Coal seam mining in-situ identification method and system based on element and spectral characteristics

Abstract

The present application relates to coal mining technical field, specifically disclose a kind of coal seam mining in-situ identification method and system based on element and spectral characteristics, method includes: real-time acquisition of mining interface spectral data and element content data, based on the coal rock identification model constructed in advance, the coal rock proportion identification result of current mining interface is obtained;If the coal rock proportion identified is higher than set threshold, carry out mining work;Real-time acquisition of mining material spectral data and element content data, based on the coal gangue identification model constructed in advance, the identification result that material belongs to coal, coal gangue or coal and coal gangue mixture material is obtained;Coal and coal gangue are respectively transported after sorting, obtain the spectral data and element content data of coal material in the conveying process, based on the coal type identification model constructed in advance, coal type is identified;The present application realizes in-situ identification and optimization of coal type in the process of mining, improves the purity and efficiency of coal mining.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mining, and particularly relates to a coal mining in-situ identification method and system based on element and spectral characteristics. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0003] In the process of coal mine tunnel mining, the sudden change of coal-rock boundary increases the mining difficulty and is easy to cause damage to the construction machinery; the mined coal is often mixed with gangue, which greatly affects the quality of the output coal; and the similarity of the appearances of different coal types makes it difficult to effectively distinguish between multiple coal types, which seriously affects the economic benefits of coal.

[0004] Therefore, rapid and effective identification of coal-rock boundary, coal gangue and coal type has important value in the whole process of coal mine tunnel mining and can improve the mining efficiency of coal mine engineering.

[0005] The prior art often only screens and identifies a single process in the mining process, such as: single coal-rock identification or single coal gangue identification, etc., and cannot realize online in-situ identification of different processes in the whole process of coal mine tunnel mining, and cannot guarantee the whole-process identification of the whole mining process.

[0006] In addition, for coal-rock boundary identification, coal gangue identification or coal type identification technology, the prior art mainly uses process signal monitoring, infrared thermal imaging, image or reflected spectrum, etc. to realize, but the method of process signal monitoring or infrared thermal imaging is too dependent on the single indirect characteristics of coal, coal gangue or rock, such as: heat, hardness, etc., and cannot distinguish from the composition essence; these characteristics may have similarities between different substances and cannot be distinguished from the fundamental composition, which is easy to cause confusion between coal and coal gangue or rock, affecting the accuracy of identification and the efficiency of mining.

[0007] And the image recognition method mainly relies on the appearance characteristics, and some coal types and coal gangues are very similar in appearance and are difficult to distinguish by naked eye or simple image recognition method; in coal mines, coal, coal gangue and rock often exist in mixture, which further increases the difficulty of identification; therefore, the image recognition method is easy to cause confusion among coal, coal gangue and coal type, and falls into the trap of inaccuracy.

[0008] The reflection spectrum and element identification have the characteristics of rapidity, non-destructiveness and high efficiency, and can reflect the corresponding characteristics from the nature of the material, but the mixture of multiple substances is easy to cause overlapping, annihilation and other variation characteristics of the mixed spectrum characteristics, which is difficult to be interpreted with high precision by traditional spectroscopy, resulting in low recognition accuracy of coal-rock boundary, coal gangue or coal type, and it is difficult to provide technical guidance for actual coal mine engineering construction. SUMMARY

[0009] In order to solve the above problems, the present application provides a coal seam mining in-situ identification method and system based on element and spectral characteristics, which can accurately identify the coal-rock boundary at the cutting stage, and can accurately distinguish coal gangue from coal after mining is completed, so as to improve the quality of coal and further identify the type of coal.

[0010] In some embodiments, the following technical solutions are adopted:

[0011] A coal seam mining in-situ identification method based on element and spectral characteristics, comprising:

[0012] Real-time acquisition of spectral data and element content data of the mining interface, based on a pre-constructed coal-rock identification model, to obtain the coal-rock proportion identification result of the current mining interface;

[0013] If the identified coal-rock proportion is higher than the set threshold, the mining work is carried out; real-time acquisition of spectral data and element content data of the mining material, based on a pre-constructed coal-gangue identification model, to obtain the identification result of the material belonging to coal, coal gangue or coal and coal gangue mixture; separation of the coal and coal gangue mixture to obtain coal;

[0014] Transporting the sorted coal and coal gangue respectively, acquiring spectral data and element content data of the coal material in the transportation process, and identifying the coal type based on a pre-constructed coal type identification model;

[0015] Among them, the coal and rock samples are mixed in different proportions to prepare a plurality of coal-rock mixed samples, the end-member spectrum and element content of the coal and rock samples are acquired respectively, the mixed spectrum and element content data of each mixed sample are acquired, a first data set is formed, and the coal-rock identification model is trained using the first data set.

[0016] As a further solution, it also includes: mixing the coal and coal gangue samples in different proportions to prepare a plurality of coal and coal gangue mixed samples, acquiring the end-member spectrum and element content of the coal and coal gangue samples respectively, acquiring the mixed spectrum and element content data of each mixed sample, forming a second data set, and training the coal-gangue identification model using the second data set.

[0017] As a further solution, further comprising: mixing the bituminous coal sample and the anthracite sample at different proportions to prepare a plurality of mixed coal samples, respectively obtaining the endmember spectrum and the element content of the bituminous coal sample and the anthracite sample, and obtaining the mixed spectrum and the element content data of each mixed sample to form a third data set, and training the coal type identification model using the third data set.

[0018] As a further solution, the spectral data includes corresponding reflectivity data at different wavelengths, and the corresponding spectral curve is obtained by fitting.

[0019] As a further solution, when training the coal type identification model, a quantitative relationship between the spectral features and the contents of different minerals in the mixed sample is established by linear regression, specifically:

[0020] I 1 C-H =I a1 C-H ·C 无烟煤 +I b1 C-H ·C 有烟煤 ;

[0021] C 无烟煤 +C 有烟煤 =1;

[0022] wherein, I 1 C-H is the intensity of the C-H characteristic peak in the mixed spectrum, C 无烟煤 is the relative content of anthracite in the mixed sample, I a1 C-H is the intensity of the C-H characteristic peak in the endmember spectrum of the anthracite; C 有烟煤 is the relative content of bituminous coal in the mixed sample; I b1 C-H is the intensity of the C-H characteristic peak in the corresponding endmember spectrum of the bituminous coal.

[0023] As a further solution, when training the coal type identification model, the coal rock identification model or the coal gangue identification model, based on the element sequence and content of the mixed sample at different mixing proportions, the change characteristics of the content of the characteristic element in the mixed sample at different mixing proportions compared with the content of the characteristic element in the anthracite are extracted, and a corresponding relationship between the mixed sample at different mixing proportions and the change characteristics of the content of the characteristic element is established; during actual prediction, based on the content of the characteristic element obtained in the to-be-detected sample, the mineral type and proportion in the to-be-detected sample are matched; wherein, the characteristic element at least includes: carbon element, hydrogen element, sulfur element and silicon element.

[0024] As a further solution, the coal rock identification model, the coal gangue identification model or the coal type identification model is implemented using a convolutional neural network structure.

[0025] In some other embodiments, the following technical solutions are adopted:

[0026] A coal seam mining in-situ identification system based on element and spectral characteristics comprises:

[0027] A coal rock identification module is configured to acquire spectral data and element content data of a mining interface in real time, and obtain a coal rock proportion identification result of the current mining interface based on a pre-constructed coal rock identification model; if the identified coal rock proportion is higher than a set threshold, mining work is performed.

[0028] A coal gangue identification module is configured to acquire spectral data and element content data of mined materials in real time after mining is completed, and obtain an identification result of whether the materials belong to coal, coal gangue or a mixture of coal and coal gangue based on a pre-constructed coal gangue identification model; the mixture of coal and coal gangue is separated to obtain coal.

[0029] A coal type identification module is configured to convey the separated coal and coal gangue respectively, acquire spectral data and element content data of the coal materials in the conveying process, and identify the coal type based on a pre-constructed coal type identification model.

[0030] The coal and rock samples are mixed at different proportions to prepare a plurality of coal rock mixed samples, the endmember spectrum and element content of the coal and rock samples, the mixed spectrum and element content data of each mixed sample are acquired respectively to form a first data set, and the coal rock identification model is trained by using the first data set.

[0031] In some other embodiments, the following technical solutions are adopted:

[0032] A terminal device comprises a processor and a memory, the processor is configured to implement instructions; the memory is configured to store a plurality of instructions, the instructions are suitable for being loaded and executed by the processor to implement the coal seam mining in-situ identification method based on element and spectral characteristics.

[0033] In some other embodiments, the following technical solutions are adopted:

[0034] A computer readable storage medium stores a plurality of instructions, the instructions are suitable for being loaded and executed by the processor of a terminal device to implement the coal seam mining in-situ identification method based on element and spectral characteristics.

[0035] Compared with the prior art, the beneficial effects of the present application are:

[0036] (1) The present application can identify the coal-rock mixed zone in real time during mining and perform quantitative and accurate cutting, which can significantly reduce the mixing of non-coal materials; at the same time, the coal and coal gangue can be accurately and effectively separated through coal gangue identification; for the screened coal samples, the bituminous coal and anthracite are distinguished through coal type identification, realizing in-situ identification and optimization of coal type during mining, and improving the purity and efficiency of coal mining.

[0037] (2) The present application pre-constructs coal-rock, coal gangue and coal type mixed samples with different mixing ratios according to actual engineering experience, respectively obtains the spectral data and element content data of each mixed sample, forms a data set of mixed samples with different mixing ratios and the corresponding spectral and element content data, and trains the corresponding coal-rock identification model, coal gangue identification model or coal type identification model using the data set, so as to obtain accurate mineral type and content identification results, and solve the problem that the mixed sample spectrum cannot be directly interpreted in the prior art; such accurate identification can maximize the use of useful resources in the ore deposit, reduce resource waste, and improve the overall resource utilization rate and separation efficiency.

[0038] (3) The present application combines spectrum and element characteristics with machine learning, so that the system can more accurately identify complex mixed spectral characteristics, and machine learning can provide higher accuracy and reliability through a large amount of data training. The present application establishes an identification system based on element and spectral variation characteristics, which can accumulate a large amount of spectral data and element variation characteristic data; these data can not only be used for real-time decision-making, but also be used for optimization training of the identification model, providing important data support for dynamic optimization of the subsequent identification model.

[0039] Other features and advantages of the additional aspects of the present application will be partially given in the following description, partially become obvious from the following description, or be understood by practicing the present application. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A flow chart of the in-situ identification method for coal mining based on element and spectral characteristics in the embodiments of the present application;

[0041] Figure 2 A schematic diagram of the coal-rock identification process in the embodiments of the present application;

[0042] Figure 3 A schematic diagram of the end-member spectrum of anthracite and carbon-containing coal gangue and the mixed spectrum data of the mixed sample in the embodiments of the present application;

[0043] Figure 4 A schematic diagram of the content of the marker element in the mixed mineral sample with different proportions in the embodiments of the present application. DETAILED DESCRIPTION

[0044] It should be noted that the following detailed description is illustrative only, and is intended to provide further description in connection with the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the application pertains.

[0045] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0046] Embodiment one

[0047] In one or more embodiments, a coal seam mining in-situ identification method based on elements and spectral features is disclosed, which combines Figure 1 , and specifically includes the following processes:

[0048] S101: Real-time acquisition of spectral data and element content data of the mining interface, and obtaining the coal rock proportion identification result of the current mining interface based on the pre-constructed coal rock identification model.

[0049] In this embodiment, first, deposit exploration and geological exploration are carried out in the to-be-measured mining area, and the geological features of the mining area are fully investigated to provide geological information constraints for mineral qualitative identification; wherein the geological features include geological structure, lithology distribution, stability, etc.

[0050] The method of deposit exploration and geological exploration includes but is not limited to: geological radar, unmanned aerial vehicle aerial photography, drilling exploration, geological mapping method, etc.; the main purpose of the deposit exploration and geological exploration in this embodiment is to obtain detailed information such as geological structure, lithological characteristics, stability of the mining area, to evaluate the geological conditions and potential risks of the mining area, and to provide geological information constraints for mineral qualitative identification.

[0051] Specifically, the mining area along the line is surveyed, and the geological structure of the mining area is identified and recorded using the geological radar, the geological mapping method and the unmanned aerial vehicle aerial photography; the core samples are obtained through drilling exploration, and petrology analysis is carried out, and the spatial distribution of the lithology distribution is determined in combination with the geological radar and the geological mapping method; the stability of the rock mass is evaluated through field observation and geotechnical engineering test; finally, it is proved that the overall structure of the mining area is mainly monocline, and small folds and faults are developed locally, and the main rock types of the mining area include sandstone, and no major geological structure movement has occurred in history. The model trained by the data of the local area in this embodiment is best applicable in the local area or in an environment similar to the geological features of the local area.

[0052] In the embodiment, before mining, the coal-rock ratio of the current mining interface is identified. If the coal-rock ratio is lower than a set threshold (for example, the threshold can be set to 0.75), it indicates that the coal content is low, which may cause the coal obtained by mining to be not clean, causing trouble to subsequent processing and affecting economic benefits. If the coal-rock ratio is higher than the set threshold, it indicates that the coal content is high, and the subsequent mining work is continued.

[0053] The embodiment can ensure the accuracy of the tunneling process by identifying the coal-rock ratio of the mining interface, thereby avoiding unnecessary waste of resources.

[0054] In S102, if the identified coal-rock ratio is higher than the set threshold, mining work is performed; the spectral data and the element content data of the mined material are acquired in real time, and based on the pre-constructed coal-gangue identification model, an identification result that the material belongs to coal, coal gangue or coal-gangue mixture is obtained; the coal-gangue mixture is separated to obtain coal.

[0055] In the embodiment, after the coal seam mining is completed, the raw coal obtained by mining is first subjected to preliminary screening and impurity removal, and then the raw coal is crushed into smaller blocky materials. The materials are uniformly spread on a conveyor belt, and the element content data and the spectral data of the materials are collected in real time by using a spectral sensor and a LIBS analyzer. The collected element content and spectral data are input into a pre-constructed coal-gangue identification model for real-time analysis and identification. The mineral types of the materials and the relative contents of coal and coal gangue in the materials are identified, preprocessed, and the separation device is controlled to select pure coal, pure coal gangue and coal-coal gangue mixture respectively. The selected coal-coal gangue mixture is further separated by using existing technology to obtain pure coal.

[0056] In S103, the sorted coal and coal gangue are respectively conveyed, the spectral data and the element content data of the coal material in the conveying process are acquired, and based on the pre-constructed coal type identification model, the coal type is identified.

[0057] In the embodiment, the obtained pure coal is uniformly spread on a conveyor belt, and the element content data and the spectral data of the pure coal are collected in real time by using a spectral sensor and a LIBS analyzer. The collected element content and spectral data are input into a pre-constructed coal type identification model for real-time analysis and identification. The coal type in the pure coal is identified, the relative contents of bituminous coal and anthracite are obtained, preprocessed, and the separation device is controlled to select bituminous coal, anthracite and mixed coal respectively. The selected mixed coal is further separated by using existing technology to obtain pure anthracite and pure bituminous coal.

[0058] The embodiment method realizes in-situ accurate identification of bituminous coal and anthracite in the coal mining process based on element content and spectral data, and is not affected by spectral data superposition.

[0059] In this embodiment, the inputs of the coal rock identification model, the coal gangue identification model and the coal type identification model are both element content data and spectral data; wherein the spectral data includes corresponding reflectivity data at multiple different wavelengths, and the corresponding spectral curve is obtained by fitting.

[0060] The coal and rock samples are mixed in different proportions to prepare a plurality of coal rock mixed samples, the end-member spectrum and element content of the coal and rock samples are obtained respectively, the mixed spectrum and element content data of each mixed sample are obtained, a first data set is formed, and the coal rock identification model is trained using the first data set.

[0061] The coal and coal gangue samples are mixed in different proportions to prepare a plurality of coal and coal gangue mixed samples, the end-member spectrum and element content of the coal and coal gangue samples are obtained respectively, the mixed spectrum and element content data of each mixed sample are obtained, a second data set is formed, and the coal gangue identification model is trained using the second data set.

[0062] The bituminous coal and anthracite samples are mixed in different proportions to prepare a plurality of mixed coal samples, the end-member spectrum and element content of the bituminous coal and anthracite samples are obtained respectively, the mixed spectrum and element content data of each mixed sample are obtained, a third data set is formed, and the coal type identification model is trained using the third data set.

[0063] The characteristics of the end-member spectrum refer to the spectral data obtained from pure samples (such as anthracite, carbon-containing coal gangue, and sandstone); including the characteristic peak position, intensity and shape of each pure mineral, representing the absorption and reflection characteristics of these samples; the characteristics of the mixed spectrum refer to the spectral data of the mixed sample, representing the combination of the spectral characteristics of the mixed minerals, manifested as changes in characteristic peaks, shifts in spectral peak values, and changes in absorption band intensity, etc.

[0064] When two minerals of different proportions are mixed together, their mixed spectral characteristics will change, showing phenomena inconsistent with the spectral characteristics of single pure minerals, such as shifts in spectral peak values, and disappearance of characteristic absorption bands, etc. The variation characteristics of the mixed spectrum band shape, absorption peak position and intensity contain spectral information of each component, and become an important basis for identifying the pattern of mixed samples. Figure 3 The spectral data of 20% anthracite mixed with 80% carbon-containing coal gangue, and the end-member spectra of anthracite and carbon-containing coal gangue are given. It can be seen that the spectral peak intensity and position of the mixed sample have shifted, therefore, the change in the proportion of the mixed sample can be reflected by the spectral data.

[0065] In addition, the main elements in anthracite, carbon-containing coal gangue and sandstone are tested in advance in this embodiment, and it is found that the content of carbon element is the highest in anthracite, the second highest in carbon-containing coal gangue, and the lowest in sandstone. After mixing, the content of carbon element decreases significantly, and the higher the ratio of coal gangue / rock after mixing, the greater the decrease. The content of hydrogen element is relatively high in anthracite, and the content of hydrogen element decreases slightly after mixing. The content of sulfur element is relatively high in anthracite, and the content of sulfur element decreases slightly after mixing. The content of silicon element is relatively low in anthracite, and the content of silicon element is relatively high in carbon-containing coal gangue and sandstone. After mixing, the content of silicon element increases significantly, and the higher the mixing ratio, the greater the increase. The change trend and characteristic mode of these elements can be used to identify the existence and relative content of each component, and reflect the change of the mixing ratio of the mixed sample. Figure 4 The content change diagram of the characteristic elements carbon (C), hydrogen (H), sulfur (S) and silicon (Si) in the mixed sample of 10% coal + 90% rock, 15% coal + 85% rock, 20% coal + 80% rock and 25% coal + 75% rock is given.

[0066] The two characteristics of spectrum and element in this embodiment can be used to more accurately analyze and identify the composition of the mixed sample.

[0067] The identification processes of the coal-rock identification model, the coal-gang identification model and the coal type identification model in this embodiment are basically the same, except that the training data sets and input data of different models are different.

[0068] As a specific example, the coal-rock identification is taken as an example for illustration, combined with Figure 2 , the specific method is as follows:

[0069] S1011: Select samples of common rocks and coal types in the process of coal mining, and use a high-resolution spectrometer to obtain end-member spectral information of the above samples. The spectral information covers the spectral range from visible light to near-infrared and even mid-infrared, i.e. it includes the reflectivity data at multiple different wavelengths, and the corresponding spectral curve can be obtained by fitting multiple (wavelength, reflectivity) data. Store the obtained end-member spectral data in a special database to establish an end-member spectral library.

[0070] When selecting samples, representative samples of coal and rock should be collected in the coal seam and rock layer enrichment area according to the mining area exploration results in (1). Ensure that the samples cover coal quality (such as anthracite, bituminous coal, lignite), different lithology (such as sandstone, shale, mudstone), and the collected samples are numbered, cleaned, dried, and properly stored in a light-proof and moisture-proof environment for subsequent experimental use.

[0071] The high-resolution spectrometer used includes a Fourier transform infrared spectrometer and a Raman spectrometer; in this example, a Fourier transform infrared spectrometer is used to perform spectral testing on the collected samples, and the spectral data of the spectral library are denoised and smoothed to improve the accuracy and readability of the data, and the data are standardized and normalized to eliminate differences between different data sources.

[0072] S1012: According to the actual engineering ratio, different types of coal and rock are mixed to prepare a plurality of mixed samples of coal and rock, to ensure that the mixed samples are representative and diverse. The mixed samples are collected for spectral analysis to obtain spectral data at different mixing ratios.

[0073] Specifically, the coal and rock ratios selected in this embodiment cover a plurality of gradients mixed in actual mining engineering, including: 10% coal + 90% rock, 15% coal + 85% rock, 20% coal + 80% rock, 25% coal + 75% rock; spectral data of these mixed samples are obtained.

[0074] In order to improve the quality of the data, highlight the spectral features, and improve the accuracy of spectral analysis, the spectral data obtained in this embodiment are preprocessed, including: removing the baseline drift in the spectral data to make the spectral curve smoother and facilitate subsequent analysis; using digital filtering techniques such as smoothing filtering and detrend filtering to reduce random noise in the spectral data and improve the signal-to-noise ratio; normalizing the spectral data to eliminate intensity differences caused by sample size, instrument response, and other factors, so that the spectral data of different samples are comparable.

[0075] In this embodiment, in order to reduce the influence of environmental factors on the spectral data, the temperature and humidity in the spectrometer laboratory are controlled to maintain within a constant range, the temperature can be controlled at 20-25°C, and the humidity can be controlled at 40%-60% RH. At the same time, direct illumination of external light sources is reduced, vibration interference is avoided, and the spectrometer is ensured to be in a stable working environment; during the collection process, attention should be paid to controlling the environmental conditions to ensure the accuracy and consistency of the data.

[0076] S1013: Detailed element testing is performed on the mixed samples in S1012 to analyze the element composition of the mixed samples. The element sequence of the samples at different mixing ratios is established, the characteristic element variation features at different mixing modes are extracted, and a data set is formed to provide basic data for subsequent analysis.

[0077] The element testing method of this embodiment uses laser-induced breakdown spectroscopy testing; the characteristic element variation features refer to changes in the content of main elements of mineral samples after mixing at different ratios, etc., specifically referring to changes in the content of elements such as carbon, hydrogen, sulfur, and silicon at different mixing ratios (extracting the element content of the mixed samples at different mixing ratios).

[0078] S1014: Constructing coal rock identification model; using the mixed samples of coal and rock with different proportions obtained in S1011-S1013 and the corresponding spectral data and element content data, the coal rock identification model is trained.

[0079] In this embodiment, the coal rock identification model performs feature analysis on the obtained spectral data, and uses spectral analysis technology to extract endmember spectrum and mixed spectrum features. Based on the endmember spectrum, the variation law of the mixed spectrum with the endmember content and type is analyzed. The quantitative relationship between the spectral features and the mineral content is established.

[0080] Specifically, the spectral analysis technology used includes derivative spectrum, peak-valley identification, multivariate curve resolution, etc., and when extracting endmember spectrum and mixed spectrum features, the position, intensity, shape and other parameters of the characteristic peaks are focused on; In this embodiment, the endmember spectrum data obtained from pure samples (anthracite, carbon-containing coal gangue, sandstone) is analyzed to obtain the main characteristic peaks of anthracite endmember spectrum at 3000-2800 cm -1 (C-H stretching vibration) and 1600 cm -1 (C=C aromatic ring vibration); the main characteristic peaks of carbon-containing coal gangue endmember spectrum are at 3600-3200 cm -1 (O-H stretching vibration), 1000-1200 cm -1 (Si-O stretching vibration); the main characteristic peaks of sandstone endmember spectrum are at 3600-3200 cm -1 (O-H stretching vibration), 1000-1200 cm -1 (Si-O stretching vibration);

[0081] In this example, based on the endmember spectrum, the variation law of the mixed spectrum with the endmember content and type is analyzed, that is, the spectral data obtained from samples with different mixing ratios are analyzed to obtain the characteristic peak positions of the mixed spectrum, which are basically consistent with the characteristic peak positions of the endmember spectrum, but the peak intensity and shape change with the endmember content. The intensity of the C-H, C=C, O-H and Si-O characteristic peaks in the mixed spectrum changes with the endmember content, the C-H characteristic peak intensity increases with the increase of anthracite content, and the O-H and Si-O characteristic peak intensity increases with the increase of carbon-containing coal gangue and sandstone content; The shape of the characteristic peak in the mixed spectrum (such as peak width, symmetry) changes with the endmember type and content, the C-H characteristic peak in the mixed sample is narrow and symmetrical at high anthracite content, and is wide and asymmetrical at high carbon-containing coal gangue and sandstone content.

[0082] The quantitative relationship between the spectral features and the mineral content is established by linear regression, and the specific formula is as follows:

[0083] ;

[0084] ;

[0085] wherein, is the intensity of the kth characteristic peak of the ith mineral in the mixed sample, is the intensity of the kth characteristic peak of the ith mineral, is the relative content of the ith mineral, n is the number of mineral species involved in the mixed sample, n≥2, k=n-1.

[0086] The above formula is common to coal rock identification model, coal gangue identification model and coal type identification model; for example:

[0087] In coal type identification, there are two minerals: bituminous coal and anthracite.

[0088] The quantitative relationship is:

[0089] I 1 C-H =I a1 C-H *C 无烟煤 +I b1 C-H *C 有烟煤 ;

[0090] C 无烟煤 +C 有烟煤 =1;

[0091] wherein, I 1 C-H is the intensity of the C-H characteristic peak in the mixed spectrum, C 无烟煤 is the relative content of anthracite in the mixed sample, I a1 C-H is the intensity of the C-H characteristic peak in the end-member spectrum of anthracite; C 有烟煤 is the relative content of bituminous coal in the mixed sample; I b1 C-H is the intensity of the C-H characteristic peak in the end-member spectrum of bituminous coal.

[0092] In coal gangue identification, there are usually four minerals: bituminous coal, anthracite, carbon-containing coal gangue and carbon-free coal gangue, and the quantitative relationship is:

[0093] I 2 C-H =I a2 C-H ·C 无烟煤 +I b2 C-H ·C 有烟煤 +I c2 C-H ·C 含碳煤矸石 +Id2 C-H ·C 无碳煤矸石 ;

[0094] I 2 O-H =I a2 O-H ·C 无烟煤 +I b2 O-H ·C 有烟煤 +I c2 O-H ·C 含碳煤矸石 +I d2 O-H ·C 无碳煤矸石 ;

[0095] I 2 SI-O =I a2 SI-O ·C 无烟煤 +I b2 SI-O ·C 有烟煤 +I c2 SI-O ·C 含碳煤矸石 +I d2 SI-O ·C 无碳煤矸石 ;

[0096] C 无烟煤 +C 有烟煤 +C 含碳煤矸石 +C 无碳煤矸石 =1;

[0097] wherein, I 2 C-H is the intensity of C-H characteristic peak in the mixed spectrum, C 无烟煤 is the relative content of anthracite in the mixed sample, I a2 C-H is the intensity of C-H characteristic peak in the end-member spectrum of anthracite; C 有烟煤 is the relative content of bituminous coal in the mixed sample; I b2 C-H is the intensity of C-H characteristic peak in the end-member spectrum corresponding to bituminous coal; C 含碳煤矸石 is the relative content of carbon-containing coal gangue in the mixed sample, I c2 C-H is the intensity of C-H characteristic peak in the end-member spectrum corresponding to carbon-containing coal gangue; C 无碳煤矸石 is the relative content of carbon-free coal gangue in the mixed sample, I d2 C-H is the intensity of C-H characteristic peak in the end-member spectrum of carbon-free coal gangue; I 2 O-H , I2 SI-O respectively the intensity of O-H characteristic peak and SI-O characteristic peak in the mixed spectrum, I a2 O-H , I a2 SI-O respectively the intensity of O-H characteristic peak and SI-O characteristic peak in the end-member spectrum of anthracite; I b2 O-H , I b2 SI-O respectively the intensity of O-H characteristic peak and SI-O characteristic peak in the end-member spectrum of bituminous coal; I c2 O-H , I c2 SI-O respectively the intensity of O-H characteristic peak and SI-O characteristic peak in the end-member spectrum of carbon-containing coal gangue; I d2 O-H , I d2 SI-O respectively the intensity of O-H characteristic peak and SI-O characteristic peak in the end-member spectrum of carbon-free coal gangue.

[0098] In the coal rock identification, the minerals usually include: bituminous coal, anthracite, carbon-containing coal gangue, carbon-free coal gangue, sandstone and shale, based on the same reason, the intensity of C-H characteristic peak, O-H characteristic peak, SI-O characteristic peak, C=C characteristic peak and S-O characteristic peak in the mixed spectrum can be used to construct the relationship respectively.

[0099] In the above relationship, the intensity of each characteristic peak in the mixed spectrum and the intensity of each characteristic peak in the end-member spectrum of different minerals can be obtained from the end-member spectrum library or obtained by collection, so the content proportion of different minerals can be determined.

[0100] In this embodiment, the coal rock identification model performs feature analysis on the input element content data, based on the element sequence and content of the mixed sample under different mixing ratios, extracts the change characteristics of the content of the carbon element, hydrogen element, sulfur element and silicon element and other marker elements of the mixed sample under different mixing ratios compared with the content of the marker elements in the anthracite, and establishes the corresponding relationship between the mixed sample under different mixing ratios and the change characteristics of the content of the marker elements; in actual prediction, based on the obtained content of the marker elements in the sample to be tested, the mineral types and proportions in the sample to be tested can be matched and obtained.

[0101] S1015: Real-time acquisition of the spectrum data and element content data of the mining interface, based on the coal rock identification model constructed and trained in S1014, the coal rock proportion identification result of the current mining interface can be output.

[0102] The identification process of coal gangue recognition and coal type recognition is basically the same as the process of coal rock recognition, and the identification principle of the coal gangue recognition model and the coal type recognition model is also completely the same as that of the coal rock recognition model. The difference lies in that:

[0103] When the coal gangue recognition model is trained, the end-member spectrum, mixed spectrum and element content data of different types of pure coal (such as anthracite, bituminous coal and lignite), pure coal gangue (such as carbon-containing gangue and carbon-free gangue), and mixed samples of pure coal and pure coal gangue in different proportions are obtained, such as 10% coal + 90% coal gangue, 15% coal + 85% coal gangue, 20% coal + 80% coal gangue, and 25% coal + 75% coal gangue. When actually predicting, the spectral data and element content data of the mined material are obtained, and based on the pre-constructed and trained coal gangue recognition model, the recognition result of the material belonging to coal, coal gangue or coal and coal gangue mixture and the respective proportion is obtained.

[0104] When the coal type recognition model is trained, the end-member spectrum, mixed spectrum and element content data of different types of pure coal (such as anthracite, bituminous coal and lignite) and mixed samples of different types of pure coal in different proportions are obtained. When actually predicting, the spectral data and element content data of the coal material in the conveying process are obtained, and based on the pre-constructed and trained coal type recognition model, the recognition result of anthracite and bituminous coal and their proportions is obtained.

[0105] Embodiment Two

[0106] In one or more embodiments, a coal seam mining in-situ recognition system based on element and spectral characteristics is disclosed, comprising:

[0107] A coal rock recognition module is configured to obtain spectral data and element content data of a mining interface in real time, and obtain a coal rock proportion recognition result of the current mining interface based on a pre-constructed coal rock recognition model. If the recognized coal rock proportion is higher than a set threshold, the mining work is performed.

[0108] A coal gangue recognition module is configured to obtain spectral data and element content data of the mined material in real time after the mining is completed, and obtain a recognition result of the material belonging to coal, coal gangue or coal and coal gangue mixture based on a pre-constructed coal gangue recognition model. The coal and coal gangue mixture is separated to obtain coal.

[0109] A coal type recognition module is configured to convey the sorted coal and coal gangue respectively, obtain spectral data and element content data of the coal material in the conveying process, and identify the coal type based on a pre-constructed coal type recognition model.

[0110] The coal and rock samples are mixed in different proportions to prepare a plurality of coal-rock mixed samples, the endmember spectrum and element content of the coal and rock samples are obtained, the mixed spectrum and element content data of each mixed sample are obtained, a first data set is formed, and the coal-rock identification model is trained by using the first data set.

[0111] It should be noted that the specific embodiments of the above modules are the same as those in Embodiment One, and will not be described in detail.

[0112] Embodiment Three

[0113] In one or more embodiments, a terminal device is disclosed, which includes a processor and a memory, the processor is used to implement instructions; the memory is used to store a plurality of instructions, the instructions are suitable for being loaded and executed by the processor to implement the coal seam mining in-situ identification method based on element and spectral characteristics described in Embodiment One.

[0114] It should be understood that in the embodiments, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, ready-to-program gate arrays FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0115] The memory can include read-only memory and random access memory, and provide instructions and data to the processor, and a part of the memory can also include non-volatile random access memory. For example, the memory can also store device type information.

[0116] In the implementation process, each step of the above method can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software.

[0117] Embodiment Four

[0118] In one or more embodiments, a computer-readable storage medium is disclosed, which stores a plurality of instructions, the instructions are suitable for being loaded and executed by the processor of the terminal device to implement the coal seam mining in-situ identification method based on element and spectral characteristics described in Embodiment One.

[0119] The above describes the specific embodiments of the present application in combination with the drawings, but is not a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications or changes made by those skilled in the art on the basis of the technical solutions of the present application without creative labor are still within the protection scope of the present application.

Claims

1. A coal seam mining in-situ identification method based on element and spectral characteristics, characterized in that, The method comprises the following steps: Real-time acquisition of spectral data and element content data of the mining interface, and obtaining the coal-rock proportion identification result of the current mining interface based on the pre-constructed coal-rock identification model; If the identified coal-rock proportion is higher than the set threshold, the mining work is carried out; real-time acquisition of spectral data and element content data of the mining material, and obtaining the identification result of whether the material belongs to coal, coal gangue or coal and coal gangue mixture based on the pre-constructed coal gangue identification model; separating the coal and coal gangue mixture to obtain coal; The separated coal and coal gangue are transported respectively, the spectral data and element content data of the coal material in the transportation process are acquired, and the coal type is identified based on the pre-constructed coal type identification model; wherein the spectral data of the coal is collected in real time by an infrared spectrometer, and the element content data of the coal is collected in real time by a LIBS analyzer; Specifically, the obtained coal is uniformly spread on a conveyor belt, and the collected element content data and spectral data are input into the pre-constructed coal type identification model for real-time analysis and identification to identify the coal type of a piece of coal and obtain the relative content of bituminous coal and anthracite, and the bituminous coal, anthracite and mixed coal are separated to obtain pure anthracite and pure bituminous coal; Wherein, the coal and rock samples are mixed in different proportions to prepare a plurality of coal-rock mixed samples, the end-member spectrum and element content of the coal and rock samples are acquired, and the mixed spectrum and element content data of each mixed sample are acquired to form a first data set, and the coal-rock identification model is trained using the first data set; The coal and coal gangue samples are mixed in different proportions to prepare a plurality of coal and coal gangue mixed samples, the end-member spectrum and element content of the coal and coal gangue samples are acquired, and the mixed spectrum and element content data of each mixed sample are acquired to form a second data set, and the coal gangue identification model is trained using the second data set; The bituminous coal and anthracite samples are mixed in different proportions to prepare a plurality of mixed coal samples, the end-member spectrum and element content of the bituminous coal and anthracite samples are acquired, and the mixed spectrum and element content data of each mixed sample are acquired to form a third data set, and the coal type identification model is trained using the third data set; During the training of the coal type identification model, a quantitative relationship between the spectral characteristics and the content of different minerals in the mixed sample is established by linear regression, specifically: where I 1 C-H is the intensity of the C-H characteristic peak in the mixed spectrum, C 无烟煤 is the relative content of anthracite in the mixed sample, I a1 C-H is the intensity of the C-H characteristic peak in the endmember spectrum of anthracite; C 有烟煤 is the relative content of bituminous coal in the mixed sample; I b1 C-H is the intensity of the C-H characteristic peak in the endmember spectrum corresponding to bituminous coal; The coal rock identification model, the coal gangue identification model or the coal type identification model is trained based on element sequences and contents of mixed samples under different mixing ratios, and a corresponding relationship between the mixed samples under different mixing ratios and the change characteristics of the content of the marker element is established by extracting the change characteristics of the content of the marker element in the mixed samples under different mixing ratios compared with the content of the marker element in anthracite.

2. The method for in-situ identification of coal seam mining based on element and spectral characteristics according to claim 1, characterized in that, The spectral data includes reflectivity data corresponding to different wavelengths, and the corresponding spectral curve is obtained by fitting.

3. The method for in-situ identification of coal seam mining based on element and spectral characteristics according to claim 1, characterized in that, The coal rock identification model, the coal gangue identification model or the coal type identification model is implemented using a convolutional neural network structure.

4. A coal seam mining in-situ identification system based on element and spectral characteristics, characterized in that, It comprises: a coal rock identification module, which is used to obtain spectral data and element content data of a mining interface in real time, and obtain a coal rock ratio identification result of the current mining interface based on a pre-constructed coal rock identification model; if the identified coal rock ratio is higher than a set threshold, mining work is performed; a coal gangue identification module, which is used to obtain spectral data and element content data of mined materials in real time after mining is completed, and obtain an identification result of whether the materials belong to coal, coal gangue or a mixture of coal and coal gangue based on a pre-constructed coal gangue identification model; the mixture of coal and coal gangue is separated to obtain coal; a coal type identification module, which is used to convey the separated coal and coal gangue, obtain spectral data and element content data of the coal materials during the conveying process, and identify the coal type based on a pre-constructed coal type identification model; wherein, the spectral data of the coal is collected in real time by an infrared spectrometer, and the element content data of the coal is collected in real time by a LIBS analyzer; Specifically, the obtained coal is evenly spread on a conveyor belt, and the collected element content data and spectral data are input into the pre-constructed coal type identification model for real-time analysis and identification to identify the coal type in a piece of coal and obtain the relative contents of bituminous coal and anthracite, so that bituminous coal, anthracite and mixed coal are separated to obtain pure anthracite and pure bituminous coal. A first data set is formed by mixing coal and rock samples in different proportions to prepare a plurality of coal rock mixed samples, obtaining the end-member spectrum and element content of the coal and rock samples, the mixed spectrum and element content data of each mixed sample, and training the coal rock identification model using the first data set. A second data set is formed by mixing coal and coal gangue samples in different proportions to prepare a plurality of coal and coal gangue mixed samples, obtaining the end-member spectrum and element content of the coal and coal gangue samples, the mixed spectrum and element content data of each mixed sample, and training the coal gangue identification model using the second data set. The bituminous coal sample and the anthracite sample are mixed at different proportions to prepare a plurality of mixed coal samples, the end-member spectrum and the element content of the bituminous coal sample and the anthracite sample are obtained respectively, the mixed spectrum and the element content data of each mixed sample are obtained, a third data set is formed, and the coal type identification model is trained by using the third data set; During the training of the coal type identification model, a quantitative relationship between the spectral features and the contents of different minerals in the mixed sample is established by linear regression, and the quantitative relationship is specifically as follows: where I 1 C-H is the intensity of C-H characteristic peak in the mixed spectrum, C 无烟煤 is the relative content of anthracite in the mixed sample, I a1 C-H is the intensity of C-H characteristic peak in the end-member spectrum of anthracite; C 有烟煤 is the relative content of bituminous coal in the mixed sample; I b1 C-H is the intensity of C-H characteristic peak in the end-member spectrum corresponding to bituminous coal; During the training of the coal type identification model, the end-member spectrum, the mixed spectrum and the element content data of different types of coal and mixed samples obtained by mixing different types of coal at different proportions are obtained; during actual prediction, the mineral types and proportions in the to-be-detected sample are matched based on the obtained content of the characteristic element in the to-be-detected sample; and the characteristic element at least includes carbon, hydrogen, sulfur and silicon. 5.A terminal device comprising a processor and a memory, the processor configured to implement instructions; the memory configured to store a plurality of instructions, and the terminal device is characterized in that, The instructions are adapted to be loaded and executed by the processor to perform the coal seam mining in-situ identification method based on element and spectral features according to any one of claims 1-3.

6. A computer readable storage medium having stored therein a plurality of instructions, wherein the instructions, when executed by a processor, cause the processor to perform the method of any one of claims 1-5. The instructions are adapted to be loaded and executed by the processor of the terminal device to perform the coal seam mining in-situ identification method based on element and spectral features according to any one of claims 1-3.

Images