2022-05-31 | 2022-08-23 | 南京林业大学 | Method and system for judging seed cotton opening effectiveness |
| CN115165847A (en) * | 2022-07-07 | 2022-10-11 | 中煤科工集团上海有限公司 | Coal rock spectrum sensing device and coal mining machine comprising same |
| CN116383704A (en) * | 2023-04-17 | 2023-07-04 | 中煤科工集团上海有限公司 | LIBS single spectral line-based coal and rock identification method |
| CN116561620A (en) * | 2023-04-17 | 2023-08-08 | 中煤科工集团上海有限公司 | LIBS spectrum data processing method, device and medium based on variable projection importance |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040036814A1 (en) * | 2002-08-20 | 2004-02-26 | Fuji Xerox Co., Ltd. | Photonic crystal, method of producing photonic crystal, and functional element |
| CN105279379A (en) * | 2015-10-28 | 2016-01-27 | 昆明理工大学 | Terahertz spectroscopy feature extraction method based on convex combination kernel function principal component analysis |
| CN105569658A (en) * | 2015-12-12 | 2016-05-11 | 江苏师范大学 | Coalcutter coal rock distribution recognition device and method adopting terahertz imaging technology |
| CN106124435A (en) * | 2016-07-04 | 2016-11-16 | 江苏大学 | Based on visible ray, near-infrared, the rice new-old quality inspection device of Terahertz fusion spectral technique and detection method |
| CN106706552A (en) * | 2016-11-25 | 2017-05-24 | 河南工业大学 | Method for detecting wheat quality based on multiple-information integration |
| CN106778815A (en) * | 2016-11-23 | 2017-05-31 | 河南工业大学 | Wheat quality THz spectral classification methods based on DS evidence theories |
| CN107328735A (en) * | 2017-08-30 | 2017-11-07 | 浙江大学 | Rape species discrimination method based on terahertz light spectral technology |
-
2018
- 2018-04-28 CN CN201810403512.0A patent/CN108458989B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040036814A1 (en) * | 2002-08-20 | 2004-02-26 | Fuji Xerox Co., Ltd. | Photonic crystal, method of producing photonic crystal, and functional element |
| CN105279379A (en) * | 2015-10-28 | 2016-01-27 | 昆明理工大学 | Terahertz spectroscopy feature extraction method based on convex combination kernel function principal component analysis |
| CN105569658A (en) * | 2015-12-12 | 2016-05-11 | 江苏师范大学 | Coalcutter coal rock distribution recognition device and method adopting terahertz imaging technology |
| CN106124435A (en) * | 2016-07-04 | 2016-11-16 | 江苏大学 | Based on visible ray, near-infrared, the rice new-old quality inspection device of Terahertz fusion spectral technique and detection method |
| CN106778815A (en) * | 2016-11-23 | 2017-05-31 | 河南工业大学 | Wheat quality THz spectral classification methods based on DS evidence theories |
| CN106706552A (en) * | 2016-11-25 | 2017-05-24 | 河南工业大学 | Method for detecting wheat quality based on multiple-information integration |
| CN107328735A (en) * | 2017-08-30 | 2017-11-07 | 浙江大学 | Rape species discrimination method based on terahertz light spectral technology |
Non-Patent Citations (4)
| Title |
|---|
| XIN WANG 等: "Characterization and Classification of Coals and Rocks Using Terahertz Time-Domain Spectroscopy", 《J INFRARED MILLI TERAHZ WAVES》 * |
| 季琲琲: "基于太赫兹时域光谱技术材料参数提取方法的研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 王昕 等: "基于太赫兹光谱技术的煤岩识别方法", 《煤矿开采》 * |
| 王昕: "基于电磁波技术的煤岩识别方法研究", 《中国博士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632693A (en) * | 2018-12-10 | 2019-04-16 | 昆明理工大学 | A kind of tera-hertz spectra recognition methods based on BLSTM-RNN |
| CN109886421A (en) * | 2019-01-08 | 2019-06-14 | 浙江大学 | Colony intelligence coalcutter cut mode identifying system based on integrated study |
| CN109765191A (en) * | 2019-01-18 | 2019-05-17 | 中国矿业大学 | A kind of movement coal petrography parallel-moving type tracking EO-1 hyperion identification device |
| CN109765191B (en) * | 2019-01-18 | 2023-11-10 | 中国矿业大学 | Motion coal rock translation type tracking hyperspectral identification device |
| CN110068543A (en) * | 2019-03-26 | 2019-07-30 | 昆明理工大学 | A kind of tera-hertz spectra recognition methods based on transfer learning |
| CN110082307A (en) * | 2019-04-30 | 2019-08-02 | 中国矿业大学 | Simulate the coal petrography reflectance spectrum identification experimental provision and method of underground coal mine environment |
| CN110080766A (en) * | 2019-04-30 | 2019-08-02 | 中国矿业大学 | Fully-mechanized mining working coal petrography identification device and method |
| CN110080766B (en) * | 2019-04-30 | 2024-03-01 | 中国矿业大学 | Comprehensive mining working face coal-rock interface identification device and method |
| CN110082307B (en) * | 2019-04-30 | 2023-08-29 | 中国矿业大学 | Coal rock reflection spectrum identification experimental device and method for simulating underground coal mine environment |
| CN110068544B (en) * | 2019-05-08 | 2021-09-17 | 广东工业大学 | Substance identification network model training method and terahertz spectrum substance identification method |
| CN110068544A (en) * | 2019-05-08 | 2019-07-30 | 广东工业大学 | Material identification network model training method and tera-hertz spectra substance identification |
| CN110749566A (en) * | 2019-10-23 | 2020-02-04 | 深圳市太赫兹科技创新研究院有限公司 | Detection method and detection device for Chinese medicinal material year and terminal equipment |
| CN110749566B (en) * | 2019-10-23 | 2024-05-10 | 深圳市太赫兹科技创新研究院有限公司 | Detection method, detection device and terminal equipment for years of traditional Chinese medicinal materials |
| CN110751230A (en) * | 2019-10-30 | 2020-02-04 | 深圳市太赫兹科技创新研究院有限公司 | Substance classification method, substance classification device, terminal device and storage medium |
| CN111337883A (en) * | 2020-04-17 | 2020-06-26 | 中国矿业大学(北京) | Intelligent detection and identification system and method for mine coal rock interface |
| CN111982838A (en) * | 2020-08-25 | 2020-11-24 | 吉林大学 | Hyperspectrum-based coal rock identification and detection method |
| CN113029995A (en) * | 2021-03-10 | 2021-06-25 | 太原理工大学 | Linear frequency modulation coal rock radiation detection device and method |
| CN113029995B (en) * | 2021-03-10 | 2022-09-27 | 太原理工大学 | Linear frequency modulation coal rock radiation detection device and method |
| CN113295673A (en) * | 2021-04-29 | 2021-08-24 | 中国科学院沈阳自动化研究所 | Laser-induced breakdown spectroscopy weak supervision feature extraction method |
| CN113569664B (en) * | 2021-07-08 | 2023-12-26 | 太原理工大学 | Coal rock identification method based on acoustic-electric signal fusion |
| CN113569664A (en) * | 2021-07-08 | 2021-10-29 | 太原理工大学 | Acoustic-electric signal fused coal rock identification method |
| CN114937190A (en) * | 2022-05-31 | 2022-08-23 | 南京林业大学 | Method and system for judging seed cotton opening effectiveness |
| CN115165847A (en) * | 2022-07-07 | 2022-10-11 | 中煤科工集团上海有限公司 | Coal rock spectrum sensing device and coal mining machine comprising same |
| CN116561620A (en) * | 2023-04-17 | 2023-08-08 | 中煤科工集团上海有限公司 | LIBS spectrum data processing method, device and medium based on variable projection importance |
| CN116383704A (en) * | 2023-04-17 | 2023-07-04 | 中煤科工集团上海有限公司 | LIBS single spectral line-based coal and rock identification method |
| CN116561620B (en) * | 2023-04-17 | 2024-05-03 | 中煤科工集团上海有限公司 | LIBS spectrum data processing method, device and medium based on variable projection importance |
| CN116383704B (en) * | 2023-04-17 | 2024-05-28 | 中煤科工集团上海有限公司 | LIBS single spectral line-based coal and rock identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108458989B (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108458989A (en) | A kind of Coal-rock identification method based on Terahertz multi-parameter spectrum | |
| CN108279217B (en) | Coal rock distinguishing method based on terahertz time-domain spectroscopy | |
| US11352879B2 (en) | Collaborative sensing and prediction of source rock properties | |
| CN102004088B (en) | Method for measuring coal property on line based on neural network | |
| CN105938099A (en) | Rock character judging method and system based on laser-induced breakdown spectroscopy | |
| CN108801934A (en) | A kind of modeling method of soil organic carbon EO-1 hyperion prediction model | |
| CN101949686A (en) | Online nondestructive testing (NDT) method and device for comprehensive internal/external qualities of fruits | |
| CN107589094B (en) | Method for determining type of Anshan-type iron ore based on spectral characteristics | |
| CN106824825A (en) | Waste and old ore method for separating and device based on LIBS | |
| CN106645037A (en) | Method for detecting heavy metal content of coal gangue filling reclamation reconstruction soil based on high spectrum technology | |
| CN104596957A (en) | Estimation method for content of copper in soil on basis of visible-light near-infrared spectrum technology | |
| CN104111234A (en) | Method and device for online detection of biomass basic characteristics based on near infrared spectroscopy | |
| US10641758B2 (en) | Apparatus, systems, and methods for enhancing hydrocarbon extraction and techniques related thereto | |
| CN105092579A (en) | Mango quality non-destructive testing device | |
| CN109001834A (en) | One kind being based on active Terahertz safety inspection method | |
| CN106501208A (en) | A kind of tobacco style similitude sorting technique based near infrared light spectrum signature | |
| CN105699319A (en) | Near infrared spectrum quick detection method for total moisture of coal based on gaussian process | |
| CN105092436B (en) | A kind of grain size of sediment spectroscopic analysis methods and device | |
| CN106384116A (en) | Terahertz imaging based plant vein recognition method and device | |
| CN111537469A (en) | Apple quality rapid nondestructive testing method based on near-infrared technology | |
| CN105486661A (en) | Near-infrared spectrum coal ash content rapid detection method based on Gaussian process | |
| Debaene et al. | Visible and near-infrared spectroscopy as a tool for soil classification and soil profile description | |
| CN106767457A (en) | A kind of water-surface oil film method for measuring thickness and device based on raman spectroscopy measurement | |
| Zhizhong et al. | A review on the geological applications of hyperspectral remote sensing technology | |
| Shankar | Field characterization by Near Infrared (NIR) mineral identifiers-A new prospecting approach |
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 |