CN116297273A - On-line analysis system and method for coal quality based on factory entry - Google Patents
On-line analysis system and method for coal quality based on factory entry Download PDFInfo
- Publication number
- CN116297273A CN116297273A CN202310576699.5A CN202310576699A CN116297273A CN 116297273 A CN116297273 A CN 116297273A CN 202310576699 A CN202310576699 A CN 202310576699A CN 116297273 A CN116297273 A CN 116297273A
- Authority
- CN
- China
- Prior art keywords
- coal
- coal sample
- sample
- matrix
- assembly
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 573
- 238000004458 analytical method Methods 0.000 title claims abstract description 152
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000001228 spectrum Methods 0.000 claims abstract description 102
- 238000002835 absorbance Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 134
- 238000012549 training Methods 0.000 claims description 96
- 238000005070 sampling Methods 0.000 claims description 45
- 238000004064 recycling Methods 0.000 claims description 36
- 238000013527 convolutional neural network Methods 0.000 claims description 35
- 230000003287 optical effect Effects 0.000 claims description 34
- 238000012360 testing method Methods 0.000 claims description 33
- 238000010276 construction Methods 0.000 claims description 23
- 238000006243 chemical reaction Methods 0.000 claims description 20
- 238000000513 principal component analysis Methods 0.000 claims description 19
- 238000012797 qualification Methods 0.000 claims description 17
- 239000002245 particle Substances 0.000 claims description 13
- 239000000428 dust Substances 0.000 claims description 10
- 230000001678 irradiating effect Effects 0.000 claims description 7
- 239000013307 optical fiber Substances 0.000 claims description 7
- 230000003595 spectral effect Effects 0.000 claims description 4
- 238000005303 weighing Methods 0.000 claims description 3
- 230000000149 penetrating effect Effects 0.000 claims description 2
- 230000000712 assembly Effects 0.000 claims 1
- 238000000429 assembly Methods 0.000 claims 1
- 239000000843 powder Substances 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 182
- 239000002817 coal dust Substances 0.000 description 8
- 238000011084 recovery Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000002536 laser-induced breakdown spectroscopy Methods 0.000 description 5
- 239000000126 substance Substances 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 210000002381 plasma Anatomy 0.000 description 4
- 239000000945 filler Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur 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
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/02—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor using a plurality of sample containers moved by a conveyor system past one or more treatment or analysis stations
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a coal quality online analysis system based on factory entry, which comprises a sampler, a conveying device and a coal quality analysis assembly, wherein the sampler is used for extracting a coal sample from a coal car; the conveying device is used for conveying the coal sample to the coal quality analysis assembly; the coal quality analysis component is arranged to emit light to the coal sample, coal sample spectrum data of reflected light of the coal sample is collected, coal quality analysis is carried out through the coal sample spectrum data, whether the coal sample is qualified or not is judged through a coal quality analysis result, and the coal sample spectrum data comprises a coal sample number, a wavelength or a wave number and absorbance corresponding to the wavelength or the wave number. The invention also provides a method. The invention can analyze the coal quality on line before the coal powder enters the factory, and prevent unqualified coal powder from entering the factory.
Description
Technical Field
The invention relates to the technical field of coal quality analysis, in particular to a coal quality online analysis system and method based on entering a factory.
Background
Coal is widely used as fuel in various industries. The instruction indexes of the coal include moisture, ash, volatile matters, total sulfur, total moisture, heating value and the like, and the price and the application of the coal are different, so that the coal quality analysis is needed before the coal enters a coal yard.
In the prior art, the coal quality analysis adopts on-site sampling and manual sample preparation and test in a laboratory, and has long detection time and low efficiency.
Laser induced breakdown spectroscopy (Laser induced breakdown spectroscopy, LIBS) has been widely used based on direct measurement of coal fines in the particulate flow regime. The LIBS directly measures the working principle of particle flow, namely, a beam of pulse laser is focused at the center of freely falling pulverized coal particle flow, so that pulverized coal particles in a certain range are ablated, further excitation is carried out to generate plasma, a spectrometer detects a spectrum signal radiated by the plasma in the attenuation cooling process, and the material type and the duty ratio concentration data of the pulverized coal are obtained by analyzing a spectrum with specific wavelength and intensity. For coal dust detection, while LIBS directly measuring particle flow has the advantage of no need for sample preparation, numerous studies have found that this measurement scheme has poor spectral signal stability. Because the number, the particle diameter and the spatial distribution of particles near the laser focus are randomly changed, the interaction between the laser and the particles is very complex, the generated plasmas have obvious differences in morphology, and the center of the plasmas can drift before and after the laser focus.
The patent application with the application number of 201610574583.8 and the name of the method and the device for analyzing the coal dust on line discloses on-line analysis of the coal dust, but a light source and a detection probe of the patent application are arranged separately, and the light source is easily influenced by dust, so that the stability of light irradiated on a coal sample is influenced; in addition, two light sources are adopted to irradiate the coal sample from different angles, so that light spots of the coal sample detected by the detection probe are not overlapped, even part of the light spots are not overlapped, the light intensities of the overlapped part and the non-overlapped part are different, namely the light intensities are inconsistent, and the accuracy of coal analysis is affected.
Disclosure of Invention
Aiming at one or more of the problems in the prior art, the invention provides a coal quality online analysis system based on entering a factory, which comprises a sampler, a conveying device and a coal quality analysis component, wherein the sampler is used for extracting a coal sample from a coal car; the conveying device is used for conveying the coal sample to the coal quality analysis assembly; the coal quality analysis component is arranged to emit light to the coal sample, coal sample spectrum data of reflected light of the coal sample is collected, coal quality analysis is carried out through the coal sample spectrum data, whether the coal sample is qualified or not is judged through a coal quality analysis result, and the coal sample spectrum data comprises a coal sample number, a wavelength or a wave number and absorbance corresponding to the wavelength or the wave number.
According to one aspect of the invention, the coal sampler further comprises a crushing device for crushing the coal sample extracted by the sampler to a set particle size and throwing the coal sample onto the conveying device.
According to one aspect of the present invention, there is further included a sampling support for mounting the sampler so that the sampler can be moved in any one of three-dimensional directions.
According to one aspect of the invention, the sampling bracket comprises a supporting frame, a first sliding block, a second sliding block, a third sliding block, a telescopic rod and a connecting block, the sampler comprises an outer cylinder, a middle cylinder and an inner cylinder, the supporting frame is provided with two sliding rails along the x direction, the first sliding block slides along the two horizontal sliding rails in the x direction, the outer cylinder is fixed on the second sliding block, one end of the telescopic rod is fixed on the second sliding block through the third sliding block, the other end of the telescopic rod is connected with the middle cylinder through the connecting block, the second sliding block and the third sliding block drive the sampler to slide in the Y direction, the telescopic rod drives the middle cylinder to move in the z direction relative to the outer cylinder, the inner cylinder rotates relative to the middle cylinder, the x direction is the carriage length direction of the coal car, the Y direction is the carriage width direction of the coal car, and the z direction is the carriage depth direction of the coal car.
According to one aspect of the invention, the coal quality analysis assembly comprises a light assembly and an analysis assembly, the light assembly comprises a shell, a light source assembly, a light transmitting sheet and a reflected light recycling assembly, the light transmitting sheet is arranged on the bottom surface of the shell, the light source assembly and the reflected light recycling assembly are arranged in the shell, the analysis assembly comprises a spectrometer and an upper computer, the reflected light recycling assembly is connected with the spectrometer through an optical fiber, the spectrometer is connected with the upper computer through a wire or a wireless way, light emitted by the light source assembly irradiates the coal sample through the light transmitting sheet, reflected light of the coal sample enters the reflected light recycling assembly after passing through the light transmitting sheet, the light source assembly and the reflected light recycling assembly are inclined relative to a plane on which the coal sample is placed, the inclination angle of the light source assembly relative to the plane is set to prevent the reflected light of the coal sample from entering the light source assembly, and the inclination angle of the reflected light recycling assembly relative to the plane is set to enable a plurality of light spots formed by the light transmitting sheet in the reflected light recycling assembly to coincide before the reflected light recycling assembly transmits the reflected light outwards; the spectrometer collects light spots of the coal sample emitted by the reflected light recycling assembly, generates coal sample spectrum data corresponding to the light spots of the coal sample, and the upper computer performs coal analysis according to the coal sample spectrum data and judges whether the coal sample is qualified or not according to a coal quality analysis result and a coal quality qualification standard.
According to one aspect of the invention, the light source assembly comprises a light source, a reflecting cup and a light source collimating lens, wherein light emitted by the light source is converged to the light source collimating lens through the reflecting cup and then converted into parallel light beams which are emitted obliquely relative to a coal sample; the reflected light recycling assembly comprises an incidence lens, a light transmitting body and an emergent lens, wherein the incidence lens and the emergent lens are respectively arranged at a light inlet and a light outlet of the light transmitting body, the incidence lens converges the reflected light of a coal sample penetrating through a light transmitting sheet to the emergent lens, and the emergent lens transmits the converged light beam of the incidence lens to an optical fiber outwards.
According to one aspect of the invention, the coal quality analysis assembly further comprises a light assembly support for securing the light assembly above the conveyor such that the light transmissive sheet of the light assembly is parallel to the plane on which the coal sample is placed on the conveyor.
According to one aspect of the invention, the conveyor comprises a conveyor belt, and the light transmissive sheet of the light assembly is parallel to the conveyor belt.
According to one aspect of the invention, the spectrometer is a grating spectrometer.
According to one aspect of the present invention, the upper computer includes:
a standard module for constructing a coal quality qualification standard;
The matrix conversion module is used for converting the coal sample spectrum data into a matrix form to obtain a coal sample spectrum data matrix, wherein the coal sample spectrum data matrix is a multidimensional matrix formed by each wavelength or wave number of each sampling of each coal sample number of a coal car and each absorbance corresponding to each wavelength or wave number of each sampling of each coal sample number;
the covariance conversion module is used for converting the coal sample spectrum data matrix obtained by the matrix conversion module into a corresponding covariance matrix;
the principal component analysis module is used for carrying out principal component analysis on the covariance matrix obtained by the covariance conversion module to obtain a principal component spectrum matrix formed by principal components of each spectrum;
the system comprises a coal index matrix construction module, a coal index matrix analysis module and a coal index matrix analysis module, wherein the coal index matrix construction module constructs one-dimensional or multidimensional coal index matrixes of one or more indexes of coal, and the indexes of the coal comprise one or more of dry ash-free bases, dry bases, air-dry bases and received bases;
the convolutional neural network construction module takes the principal component spectrum matrix of the principal component analysis module as input, takes the coal index matrix constructed by the coal index matrix construction module as output, and constructs a convolutional neural network:
the training module trains the convolutional neural network through a training set, and comprises: the training set construction unit is used for constructing a training set; the network training unit sequentially passes the training set through the matrix conversion module, the covariance conversion module and the principal component analysis module to obtain a principal component spectrum matrix of the training set, and the coal index matrix of the training set is obtained through the coal index matrix construction module, so that the principal component spectrum matrix and the coal index matrix of the training set are used for training the convolutional neural network constructed by the convolutional neural network construction module;
And the analysis and judgment module inputs the main component spectrum matrix of the coal sample into the trained convolutional neural network to obtain a corresponding coal index matrix of the coal sample, and compares the coal index matrix with the qualified standard of the coal sample which is called from the standard module to judge whether the coal sample is qualified.
According to one aspect of the invention, the light assembly further comprises a dust removal assembly for removing dust from the light transmissive sheet.
According to one aspect of the invention, the coal vehicle control system further comprises a traffic control component, wherein the traffic control component is used for controlling traffic of the coal vehicle, the traffic control component is connected with the coal quality analysis component in a wired or wireless mode, a traffic instruction is sent to the traffic control component after all coal samples of the coal vehicle are judged to be qualified through the coal quality analysis component, and a traffic prohibition instruction is sent to the traffic control component after the coal quality analysis component judges that the coal vehicle has the coal samples with unqualified coal quality.
According to one aspect of the invention, an electronic scale for weighing the weight of the coal car is also included.
According to one aspect of the invention, the device further comprises a distance sensor for measuring the thickness of the coal sample on the conveyor; the coal quality analysis component is also used for judging whether a coal sample exists below the optical component according to the thickness of the coal sample.
According to another aspect of the present invention, there is also provided a method for performing coal quality analysis using the above-mentioned on-line coal quality analysis system based on factory entry, comprising:
multipoint sampling is carried out on the pulverized coal on the coal car, and coal samples of a plurality of sampling points are obtained in sequence;
sequentially transmitting the coal sample of each sampling point to an optical assembly;
irradiating light on a coal sample through a light assembly, and collecting reflected light of the coal sample;
generating coal sample spectrum data through reflected light of the coal sample;
carrying out coal quality analysis through coal sample spectrum data;
judging whether the coal sample is qualified or not according to the coal quality analysis result.
According to another aspect of the invention, the step of performing coal quality analysis by coal sample spectral data comprises:
converting the coal sample spectrum data into a matrix form to obtain a coal sample spectrum data matrix, wherein one or more formed spectrums of each sampling point are provided, and the coal sample spectrum data matrix is a multidimensional matrix formed by each wavelength or wave number of each sampling of each coal sample number of a coal car and each absorbance corresponding to each wavelength or wave number of each sampling of each coal sample number;
converting the coal sample spectrum data matrix into a corresponding covariance matrix;
principal component analysis is carried out on the covariance matrix to obtain a principal component spectrum matrix formed by principal components of each spectrum;
Principal component analysis is carried out on the covariance matrix to obtain a principal component spectrum matrix formed by principal components of each spectrum;
constructing one or more one-dimensional or multidimensional coal index matrices of indexes of the coal, wherein the indexes of the coal comprise one or more of dry ash-free bases, dry bases, air-dry bases and received bases;
taking a main component spectrum matrix as input and taking a coal index matrix as output, and constructing a convolutional neural network:
training a convolutional neural network through a training set, comprising: constructing a training set; obtaining a main component spectrum matrix of a training set; obtaining a coal index matrix of a training set; training the convolutional neural network by using the main component spectrum matrix and the coal index matrix of the training set;
and inputting the main component spectrum matrix of the coal sample into the trained convolutional neural network to obtain a corresponding coal index matrix.
According to another aspect of the invention, the step of judging whether the coal sample is qualified or not according to the coal quality analysis result comprises the following steps:
obtaining a qualified standard of the coal sample;
judging whether the value of each coal index of each coal sample in the coal index matrix of the coal sample accords with the corresponding coal sample qualification standard, accords with the coal sample qualification standard, and is qualified, otherwise, the coal sample is unqualified.
According to another aspect of the invention, the step of obtaining a coal sample qualification standard comprises;
Obtaining a geographical area of the coal sample;
and obtaining the coal sample qualification standard of the geographic area.
According to another aspect of the invention, the step of judging whether the coal sample is qualified according to the coal quality analysis result further comprises the following steps: when all coal samples of the coal car are qualified, the coal car passes through; when the coal car has unqualified coal samples, the coal car does not pass.
According to another aspect of the invention, when the coal car has an unqualified coal sample, sampling and testing are also carried out on the unqualified coal sample; and when the test result is qualified, adding the coal quality analysis result of the unqualified coal sample into the training set.
According to another aspect of the present invention, further comprising: the training set is divided into a positive training set and a negative training set, the coal quality analysis results which are unqualified in coal quality analysis and are unqualified in test result are added into the negative training set, and the coal quality analysis results which are qualified in coal quality analysis and are also qualified in test result are added into the positive training set.
According to another aspect of the present invention, the method further includes a step of determining whether there is a coal sample under the optical module, and the step of determining whether there is a coal sample under the optical module includes:
judging whether the thickness of the coal sample reaches a set thickness;
if the thickness of the coal sample reaches the set thickness, the coal sample is arranged under the optical component;
If the thickness of the coal sample does not reach the set thickness, no coal sample exists under the optical assembly.
According to another aspect of the present invention, further comprising: and when no coal sample exists under the optical component, the transparent sheet is dedusted.
According to another aspect of the present invention, before the step of sequentially transferring the coal sample at each sampling point to the optical assembly, the method further comprises:
crushing the coal sample.
According to another aspect of the present invention, the step of sequentially transferring the coal sample at each sampling point to the optical assembly further comprises:
and extracting the coal sample for testing.
According to another aspect of the invention, the step of judging whether the coal sample is qualified according to the coal quality analysis result further comprises the following steps:
and when the test result is qualified, adding the test result into the training set instead of the coal quality analysis result of the coal sample.
According to another aspect of the present invention, further comprising: dividing the training set into a positive training set and a negative training set, and adding the test result instead of the coal quality analysis result of the coal sample when the test result is qualified; and when the test result is unqualified, adding the coal quality analysis result into the negative training set.
According to the invention, the sampler is used for sampling the coal from the coal car, the coal sample is transmitted to the coal quality analysis assembly through the transmission device, and the coal quality analysis is carried out on the coal sample through the coal quality analysis assembly, so that the coal quality can be analyzed on line before the coal dust enters the factory, and unqualified coal dust is prevented from entering the factory.
The sampling bracket provided by the invention enables the sampler to move in any direction of three-dimensional directions, thereby realizing sampling at any position on the coal car.
The crushing device crushes the pulverized coal to the same particle size, and prevents the influence of different particle sizes on the spectrum.
The light source component is positioned in the shell of the light component, prevents the pollution of coal dust to the light source, and has a compact structure.
According to the invention, the light source assembly is inclined relative to the plane on which the coal sample is placed on the conveying device, so that reflected light of the coal sample is prevented from returning to the light source assembly after passing through the light transmitting sheet, and the signal to noise ratio is improved; the reflected light recycling assembly is inclined relative to the plane of the coal sample placed on the conveying device, so that reflected light of the coal sample passes through the light transmitting sheet and then is overlapped on light spots of the reflected light recycling assembly, the influence of light spot overlapping and non-overlapping on the spectrum of the coal sample is prevented, and the accuracy of analysis of the coal sample is improved.
The spectrometer of the invention adopts a grating spectrometer, has strong anti-interference capability and is beneficial to the on-line analysis of coal quality.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of one direction of a coal quality on-line analysis system based on entry into a plant according to the present invention;
FIG. 2 is a schematic diagram of another direction of the in-plant based on-line analysis system of coal quality according to the present invention;
FIG. 3 is a schematic diagram of a block diagram of a coal quality online analysis system based on a factory entry according to the present invention;
FIG. 4 is a schematic perspective view, in semi-section, of an optical assembly according to the present invention;
the sampler 1, the outer cylinder 11, the middle cylinder 12, the inner cylinder 13, the sampling support 2, the support frame 21, the first slider 22, the second slider 23, the third slider 24, the telescopic rod 25, the connection block 26, the crushing device 3, the transmitting device 4, the coal quality analysis module 5, the optical module 51, the housing 511, the light source module 512, the light source 5121, the light reflecting cup 5122, the light source collimating lens 5123, the light transmitting sheet 513, the reflected light recycling module 514, the incident lens 5141, the light transmitting body 5142, the emergent lens 5143, the dust removing module 515, the optical module support 52, the optical fiber 53, the analysis module 54, the spectrometer 541, the host computer 542, the standard module 5421, the matrix conversion module 5422, the covariance conversion module 5423, the principal component analysis module 5424, the coal index matrix construction module 5425, the convolutional neural network construction module 5426, the training module 5427, the training set construction unit 54271, the network training unit 54272, the analysis and judgment module 5428, the electronic balance 6, the traffic control module 7, and the distance sensor 8.
Detailed Description
Hereinafter, only certain exemplary embodiments are briefly described. As will be recognized by those of skill in the pertinent art, the described embodiments may be modified in various different ways without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive.
The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. They are, of course, merely examples and are not intended to limit the invention. The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Fig. 1 is an intention of the in-plant based on-line coal analysis system of the present invention, fig. 2 is a schematic view of another direction of the in-plant based on-line coal analysis system of the present invention, fig. 3 is a schematic view of a block diagram of the in-plant based on-line coal analysis system of the present invention, and as shown in fig. 1, 2 and 3, the in-plant based on-line coal analysis system includes a sampler 1, a conveying device 4 and a coal analysis component 5, wherein the sampler 1 is used for extracting a coal sample from a coal car; the conveying device 4 is used for conveying the coal sample to the coal quality analysis assembly 5; the coal quality analysis component 5 is arranged to emit light to a coal sample, collect coal sample spectrum data of reflected light of the coal sample, analyze the coal quality through the coal sample spectrum data and judge whether the coal sample is qualified through a coal quality analysis result, wherein the coal sample spectrum data comprises a coal sample number, a wavelength or a wave number and absorbance corresponding to the wavelength or wave number.
In one embodiment, the on-line analysis system for coal quality based on entering factories further comprises a crushing device 3, wherein the crushing device 3 is used for crushing the coal samples extracted by the sampler 1 to a set particle size and throwing the coal samples onto the conveying device 4.
In one embodiment, the on-line analysis system for coal quality based on entering factories further comprises a pass control component 7, wherein the pass control component 7 is used for controlling passing of the coal cars, the pass control component 7 is connected with the coal quality analysis component 5 in a wired or wireless mode, after judging that all coal samples of the coal cars are qualified through the coal quality analysis component 5, a pass instruction is sent to the pass control component, and after judging that the coal cars have unqualified coal samples through the coal quality analysis component 5, a pass prohibition instruction is sent to the pass control component.
In one embodiment, the on-line analysis system for coal quality based on factory further comprises an electronic scale 6, wherein the electronic scale 6 is used for weighing the coal car.
In one embodiment, the on-line analysis system for coal quality based on factory further comprises a sampling bracket 2, wherein the sampling bracket 2 is used for connecting the sampler 1, so that the sampler 1 can move in any one direction of three-dimensional directions.
Preferably, as shown in fig. 2, the sampling support 2 includes a supporting frame 21, a first sliding block 22, a second sliding block 23, a third sliding block 24, a telescopic rod 25 and a connecting block 26, the sampler 1 includes an outer cylinder 11, an intermediate cylinder 12 and an inner cylinder 13, the supporting frame 21 is provided with two sliding rails along an x direction, the first sliding block 22 slides along two horizontal sliding rails in the x direction, the outer cylinder 11 is fixed on the second sliding block 23, one end of the telescopic rod 25 is fixed on the second sliding block 23 through the third sliding block 24, the other end of the telescopic rod 25 is connected with the intermediate cylinder 12 through the connecting block 26, the second sliding block 23 and the third sliding block 24 drive the sampler 1 to slide in a Y direction, the telescopic rod 25 drives the intermediate cylinder 12 to move in a z direction relative to the outer cylinder 11, the inner cylinder 13 rotates relative to the intermediate cylinder 12, the x direction is a carriage length direction of the coal car, the Y direction is a carriage depth direction of the coal car, and the z direction is a carriage depth direction of the coal car, so that the sampler 1 can move in the three-dimensional directions of the carriage length, width direction and height direction of the coal car.
Preferably, the inner cylinder 13 of the sampler 1 extends into the bottom of the coal car to sample, so that the coal sample comprises coal dust with any depth in the coal car, and the universality of coal quality analysis of the coal dust in the coal car is enhanced. In addition, when the bottom of the coal car is stone and the upper layer is coal powder, the inner cylinder 13 cannot penetrate into the bottom of the coal car, so that the situation of false and spurious can be prevented.
As shown in fig. 3 and fig. 4, the coal quality analysis module 5 includes a light module 51 and an analysis module 54, the light module 51 includes a housing 511, a light source module 512, a light transmitting sheet 513 and a reflected light recycling module 514, the light transmitting sheet 513 is disposed on a bottom surface of the housing 511, the light source module 512 and the reflected light recycling module 514 are disposed in the housing 511, the analysis module 54 includes a spectrometer 541 and a host computer 542, the reflected light recycling module 514 is connected with the spectrometer 541 through an optical fiber 53, the spectrometer 541 and the host computer 542 are connected by a wired or wireless connection, light emitted by the light source module 512 irradiates a coal sample through a light transmitting sheet 513, reflected light of the coal sample enters the reflected light recycling module 514 after passing through the light transmitting sheet 513, the light source module 512 and the reflected light recycling module 514 are inclined relative to a plane on which the coal sample is disposed, an inclination angle of the light source module 512 relative to the plane is set to prevent reflected light of the sample from entering the light source module 512, and an inclination angle of the reflected light recycling module 514 relative to the plane is set such that reflected light forms multiple reflected light recycling light spots before the reflected light passes through the light transmitting sheet 513 and overlaps the reflected light recycling module 514; the spectrometer 541 collects the light spot of the coal sample emitted by the reflected light recycling component 514, generates the coal sample spectrum data corresponding to the light spot of the coal sample, and the upper computer 542 performs coal analysis according to the coal sample spectrum data, and determines whether the coal sample is qualified according to the coal sample analysis result and the coal quality qualification standard.
Preferably, the spectrometer 541 is a grating spectrometer.
In one embodiment, the light source assembly 512 includes a light source 5121, a light reflecting cup 5122 and a light source collimating lens 5123, wherein the light emitted by the light source 5121 is converged by the light reflecting cup 5122 to the light source collimating lens 5123 and then converted into a parallel light beam to be emitted obliquely relative to the coal sample; the reflected light recycling assembly 514 includes an incident lens 5141, a light transmitting body 5142 and an exit lens 5143, the incident lens 5141 and the exit lens 5143 are respectively disposed at a light inlet and a light outlet of the light transmitting body 5142, the incident lens 5141 converges the reflected light of the coal sample passing through the light transmitting sheet 513 to the exit lens 5143, and the exit lens 5143 transmits the converged light beam of the incident lens 5141 to the optical fiber 53.
In one embodiment, the coal analysis assembly 5 further includes a light assembly support bracket 52 for securing the light assembly 51 above the conveyor 4 such that the light transmissive sheet 513 of the light assembly 51 is parallel to the plane on the conveyor 4 where the coal sample is placed.
In one embodiment, the conveyor 4 comprises a conveyor belt, and the light-transmitting sheet 513 of the light assembly 51 is parallel to the conveyor belt.
In one embodiment, the upper computer 542 includes:
The standard module 5421 is used for constructing a coal quality standard, and preferably, the standard module 5421 is used for constructing the coal quality standard according to the geographical area of the coal mine;
the matrix conversion module 5422 converts the coal sample spectrum data into a matrix form to obtain a coal sample spectrum data matrix, wherein the coal sample spectrum data matrix is a multidimensional matrix formed by each wavelength or wave number of each sampling of each coal sample number of a coal car and each absorbance corresponding to each wavelength or wave number of each sampling of each coal sample number;
the covariance conversion module 5423 converts the coal sample spectrum data matrix obtained by the matrix conversion module 5422 into a corresponding covariance matrix;
principal component analysis module 5424 performs principal component analysis on the covariance matrix obtained by covariance conversion module 5423 to obtain principal component spectrum matrix composed of principal components of each spectrum;
the coal index matrix construction module 5425 constructs one or more one-dimensional or multi-dimensional coal index matrices of indexes of the coal including one or more of dry ash free basis, dry basis, empty basis and received basis;
the convolutional neural network construction module 5426 takes the principal component spectrum matrix of the principal component analysis module 5424 as input, and takes the coal index matrix constructed by the coal index matrix construction module as output to construct a convolutional neural network:
The training module 5427 trains the convolutional neural network through a training set, including: a training set construction unit 54271 for constructing a training set; the network training unit 54272 sequentially passes the training set through the matrix conversion module 5422, the covariance conversion module 5423 and the principal component analysis module 5424 to obtain a principal component spectrum matrix of the training set, and passes the coal index matrix of the training set through the coal index matrix construction module to train the convolutional neural network constructed by the convolutional neural network construction module through the principal component spectrum matrix and the coal index matrix of the training set;
the analysis and judgment module 5428 inputs the main component spectrum matrix of the coal sample into the trained convolutional neural network to obtain a corresponding coal index matrix of the coal sample, and compares the coal index matrix with the qualified standard of the coal sample obtained by the standard module 5421 to judge whether the coal sample is qualified.
In one embodiment, the analysis assembly 54 further includes a cabinet, the spectrometer 541 is disposed in the cabinet, and the host computer 542 is disposed in the cabinet or outside the cabinet.
Preferably, a display screen is arranged on the cabinet body and used for displaying the coal quality analysis result.
In one embodiment, the on-line analysis system for coal quality based on factory entry further comprises a distance sensor 8, wherein the distance sensor 8 is used for measuring the thickness of the coal sample on the conveying device 4; the coal quality analysis component 5 is further used for judging whether a coal sample exists below the optical component 51 according to the thickness of the coal sample;
Preferably, the distance sensor 8 is an ultrasonic distance sensor 8.
In one embodiment, the light assembly 51 further includes a dust removing assembly 515, the dust removing assembly 515 being configured to remove dust from the light transmissive sheet 513;
preferably, the dust removing assembly 515 includes a scraper rotatably coupled to the base plate, and the scraper has a length greater than a diameter of the light transmitting sheet 513.
The invention also provides a method for analyzing the coal quality by using the on-line coal quality analysis system based on the entering factories, which comprises the following steps:
multipoint sampling is carried out on the pulverized coal on the coal car, and coal samples of a plurality of sampling points are obtained in sequence;
sequentially transmitting the coal sample of each sampling point to the optical component 51;
irradiating light on the coal sample through the light assembly 51, and collecting reflected light of the coal sample;
generating coal sample spectrum data through reflected light of the coal sample;
carrying out coal quality analysis through coal sample spectrum data;
judging whether the coal sample is qualified or not according to the coal quality analysis result.
In one embodiment, the step of performing a coal quality analysis from the coal sample spectral data comprises:
converting the coal sample spectrum data into a matrix form to obtain a coal sample spectrum data matrix, wherein one or more formed spectrums of each sampling point are provided, and the coal sample spectrum data matrix is a multidimensional matrix formed by each wavelength or wave number of each sampling of each coal sample number of a coal car and each absorbance corresponding to each wavelength or wave number of each sampling of each coal sample number;
Converting the coal sample spectrum data matrix into a corresponding covariance matrix;
principal component analysis is carried out on the covariance matrix to obtain a principal component spectrum matrix formed by principal components of each spectrum;
principal component analysis is carried out on the covariance matrix to obtain a principal component spectrum matrix formed by principal components of each spectrum;
constructing one or more one-dimensional or multidimensional coal index matrices of indexes of the coal, wherein the indexes of the coal comprise one or more of dry ash-free bases, dry bases, air-dry bases and received bases;
taking a main component spectrum matrix as input and taking a coal index matrix as output, and constructing a convolutional neural network:
training a convolutional neural network through a training set, comprising: constructing a training set; obtaining a main component spectrum matrix of a training set; obtaining a coal index matrix of a training set; training the convolutional neural network by using the main component spectrum matrix and the coal index matrix of the training set;
and inputting the main component spectrum matrix of the coal sample into the trained convolutional neural network to obtain a corresponding coal index matrix.
In one embodiment, the step of determining whether the coal sample is qualified according to the coal quality analysis result includes:
obtaining a qualified standard of the coal sample;
judging whether the value of each coal index of each coal sample in the coal index matrix of the coal sample accords with the corresponding coal sample qualification standard, accords with the coal sample qualification standard, and is qualified, otherwise, the coal sample is unqualified.
Preferably, the step of obtaining the coal sample qualification standard comprises the following steps of;
obtaining a geographical area of the coal sample;
and obtaining the coal sample qualification standard of the geographic area.
Preferably, when all coal samples of the coal vehicle are qualified, the coal vehicle passes through; when the coal car has unqualified coal samples, the coal car does not pass.
Further preferably, when the coal car has an unqualified coal sample, sampling and testing the coal sample; when the test result is qualified, the coal quality analysis result of the coal sample is added into the training set, the training set is enlarged, the training accuracy is enhanced, the situation that the test qualified coal quality analysis is unqualified is prevented from happening again, particularly when a new geographic area of coal is put into factories, the training set which does not comprise the coal sample of the geographic area is adopted for training, and the coal quality analysis result is likely to deviate.
Still further preferably, the training set is divided into a positive training set and a negative training set, the coal quality analysis result which is unqualified in coal quality analysis and unqualified in test result is added into the negative training set, the coal quality analysis result which is qualified in coal quality analysis and qualified in test result is added into the positive training set, the convolutional neural network can be trained through the positive training set and the negative training set, and the robustness of the convolutional neural network is increased.
In one embodiment, the step of irradiating the light onto the coal sample through the light assembly 51 and collecting the reflected light of the coal sample further includes the step of calibrating the inclination angle of the reflected light recovery assembly 514, and the step of calibrating the inclination angle of the reflected light recovery assembly 514 includes:
irradiating light onto the standard substance through the light assembly 51;
adjusting the inclination angle of the reflected light recycling component 514 to obtain the spectrum and the signal to noise ratio of the standard substance of the reflected light recycling component 514 under different inclination angles;
the tilt angle corresponding to the highest signal-to-noise ratio is taken as the optimal tilt angle for the reflected light recovery assembly 514.
In one embodiment, the step of irradiating the light onto the coal sample through the light assembly 51 and collecting the reflected light of the coal sample further includes the step of calibrating the inclination angle of the light source assembly 512, and the step of calibrating the inclination angle of the light source assembly 512 includes:
irradiating light onto the standard substance through the light assembly 51;
adjusting the inclination angle of the light source component 512 to obtain the spectrum of the standard substance under different inclination angles;
comparing the spectrum with the standard spectrum of the standard substance, and taking the inclination angle corresponding to the spectrum with the most similar absorbance characteristic peak shape as the optimal inclination angle of the light source component 512.
Preferably, the step of calibrating the tilt angle of the light source module 512 is performed before the step of calibrating the tilt angle of the reflected light recovery module 514.
In one embodiment, the method further includes a step of determining whether there is a coal sample under the optical component 51, and the step of determining whether there is a coal sample under the optical component 51 includes:
judging whether the thickness of the coal sample reaches a set thickness;
if the thickness of the coal sample reaches the set thickness, the coal sample is arranged under the optical component 51;
if the thickness of the coal sample does not reach the set thickness, there is no coal sample under the optical assembly 51.
Preferably, the light transmissive sheet 513 is de-dusted when there is no coal sample under the light assembly 51.
In one embodiment, the step of sequentially transferring the coal sample at each sampling point to the optical assembly 51 further comprises:
crushing a coal sample;
preferably, the step of crushing the coal sample comprises:
the coal sample was crushed to a particle size of 6mm.
In one embodiment, the step of sequentially transferring the coal sample at each sampling point to the optical assembly 51 further comprises:
extracting a coal sample for testing;
preferably, the step of judging whether the coal sample is qualified according to the coal quality analysis result further comprises the following steps:
when the test result is qualified, the test result is added into the training set to replace the coal quality analysis result of the coal sample, and the coal quality analysis result is updated through the test result, so that the accuracy of the training set is improved.
Further, preferably, the training set is divided into a positive training set and a negative training set, and when the test result is qualified, the test result is added instead of the coal quality analysis result of the coal sample; and when the test result is unqualified, adding the coal quality analysis result into a negative training set, and training the convolutional neural network through the positive training set and the negative training set, so that the robustness of the convolutional neural network is improved.
In the above embodiments, the light source module 512 and the reflected light recovery module 514 may be fixed on the housing after adjusting the inclination angle, or may be provided with a bracket, and fixed on the housing by the bracket, or may be provided with a filler having a heat dissipation function between the housing and the light source module 512 and the reflected light recovery module 514, and the light source module 512 and the reflected light recovery module 514 may be fixed on the filler after adjusting the inclination angle. The inclination angle adjustment of the light source module 512 and the reflected light recovery module 514 may be achieved by an existing rotating platform having an angle adjustment function.
The foregoing is a preferred embodiment of the present invention, and although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (27)
1. The on-line coal quality analysis system based on the factory entering is characterized by comprising a sampler, a conveying device and a coal quality analysis assembly, wherein the sampler is used for extracting a coal sample from a coal car; the conveying device is used for conveying the coal sample to the coal quality analysis assembly; the coal quality analysis component is arranged to emit light to the coal sample, coal sample spectrum data of reflected light of the coal sample is collected, coal quality analysis is carried out through the coal sample spectrum data, whether the coal sample is qualified or not is judged through a coal quality analysis result, and the coal sample spectrum data comprises a coal sample number, a wavelength or a wave number and absorbance corresponding to the wavelength or the wave number.
2. The on-line analysis system for coal quality based on factory entry of claim 1, further comprising a crushing device for crushing the coal sample extracted by the sampler to a set particle size and delivering the crushed coal sample to the conveyor.
3. The on-line mill-based coal analysis system according to claim 1, further comprising a sampling support for mounting the sampler such that the sampler can be moved in any one of three-dimensional directions.
4. The on-line analysis system for coal quality based on factory entry according to claim 3, wherein the sampling bracket comprises a supporting frame, a first sliding block, a second sliding block, a third sliding block, a telescopic rod and a connecting block, the sampler comprises an outer cylinder, an intermediate cylinder and an inner cylinder, the supporting frame is provided with two sliding rails along the x direction, the first sliding block slides along the two horizontal sliding rails in the x direction, the outer cylinder is fixed on the second sliding block, one end of the telescopic rod is fixed on the second sliding block through the third sliding block, the other end of the telescopic rod is connected with the intermediate cylinder through the connecting block, the second sliding block and the third sliding block drive the sampler to slide in the Y direction, the telescopic rod drives the intermediate cylinder to move relative to the outer cylinder in the z direction, the inner cylinder rotates relative to the intermediate cylinder, the x direction is the carriage length direction of the coal car, the Y direction is the carriage width direction of the coal car, and the z direction is the carriage depth direction of the coal car.
5. The on-line coal analysis system based on factory entry according to claim 1, wherein the coal analysis assembly comprises an optical assembly and an analysis assembly, the optical assembly comprises a shell, a light source assembly, a light transmitting sheet and a reflected light recycling assembly, the light transmitting sheet is arranged on the bottom surface of the shell, the light source assembly and the reflected light recycling assembly are arranged in the shell, the analysis assembly comprises a spectrometer and an upper computer, the reflected light recycling assembly is connected with the spectrometer through an optical fiber, the spectrometer and the upper computer are connected through a wire or a wireless, light emitted by the light source assembly irradiates the coal sample through the light transmitting sheet, reflected light of the coal sample enters the reflected light recycling assembly after passing through the light transmitting sheet, the light source assembly and the reflected light recycling assembly are inclined relative to a plane on which the coal sample is placed, the inclination angle of the light source assembly relative to the plane is set to prevent the reflected light of the coal sample from entering the light source assembly, the inclination angle of the reflected light recycling assembly relative to the plane is set to enable the reflected light of the coal sample to pass through the light transmitting sheet to irradiate the reflected light recycling assembly formed by the light of the reflected light recycling assembly to coincide outside a plurality of reflected light recycling assemblies; the spectrometer collects light spots of the coal sample emitted by the reflected light recycling assembly, generates coal sample spectrum data corresponding to the light spots of the coal sample, and the upper computer performs coal analysis according to the coal sample spectrum data and judges whether the coal sample is qualified or not according to a coal quality analysis result and a coal quality qualification standard.
6. The on-line analysis system for coal quality based on factory entry according to claim 5, wherein the light source assembly comprises a light source, a reflecting cup and a light source collimating lens, wherein light emitted by the light source is converged to the light source collimating lens through the reflecting cup and then converted into parallel light beams to be emitted obliquely relative to a coal sample; the reflected light recycling assembly comprises an incidence lens, a light transmitting body and an emergent lens, wherein the incidence lens and the emergent lens are respectively arranged at a light inlet and a light outlet of the light transmitting body, the incidence lens converges the reflected light of a coal sample penetrating through a light transmitting sheet to the emergent lens, and the emergent lens transmits the converged light beam of the incidence lens to an optical fiber outwards.
7. The on-line coal analysis system based on factory entry of claim 5, wherein the coal analysis assembly further comprises an optical assembly support for securing the optical assembly above the conveyor such that the optically transparent sheet of the optical assembly is parallel to the plane on which the coal sample is placed on the conveyor.
8. The on-line mill-based coal analysis system according to claim 7, wherein the conveyor comprises a conveyor belt, and the light-transmitting sheet of the light assembly is parallel to the conveyor belt.
9. The on-line analysis system for coal quality in factories of claim 8, wherein the spectrometer is a grating spectrometer.
10. The on-line analysis system for coal quality based on factory entry of claim 5, wherein the host computer comprises:
a standard module for constructing a coal quality qualification standard;
the matrix conversion module is used for converting the coal sample spectrum data into a matrix form to obtain a coal sample spectrum data matrix, wherein the coal sample spectrum data matrix is a multidimensional matrix formed by each wavelength or wave number of each sampling of each coal sample number of a coal car and each absorbance corresponding to each wavelength or wave number of each sampling of each coal sample number;
the covariance conversion module is used for converting the coal sample spectrum data matrix obtained by the matrix conversion module into a corresponding covariance matrix;
the principal component analysis module is used for carrying out principal component analysis on the covariance matrix obtained by the covariance conversion module to obtain a principal component spectrum matrix formed by principal components of each spectrum;
the system comprises a coal index matrix construction module, a coal index matrix analysis module and a coal index matrix analysis module, wherein the coal index matrix construction module constructs one-dimensional or multidimensional coal index matrixes of one or more indexes of coal, and the indexes of the coal comprise one or more of dry ash-free bases, dry bases, air-dry bases and received bases;
the convolutional neural network construction module takes the principal component spectrum matrix of the principal component analysis module as input, takes the coal index matrix constructed by the coal index matrix construction module as output, and constructs a convolutional neural network:
The training module trains the convolutional neural network through a training set, and comprises: the training set construction unit is used for constructing a training set; the network training unit sequentially passes the training set through the matrix conversion module, the covariance conversion module and the principal component analysis module to obtain a principal component spectrum matrix of the training set, and the coal index matrix of the training set is obtained through the coal index matrix construction module, so that the principal component spectrum matrix and the coal index matrix of the training set are used for training the convolutional neural network constructed by the convolutional neural network construction module;
and the analysis and judgment module inputs the main component spectrum matrix of the coal sample into the trained convolutional neural network to obtain a corresponding coal index matrix of the coal sample, and compares the coal index matrix with the qualified standard of the coal sample which is called from the standard module to judge whether the coal sample is qualified.
11. The on-line mill-based coal analysis system of claim 5, wherein the light assembly further comprises a dust removal assembly for removing dust from the light transmissive sheet.
12. The on-line analysis system for coal quality based on factory entry according to claim 1, further comprising a traffic control component, wherein the traffic control component is used for controlling traffic of the coal vehicle, the traffic control component is connected with the coal quality analysis component in a wired or wireless mode, a traffic instruction is sent to the traffic control component after all coal samples of the coal vehicle are judged to be qualified through the coal quality analysis component, and a traffic prohibition instruction is sent to the traffic control component after the coal quality analysis component judges that the coal vehicle has the coal samples with unqualified coal quality.
13. The on-line mill-based coal quality analysis system of claim 1, further comprising an electronic scale for weighing the coal vehicle.
14. The on-line analysis system for coal quality based on factory entry of claim 1, further comprising a distance sensor for measuring a thickness of the coal sample on the conveyor; the coal quality analysis component is also used for judging whether a coal sample exists below the optical component according to the thickness of the coal sample.
15. A method of performing coal quality analysis using the in-plant based on-line coal quality analysis system of any one of claims 1-14, comprising:
multipoint sampling is carried out on the pulverized coal on the coal car, and coal samples of a plurality of sampling points are obtained in sequence;
sequentially transmitting the coal sample of each sampling point to an optical assembly;
irradiating light on a coal sample through a light assembly, and collecting reflected light of the coal sample;
generating coal sample spectrum data through reflected light of the coal sample;
carrying out coal quality analysis through coal sample spectrum data;
judging whether the coal sample is qualified or not according to the coal quality analysis result.
16. The method of claim 15, wherein the step of performing a coal quality analysis from the coal sample spectral data comprises:
Converting the coal sample spectrum data into a matrix form to obtain a coal sample spectrum data matrix, wherein one or more formed spectrums of each sampling point are provided, and the coal sample spectrum data matrix is a multidimensional matrix formed by each wavelength or wave number of each sampling of each coal sample number of a coal car and each absorbance corresponding to each wavelength or wave number of each sampling of each coal sample number;
converting the coal sample spectrum data matrix into a corresponding covariance matrix;
principal component analysis is carried out on the covariance matrix to obtain a principal component spectrum matrix formed by principal components of each spectrum;
principal component analysis is carried out on the covariance matrix to obtain a principal component spectrum matrix formed by principal components of each spectrum;
constructing one or more one-dimensional or multidimensional coal index matrices of indexes of the coal, wherein the indexes of the coal comprise one or more of dry ash-free bases, dry bases, air-dry bases and received bases;
taking a main component spectrum matrix as input and taking a coal index matrix as output, and constructing a convolutional neural network:
training a convolutional neural network through a training set, comprising: constructing a training set; obtaining a main component spectrum matrix of a training set; obtaining a coal index matrix of a training set; training the convolutional neural network by using the main component spectrum matrix and the coal index matrix of the training set;
And inputting the main component spectrum matrix of the coal sample into the trained convolutional neural network to obtain a corresponding coal index matrix.
17. The method of claim 16, wherein the step of determining whether the coal sample is acceptable based on the results of the coal quality analysis comprises:
obtaining a qualified standard of the coal sample;
judging whether the value of each coal index of each coal sample in the coal index matrix of the coal sample accords with the corresponding coal sample qualification standard, accords with the coal sample qualification standard, and is qualified, otherwise, the coal sample is unqualified.
18. The method of claim 17, wherein the step of obtaining a coal sample qualification standard comprises;
obtaining a geographical area of the coal sample;
and obtaining the coal sample qualification standard of the geographic area.
19. The method of claim 16, wherein the step of determining whether the coal sample is acceptable based on the result of the coal quality analysis further comprises: when all coal samples of the coal car are qualified, the coal car passes through; when the coal car has unqualified coal samples, the coal car does not pass.
20. The method of claim 19, wherein when the coal car has an unacceptable coal sample, further performing a sampling test on the unacceptable coal sample; and when the test result is qualified, adding the coal quality analysis result of the unqualified coal sample into the training set.
21. The method as recited in claim 20, further comprising: the training set is divided into a positive training set and a negative training set, the coal quality analysis results which are unqualified in coal quality analysis and are unqualified in test result are added into the negative training set, and the coal quality analysis results which are qualified in coal quality analysis and are also qualified in test result are added into the positive training set.
22. The method of claim 21, further comprising the step of determining whether there is a coal sample under the optical assembly, the step of determining whether there is a coal sample under the optical assembly comprising:
judging whether the thickness of the coal sample reaches a set thickness;
if the thickness of the coal sample reaches the set thickness, the coal sample is arranged under the optical component;
if the thickness of the coal sample does not reach the set thickness, no coal sample exists under the optical assembly.
23. The method as recited in claim 22, further comprising: and when no coal sample exists under the optical component, the transparent sheet is dedusted.
24. The method of claim 15, wherein the step of sequentially transferring the coal sample at each sampling point to the optical assembly further comprises:
crushing the coal sample.
25. The method of claim 16, wherein the step of sequentially transferring the coal sample at each sampling point to the optical assembly further comprises:
And extracting the coal sample for testing.
26. The method of claim 25, wherein the step of determining whether the coal sample is acceptable based on the results of the coal quality analysis further comprises:
and when the test result is qualified, adding the test result into the training set instead of the coal quality analysis result of the coal sample.
27. The method as recited in claim 26, further comprising: dividing the training set into a positive training set and a negative training set, and adding the test result instead of the coal quality analysis result of the coal sample when the test result is qualified; and when the test result is unqualified, adding the coal quality analysis result into the negative training set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310576699.5A CN116297273B (en) | 2023-05-22 | 2023-05-22 | On-line analysis system and method for coal quality based on factory entry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310576699.5A CN116297273B (en) | 2023-05-22 | 2023-05-22 | On-line analysis system and method for coal quality based on factory entry |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116297273A true CN116297273A (en) | 2023-06-23 |
| CN116297273B CN116297273B (en) | 2023-08-18 |
Family
ID=86798188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310576699.5A Active CN116297273B (en) | 2023-05-22 | 2023-05-22 | On-line analysis system and method for coal quality based on factory entry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116297273B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004088A (en) * | 2010-11-09 | 2011-04-06 | 清华大学 | Method for measuring coal property on line based on neural network |
| CN102324120A (en) * | 2011-04-27 | 2012-01-18 | 柳威 | Device and method for monitoring coal quality |
| CN106093011A (en) * | 2016-07-12 | 2016-11-09 | 宝瑞激光科技（常州）有限公司 | The ature of coal laser detection analytical tool of coal quality detecting method and application thereof |
| WO2016206401A1 (en) * | 2015-06-26 | 2016-12-29 | 国电新能源技术研究院 | Device for detecting characteristic nature of coal on-line |
| CN107462662A (en) * | 2017-08-07 | 2017-12-12 | 长沙开元仪器股份有限公司 | A kind of on-line element analysis of coal system |
| CN107631997A (en) * | 2017-09-29 | 2018-01-26 | 北京国电新创科技有限公司 | A kind of real-time, non-intruding, a variety of coal Main Ingredients and Appearance simultaneous measuring apparatus |
| CN109580499A (en) * | 2019-01-03 | 2019-04-05 | 中国神华能源股份有限公司 | Coal quality measuring device |
| CN111189671A (en) * | 2020-03-31 | 2020-05-22 | 中国二十二冶集团有限公司 | Automatic sampling device and sampling method for entering crushed stone of mixing station |
| CN211443784U (en) * | 2019-12-08 | 2020-09-08 | 国家能源聊城发电有限公司 | Device for on-line monitoring of coal quality and composition of coal entering plant |
| CN218239818U (en) * | 2022-06-29 | 2023-01-06 | 深圳数马电子技术有限公司 | Diffuse reflection optical sensor |
-
2023
- 2023-05-22 CN CN202310576699.5A patent/CN116297273B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004088A (en) * | 2010-11-09 | 2011-04-06 | 清华大学 | Method for measuring coal property on line based on neural network |
| CN102324120A (en) * | 2011-04-27 | 2012-01-18 | 柳威 | Device and method for monitoring coal quality |
| WO2016206401A1 (en) * | 2015-06-26 | 2016-12-29 | 国电新能源技术研究院 | Device for detecting characteristic nature of coal on-line |
| CN106093011A (en) * | 2016-07-12 | 2016-11-09 | 宝瑞激光科技（常州）有限公司 | The ature of coal laser detection analytical tool of coal quality detecting method and application thereof |
| CN107462662A (en) * | 2017-08-07 | 2017-12-12 | 长沙开元仪器股份有限公司 | A kind of on-line element analysis of coal system |
| CN107631997A (en) * | 2017-09-29 | 2018-01-26 | 北京国电新创科技有限公司 | A kind of real-time, non-intruding, a variety of coal Main Ingredients and Appearance simultaneous measuring apparatus |
| CN109580499A (en) * | 2019-01-03 | 2019-04-05 | 中国神华能源股份有限公司 | Coal quality measuring device |
| CN211443784U (en) * | 2019-12-08 | 2020-09-08 | 国家能源聊城发电有限公司 | Device for on-line monitoring of coal quality and composition of coal entering plant |
| CN111189671A (en) * | 2020-03-31 | 2020-05-22 | 中国二十二冶集团有限公司 | Automatic sampling device and sampling method for entering crushed stone of mixing station |
| CN218239818U (en) * | 2022-06-29 | 2023-01-06 | 深圳数马电子技术有限公司 | Diffuse reflection optical sensor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116297273B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6483581B1 (en) | Raman system for rapid sample indentification | |
| JP2638595B2 (en) | Method and apparatus for measuring parameters of gaseous substances | |
| CN101995395B (en) | Method for online detecting material by laser induction multiple spectrum united fingerprint network | |
| CN106093011B (en) | Coal quality detecting method and its coal quality laser detection analysis instrument of application | |
| US9001331B2 (en) | Arrangement adapted for spectral analysis of high concentrations of gas | |
| CN108020540B (en) | Laser-induced breakdown spectroscopy detection system | |
| CN1554022A (en) | Exhaust opacity measuring device | |
| CN108007890A (en) | A kind of motor-vehicle tail-gas detection light beam reflection unit and detecting system | |
| CN1218178C (en) | Method and device for analysing three dimensional distribution of component in a sample | |
| CN114636691A (en) | Online detection system and detection method based on laser multi-energy spectrum | |
| CN116297272B (en) | On-line coal quality analysis system and method | |
| CN1221799C (en) | Identifying recycable carpet materials using hand-held infrared spectrometer | |
| CN116297273B (en) | On-line analysis system and method for coal quality based on factory entry | |
| CN216284812U (en) | Measuring device for measuring granularity of wide-screened particles on conveying belt | |
| CN113252618B (en) | Linkage device of laser-induced breakdown spectroscopy analysis system and spectroscopy analysis system | |
| CN108195823B (en) | Laser-induced breakdown spectroscopy detection system | |
| CN106338499A (en) | Element laser detection and analysis instrument and mineral element analysis method | |
| CN205449805U (en) | Surface reinforcing raman spectroscopy test system | |
| CN108195824A (en) | A kind of laser induced breakdown spectroscopy detecting system | |
| CN111413318B (en) | Serum detection system and method based on Raman spectrum | |
| CN111272736B (en) | Breakdown spectrum and absorption spectrum combined measurement system and method | |
| CN208125648U (en) | MICRO-BEAM XRF ANALYSIS system based on combination X-ray capillary | |
| CN206132617U (en) | Element laser detecting analyzer ware | |
| CN219455944U (en) | Large-particle coal sample coal quality detection device, system and boiler | |
| CN108709898A (en) | MICRO-BEAM XRF ANALYSIS system based on combination X-ray capillary |
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 |