Coal quality detection method, device, electronic equipment and storage medium

Abstract

The present application discloses a coal quality detection method, device, electronic device and storage medium. Specifically, it includes: obtaining a coal sample to be detected; using a laser induced breakdown spectrometer with a temperature and humidity sensor to detect the coal sample to be detected, and obtaining the spectral data and current temperature and humidity data of the coal sample to be detected; according to the spectral data and the current temperature and humidity data, through a pre-trained indicator detection model, determining at least one coal quality indicator of the coal sample to be detected; according to each coal quality indicator, through a pre-trained indicator correction model, determining the correction amount of each coal quality indicator, and adjusting each coal quality indicator based on the correction amount. In the technical solution of the embodiment of the present application, LIBS with a temperature and humidity sensor is used for coal quality detection. Since the indicator detection model takes into account the temperature and humidity conditions, it reduces the influence of the external environment on coal quality detection; at the same time, the indicator correction model is used to compensate for the error of the detected coal quality indicator, thereby further improving the accuracy of coal quality detection.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a coal quality detection method, device, electronic device and storage medium. Background Art

[0002] With the development of social production and life, coal, as one of the main energy sources, how to use coal resources more efficiently and fully has become one of the focuses of the current coal industry. Among them, coal quality testing for different coal samples, such as laser induced breakdown spectroscopy, identifies coal elements, spectra and other information, and distinguishes coal quality, which helps to better distinguish different coals for different production.

[0003] Currently, laser induced breakdown spectroscopy is the most commonly used method for coal quality testing. However, the hardware of laser equipment is affected by the external environment and differences in manual assembly, resulting in different spectral performances of the same coal sample detected on different devices. There are certain errors, and if no calibration is performed, the accuracy will be low. Summary of the invention

[0004] The present application provides a coal quality detection method, device, electronic device and storage medium to improve the recognition accuracy of coal quality.

[0005] According to one aspect of the present application, a coal quality detection method is provided, comprising:

[0006] Obtaining coal samples to be tested;

[0007] A laser induced breakdown spectrometer with a temperature and humidity sensor is used to detect the coal sample to obtain the spectrum data and current temperature and humidity data of the coal sample to be detected;

[0008] According to the spectral data and the current temperature and humidity data, at least one coal quality index of the coal sample to be tested is determined by using a pre-trained index detection model;

[0009] According to each coal quality index, a correction amount of each coal quality index is determined through a pre-trained index correction model, and each coal quality index is adjusted based on the correction amount.

[0010] According to another aspect of the present application, a coal quality detection device is provided, comprising:

[0011] A coal sample acquisition module, used to acquire the coal sample to be tested;

[0012] The data determination module uses a laser induced breakdown spectrometer with a temperature and humidity sensor to detect the coal sample to be detected, and obtains the spectrum data and current temperature and humidity data of the coal sample to be detected;

[0013] An index detection module is used to determine at least one coal quality index of the coal sample to be detected based on the spectral data and the current temperature and humidity data through a pre-trained index detection model;

[0014] The index correction module is used to determine the correction amount of each coal quality index according to each coal quality index through a pre-trained index correction model, and adjust each coal quality index based on the correction amount.

[0015] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the coal quality detection method described in any embodiment of the present application.

[0019] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the coal quality detection method described in any embodiment of the present application when executed.

[0020] In the technical solution of the embodiment of the present application, LIBS with temperature and humidity sensors is used to perform coal quality detection. The index detection model takes temperature and humidity conditions into consideration, thereby reducing the impact of the external environment on coal quality detection. At the same time, the index correction model is used to compensate for the errors in the detected coal quality indicators, thereby further improving the accuracy of coal quality detection.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a coal quality detection method provided according to Example 1 of the present application;

[0024] Figure 2It is a schematic diagram of coal quality detection, correction model training and use provided in Example 2 of the present application;

[0025] Figure 3 It is a structural schematic diagram of a coal quality detection device provided according to the third embodiment of the present application;

[0026] Figure 4 It is a structural schematic diagram of an electronic device for implementing the coal quality detection method of an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 A flow chart of a coal quality detection method is provided for the first embodiment of the present application. This embodiment is applicable to the case of detecting coal quality. The method can be performed by a coal quality detection device. The coal quality detection device can be implemented in the form of hardware and / or software. The coal quality detection device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110, obtaining a coal sample to be tested.

[0032] S120, using a laser induced breakdown spectrometer with a temperature and humidity sensor to detect the coal sample to be detected, and obtaining spectrum data and current temperature and humidity data of the coal sample to be detected.

[0033] S130. Determine at least one coal quality index of the coal sample to be tested based on the spectral data and the current temperature and humidity data by using a pre-trained index detection model.

[0034] S140. According to each coal quality index, a correction amount of each coal quality index is determined through a pre-trained index correction model, and each coal quality index is adjusted based on the correction amount.

[0035] Among them, the coal quality index is an index quantity used to characterize the quality of the coal sample to be tested. There is more than one index that can be used to evaluate the quality of coal, and different coal quality indexes generally have different evaluation dimensions. The coal quality index may include element content, calorific value, and ash content. The element content can be the content or concentration of a certain element in the coal sample to be tested, such as carbon content, sulfur content, precious metal concentration, etc. The calorific value is used to indicate the calorific value of the quality of the fuel (coal in the embodiment of the present application), and the ash content is the residue after combustion.

[0036] In S110, the coal sample to be tested may be any quality of coal that needs to be tested for coal quality.

[0037] In S120, Laser Induced Breakdown Spectroscopy (LIBS) has attracted much attention in the field of coal quality inspection due to its unique advantages such as simple operation, no need for complex sample pretreatment and simultaneous online analysis of multiple elements. The working principle is to focus a pulsed laser on the sample surface and excite the plasma, collect the light radiation signal emitted during the plasma cooling process by a high-resolution spectrometer, and then use the coal sample to identify the model to obtain information about the elements, concentrations, calorific values, etc. of the coal sample. However, LIBS in the prior art lacks consideration of environmental factors such as temperature and humidity, resulting in different results for coal quality indicators of the same coal sample under different temperature and humidity environments. Therefore, the embodiment of the present application introduces a temperature and humidity sensor in LIBS, and records the current temperature and humidity data corresponding to the spectral data while obtaining the spectral data results. So that the coal quality indicators obtained by the spectral data analysis can be compensated according to the current temperature and humidity data in the future, thereby improving the accuracy of the coal quality indicators.

[0038] In S130, the index detection model is used to analyze a variety of coal quality indicators of the coal sample to be detected from the spectral data in combination with the current temperature and humidity data. The input of the index detection model is the spectral data and the current temperature and humidity data, and the output is a plurality of coal quality indicators of the coal sample to be detected. It can be understood that there are multiple parallel detection models in the index detection model, and different detection models detect different coal quality indicators respectively. In other words, the input of each of these parallel detection models is the current temperature and humidity data and the spectral data, and the output of each detection model is one of the coal quality indicators.

[0039] In an optional embodiment, the index detection model is determined by the following method: obtaining coal samples of different qualities and corresponding sample indicators corresponding to the different coal samples; using a laser induced breakdown spectrometer with a temperature and humidity sensor to detect coal samples of different qualities to obtain sample spectra of each coal sample under different temperature and humidity conditions; constructing mapping data sets according to the sample spectra, temperature and humidity conditions and each sample indicator; and using each mapping data set to train the index detection model.

[0040] Among them, it should be noted that the index detection model mentioned in the embodiment of the present application can be trained based on any machine learning model, for example, it can be a neural network model. Then, the training of the machine learning model requires a large amount of data as a basis. In this embodiment, coal samples of different qualities and their corresponding sample indicators are used as the basis for the training model. It can be understood that a large number of coal samples with different sources and qualities are first detected by LIBS with a temperature and humidity sensor to obtain the correspondence between the sample spectra and sample indicators obtained under different temperature and humidity conditions, and this correspondence is constructed as a mapping data set. It is equivalent to labeling the data used for training. Of course, the sample indicators can be determined by the manufacturer of the coal sample or a third party using traditional instruments according to the national standard, and the determination of the sample indicators in the embodiment of the present application is not limited.

[0041] Furthermore, when the mapping data set is used to train the index detection model, the mapping data set can be cleaned to remove abnormal outliers and perform dimensionality reduction to reduce the difficulty of training. The training set and prediction set are further divided for search and prediction, and feedback adjustment is performed based on the prediction results. The index detection model trained after considering the temperature and humidity conditions can more accurately identify the coal quality indicators of coal samples according to the different ambient temperature and humidity, providing users with a reliable basis for index detection.

[0042] In S140, the index correction model is used to correct the coal quality index determined by the index detection model. It can be understood that there are multiple parallel correction models in the index correction model, and different correction models determine the correction amount of different indicators respectively. The correction amount can be an adjustment value of the result of the index detection model detecting the coal quality, which is used to compensate for the error caused by the actual operation situation.

[0043] It should be noted that in actual situations, in order to ensure the accuracy of the index detection model, the calibration process generally requires the use of a large amount of sample data to generate a targeted data set, and the spectral data is highly bound to the LIBS instrument hardware. Minor differences in manual assembly, installation environment and hardware components may cause the spectra of the same sample to be different on different LIBS. This requires targeted calibration for each LIBS, which results in the identification model of each LIBS not being completely consistent, which is not conducive to assembly line production. Moreover, after being installed at the industrial site, it is impossible to quickly calibrate the secondary calibration, otherwise a large number of coal samples must be used again on site for calibration, which makes the efficiency of LIBS very low. Therefore, by using the coal samples used by the user recently (for example, within the past three months), a machine learning model is trained again, which is used for the index correction model to correct the results of coal quality index detection based on the index detection model according to the different users (the use of coal) after the user uses LIBS for detection. It can be understood that the index detection model set in LIBS is pre-trained and loaded, while the index correction model can be trained in a small range by the user according to his own needs when using LIBS, which improves the efficiency of the user in detecting coal quality indicators.

[0044] In the technical solution of the embodiment of the present application, LIBS with temperature and humidity sensors is used to perform coal quality detection. The index detection model takes temperature and humidity conditions into consideration, thereby reducing the impact of the external environment on coal quality detection. At the same time, the index correction model is used to compensate for the errors in the detected coal quality indicators, thereby further improving the accuracy of coal quality detection.

[0045] In an optional embodiment, the index correction model is determined by: obtaining predicted data obtained by performing coal quality index tests on each preset coal sample using the index detection model; for any coal quality index, determining reference correction amounts within different preset gradient ranges based on the data difference between the predicted data and the sample index; and training the index correction model based on each reference correction amount.

[0046] Among them, the preset coal samples are different from the aforementioned coal samples of different qualities. The preset coal samples only represent several types of coal that users have recently used. It can be understood that the index detection model is applied to all LIBS equipment, and the model can be loaded when the equipment is produced. The coal samples used to train the index detection model have the characteristics of a wide range, different qualities, and many types, which can improve the universality of the index detection model. Therefore, a large number of coal samples of different qualities are used. As for the index correction model, when users use LIBS equipment, different users use different coals, and the differences in installing LIBS equipment are also different. Therefore, after the user installs the LIBS equipment, the coal that the user has recently used is used as a sample for a small degree of training to help the index correction model determine the correction amount of different coal quality indicators.

[0047] The predicted data can be the index data obtained by the aforementioned index detection model for coal quality detection of the preset coal sample. These predicted data have certain errors. The sample coal quality of the preset coal sample can be obtained by the user or a third party's traditional instrument according to the national standard. It is accurate data, which is equivalent to marking the coal quality index of the preset coal sample, so as to train the index correction model.

[0048] It should be noted that, like the index detection model, the index correction model also includes multiple small models, each of which corrects a coal quality index. It can be understood that the correction amount is the compensation value of the result determined by the index correction model in the use stage; the reference correction amount is the compensation value within each gradient range determined by the index correction model in the training stage. Then, for any index, the data difference between the predicted data and the sample index is the reference correction amount that the coal sample should compensate for in the index. For example, the value A of the predicted data minus the value B of the sample index is equal to -0.5, then the reference correction amount should be +0.5. The preset gradient range can be a division of the value of the reference correction amount. The preset gradient range can be set by relevant technical personnel according to actual conditions or manual experience. For example, for any coal quality index, a range can be set, and the range can be divided into five equal parts, each of which is a gradient range. The case where the reference correction amount detected and calculated is within the same gradient range can be approximately regarded as a case, and a value is selected as the correction amount corresponding to the gradient range.

[0049] The above implementation method, based on LIBS, analyzes the preset coal samples for training the index correction model. The index correction model specifically identifies the differences between different users and different equipment installation and usage conditions, thereby effectively identifying the differences between users' commonly used coal samples and the index detection model and making corrections. This can not only improve the accuracy of index identification, but also help users ensure the use of LIBS equipment as soon as possible, and can improve the efficiency of users in coal sample identification.

[0050] In an optional embodiment, determining the reference correction amount within different preset gradient ranges based on the data difference between the predicted data and the sample index may include: for any coal quality index, taking the median of each data difference corresponding to each preset coal sample within each preset gradient range as the reference correction amount within the preset gradient range.

[0051] Multiple preset coal samples correspond to multiple predicted data, and there are multiple data differences between each predicted data and the sample index. If the data differences obtained from multiple samples of the same coal sample are in the same gradient range, the median of these data differences is selected as the reference correction amount for this gradient range.

[0052] For example, if the range of the reference correction amount is divided into five equal parts, each 20% is a gradient range interval (0-20% / 21-40% / 41-60% / 61-80% / 81-100%). If the reference correction amount data obtained after testing and calculation for a certain type of coal sample currently being tested has 5 values ​​in the range of 41-60%, and the median of these 5 values ​​is +0.7, then +0.7 is used as the median of the range of 41-60%; for another example, if the reference correction amount data obtained after testing and calculation for a certain type of coal sample currently being tested has 9 values ​​in the range of 61-80%, and the median of these 9 values ​​is +0.4, then +0.4 is used as the reference correction amount for the range of 61-80%.

[0053] Further, if there is no corresponding data difference in the maximum gradient range and / or the minimum gradient range, the corresponding reference correction amount is determined to be zero.

[0054] Continuing with the previous example, if there is no corresponding data difference between the two intervals of 0-20% and / or 81-100%, then the reference correction value between these two ranges can be set to 0.

[0055] If there is no corresponding data difference in other gradient ranges, the reference correction amount is supplemented according to the existing reference correction amount in accordance with a linear change; wherein the other gradient ranges are the range intervals outside the maximum gradient range and the minimum gradient range.

[0056] Continuing with the previous example, the reference correction value for the 0-20% interval is 0, the reference correction value for the 41-60% interval is +0.7, the reference correction value for the 61-80% interval is +0.4, and the correction value for the 81-100% interval is 0; then the reference correction value in the 21-40% interval is missing, and the reference correction value (0+0.7) / 2=+0.35 is filled in according to the linear change as the reference correction value for this interval.

[0057] In the above-mentioned embodiments, the user uses common coal to train the model before using LIBS, so that the model is converted from a general type to a user-adaptive type, so that the user can adjust LIBS according to his or her own situation without causing the problem of repeated correction and calibration, thereby improving the use efficiency of LIBS.

[0058] Embodiment 2

[0059] Figure 2 A flow chart of coal quality detection and correction provided in Example 2 of this application. This application example is a preferred implementation method provided on the basis of the above-mentioned example. The details are as follows:

[0060] In the first part, a general main model group (equivalent to the indicator detection model in the aforementioned embodiment) is trained.

[0061] A certain type of LIBS instrument is designed with a temperature and humidity sensor inside. During model training, the input data includes spectral data and temperature and humidity data, and the output data can be a single coal quality index or multiple coal quality indexes, such as carbon, sulfur, heavy metal element concentration, calorific value, and ash content.

[0062] When obtaining the input data of dry coal samples, the temperature data of the LIBS instrument environment must cover 18℃~28℃, the relative humidity must cover 40%RH~80%RH, and at least 3 temperature gradient points must be controlled by air conditioning;

[0063] It is necessary to prepare a large number of coal samples and standard coal samples of various scenarios and qualities;

[0064] All collected coal samples were dried according to the requirements of coal power industry analysis and calorific value test to obtain dry basis coal samples of about 0.2mm;

[0065] The data is sent to the LIBS instrument containing temperature and humidity sensors to generate spectrum, temperature and humidity data of each sample under different temperature and humidity conditions;

[0066] The output data of the same batch of dry basis coal samples is recommended to be obtained by the manufacturer or third-party traditional instruments according to national standards, which can be carbon, sulfur, heavy metal element concentration, calorific value and ash content;

[0067] According to the samples, the input data and the output data are matched one by one to establish a mapping data set;

[0068] Clean the mapping data set, use dimensionality reduction to produce a two-dimensional or three-dimensional data set, and then filter out abnormal outliers;

[0069] Divide the training set and prediction set, use multivariate linear algorithm, neural network fitting and other algorithms for fitting, the output index during fitting is a single coal quality index, and optimize the parameters according to the prediction effect feedback;

[0070] Obtain a single-index output fitting model with spectrum, temperature, humidity data as input and element content, calorific value or ash content data as output;

[0071] Multiple single-index models are packaged in parallel, so that the entire model group takes spectrum, temperature, and humidity data as input, and multiple data such as element content, calorific value or ash content as output, and multiple independent models are recognized in parallel internally;

[0072] Finally, a universal master model of a certain type of LIBS instrument is obtained.

[0073] The second part is to train the fine-tuning model (equivalent to the indicator correction model in the aforementioned embodiment).

[0074] During model training, the prediction data is a single coal quality index or multiple coal quality indexes detected by a certain type of LIBS instrument (the same instrument as (1)) including a temperature and humidity sensor, such as carbon, sulfur, heavy metal element concentration, calorific value and ash content, etc. The real data is obtained by the user or a third party's national standard traditional instrument testing the same coal sample according to the national standard;

[0075] It is necessary to prepare a small amount of typical dry basis coal samples recently used by users;

[0076] All collected coal samples were dried according to the requirements of coal power industry analysis and calorific value test to obtain dry basis coal samples of about 0.2mm;

[0077] The data is sent to a LIBS instrument of a certain type (the same instrument as (1)) containing a temperature and humidity sensor to generate a single coal quality index or multiple coal quality indexes for each sample, i.e., prediction data;

[0078] The real data of the same batch of dry basis coal samples are obtained by the user or a third party using traditional national standard instruments to test the same coal samples according to national standards, which can be carbon, sulfur, heavy metal element concentration, calorific value and ash content;

[0079] Establish a mapping data set by matching the predicted data with the real data one by one according to the samples;

[0080] Subtract the actual data from the predicted data for sample use, and then take the median value according to the gradient range (each indicator contains more than 3 gradient divisions, the starting point is the minimum value of the detection result range of the indicator in the general main model group, and the end point is the maximum value of the detection result range of the indicator in the general main model group), and obtain the correction amount of each indicator in each gradient range. For example, assuming that the range is divided into 5 gradient range intervals, namely 0-20 / 21-40 / 41-60 / 61-80 / 81-100 range percentages, and the user's recent typical coal samples have been tested and calculated to have 5 data within the range of 41-60 percentages, the median value of the correction amount of a certain indicator is +0.7, the data within the range of 61-80 percentages is 9, the median value of the correction amount of a certain indicator is +0.4, and there is no data in other ranges;

[0081] The data-free range is linearly filled. When there is no data in the gradient range at both ends corresponding to the zero point and the full scale, 0 is taken to obtain a segmented correction fine-tuning model of a certain indicator for different gradient ranges. Taking the above example, the final correction model of a certain indicator is 0-20 / 21-40 / 41-60 / 61-80 / 81-100, and the correction amount is 0 / +0.35 / +0.7 / +0.4 / 0 respectively. When correcting and identifying, first identify the gradient range of the predicted data, and then perform the sum calculation of the correction amount;

[0082] Multiple fine-tuning models are packaged in parallel, so that the entire model group takes the prediction data of a single or multiple indicators of the general main model group as input, and the segmented correction amount of a certain indicator with respect to different gradient ranges as output, and multiple independent models are recognized in parallel internally;

[0083] Obtain a fine-tuned model of a certain type of LIBS instrument in a user scenario.

[0084] The third part, after calibration, allows users to perform coal quality testing.

[0085] The processed coal sample is placed in a certain model of LIBS instrument containing temperature and humidity sensors for detection. The instrument obtains spectrum, temperature, and humidity data, imports these data into the main model for identification, obtains intermediate prediction data of a certain indicator or multiple indicators, and then corrects it through fine-tuning the model to finally obtain the detection results of coal quality indicators.

[0086] Embodiment 3

[0087] Figure 3 This is a schematic diagram of the structure of a coal quality detection device provided in Example 3 of this application. Figure 3 As shown, the device 300 includes:

[0088] A coal sample acquisition module 310 is used to acquire a coal sample to be tested;

[0089] The data determination module 320 detects the coal sample to be detected by using a laser induced breakdown spectrometer with a temperature and humidity sensor to obtain spectrum data and current temperature and humidity data of the coal sample to be detected;

[0090] The index detection module 330 is used to determine at least one coal quality index of the coal sample to be detected based on the spectrum data and the current temperature and humidity data through a pre-trained index detection model;

[0091] The index correction module 340 is used to determine the correction amount of each coal quality index according to each coal quality index through a pre-trained index correction model, and adjust each coal quality index based on the correction amount.

[0092] In the technical solution of the embodiment of the present application, LIBS with temperature and humidity sensors is used to perform coal quality detection. The index detection model takes temperature and humidity conditions into consideration, thereby reducing the impact of the external environment on coal quality detection. At the same time, the index correction model is used to compensate for the errors in the detected coal quality indicators, thereby further improving the accuracy of coal quality detection.

[0093] In an optional implementation, the device 300 includes an indicator detection model training module, and the indicator detection model training module includes:

[0094] A sample index acquisition unit, used to acquire the preset coal sample and the sample indexes corresponding to the corresponding different coal samples;

[0095] A sample spectrum acquisition unit is used to detect the preset coal samples using a laser induced breakdown spectrometer with a temperature and humidity sensor to obtain sample spectra of each coal sample under different temperature and humidity conditions;

[0096] A data set construction unit, used to construct mapping data sets according to sample spectra, temperature and humidity conditions and indicators of each sample;

[0097] The detection model training unit is used to train the indicator detection model using each mapping data set.

[0098] In an optional implementation, the device 300 includes an indicator correction model training module, and the indicator correction model training module includes:

[0099] A prediction data acquisition unit, used to acquire prediction data obtained by performing coal quality index testing on each preset coal sample by an index detection model;

[0100] A reference correction amount determination unit is used to determine, for any coal quality index, reference correction amounts within different preset gradient ranges according to the data difference between the predicted data and the sample index;

[0101] According to each reference correction amount, the training indicator correction model is constructed.

[0102] In an optional implementation manner, the reference correction amount determination unit may be specifically used to:

[0103] For any coal quality index, the median of each data difference corresponding to each preset coal sample within each preset gradient range is used as a reference correction amount within the preset gradient range.

[0104] In an optional implementation, the indicator correction model training module may include:

[0105] The first reference correction amount adjustment unit is used to determine the corresponding reference correction amount to zero if there is no corresponding data difference in the maximum gradient range and / or the minimum gradient range.

[0106] In another optional implementation, the indicator correction model training module may include:

[0107] The second reference correction adjustment unit is used to fill in the reference correction according to the existing reference correction according to the linear change if there is no corresponding data difference in other gradient ranges; wherein the other gradient ranges are the range intervals outside the maximum gradient range and the minimum gradient range.

[0108] Optionally, the coal quality indicators include element content, calorific value and ash content.

[0109] The coal quality detection device provided in the embodiment of the present application can execute the coal quality detection method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing each coal quality detection method.

[0110] Embodiment 4

[0111] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0112] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0113] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0114] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a coal quality detection method.

[0115] In some embodiments, the coal quality detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the coal quality detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the coal quality detection method in any other appropriate manner (e.g., by means of firmware).

[0116] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0118] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0120] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0121] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0122] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0123] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A coal quality detection method, characterized in that: include: Obtaining coal samples to be tested; Using a laser induced breakdown spectrometer with a temperature and humidity sensor to detect the coal sample to be detected, and obtaining spectrum data and current temperature and humidity data of the coal sample to be detected; According to the spectral data and the current temperature and humidity data, at least one coal quality index of the coal sample to be tested is determined by a pre-trained index detection model; wherein the index detection model includes at least one parallel detection model, and the output of each detection model is one of the coal quality indexes; According to each of the coal quality indicators, a correction amount of each of the coal quality indicators is determined through a pre-trained indicator correction model, and each of the coal quality indicators is adjusted based on the correction amount; The indicator detection model is determined by the following method: Obtain coal samples of different qualities and corresponding sample indicators of different coal samples; Using a laser induced breakdown spectrometer with a temperature and humidity sensor to detect the coal samples of different qualities, and obtaining sample spectra of each coal sample under different temperature and humidity conditions; constructing mapping data sets according to the sample spectrum, the temperature and humidity conditions and each of the sample indicators; Using each of the mapping data sets to train the indicator detection model; The index correction model is determined by the following method: Obtaining prediction data obtained by testing the coal quality index of each preset coal sample using the index detection model; wherein the preset coal sample is a coal sample that is frequently used by the user in the recent period; For any coal quality index, determining reference correction amounts within different preset gradient ranges according to the data difference between the predicted data and the sample index; The indicator correction model is trained according to each of the reference correction values.

2. The method according to claim 1, characterized in that Determining reference correction amounts within different preset gradient ranges according to the data difference between the predicted data and the sample index includes: For any coal quality index, the median of each data difference corresponding to each preset coal sample within each preset gradient range is used as a reference correction amount within the preset gradient range.

3. The method according to claim 2, characterized in that The method comprises: If the corresponding data difference does not exist in the maximum gradient range and / or the minimum gradient range, the corresponding reference correction amount is determined to be zero.

4. The method according to claim 3, characterized in that: The method comprises: If there is no corresponding data difference in other gradient ranges, the reference correction amount is supplemented according to the existing reference correction amount in accordance with a linear change; wherein the other gradient ranges are range intervals outside the maximum gradient range and the minimum gradient range.

5. The method according to any one of claims 1 to 4, characterized in that: The coal quality indicators include element content, calorific value and ash content.

6. A coal quality detection device, characterized in that: include: A coal sample acquisition module, used to acquire the coal sample to be tested; A data determination module detects the coal sample to be detected by using a laser induced breakdown spectrometer with a temperature and humidity sensor to obtain spectrum data and current temperature and humidity data of the coal sample to be detected; An index detection module, used to determine at least one coal quality index of the coal sample to be detected according to the spectral data and the current temperature and humidity data through a pre-trained index detection model; wherein the index detection model includes at least one parallel detection model, and the output of each detection model is one of the coal quality indicators; An index correction module, used to determine a reference correction amount of each coal quality index according to each coal quality index through a pre-trained index correction model, and adjust each coal quality index based on the reference correction amount; The device includes an indicator detection model training module, and the indicator detection model training module includes: A sample index acquisition unit, used to acquire the preset coal sample and the sample indexes corresponding to the corresponding different coal samples; A sample spectrum acquisition unit is used to detect the preset coal samples using a laser induced breakdown spectrometer with a temperature and humidity sensor to obtain sample spectra of each coal sample under different temperature and humidity conditions; A data set construction unit, used to construct mapping data sets according to the sample spectrum, the temperature and humidity conditions and each of the sample indicators; A detection model training unit, used to train the indicator detection model using each of the mapping data sets; The indicator correction model training module includes: A prediction data acquisition unit, used to acquire prediction data obtained by testing the coal quality index of each preset coal sample using the index detection model; wherein the preset coal sample is a coal sample that is frequently used by the user in the near future; The reference correction value determination unit is used to determine the reference correction values ​​within different preset gradient ranges for any coal quality index according to the data difference between the predicted data and the sample index; and train the index correction model according to each reference correction value.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the coal quality detection method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the coal quality detection method according to any one of claims 1 to 5 when executed.

Images