A full-grain dry coal separation system based on digital twinning

Abstract

The application discloses a kind of full grain level dry method coal preparation system based on digital twinning, comprising: raw coal preparation module, configured to crush raw coal and control the moisture of raw coal;Separation and upgrading module, configured to separate and size classification to the raw coal after crushing;Medium circulation module, configured to separate clean coal product and heavy medium, to recycle heavy medium in the separation process;Computer module, configured to establish a prediction model according to historical data, load the working data of each module into the prediction model for coal quality prediction, and output the optimal equipment parameters of the coal preparation system under the current working condition to guide the production process of the coal preparation system;Digital twinning module is used to receive the state detection data of each module, and a three-dimensional model of the coal preparation system is established and visualization is realized, and the computer module displays the working state of the coal preparation system in real time based on the digital twinning module, and adjusts the operating parameters of each module according to the working state.

Description

Technical Field

[0001] This invention relates to the field of coal preparation technology, and in particular to a full-scale dry coal preparation system based on digital twins. Background Technology

[0002] my country is a major coal-producing country, with coal consistently accounting for over 60% of its energy consumption and remaining its primary fossil fuel. Therefore, the efficient and clean utilization of coal and the promotion of its green development have become crucial directions for current coal industry development. Furthermore, with the rapid development of new energy sources, the country's reliance on coal is gradually decreasing, and overcapacity has become a significant challenge. Therefore, in this era, accelerating supply-side structural reforms in the coal sector, focusing on promoting clean, efficient, and low-carbon development, strengthening coal technology innovation, and improving the efficient utilization of coal are essential. The world today faces a severe water shortage problem; therefore, efficient dry coal preparation processes can help address existing challenges in coal sorting technologies. With the rapid development of industrial technology and new-generation information technology, the level of intelligence in equipment in industrial manufacturing and other fields is increasing. Online monitoring of complex equipment operation status, anomaly alarms, fault diagnosis, and lifespan prediction have become current hot topics and areas.

[0003] In related technologies, during the coal preparation process, the operating parameters of each coal preparation device in the coal preparation system are difficult to adjust accurately, and the coal preparation system cannot directly interact with the user, making it impossible for the user to directly understand the operating status of each device, resulting in low process efficiency and high process cost. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, the first objective of this invention is to propose a full-scale dry coal preparation system based on digital twins. Through intelligent control of the coal preparation equipment via a computer module, it overcomes the limitation of inaccurate adjustment of operating parameters during the coal preparation process. The three-dimensional model established by the digital twin module enables immersive human-computer interaction between the user and the physical entity, offering advantages such as equipment health monitoring, process effect prediction and analysis, process data optimization, improved process efficiency, and reduced process costs.

[0005] To achieve the above objectives, a first aspect of the present invention proposes a full-particle-size dry coal preparation system based on digital twins, comprising: a raw coal preparation module configured to crush raw coal and control its moisture content; a sorting and upgrading module configured to sort and classify the crushed raw coal; a media circulation module configured to separate clean coal products and heavy media, and to separate heavy media from coal powder to recycle the heavy media during the sorting process; and a computer module coupled to the raw coal preparation module, the sorting and upgrading module, and the media circulation module, configured to establish a predictive model based on historical data, and to optimize the performance of the raw coal preparation module, the sorting and upgrading module, and the media circulation module. Working data is loaded into the prediction model for coal quality prediction, and the optimal equipment parameters of the coal preparation system under the current operating conditions are output to guide the production process of the coal preparation system. A digital twin module is used, with one end coupled to the raw coal preparation module, the sorting and upgrading module, and the media circulation module, respectively. This module receives status detection data from each module, establishes a three-dimensional model of the coal preparation system, and enables visualization. The other end of the digital twin module is coupled to the computer module, which displays the real-time operating status of the coal preparation system based on the digital twin module and controls the adjustment of the operating parameters of the raw coal preparation module, the sorting and upgrading module, and the media circulation module according to the operating status.

[0006] According to an embodiment of the present invention, a full-size dry coal preparation system based on digital twins comprises a raw coal preparation module for crushing and controlling the moisture content of raw coal; a sorting and upgrading module for sorting and particle size classification of the crushed raw coal; a media circulation module for separating clean coal products and heavy media, and for separating heavy media from coal powder to recycle heavy media during the sorting process; a computer module for building a prediction model based on historical data, loading the working data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module into the prediction model for coal quality prediction, and outputting the optimal equipment parameters of the coal preparation system under the current working conditions to guide the production process of the coal preparation system; a digital twin module for receiving status detection data from each module, building a three-dimensional model of the coal preparation system and enabling visualization; and a computer module for displaying the working status of the coal preparation system in real time based on the digital twin module, and adjusting the operating parameters of the raw coal preparation module, the sorting and upgrading module, and the media circulation module according to the working status. Therefore, the system solves the limitation of the difficulty in accurately adjusting the operating parameters in the coal preparation process by intelligently controlling the coal preparation equipment through the computer module. Through the three-dimensional model established by the digital twin module, it realizes the immersive human-computer interaction function between the user and the physical entity, and has the advantages of equipment health detection, process effect prediction and analysis, optimization of process data, improvement of process efficiency and reduction of process cost.

[0007] In addition, the full-grain-scale dry coal preparation system based on digital twins according to the above embodiments of the present invention may also have the following additional technical features:

[0008] According to one embodiment of the present invention, the computer module includes: a PC computer configured to process and save the working data of the coal preparation system, establish the prediction model based on an intelligent algorithm, and input the working data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module into the prediction model to obtain the optimal equipment parameters of the coal preparation system; and a PLC control unit coupled to the PC computer, configured to receive the optimal equipment parameters obtained by the PC computer and input them into the raw coal preparation module, the sorting and upgrading module, and the media circulation module to control the production process of the coal preparation system.

[0009] According to one embodiment of the present invention, the PC computer includes: a MySQL database unit configured to store and retrieve working parameter data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module; and a Python environment programming unit configured to perform data preprocessing and parameter optimization on the data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module by calling machine learning algorithm models based on the Python compilation language environment.

[0010] According to one embodiment of the present invention, the digital twin module includes: a three-dimensional modeling unit configured to establish a three-dimensional model of the coal preparation system based on the operating parameters, production data and dimensional data of the coal preparation system under the current working conditions; and a data visualization unit configured to visualize the three-dimensional model of the coal preparation system to visualize the production process of the coal preparation system.

[0011] According to one embodiment of the present invention, the digital twin module further includes: a feedback unit configured to receive operation instructions and feed the operation instructions back to the computer module, so that the computer module controls the coal preparation work of the raw coal preparation module, the sorting and upgrading module and the media circulation module according to the operation instructions.

[0012] According to one embodiment of the present invention, the raw coal preparation module includes: a pre-screening device configured to classify the particle size of the raw coal; a crushing device configured to crush the raw coal; and a drying device configured to control the moisture content of the raw coal.

[0013] According to one embodiment of the present invention, the raw coal preparation module further includes a state detection unit, which includes a vibration sensor and a temperature sensor, wherein the vibration sensor is used to detect the vibration amplitude and vibration frequency of the crushing device, and the temperature sensor is used to detect the temperature of the drying device.

[0014] According to one embodiment of the present invention, the sorting and upgrading module includes: a sorting machine configured to sort crushed raw coal, wherein the sorting machine includes a photoelectric sorting machine, a composite dry sorting machine, and a heavy medium fluidized bed sorting machine; a grading screen configured to classify the crushed raw coal by particle size; and a coal quality testing unit, wherein the coal quality testing unit includes: an online ash content detection device and a parameter sensor, wherein the online ash content detection device is used to detect the ash content and calorific value of each raw coal sorting product, and the parameter sensor is used to detect the vibration frequency, bed surface inclination angle, air volume in the air chamber, inner bed air velocity, bed pressure, and bed height of the sorting machine.

[0015] According to one embodiment of the present invention, the media circulation module includes: a desliming screen configured to separate clean coal products and heavy media; a magnetic separator configured to separate heavy media from coal powder; and a dust collector configured to adsorb dust generated during the separation process.

[0016] According to one embodiment of the present invention, the media circulation module further includes: a bed detection unit configured to detect the bed density of the separator; a quantitative feeding device configured to replenish the media of the separator based on the bed density of the separator; and a media flow detection unit configured to collect the media and coal powder flow rates of the quantitative feeding device.

[0017] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0018] Figure 1 This is a block diagram of a full-grain-scale dry coal preparation system based on digital twins according to an embodiment of the present invention;

[0019] Figure 2 This is a block diagram of a full-scale dry coal preparation system based on digital twins according to an embodiment of the present invention.

[0020] Figure label:

[0021] 100. Coal preparation system; 110. Raw coal preparation module; 111. Pre-screening device; 112. Crushing device; 113. Drying device; 114. Status monitoring unit; 120. Separation and upgrading module; 121. Photoelectric separator; 122. Composite separator; 123. Heavy medium fluidized bed separator; 124. Grading screen; 125. Coal quality testing unit; 1251. Online ash content detection device; 1252. Parameter sensor; 130. Medium circulation module; 131. Desiccant screen ; 132. Diversion device; 133. Magnetic separator; 134. Quantitative feeding device; 135. Dust collector; 136. Bed detection unit; 137. Flow detection unit; 140. Computer module; 141. PC computer; 1411. MySQL database unit; 1412. Python environment programming unit; 142. PLC control unit; 150. Digital twin module; 151. 3D modeling unit; 152. Data visualization unit; 153. Feedback unit. Detailed Implementation

[0022] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0023] The following description, with reference to the accompanying drawings, describes the full-scale dry coal preparation system based on digital twins proposed in the embodiments of the present invention.

[0024] Figure 1 This is a block diagram of a full-scale dry coal preparation system based on digital twins according to an embodiment of the present invention.

[0025] like Figure 1 As shown, the full-grain-scale dry coal preparation system 100 based on digital twin of the present invention may include: raw coal preparation module 110, sorting and upgrading module 120, media circulation module 130, computer module 140 and digital twin module 150.

[0026] The system includes three modules: a raw coal preparation module 110, configured to crush raw coal and control its moisture content; a sorting and upgrading module 120, configured to sort and classify the crushed raw coal; a media circulation module 130, configured to separate clean coal products and heavy media, and to separate heavy media from pulverized coal to recycle the heavy media during the sorting process; and a computer module 140, coupled to the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130, configured to build a prediction model based on historical data, load the working data of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130 into the prediction model for coal quality prediction. The system outputs the optimal equipment parameters of the coal preparation system 100 under the current operating conditions to guide the production process of the coal preparation system 100. One end of the digital twin module 150 is coupled to the raw coal preparation module 110, the sorting and upgrading module 120 and the media circulation module 130 respectively, and is used to receive the status detection data of each module, establish a three-dimensional model of the coal preparation system 100 and realize visualization. The other end of the digital twin module 150 is coupled to the computer module 140. The computer module 140 displays the working status of the coal preparation system 100 in real time based on the digital twin module 150, and controls the adjustment of the operating parameters of the raw coal preparation module 110, the sorting and upgrading module 120 and the media circulation module 130 according to the working status.

[0027] Specifically, when sorting raw coal, the raw coal preparation module 110 first crushes large pieces of raw coal and controls the moisture content of the raw coal. Then, the sorting and upgrading module 120 sorts and classifies the crushed raw coal to obtain clean coal products and coal powder. The media circulation module 130 then separates the clean coal products and heavy media, and separates the heavy media in the coal powder to recycle the heavy media during the sorting process. Computer module 140 obtains the operating parameters of coal preparation system 100 from raw coal preparation module 110, sorting and upgrading module 120, and media circulation module 130. It then performs preprocessing work in the machine learning library of computer module 140, including data recombination, classification, alignment, and sorting. The preprocessed dataset is divided into raw coal preparation dataset, sorting and upgrading dataset, and media circulation dataset, and stored in computer module 140. Based on the intelligent algorithm of computer module 140, a prediction model is established using a large amount of historical data. The optimal hyperparameters of the model are automatically saved using a threshold comparison method, generating the best prediction model. The collected and preprocessed dataset is loaded into the saved machine learning prediction model. The optimal hyperparameters stored in the database of computer module 140 are called to predict coal quality and output the optimal equipment parameters under the current operating conditions. The optimal equipment parameters output by computer module 140 under the current operating conditions are fed back to the physical entities of raw coal preparation module 110, sorting and upgrading module 120, and media circulation module 130 to adjust the equipment operating parameters, thereby guiding actual production.

[0028] Furthermore, the digital twin module 150 receives status detection data from the corresponding modules and establishes a three-dimensional model of the coal preparation system 100 based on the status detection data and relevant parameter data of each module. This three-dimensional model is then visualized, allowing for real-time display of the coal preparation system 100's operating status. The digital twin module 150 transmits the operating status of the coal preparation system 100 to the computer module 140, enabling the computer module 140 to adjust the operating parameters of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130 according to the operating status. This guides actual production, making the working process of the coal preparation system 100 more intuitive.

[0029] According to one embodiment of the present invention, such as Figure 2 As shown, the computer module 140 includes: a PC computer 141, configured to process and save the working data of the coal preparation system 100, establish a prediction model based on intelligent algorithms, and input the working data of the raw coal preparation module 110, the sorting and upgrading module 120 and the media circulation module 130 into the prediction model to obtain the optimal equipment parameters of the coal preparation system 100; and a PLC control unit 142, coupled to the PC computer 141, configured to receive the optimal equipment parameters obtained by the PC computer 141 and input them into the raw coal preparation module 110, the sorting and upgrading module 120 and the media circulation module 130 to control the production process of the coal preparation system 100.

[0030] Furthermore, according to one embodiment of the present invention, such as Figure 2 As shown, the PC computer 141 includes: a MySQL database unit 1411, configured to store and retrieve working parameter data of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130; and a Python environment programming unit 1412, configured to perform data preprocessing and parameter optimization on the data of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130 by calling machine learning algorithm models based on the Python compilation language environment.

[0031] Specifically, the PC computer 141 can analyze, predict, and optimize the working status of various equipment within the coal preparation system 100. Specifically, the MySQL database unit 1411 stores and calls the parameter data collected by the sensors, the density control model of the heavy medium fluidized bed, and the quality improvement control model of each coal preparation equipment, and inputs them into the Python environment programming unit 1412 through the configured TCP / IP communication protocol. The Python environment programming unit 1412, based on the Python compilation language environment, performs corresponding data preprocessing and parameter optimization on the data from different modules by calling machine learning algorithm models. The PLC control unit 142 controls the physical entities of the coal preparation system 100, such as the input interface, the central processing unit (CPU), I / O converters, and output interfaces.

[0032] Specifically, the input interface connects the PC computer 141 and the PLC control unit 142 to receive the data signals processed by the PC computer 141 and transmit them to the central processing unit (CPU). The CPU interprets the input signals and performs the prescribed tasks according to the instructions. The generated control instructions are transmitted to each physical module of the coal preparation system 100 via the output interface through the I / O converter to complete the adjustment of the working conditions.

[0033] In other words, the PC computer 141 first obtains the operating parameters of the coal preparation system 100 from the detection units such as the status detection unit 114, coal quality detection unit 125, bed detection unit 136, and media flow detection unit 137. Preprocessing is then performed using the scikit-learn machine learning library under the Python programming language, including data recombination, classification, alignment, and sorting. The preprocessed dataset is divided into a raw coal preparation dataset, a sorting and upgrading dataset, and a media circulation dataset, and stored in a MySQL database unit 1411. The MySQL database unit 1411 and the Python programming unit 1412 are configured with a TCP / IP communication protocol to complete the input of the dataset to the Python programming unit 1412. Then, the Python programming unit 1412 uses a random forest intelligent algorithm based on PSO optimization and improvement to... A large amount of historical data is used to build a predictive model, and the optimal hyperparameters of the model are automatically saved through threshold comparison. The best predictive model is generated and stored in a comma-separated CSV file in MySQL database unit 1411. The Python environment programming unit 1412 loads the collected and preprocessed dataset CSV file into the saved machine learning predictive model, calls the optimal hyperparameters stored in the MySQL database, performs coal quality prediction, and outputs the optimal equipment parameters under the current working conditions. Finally, the optimal equipment parameters under the current working conditions output by the Python environment programming unit 1412 are transmitted to the PLC control unit 142. The PLC control unit 142 reads and interprets the commands transmitted to it and feeds them back to the physical entities of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130 to adjust the equipment operating parameters, thereby guiding actual production.

[0034] Therefore, this invention, combined with the full-particle-scale high-efficiency dry coal preparation process, creatively proposes a full-particle-scale high-efficiency dry coal preparation system 100 based on a digital twin framework. Through the intelligent control of the coal preparation equipment by the Python environment programming unit 1412 based on the Python language, the limitation of the difficulty in accurately adjusting the operating parameters in the coal preparation process is solved. Through the three-dimensional model established by the digital twin module 150, the immersive human-computer interaction function between the user and the physical entity is realized, which has the advantages of equipment health detection, process effect prediction and analysis, optimization of process data, improvement of process efficiency, and reduction of process cost.

[0035] According to one embodiment of the present invention, such as Figure 2As shown, the digital twin module 150 includes: a 3D modeling unit 151, configured to establish a 3D model of the coal preparation system 100 based on the operating parameters, production data and dimensional data of the coal preparation system 100 under the current working conditions; and a data visualization unit 152, configured to visualize the 3D model of the coal preparation system 100 to visualize the production process of the coal preparation system 100.

[0036] Furthermore, according to one embodiment of the present invention, such as Figure 2 As shown, the digital twin module 150 also includes a feedback unit 153, configured to receive operation instructions and feed them back to the computer module 140, so that the computer module 140 controls the coal preparation work of the raw coal preparation module 110, the sorting and upgrading module 120 and the media circulation module 130 according to the operation instructions.

[0037] Specifically, the 3D modeling unit 151 can utilize its embedded 3D modeling software to perform comprehensive, high-fidelity 3D rendering and modeling of the coal preparation system 100 at a certain scale based on operating parameters, production data, and dimensional data under the current operating conditions of the coal preparation system 100, thereby obtaining a 3D model of the coal preparation system 100. The data visualization unit 152 visualizes the 3D model using HTML5+U3D technology, which may include data acquisition, data graphical display, data storage, and data export. Thus, operators can input commands into the computer module 140 in real time based on the visualized 3D model, thereby controlling the coal preparation operations of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130.

[0038] Furthermore, the feedback unit 153 can digitize the operation instructions fed back by the operator and transmit the result instructions wirelessly to the PLC control unit 142, thereby guiding actual production and forming an immersive interaction between the user and the physical entity module.

[0039] Specifically, firstly, sensors distributed in the raw coal preparation module 110, sorting and upgrading module 120, and media circulation module 130 collect operating parameters, production data, and dimensional data of the equipment in the dry coal preparation system 100 under the current working conditions. The converted digital signals are then transmitted to the 3D modeling unit 151 via an RS-232 interface. The 3D modeling unit 151, relying on 3D modeling and rendering engines such as 3Dmax / Creo 5.0 / MODO, uses the unified modeling language UML to perform comprehensive, high-fidelity 3D modeling and rendering of the entire coal preparation system 100 at a certain scale. Then, the data visualization unit 152, using a web visualization approach and a B / S architecture developed based on Java + HTML technology, visualizes the 3D model generated by the 3D modeling unit 151 on the web, supporting mainstream browsers including Google Chrome, 360 Speed ​​Browser, Firefox, and IE. The web display page is divided into three parts: exhibition... The system includes an interactive display area, a parameter display area, and a human-machine interaction area. A 3D model is displayed in the interactive display area, which users can drag and zoom in on. The current operating status and parameters of the equipment are displayed in the parameter display area. Each piece of equipment in the system has two threshold values: a maximum threshold and a minimum threshold. When the operating parameters of an equipment exceed the maximum threshold or fall below the minimum threshold, the coal preparation system 100 will issue an alarm and automatically send a termination command to the PLC control unit 142, requesting the entire coal preparation process to stop. Problematic equipment will be marked in red in the interactive display area, and the problematic operating parameters will also be marked in red in the parameter display area. Commands sent by the user in the human-machine interaction area are input as digital signals to the PLC control unit 142 via an RS232 interface. After processing by the CPU, I / O converter, and output interface, the commands are fed back to the physical entities of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130, thus realizing the system's human-machine interaction.

[0040] According to one embodiment of the present invention, such as Figure 2 As shown, the raw coal preparation module 110 includes: a pre-screening device 111 configured to classify the particle size of the raw coal; a crushing device 112 configured to crush the raw coal; and a drying device 113 configured to control the moisture content of the raw coal.

[0041] According to one embodiment of the present invention, such as Figure 2 As shown, the raw coal preparation module 110 also includes a status detection unit 114, which includes a vibration sensor and a temperature sensor. The vibration sensor is used to detect the vibration amplitude and vibration frequency of the crushing device 112, and the temperature sensor is used to detect the temperature of the drying device 113.

[0042] Specifically, the raw coal is first classified into +100mm and -100mm particle sizes by a pre-screening device 111. The +100mm particle size raw coal is then crushed to -100mm particle size by a crushing device 112 and mixed with the raw coal before crushing. The mixed raw coal enters a drying device 113 to control the moisture content to below 8%. Then, the status detection unit 114 collects and detects the operating status parameters of each device through sensors distributed on the equipment, including belt gear speed, temperature of the drying device 113, and moisture content of the raw coal. The collected analog signals are converted into digital signals by an A / D converter and transmitted to a PC computer 141 via 5G network communication for the preprocessing of raw data.

[0043] Specifically, the status detection unit 114 is composed of high-precision sensors such as vibration sensors and temperature sensors, which collect the operating parameters during the actual operation of the equipment. The operating parameters include the vibration amplitude and vibration frequency of the pre-screening device 111 and the crushing device 112, the temperature of the drying device 113, etc.

[0044] According to one embodiment of the present invention, such as Figure 2 As shown, the sorting and upgrading module 120 includes: a sorting machine configured to sort crushed raw coal, wherein the sorting machine includes a photoelectric sorting machine 121, a composite dry sorting machine, and a heavy medium fluidized bed sorting machine 123; a grading screen 124 configured to classify the particle size of crushed raw coal; and a coal quality testing unit 125, which includes: an online ash content detection device 1251 and a parameter sensor 1252, wherein the online ash content detection device 1251 is used to detect the ash content and calorific value of each raw coal sorting product, and the parameter sensor 1252 is used to detect the vibration frequency, bed surface inclination angle, air volume in the air chamber, inner bed air velocity, bed pressure, and bed height of the sorting machine.

[0045] Specifically, the raw coal processed by the raw coal preparation module 110 is first separated into oversize and undersize by a grading screen 124 according to a 25mm particle size. The oversize, which is 100-25mm raw coal, enters the photoelectric separator 121 for separation to obtain two products: coarse clean coal and gangue. The undersize is then separated into 25-6mm and -6mm particle sizes by a grading screen 124 according to a 6mm particle size. The 25-6mm particle size raw coal enters the compound separator 122 for separation to obtain two products: lump clean coal and gangue. The -6mm particle size raw coal enters the heavy medium fluidized bed separator 123 for separation to obtain two products: fine clean coal and gangue.

[0046] Furthermore, parameter sensors 1252 are distributed in the composite separator 122 and the heavy medium fluidized bed separator 123 to collect equipment operating parameters. These parameters include the bed tilt angle, vibration frequency, and airflow of the composite separator 122, and the bed air velocity, bed pressure, and bed height of the heavy medium fluidized bed separator 123. An online ash content detection device 1251 detects the ash content of the corresponding products from the photoelectric separator 121, the composite separator 122, and the heavy medium fluidized bed separator 123. The analog signals collected by the online ash content detection device 1251 and the parameter sensors 1252 are converted into digital signals by an A / D converter and transmitted wirelessly to a PC computer 141141 via 5G.

[0047] According to one embodiment of the present invention, such as Figure 2 As shown, the media circulation module 130 includes: a desliming screen 131, configured to separate clean coal products and heavy media; a magnetic separator 133, configured to separate heavy media from coal powder; and a dust collector 135, configured to adsorb dust generated during the separation process.

[0048] Furthermore, according to one embodiment of the present invention, such as Figure 2 As shown, the media circulation module 130 also includes: a bed detection unit 136, configured to detect the bed density of the separator; a quantitative feeding device 134, configured to replenish the media of the separator based on the bed density of the separator; and a media flow detection unit 137, configured to collect the media and coal powder flow of the quantitative feeding device 134.

[0049] Specifically, the product separated by the heavy medium fluidized bed separator 123 is separated from the heavy medium and coal powder mixture by the desliming screen 131 and then divided into two parts by the diversion device 132. One part directly enters the heavy medium fluidized bed separator 123 to form a medium circulation, and the other part enters the magnetic separator 133 to separate the magnetic material of the heavy medium from the mixture, forming two products: magnetic material and coal powder. The magnetic material and coal powder are then fed into the heavy medium fluidized bed separator 123 through the quantitative feeding device 134 to complete the bed density regulation. The dust generated in the heavy medium fluidized bed separator 123 and the desliming screen 131 is discharged as exhaust air and mixed medium by the dust collector 135. The mixed medium is then conveyed by belt to the quantitative feeding device 134 and re-enters the heavy medium fluidized bed separator 123 to form a medium circulation.

[0050] The flow detection unit 137 detects the valve opening of the flow distribution device, the real-time flow rate, and the feeding speed of the quantitative feeding device 134 through sensors distributed on the flow distribution device 132 and the quantitative feeding device 134; the bed detection unit 136 is responsible for detecting the bed information of the heavy medium fluidized bed separator 123, including the bed air velocity, bed pressure, and bed height; the analog signals are converted by the A / D converter and then uniformly sent to the PC computer 141.

[0051] The following details the specific coal preparation process of the full-grain-scale drying coal preparation system 100 based on digital twins according to an embodiment of the present invention, which may include the following steps:

[0052] S10: The PC computer 141 obtains the working parameters of the coal preparation system 100 from units such as the status detection unit 114, coal quality detection unit 125, bed detection unit 136, and media flow detection unit 137. The PC computer 141 performs data recombination, classification, reorganization, alignment, and sorting preprocessing in the scikit-learn machine learning library under the Python programming language. The preprocessed dataset is divided into raw coal preparation dataset, sorting and upgrading dataset, and media circulation dataset and stored in MySQL database unit 1411. The MySQL database unit 1411 and the Python programming unit 1412 are configured with TCP / IP communication protocol to complete the input of the dataset to the Python programming unit 1412.

[0053] S20: Python environment programming unit 1412 uses a random forest intelligent algorithm based on PSO optimization to build a prediction model using a large amount of historical data, and automatically saves the optimal hyperparameters of the model through threshold comparison method to generate the best prediction model. The model is stored in comma-separated value file CSV format in MySQL database unit 1411. Python environment programming unit 1412 loads the collected and preprocessed dataset CSV file into the saved machine learning prediction model, calls the optimal hyperparameters stored in the MySQL database, performs coal quality prediction, and outputs the optimal equipment parameters under the current working conditions.

[0054] S30: The current optimal equipment parameters output by the Python environment programming unit 1412 are transmitted to the PLC control unit 142. The PLC control unit 142 reads and interprets the commands transmitted to the PLC control unit 142 and feeds them back to the physical entities of the raw coal preparation module 110, the sorting and upgrading module 120 and the media circulation module 130 to adjust the equipment operating parameters and thus guide actual production.

[0055] S40: Sensors distributed in the raw coal preparation module 110, sorting and upgrading module 120, and media circulation module 130 collect operating parameters, production data, and dimensional data of the equipment in the dry coal preparation system 100 under the current working conditions. The converted digital signals are transmitted to the 3D modeling unit 151 via an RS-232 interface. The 3D modeling unit 151, relying on 3D modeling and rendering engines such as 3Dmax / Creo 5.0 / MODO, uses the unified modeling language UML to perform comprehensive, high-fidelity 3D modeling and rendering of the entire coal preparation system 100 at a certain scale. Then, the data visualization unit 152 uses a web visualization method, employing a B / S architecture and developed based on Java + HTML technology, to visualize the 3D model generated by the 3D modeling unit 151 on the web. The web display page is divided into three parts: an interactive display area, a parameter display area, and a human-computer interaction area, showcasing the 3D model. The interactive display area allows users to drag and zoom in on the 3D model. The current operating status and parameters of the equipment are displayed in the parameter display area. Each piece of equipment in the system has two threshold values: a maximum threshold and a minimum threshold. When the operating parameters of the equipment are higher than the maximum threshold or lower than the minimum threshold, the coal preparation system 100 will issue an alarm and send a termination command to the PLC control unit 142 to stop the entire coal preparation process. The problematic equipment will be marked in red in the interactive display area, and the problematic operating parameters will also be marked in red in the parameter display area. Commands sent by the user in the human-machine interaction area are input as digital signals to the PLC control unit 142 via the RS232 interface. After being processed by the central processing unit (CPU), I / O converter, and output interface, the commands are fed back to the physical entities of the raw coal preparation module 110, the sorting and upgrading module 120, and the media circulation module 130, thus realizing the human-machine interaction of the system.

[0056] Therefore, the coal preparation system of the present invention solves the limitation of the difficulty in accurately adjusting the operating parameters in the coal preparation process by intelligently controlling the coal preparation equipment through the Python environment programming unit based on the Python language. Through the three-dimensional model established by the digital twin module, it realizes the immersive human-computer interaction function between the user and the physical entity, and has the advantages of equipment health detection, process effect prediction and analysis, optimization of process data, improvement of process efficiency, and reduction of process cost.

[0057] In summary, according to the embodiment of the present invention, the full-size dry coal preparation system based on digital twin comprises the following modules: a raw coal preparation module for crushing and controlling the moisture content of raw coal; a sorting and upgrading module for sorting and particle size classification of the crushed raw coal; a media circulation module for separating clean coal products and heavy media, and separating heavy media from coal powder to recycle heavy media during the sorting process; a computer module for building a prediction model based on historical data, loading the working data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module into the prediction model for coal quality prediction, and outputting the optimal equipment parameters of the coal preparation system under the current working conditions to guide the production process of the coal preparation system; a digital twin module for receiving status detection data from each module, building a three-dimensional model of the coal preparation system and enabling visualization; and a computer module for displaying the working status of the coal preparation system in real time based on the digital twin module, and controlling the adjustment of the operating parameters of the raw coal preparation module, the sorting and upgrading module, and the media circulation module according to the working status. Therefore, the system solves the limitation of the difficulty in accurately adjusting the operating parameters in the coal preparation process by intelligently controlling the coal preparation equipment through the computer module. Through the three-dimensional model established by the digital twin module, it realizes the immersive human-computer interaction function between the user and the physical entity, and has the advantages of equipment health detection, process effect prediction and analysis, optimization of process data, improvement of process efficiency and reduction of process cost.

[0058] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0059] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0060] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0061] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A full-scale dry coal preparation system based on digital twins, characterized in that, include: The raw coal preparation module is configured to crush raw coal and control its moisture content. The sorting and upgrading module is configured to sort and classify the crushed raw coal by particle size. The media circulation module is configured to separate the clean coal product and the heavy media, and to separate the heavy media in the coal powder, so as to recycle the heavy media during the separation process; A computer module is coupled to the raw coal preparation module, the sorting and upgrading module, and the media circulation module, respectively. It is configured to establish a prediction model based on historical data, load the working data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module into the prediction model to predict coal quality, and output the optimal equipment parameters of the coal preparation system under the current working conditions to guide the production process of the coal preparation system. A digital twin module is provided, with one end of which is coupled to the raw coal preparation module, the sorting and upgrading module, and the media circulation module, respectively, for receiving status detection data from each module, establishing a three-dimensional model of the coal preparation system, and realizing visualization; the other end of the digital twin module is coupled to the computer module, which displays the working status of the coal preparation system in real time based on the digital twin module, and controls the adjustment of the operating parameters of the raw coal preparation module, the sorting and upgrading module, and the media circulation module according to the working status. The computer module includes: A PC computer is configured to process and save the working data of the coal preparation system, establish the prediction model based on intelligent algorithms, and input the working data of the raw coal preparation module, the sorting and upgrading module and the media circulation module into the prediction model to obtain the optimal equipment parameters of the coal preparation system. The PLC control unit is coupled to the PC computer and configured to receive the optimal equipment parameters obtained by the PC computer and input them into the raw coal preparation module, the sorting and upgrading module and the media circulation module to control the production process of the coal preparation system.

2. The full-scale dry coal preparation system based on digital twins according to claim 1, characterized in that, The PC computer includes: The MySQL database unit is configured to store and retrieve the working parameter data of the raw coal preparation module, the sorting and upgrading module, and the media circulation module. The Python environment programming unit is configured to use a Python-based compilation language environment to perform data preprocessing and parameter optimization on the data from the raw coal preparation module, the sorting and upgrading module, and the media circulation module by calling machine learning algorithm models.

3. The full-scale dry coal preparation system based on digital twins according to claim 1, characterized in that, The digital twin module includes: The three-dimensional modeling unit is configured to establish a three-dimensional model of the coal preparation system based on the operating parameters, production data, and dimensional data of the coal preparation system under the current operating conditions. The data visualization unit is configured to visualize the three-dimensional model of the coal preparation system in order to visualize the production process of the coal preparation system.

4. The full-scale dry coal preparation system based on digital twins according to claim 3, characterized in that, The digital twin module also includes: The feedback unit is configured to receive operation instructions and feed them back to the computer module, so that the computer module controls the coal preparation module, the sorting and upgrading module and the media circulation module according to the operation instructions.

5. The full-scale dry coal preparation system based on digital twins according to claim 1, characterized in that, The raw coal preparation module includes: A pre-screening device is configured to classify the particle size of raw coal; Crushing device, configured to crush raw coal; The drying device is configured to control the moisture content of the raw coal.

6. The full-scale dry coal preparation system based on digital twins according to claim 5, characterized in that, The raw coal preparation module also includes: The status detection unit includes a vibration sensor and a temperature sensor, wherein the vibration sensor is used to detect the vibration amplitude and vibration frequency of the crushing device, and the temperature sensor is used to detect the temperature of the drying device.

7. The full-scale dry coal preparation system based on digital twins according to claim 1, characterized in that, The sorting and quality improvement module includes: The separator is configured to separate crushed raw coal, and the separator includes a photoelectric separator, a composite dry separator, and a heavy medium fluidized bed separator. A grading screen is configured to classify the particle size of crushed raw coal. The coal quality testing unit includes an online ash content detection device and a parameter sensor. The online ash content detection device is used to detect the ash content and calorific value of each raw coal sorting product. The parameter sensor is used to detect the vibration frequency, bed inclination angle, air volume in the air chamber, air velocity in the inner bed layer, bed pressure, and bed height of the sorting machine.

8. The full-scale dry coal preparation system based on digital twins according to claim 1, characterized in that, The medium circulation module includes: The desliming screen is configured to separate clean coal products from heavy media; A magnetic separator is configured to separate heavy media from pulverized coal. A dust collector is configured to adsorb and separate dust generated during the sorting process.

9. The full-scale dry coal preparation system based on digital twins according to claim 8, characterized in that, The medium circulation module further includes: The bed detection unit is configured to detect the bed density of the sorting machine; A quantitative feeding device is configured to replenish the media in the separator based on the bed density of the separator; The medium flow detection unit is configured to collect the flow rates of the medium and pulverized coal in the quantitative feeding device.

Images