CN117074643A - Coal quality evaluation method, system, equipment and medium - Google Patents
Coal quality evaluation method, system, equipment and medium Download PDFInfo
- Publication number
- CN117074643A CN117074643A CN202311056901.8A CN202311056901A CN117074643A CN 117074643 A CN117074643 A CN 117074643A CN 202311056901 A CN202311056901 A CN 202311056901A CN 117074643 A CN117074643 A CN 117074643A
- Authority
- CN
- China
- Prior art keywords
- target
- data
- coal quality
- features
- quality evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000003245 coal Substances 0.000 title claims abstract description 128
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims description 47
- 230000003287 optical effect Effects 0.000 claims description 38
- 230000009467 reduction Effects 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000002485 combustion reaction Methods 0.000 claims description 7
- 238000001303 quality assessment method Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004939 coking Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000000571 coke Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 229910052717 sulfur Inorganic materials 0.000 description 2
- 239000011593 sulfur Substances 0.000 description 2
- 239000003039 volatile agent Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000002956 ash Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000003610 charcoal Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009257 reactivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/22—Fuels; Explosives
- G01N33/222—Solid fuels, e.g. coal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Chemical & Material Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Analytical Chemistry (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Biochemistry (AREA)
- Development Economics (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
Abstract
The present disclosure provides a coal quality evaluation method, system, device and medium, the coal quality evaluation method comprising: acquiring multi-mode data of coal to be evaluated; extracting features of each modal data in the multi-modal data respectively, and determining target features corresponding to each modal data respectively; and determining target evaluation results corresponding to the target features respectively according to the target features, and determining a final coal quality evaluation result according to the target evaluation results. The method comprises the steps of obtaining multi-mode data of coal to be evaluated to obtain multi-dimensional target characteristics, and determining final coal quality evaluation according to the target characteristics and historical data. The evaluation information can be richer, and the evaluation accuracy can be improved. Meanwhile, the evaluation information can be determined only by the target characteristics of the coal to be evaluated, so that the processing efficiency of coal quality evaluation is improved.
Description
Technical Field
The disclosure relates to the field of coal chemical industry, in particular to a coal quality evaluation method, a system, equipment and a medium.
Background
Coal mines are an important resource and are indispensable strategic resources in industry. Therefore, in order to use the mine resources to the maximum, it is an important issue to evaluate the coal quality. The main methods for evaluating the coal quality at present are to conduct quantitative calculation based on an evaluation function or conduct prediction by using a prediction model.
However, the above method has the following problems: on the one hand, the evaluation accuracy is not high, on the other hand, the evaluation index is single, and more abundant evaluation information cannot be obtained.
Disclosure of Invention
The problem to be solved by the present disclosure is to overcome the defect of low evaluation accuracy in the prior art, and provide a coal quality evaluation method, system, device and medium.
The technical problems are solved by the following technical scheme:
the present disclosure provides a coal quality evaluation method, the coal quality evaluation method comprising:
acquiring multi-mode data of coal to be evaluated;
extracting features of each modal data in the multi-modal data respectively, and determining target features corresponding to each modal data respectively;
and determining target evaluation results corresponding to the target features respectively according to the target features, and determining a final coal quality evaluation result according to the target evaluation results.
Preferably, the multimodal data includes attribute data; the feature extraction is performed on each mode data in the multi-mode data, and the target feature corresponding to each mode data is determined, which includes:
extracting the attribute data from the multi-modal data, wherein the attribute data comprises attribute characteristics;
performing dimension reduction on the attribute features by using a data dimension reduction model, and taking the attribute features subjected to dimension reduction as the target features; the target features include physicochemical features and combustion features.
Preferably, the multimodal data includes an optical tissue image; the feature extraction is performed on each mode data in the multi-mode data, and the target feature corresponding to each mode data is determined, which includes:
extracting the optical tissue image from the multimodal data;
and taking the optical tissue characteristics obtained after the optical tissue image is processed through a first convolution neural network model which is trained in advance as the target characteristics.
Preferably, the first convolutional neural network model comprises at least one fully connected layer; the optical tissue feature obtained after the optical tissue image is processed through a first convolutional neural network model which is trained in advance is used as the target feature, and the method comprises the following steps:
inputting the optical tissue image into the first convolutional neural network model;
and taking the feature vector output by the full connection layer of the first convolutional neural network model as the target feature.
Preferably, the multimodal data includes text description data; the feature extraction is performed on each mode data in the multi-mode data, and the target feature corresponding to each mode data is determined, which includes:
extracting the text description data from the multimodal data;
and taking the text description characteristic obtained after the text description data is processed through a second convolutional neural network model which is trained in advance as the target characteristic.
Preferably, the second convolutional neural network model comprises at least one fully connected layer; the text description feature obtained after the text description data is processed through a pre-trained second convolutional neural network model is used as the target feature, and the method comprises the following steps:
inputting the text description data into the second convolutional neural network model;
and taking the feature vector output by the full connection layer of the second convolutional neural network model as the target feature.
Preferably, the determining, according to the target features, target evaluation results corresponding to the target features, and determining, according to the target evaluation results, a final coal quality evaluation result includes:
according to the classifier which is trained in advance and based on the target features, respectively determining preset evaluation results of preset numbers corresponding to the target features from a preset feature library; the preset feature library comprises preset features and preset evaluation results corresponding to the preset features;
counting the occurrence times corresponding to the coal quality ratings included in all the preset evaluation results;
and taking the coal quality rating with the largest occurrence frequency and/or descriptive data corresponding to the coal quality rating as a final coal quality evaluation result.
The present disclosure also provides a coal quality evaluation system, the coal quality evaluation system comprising:
the acquisition module is used for acquiring multi-mode data of the coal to be evaluated;
the processing module is used for extracting the characteristics of each modal data in the multi-modal data respectively and determining target characteristics corresponding to each modal data respectively;
and the evaluation module is used for determining target evaluation results corresponding to the target features respectively according to the target features and determining a final coal quality evaluation result according to the target evaluation results.
Preferably, the multimodal data includes attribute data; the processing module comprises:
an extracting unit, configured to extract the attribute data from the multimodal data, where the attribute data includes an attribute feature;
the first processing unit is used for reducing the dimension of the attribute features by using a data dimension reduction model, and taking the attribute features subjected to dimension reduction as the target features; the target features include physicochemical features and combustion features.
Preferably, the multimodal data includes an optical tissue image; the processing module comprises:
the extraction unit is used for extracting the optical tissue image from the multi-mode data;
and the second processing unit is used for taking the optical tissue characteristics obtained after the optical tissue image is processed through the first convolutional neural network model which is trained in advance as the target characteristics.
Preferably, the first convolutional neural network model comprises at least one fully connected layer; the second processing unit is specifically configured to:
inputting the optical tissue image into the first convolutional neural network model;
and taking the feature vector output by the full connection layer of the first convolutional neural network model as the target feature.
Preferably, the multimodal data includes text description data; the processing module comprises:
the extracting unit is used for extracting the text description data from the multi-modal data;
and the third processing unit is used for taking the text description characteristic obtained after the text description data is processed through the second convolutional neural network model which is trained in advance as the target characteristic.
Preferably, the second convolutional neural network model comprises at least one fully connected layer; the third processing unit is specifically configured to:
inputting the text description data into the second convolutional neural network model;
and taking the feature vector output by the full connection layer of the second convolutional neural network model as the target feature.
Preferably, the evaluation module is specifically configured to:
according to the classifier which is trained in advance and based on the target features, respectively determining preset evaluation results of preset numbers corresponding to the target features from a preset feature library; the preset feature library comprises preset features and preset evaluation results corresponding to the preset features;
counting the occurrence times corresponding to the coal quality ratings included in all the preset evaluation results;
and taking the coal quality rating with the largest occurrence frequency and/or descriptive data corresponding to the coal quality rating as a final coal quality evaluation result.
The disclosure also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and used for running on the processor, wherein the processor realizes the coal quality evaluation method when executing the computer program.
The present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the aforementioned coal quality evaluation method.
On the basis of conforming to the common knowledge in the art, the preferred conditions can be arbitrarily combined to obtain the preferred examples of the disclosure.
The positive progress effect of the present disclosure is: and acquiring multi-mode data of the coal to be evaluated to acquire multi-dimensional target characteristics, and determining the final coal quality evaluation according to the target characteristics and the historical data. The evaluation information can be richer, and the evaluation accuracy can be improved. Meanwhile, the evaluation information can be determined only by the target characteristics of the coal to be evaluated, so that the processing efficiency of coal quality evaluation is improved.
Drawings
FIG. 1 is a flow chart of a coal quality assessment method provided in an exemplary embodiment 1 of the present disclosure;
FIG. 2 is a flowchart of a method step 102 for evaluating coal quality according to an exemplary embodiment 1 of the present disclosure;
FIG. 3 is a flowchart of another method step 102 for evaluating coal quality according to an exemplary embodiment 1 of the present disclosure;
FIG. 4 is a flowchart of another method step 102 for evaluating coal quality according to an exemplary embodiment 1 of the present disclosure;
FIG. 5 is a flowchart of another coal quality assessment method step 103 provided in an exemplary embodiment 1 of the present disclosure;
FIG. 6 is a schematic block diagram of a coal quality evaluation system according to an exemplary embodiment 2 of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an exemplary embodiment 3 of the present disclosure.
Detailed Description
The present disclosure is further illustrated by way of examples below, but is not thereby limited to the scope of the examples described. The present disclosure provides several schemes for coal quality evaluation that can be evaluated for a certain type of coal (e.g., a single type of coal), as will be described in more detail below by way of example.
Example 1
Fig. 1 is a flowchart of a coal quality evaluation method according to an exemplary embodiment of the present disclosure, where the coal quality evaluation method includes:
and 101, acquiring multi-mode data of the coal to be evaluated.
In this step, the multi-modal data is data information for multi-dimensionally describing the coal.
And 102, respectively extracting the characteristics of each modal data in the multi-modal data, and determining target characteristics respectively corresponding to each modal data.
In this step, the multimodal data mainly includes attribute data, an optical organization image, and text description data. Different processing modes are provided for different multi-mode data.
First, when the multi-modal data is attribute data, referring to fig. 2, the step 102 further includes:
step 1021, extracting attribute data from the multi-modal data, wherein the attribute data comprises attribute features.
Wherein the attribute data specifically includes any one or more of the following: color, gloss, ash, volatiles, sulfur, moisture, fixed carbon content, ash content, base fluidity, plasticity interval, and combustion characteristics, wherein combustion characteristics include CRI (coke reactivity), CSR (post reaction strength). The attribute features include quantifiable attribute features and non-quantifiable attribute features. Quantifiable attribute features are attribute features that can be embodied in numerical values, such as CRI and CSR are embodied in percent numerical values. Non-quantized attribute features are attribute features embodied in descriptive language, such as color, luster. To facilitate data processing, all attribute data may be converted into numerical values according to actual needs, for example, the gloss may be classified into 5 levels and may be represented by numbers 1 to 5. It should be appreciated that the conversion rules of the values may be adjusted as desired.
And 1022, performing dimension reduction on the attribute features by using a data dimension reduction model, and taking the dimension-reduced attribute features as target features. Target features include physicochemical features and combustion features.
Wherein the dimension reduction model is based on a PCA (principal component analysis) algorithm or an LDA (Linear discriminant analysis) algorithm. The purpose of dimension reduction of the attribute features is to reduce the influence of invalid and error data on modeling, improve the modeling accuracy, save the operation time cost and reduce the cost of data storage. It should be appreciated that the dimension reduction model is not limited to PCA and LDA algorithms, and any method that can achieve data dimension reduction is suitable for use with the disclosed embodiments.
Secondly, when the multi-mode data is an optical tissue image, referring to fig. 3, the step 102 further includes:
step 1023, extracting the optical tissue image from the multi-modal data.
Wherein the optical tissue image comprises a plurality of coke microstructures including any one or more of: mosaic, silk charcoal, broken flake.
Step 1024, the optical tissue image is processed by the first convolutional neural network model which is trained in advance, and the obtained optical tissue characteristic is used as a target characteristic.
In this step, in order to facilitate the processing of the convolutional neural network model, the optical tissue image is preprocessed based on the RBG in advance, for example, the optical tissue image is converted into a 512×512×3 image, where 512×512 is the size of the image, and 3 represents three channels of the RBG. It should be understood that the size of the image in the image preprocessing is set according to the actual requirement, and the method is not limited to the RBG three-channel method. The first convolutional neural network model is completed by historical data training of a large number of optical organization images, and comprises at least one convolutional layer, at least one pooling layer and at least one full-connection layer. And the output result of the first convolutional neural network is coal quality rating, and training is considered to be completed when the accuracy reaches the accuracy threshold in the model training stage.
The method specifically comprises the following steps: inputting the optical tissue image into a first convolutional neural network model; and taking the feature vector of the last full-connection layer of the first convolutional neural network model as a target feature. It should be appreciated that feature vectors output by all full connection layers are possible to use as target features.
Third, when the multimodal data includes text description data, referring to fig. 4, the step 102 further includes:
step 1025, extracting text description data from the multi-modal data.
And 1026, processing the text description data through a second convolutional neural network model which is trained in advance, and taking the obtained text description feature as a target feature.
In the step, in order to facilitate the processing of the convolutional neural network model, after cleaning and Word segmentation of text description data, word2Vec model is adopted to obtain Word vectors as text description characteristics. It should be understood that the steps are not limited to cleaning and Word segmentation when processing text description data, steps can be added or the processing sequence can be changed according to actual needs, and the processing model is not limited to the Word2Vec model. Wherein the second convolutional neural network model is completed by a plurality of historical data training of text description features, and the second convolutional neural network comprises at least one convolutional layer, at least one pooling layer and at least one full-connection layer. And the output result of the second convolutional neural network is coal quality rating, and training is considered to be completed when the accuracy reaches the accuracy threshold in the model training stage.
The method specifically comprises the following steps: inputting the text description data into a second convolutional neural network model; and taking the characteristic vector of the last full connection layer of the second convolutional neural network model as a target characteristic. It should be appreciated that feature vectors output by all full connection layers are possible to use as target features.
And 103, determining target evaluation results corresponding to the target features respectively according to the target features, and determining a final coal quality evaluation result according to the target evaluation results. Referring to fig. 5, the steps specifically include:
step 1031, respectively determining preset evaluation results of preset numbers corresponding to the target features from a preset feature library according to the classifier which is trained in advance and based on the target features; the preset feature library comprises preset features and preset evaluation results corresponding to the preset features.
The classifier is trained on different multi-mode data respectively: training for attribute features of the attribute data, training for optical tissue features of the optical tissue image, and training for text description features of the text description data. The class of classifier is optionally a KNN (K-nearest neighbor) classifier. For example, k preset evaluation results may be determined from a preset feature library according to a classifier for the current target feature. Therefore, when the multimodal data includes three kinds of attribute data, optical organization images, and text description data, k pieces of preset evaluation results are extracted based on the respective classifiers, respectively, for a total of 3*k pieces. It should be understood that the type of classifier can be set according to actual needs.
Step 1032, counting the occurrence times corresponding to the coal quality ratings included in all the preset evaluation results.
In this step, all the preset evaluation results obtained in step 1031 are counted, and the number of occurrences of each coal quality rating is obtained. For example, a total of 30 preset evaluation results are obtained in step 1031, wherein 18 coals are rated as primary coking coals, 10 coals are rated as primary fat coals, and 2 coals are rated as lean coals.
Step 1033, taking the coal quality rating with the largest occurrence number and/or description data corresponding to the coal quality rating as a final coal quality evaluation result.
In this step, the coal quality rating most frequently occurring in step 1032 is determined, and is theoretically the rating most conforming to the coal to be evaluated. For example, 18 of the 30 preset evaluation results are about the coal quality rating as the primary coking coal, and the 18 preset evaluation results are the coal quality evaluation results which are most consistent with the current coal to be evaluated, namely the coal quality rating of the coal to be evaluated is the primary coking coal. It should be understood that the coal quality evaluation result includes not only the coal quality rating, but also the content of the coal quality evaluation result may be further enriched based on all the description information corresponding to the coal quality rating. For example, one piece of descriptive data may be randomly selected as the content of the coal quality evaluation result in the coal quality evaluation result that best matches the current coal to be evaluated.
Further, in order to make the content of the coal quality evaluation result more accurate, a content-rich analysis report may be formed based on the final coal quality evaluation result. The method comprises the following steps: and retrieving historical data conforming to the coal quality evaluation result from a preset feature library. And taking the physical and chemical properties of ash, sulfur, volatile matters, bonding index, basic fluidity and the like of the coal into account in the historical data conforming to the coal quality evaluation result, and obtaining the percentile of the physical and chemical properties of the coal to be evaluated in the corresponding rating. The analysis report content of the coal to be evaluated includes: coal quality rating, ash, volatiles, etc. in the corresponding ratings.
According to the coal quality evaluation method, multi-mode data of the coal to be evaluated are obtained to obtain multi-dimensional target characteristics, and the final coal quality evaluation is determined according to the target characteristics and the historical data. The evaluation information can be richer, and the evaluation accuracy can be improved. Meanwhile, the evaluation information can be determined only by the target characteristics of the coal to be evaluated, so that the processing efficiency of coal quality evaluation is improved.
Example 2
Referring to fig. 6, a schematic block diagram of a coal quality evaluation system according to an exemplary embodiment of the present disclosure is provided, where the coal quality evaluation system corresponds to the foregoing coal quality evaluation method. The coal quality evaluation system comprises:
an acquisition module 21 for acquiring multi-modal data of the coal to be evaluated.
The processing module 22 is configured to perform feature extraction on each of the multi-mode data, and determine target features corresponding to each of the multi-mode data.
And the evaluation module 23 is used for determining target evaluation results corresponding to the target features respectively according to the target features and determining a final coal quality evaluation result according to the target evaluation results.
Preferably, the multimodal data includes attribute data; the processing module 22 includes:
and the extraction unit is used for extracting attribute data from the multi-mode data, wherein the attribute data comprises attribute characteristics.
The first processing unit is used for reducing the dimension of the attribute features by using a data dimension reduction model, and taking the dimension-reduced attribute features as target features; target features include physicochemical features and combustion features.
Preferably, the multimodal data includes an optical tissue image; the processing module 22 includes:
and the extraction unit is used for extracting the optical tissue image from the multi-mode data.
And the second processing unit is used for taking the optical tissue characteristics obtained after the optical tissue images are processed through the first convolutional neural network model which is trained in advance as target characteristics.
Preferably, the first convolutional neural network model comprises at least one fully connected layer; the second processing unit is specifically configured to:
the optical tissue image is input into a first convolutional neural network model.
And taking the feature vector of the last full-connection layer of the first convolutional neural network model as a target feature.
Preferably, the multimodal data includes text description data; the processing module 22 includes:
and the extraction unit is used for extracting the text description data from the multi-mode data.
And the third processing unit is used for taking the text description characteristic obtained after the text description data is processed through the second convolutional neural network model which is trained in advance as a target characteristic.
Preferably, the second convolutional neural network model comprises at least one fully connected layer; the third processing unit is specifically configured to:
inputting the text description data into a second convolutional neural network model;
and taking the characteristic vector of the last full connection layer of the second convolutional neural network model as a target characteristic.
Preferably, the evaluation module 23 is specifically configured to:
according to the classifier which is trained in advance and based on target features, respectively determining preset evaluation results of preset numbers corresponding to the target features from a preset feature library; the preset feature library comprises preset features and preset evaluation results corresponding to the preset features;
counting the occurrence times corresponding to the coal quality ratings included in all preset evaluation results;
and taking the coal quality rating with the largest occurrence number and/or descriptive data corresponding to the coal quality rating as a final coal quality evaluation result.
The coal quality evaluation system acquires multi-mode data of the coal to be evaluated to acquire multi-dimensional target characteristics, and determines final coal quality evaluation according to the target characteristics and historical data. The evaluation information can be richer, and the evaluation accuracy can be improved. Meanwhile, the evaluation information can be determined only by the target characteristics of the coal to be evaluated, so that the processing efficiency of coal quality evaluation is improved.
Example 3
Fig. 7 is a schematic structural diagram of an electronic device according to the present embodiment. The electronic equipment comprises a memory, a processor and a computer program stored on the memory and used for running on the processor, wherein the processor realizes the coal quality evaluation method provided by any embodiment when executing the program. The electronic device 300 shown in fig. 7 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present disclosure in any way.
Referring to fig. 7, the electronic device 300 may be embodied in the form of a general purpose computing device, which may be a server device, for example. Components of electronic device 300 may include, but are not limited to: the at least one processor 301, the at least one memory 302, a bus 303 connecting the different system components, including the memory 302 and the processor 301.
The bus 303 includes a data bus, an address bus, and a control bus.
Memory 302 may include volatile memory such as Random Access Memory (RAM) 321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
Memory 302 may also include a program/utility 325 having a set (at least one) of program modules 324, such program modules 324 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The processor 301 executes a computer program stored in the memory 302 to thereby perform various functional applications and data processing, such as a coal quality evaluation method of the embodiment of the present disclosure.
The electronic device 300 may also communicate with one or more external devices 304 (e.g., keyboard, pointing device, etc.). Such communication may occur through an input/output (I/O) interface 305. Also, model-generated device 300 may also communicate with one or more networks, such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet, through network adapter 306. As shown, the network adapter 306 communicates with other modules of the model-generated device 300 via the bus 303. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in connection with the model-generating device 300, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, data backup storage systems, and the like.
It should be noted that although several units/modules or sub-units/modules of an electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present disclosure. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.
Example 4
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the coal quality evaluation method provided in any one of the above embodiments.
More specifically, among others, readable storage media may be employed including, but not limited to: portable disk, hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation manner, the disclosure may also be implemented in a form of a program product, which includes program code for causing a terminal device to perform implementing the coal quality assessment method provided in any of the above embodiments, when the program product is run on the terminal device.
Wherein the program code for carrying out the present disclosure may be written in any combination of one or more programming languages, which program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device, partly on the remote device or entirely on the remote device.
While specific embodiments of the present disclosure have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the disclosure is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the disclosure, but such changes and modifications fall within the scope of the disclosure.
Claims (10)
1. The coal quality evaluation method is characterized by comprising the following steps:
acquiring multi-mode data of coal to be evaluated;
extracting features of each modal data in the multi-modal data respectively, and determining target features corresponding to each modal data respectively;
and determining target evaluation results corresponding to the target features respectively according to the target features, and determining a final coal quality evaluation result according to the target evaluation results.
2. The coal quality evaluation method according to claim 1, wherein the multi-modal data includes attribute data; the feature extraction is performed on each mode data in the multi-mode data, and the target feature corresponding to each mode data is determined, which includes:
extracting the attribute data from the multi-modal data, wherein the attribute data comprises attribute characteristics;
performing dimension reduction on the attribute features by using a data dimension reduction model, and taking the attribute features subjected to dimension reduction as the target features; the target features include physicochemical features and combustion features.
3. The coal quality assessment method according to claim 1, wherein the multi-modal data comprises an optical tissue image; the feature extraction is performed on each mode data in the multi-mode data, and the target feature corresponding to each mode data is determined, which includes:
extracting the optical tissue image from the multimodal data;
and taking the optical tissue characteristics obtained after the optical tissue image is processed through a first convolution neural network model which is trained in advance as the target characteristics.
4. The coal quality evaluation method according to claim 3, wherein the first convolutional neural network model comprises at least one fully connected layer; the optical tissue feature obtained after the optical tissue image is processed through a first convolutional neural network model which is trained in advance is used as the target feature, and the method comprises the following steps:
inputting the optical tissue image into the first convolutional neural network model;
and taking the feature vector output by the full connection layer of the first convolutional neural network model as the target feature.
5. The coal quality assessment method according to claim 1, wherein the multimodal data includes text description data; the feature extraction is performed on each mode data in the multi-mode data, and the target feature corresponding to each mode data is determined, which includes:
extracting the text description data from the multimodal data;
and taking the text description characteristic obtained after the text description data is processed through a second convolutional neural network model which is trained in advance as the target characteristic.
6. The coal quality evaluation method according to claim 5, wherein the second convolutional neural network model comprises at least one fully connected layer; the text description feature obtained after the text description data is processed through a pre-trained second convolutional neural network model is used as the target feature, and the method comprises the following steps:
inputting the text description data into the second convolutional neural network model;
and taking the feature vector output by the full connection layer of the second convolutional neural network model as the target feature.
7. The coal quality evaluation method according to any one of claims 1 to 6, characterized in that the determining a target evaluation result corresponding to each of the target features from the target features, and determining a final coal quality evaluation result from the target evaluation result, comprises:
according to the classifier which is trained in advance and based on the target features, respectively determining preset evaluation results of preset numbers corresponding to the target features from a preset feature library; the preset feature library comprises preset features and preset evaluation results corresponding to the preset features;
counting the occurrence times corresponding to the coal quality ratings included in all the preset evaluation results;
and taking the coal quality rating with the largest occurrence frequency and/or descriptive data corresponding to the coal quality rating as a final coal quality evaluation result.
8. A coal quality evaluation system, characterized in that the coal quality evaluation system comprises:
the acquisition module is used for acquiring multi-mode data of the coal to be evaluated;
the processing module is used for extracting the characteristics of each modal data in the multi-modal data respectively and determining target characteristics corresponding to each modal data respectively;
and the evaluation module is used for determining target evaluation results corresponding to the target features respectively according to the target features and determining a final coal quality evaluation result according to the target evaluation results.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory for execution on the processor, wherein the processor implements the coal quality assessment method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the coal quality evaluation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311056901.8A CN117074643B (en) | 2023-08-21 | 2023-08-21 | Coal quality evaluation method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311056901.8A CN117074643B (en) | 2023-08-21 | 2023-08-21 | Coal quality evaluation method, system, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117074643A true CN117074643A (en) | 2023-11-17 |
| CN117074643B CN117074643B (en) | 2024-06-07 |
Family
ID=88701851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311056901.8A Active CN117074643B (en) | 2023-08-21 | 2023-08-21 | Coal quality evaluation method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117074643B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106501481A (en) * | 2015-09-08 | 2017-03-15 | 上海梅山钢铁股份有限公司 | A kind of evaluation methodology of rich coal ature of coal |
| CN109064061A (en) * | 2018-09-11 | 2018-12-21 | 辽宁科技大学 | A kind of coking coal multidimensional property evaluation method based on AHP analytic hierarchy process (AHP) |
| CN110910032A (en) * | 2019-11-29 | 2020-03-24 | 华润电力技术研究院有限公司 | Coal quality index evaluation method and related device |
| CN111881909A (en) * | 2020-07-27 | 2020-11-03 | 精英数智科技股份有限公司 | Coal and gangue identification method and device, electronic equipment and storage medium |
| WO2021114840A1 (en) * | 2020-05-28 | 2021-06-17 | 平安科技（深圳）有限公司 | Scoring method and apparatus based on semantic analysis, terminal device, and storage medium |
| CN113191452A (en) * | 2021-05-21 | 2021-07-30 | 中国矿业大学(北京) | Coal ash content online detection system based on deep learning and detection method thereof |
| CN114535133A (en) * | 2022-01-12 | 2022-05-27 | 山东大学 | Coal and gangue sorting method, device and system based on dual-energy ray transmission imaging |
| US20220319154A1 (en) * | 2019-12-19 | 2022-10-06 | Huawei Technologies Co., Ltd. | Neural network model update method, image processing method, and apparatus |
| JP2023021917A (en) * | 2021-08-02 | 2023-02-14 | 華院計算技術（上海）股▲ふん▼有限公司 | Coal blending method, system, apparatus and storage medium based on robust optimization |
| CN116206169A (en) * | 2022-08-17 | 2023-06-02 | 沈阳工业大学 | Intelligent gangue target detection method |
| FR3132371A3 (en) * | 2022-01-28 | 2023-08-04 | Anhui University of Science and Technology | A model for classifying the residual capsule network of coal gangue images and a method of using this model to classify coal gangue images. |
-
2023
- 2023-08-21 CN CN202311056901.8A patent/CN117074643B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106501481A (en) * | 2015-09-08 | 2017-03-15 | 上海梅山钢铁股份有限公司 | A kind of evaluation methodology of rich coal ature of coal |
| CN109064061A (en) * | 2018-09-11 | 2018-12-21 | 辽宁科技大学 | A kind of coking coal multidimensional property evaluation method based on AHP analytic hierarchy process (AHP) |
| CN110910032A (en) * | 2019-11-29 | 2020-03-24 | 华润电力技术研究院有限公司 | Coal quality index evaluation method and related device |
| US20220319154A1 (en) * | 2019-12-19 | 2022-10-06 | Huawei Technologies Co., Ltd. | Neural network model update method, image processing method, and apparatus |
| WO2021114840A1 (en) * | 2020-05-28 | 2021-06-17 | 平安科技（深圳）有限公司 | Scoring method and apparatus based on semantic analysis, terminal device, and storage medium |
| CN111881909A (en) * | 2020-07-27 | 2020-11-03 | 精英数智科技股份有限公司 | Coal and gangue identification method and device, electronic equipment and storage medium |
| CN113191452A (en) * | 2021-05-21 | 2021-07-30 | 中国矿业大学(北京) | Coal ash content online detection system based on deep learning and detection method thereof |
| JP2023021917A (en) * | 2021-08-02 | 2023-02-14 | 華院計算技術（上海）股▲ふん▼有限公司 | Coal blending method, system, apparatus and storage medium based on robust optimization |
| CN114535133A (en) * | 2022-01-12 | 2022-05-27 | 山东大学 | Coal and gangue sorting method, device and system based on dual-energy ray transmission imaging |
| FR3132371A3 (en) * | 2022-01-28 | 2023-08-04 | Anhui University of Science and Technology | A model for classifying the residual capsule network of coal gangue images and a method of using this model to classify coal gangue images. |
| CN116206169A (en) * | 2022-08-17 | 2023-06-02 | 沈阳工业大学 | Intelligent gangue target detection method |
Non-Patent Citations (3)
| Title |
|---|
| FENG HU, 等: "A Bayesian optimal convolutional neural network approach for classification of coal and gangue with multispectral imaging", OPTICS AND LASERS IN ENGINEERING, vol. 156, 29 April 2022 (2022-04-29) * |
| 周德炀;张立忠;景治;杨建国;窦东阳;: "基于机器视觉的煤质快速分析法及其应用", 煤炭加工与综合利用, no. 08, 25 August 2020 (2020-08-25) * |
| 张玮;张丹;: "基于Elman动态神经网络的煤质预测算法研究", 中国矿业, no. 03, 15 March 2013 (2013-03-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117074643B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108959246B (en) | Answer selection method and device based on improved attention mechanism and electronic equipment | |
| US11182568B2 (en) | Sentence evaluation apparatus and sentence evaluation method | |
| CN112270196B (en) | Entity relationship identification method and device and electronic equipment | |
| US8266078B2 (en) | Platform for learning based recognition research | |
| CN109189767B (en) | Data processing method and device, electronic equipment and storage medium | |
| US11520993B2 (en) | Word-overlap-based clustering cross-modal retrieval | |
| CN116097250A (en) | Layout aware multimodal pre-training for multimodal document understanding | |
| CN111985228A (en) | Text keyword extraction method and device, computer equipment and storage medium | |
| CN116719520B (en) | Code generation method and device | |
| CN116561542B (en) | Model optimization training system, method and related device | |
| CN110929119A (en) | Data annotation method, device, equipment and computer storage medium | |
| CN115617614A (en) | Log sequence anomaly detection method based on time interval perception self-attention mechanism | |
| CN113255752A (en) | Solid material consistency sorting method based on feature clustering | |
| CN117074643B (en) | Coal quality evaluation method, system, equipment and medium | |
| CN113743448B (en) | Model training data acquisition method, model training method and device | |
| US20220051077A1 (en) | System and method for selecting components in designing machine learning models | |
| US20170293863A1 (en) | Data analysis system, and control method, program, and recording medium therefor | |
| JP6509391B1 (en) | Computer system | |
| WO2021128342A1 (en) | Document processing method and apparatus | |
| CN112463964A (en) | Text classification and model training method, device, equipment and storage medium | |
| CN113742451B (en) | Machine reading understanding system based on multi-type questions and multi-fragment answer extraction | |
| CN112115705B (en) | Screening method and device of electronic resume | |
| CN117668237B (en) | Sample data processing method and system for intelligent model training and intelligent model | |
| Ye et al. | Multi-Granularity Framework for Unsupervised Representation Learning of Time Series | |
| CN116450826A (en) | Method for realizing automatic classification of system logs based on Bert_RNN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |