Coal blending coking control parameter optimization method and system

Through the optimization method of humidity control parameter based on the initial coal material analysis model and virtual model, the coking stability and pollution problems caused by improper coal material moisture control are solved, and the precise control of coal material moisture and the stability and efficiency of the coking process are achieved. promote.

CN119045584AInactive Publication Date: 2024-11-29FENGCHENG XINGAO COKING CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411242877.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In traditional coal-based coking technology, improper control of coal moisture will affect the operation stability of the coke oven and environmental pollution. Too high or too low moisture will lead to energy waste and dust pollution.

Method used

The humidity control parameter optimization method based on the initial coal material analysis model and virtual model is adopted. Through data preprocessing, target value determination and exhaust gas control, the coal material moisture is monitored and adjusted in real time to ensure that the coal material moisture content reaches the optimal state.

Benefits of technology

It realizes precise control of coal moisture, reduces environmental pollution and energy waste, improves the stability and efficiency of the coking process, and dynamically adjusts the humidity regulation parameters to adapt to production changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119045584A_ABST
    Figure CN119045584A_ABST
Patent Text Reader

Abstract

The invention discloses a coal blending coking control parameter optimization method and system, and relates to the technical field of coal blending coking. A coal blending and coking control parameter optimization system comprises a coal blending and coking coal determination module, a coal blending and coking parameter output module and a coal blending and coking parameter optimization module. According to the invention, through the coal blending and coking coal material determination module, comprehensive analysis of wet coal materials, including moisture and coal quality information, is realized, and accurate data support is provided for subsequent humidifying operation; the coal blending coking parameter output module provides initial humidity control parameters through pretreatment and target value determination, and the coal moisture content can be easily adjusted to be close to the optimal state. By acquiring and analyzing the moisture information of the to-be-analyzed dewatered coking wet coal in real time, the coal blending coking parameter optimization module can dynamically adjust the humidity adjusting parameters to ensure that the moisture content of the coal reaches a target value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of coal blending and coking, and in particular to a method and system for optimizing control parameters of coal blending and coking. Background Art

[0002] In the traditional coal blending coking control method, the moisture control process of the charged coal is a necessary step. If the moisture content of the coal is too high, the water vapor carried in the coke oven gas will increase, which may affect the normal operation of the smoke and dust removal vehicle and increase the load of wastewater treatment, thereby affecting the stability of the coke oven operation. On the other hand, if the moisture content of the coal is too low, that is, the coal is too dry, it will not only lead to a waste of energy because more coke oven exhaust gas is needed to remove the additional moisture, but also the water film on the surface of the coal particles will become incomplete. This will reduce the gaps between the coal particles and increase the bulk density of the charged coal, thereby generating a large amount of dust during the charging process and polluting the environment. Therefore, proper control of the coal blending coking parameters is crucial to ensure the stability of the coke oven operation and reduce environmental pollution. Summary of the invention

[0003] The present invention aims to provide a method and system for optimizing the control parameters of coal blending coking, so as to flexibly control the control parameters of coal blending coking and provide support for subsequent coal blending coking operations.

[0004] A method for optimizing coal blending coking control parameters, comprising: S1. Based on the initial coal analysis model for coal blending and coking and the wet coal to be coked, the coal information to be analyzed and the virtual model of the wet coal to be coked are obtained. The coal information to be analyzed includes the moisture information of the coal to be analyzed and the coal quality information of the coal to be analyzed. The initial coal analysis model for coal blending and coking includes a model construction layer, a volume analysis layer, a moisture determination layer and a result output layer, providing comprehensive coal quality and moisture information to optimize the coal blending and coking process; S2. Input the coal information to be analyzed and the virtual model of the wet coal to be coked into the coal blending and coking moisture control parameter analysis model for analysis, and obtain the initial coal blending and coking moisture control parameters and the target coal moisture content; the coal blending and coking moisture control parameter analysis model includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer to ensure that the moisture content of the coal is adjusted to the optimal state, thereby optimizing the coking process; according to the initial coal blending and coking moisture control parameters, the wet coal to be coked is subjected to coal moisture adjustment operation to obtain the dehydrated wet coal to be analyzed; S3. Real-time acquisition of moisture information of the dehydrated coking wet coal to be analyzed and current coal blending and coking humidity control parameters, to obtain moisture information of the coal to be adjusted and humidity control parameters of the coal blending and coking to be adjusted; input the moisture information of the coal to be adjusted, humidity control parameters of the coal blending and coking to be adjusted and target moisture content of the coal to be adjusted into the coal blending and coking humidity control parameter optimization model for analysis, to obtain optimized humidity control parameters of the coal blending and coking, the coal blending and coking humidity control parameter optimization model includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer, which automatically adjusts and outputs the humidity control parameters most suitable for coal coking; the coal commissioning process of the dehydrated coking wet coal to be analyzed is adjusted in real time using the optimized coal blending and coking humidity control parameters, until the dehydrated coking wet coal to be analyzed meets the target moisture content of the coal.

[0005] As a preferred technical solution of the present invention, the initial coal material analysis model for coal blending and coking in step S1 includes a model building layer, a volume analysis layer, a moisture measurement layer and a result output layer; The model building layer is used to scan the wet coal to be coked by using point cloud technology to obtain point cloud data of the wet coal to be coked; and to build a virtual model of the wet coal to be coked by using the point cloud data of the wet coal to be coked and the digital twin technology; The volume analysis layer is used to perform volume analysis based on the virtual model of the wet coal to be coked, and obtain the coal quality information of the coal to be analyzed; The moisture determination layer is used to monitor the moisture content of the wet coal to be coked and obtain the moisture information of the coal to be analyzed; The result output layer is used to combine the coal quality information and the moisture information of the coal to be analyzed to obtain the coal information to be analyzed.

[0006] As a preferred technical solution of the present invention, the coal blending coking debugging control parameter analysis model in step S2 includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer; The data preprocessing layer is used to preprocess the coal information to be analyzed to obtain preprocessed coal information; The target value determination layer is used to calculate the target moisture content of the coal according to the virtual model of the wet coal to be coked; The tail gas control layer is used to perform characteristic analysis based on the target coal moisture content and pre-treated coal information to obtain the initial coal blending coking coke oven tail gas intake volume, so as to reduce the moisture content of the wet coal to be coked to the target coal moisture content, and determine the initial coal blending coking humidity control parameters based on the initial coal blending coke oven tail gas intake volume; The result output layer is used to output the initial coal blending and coking humidity control parameters.

[0007] As a preferred technical solution of the present invention, the specific steps of determining the target coal moisture content include: According to the virtual model of wet coal to be coked, K target coal moisture content individuals W are constructed. k ; Each target coal moisture content individual W k The target coal moisture content to be optimized is included according to the virtual model of wet coal to be coked; the K target coal moisture content individuals W k Combine to obtain the target coal moisture content iterative population; set the maximum number of iterations; According to the target coal moisture content, iterate the target coal moisture content individuals W in the population k Perform simulation calculation to obtain the target coal moisture content individual W k The fitness Y k ; The specific steps of simulation calculation are: According to the virtual model of wet coal to be coked, simulation is performed. When the moisture content of the wet coal to be coked in the virtual model of wet coal to be coked reaches the target moisture content of the individual coal W k When the target coal moisture content to be optimized is , a simulated coal blending coking operation is performed to obtain the simulated coke yield M k And simulated exhaust gas volume Q k ; Using formula F k =W 1 *M k +W 2 * (1 / Q k ) to obtain the evaluation index F k , W 1 and W 2 is the weight coefficient; the evaluation index F k As the target coal moisture content individual W k The fitness Y k ; When the maximum number of iterations is reached, the target coal moisture content individual W corresponding to the maximum fitness is output. k , which is the optimal target coal moisture content individual; the target coal moisture content to be optimized that is fitted according to the virtual model of the wet coal to be coked in the optimal target coal moisture content individual is used as the target coal moisture content.

[0008] As a preferred technical solution of the present invention, the specific steps of training the coal blending coking debugging control parameter analysis model include: Collect several groups of coke oven tail gas drying training samples; each group of coke oven tail gas drying training samples contains the volume of wet coal to be dried, the moisture content before drying and the target moisture content, and marks the coke oven tail gas content required for drying as the target value; combine several groups of coke oven tail gas drying training samples to obtain a coke oven tail gas drying training set; The coke oven exhaust gas drying training set is input into the coal blending coking debugging control parameter analysis model for training with the target value as the target, so as to obtain the initial coal blending coking debugging control parameter analysis model; the initial coal blending coking debugging control parameter analysis model is model verified to obtain the initial coal blending coking debugging control parameter analysis model verification result; if the initial coal blending coking debugging control parameter analysis model verification result is passed, the trained initial coal blending coking debugging control parameter analysis model is output as the coal blending coking debugging control parameter analysis model; otherwise, the model training is continued using the coke oven exhaust gas drying training set.

[0009] As a preferred technical solution of the present invention, the coal blending coking humidity control parameter optimization model in step S3 includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer; The data preprocessing layer is used to preprocess the moisture information of the coal material to be regulated and the humidity control parameters of the coal blending and coking to be regulated, and obtain the preprocessed moisture information of the coal material to be regulated and the preprocessed humidity control parameters of the coal blending and coking to be regulated; The feature prediction layer is used to perform prediction analysis based on the moisture information of the pre-processed coal to be regulated and the pre-processed coal blending and coking moisture control parameters to be regulated, and obtain the predicted target coal moisture content; The parameter optimization layer is used to compare the predicted target coal moisture content with the target coal moisture content. If the difference between the predicted target coal moisture content and the target coal moisture content is within the preset moisture difference threshold, the coal blending and coking humidity control parameters to be adjusted will continue to be used as the optimized coal blending and coking humidity control parameters; otherwise, the parameters are optimized according to the difference between the predicted target coal moisture content and the target coal moisture content to obtain the optimized coal blending and coking humidity control parameters; The result output layer is used to output the optimized coal blending and coking humidity control parameters.

[0010] As a preferred technical solution of the present invention, the specific steps of training the feature prediction layer in the coal blending coking humidity control parameter optimization model include: Collect several groups of coal blending coking humidity control parameter prediction training samples, each group of coal blending coking humidity control parameter prediction training samples contains a group of target controlled coal moisture content, current coal moisture content and current coal blending coking humidity control parameters; use the target controlled coal moisture content as the prediction target value of each group of coal blending coking humidity control parameter prediction training samples; combine several groups of coal blending coking humidity control parameter prediction training samples to obtain a coal blending coking humidity control parameter prediction training set; The training set of prediction of humidity control parameters for coking with coal blending is input into the optimization model of humidity control parameters for coking with coal blending to train the feature prediction layer and obtain the initial feature prediction layer; the model of the initial feature prediction layer is evaluated to obtain the model evaluation result of the initial feature prediction layer; if the model evaluation result of the initial feature prediction layer is passed, the initial feature prediction layer model is used as the feature prediction layer in the optimization model of humidity control parameters for coking with coal blending; otherwise, the model training is continued using the training set of prediction of humidity control parameters for coking with coal blending.

[0011] A coal blending coking control parameter optimization system, comprising: Coal blending and coking coal material determination module is used to deploy the initial coal material analysis model for coal blending and coking, and obtain the coal material information to be analyzed and the virtual model of the wet coal material to be coked based on the initial coal material analysis model for coal blending and coking and the wet coal material to be coked. The coal material information to be analyzed includes the moisture information and coal quality information of the coal material to be analyzed. The initial coal material analysis model for coal blending and coking includes a model construction layer, a volume analysis layer, a moisture determination layer and a result output layer, and provides comprehensive coal quality and moisture information to optimize the coal blending and coking process; The coal blending coking parameter output module is used to deploy the coal blending coking moisture control parameter analysis model, input the coal information to be analyzed and the virtual model of the wet coal to be coked into the coal blending coking moisture control parameter analysis model for analysis, and obtain the initial coal blending coking moisture control parameters and the target coal moisture content; the coal blending coking moisture control parameter analysis model includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer to ensure that the moisture content of the coal is adjusted to the optimal state, thereby optimizing the coking process; according to the initial coal blending coking moisture control parameters, the wet coal to be coked is subjected to coal moisture adjustment operation to obtain the dehydrated wet coal to be analyzed; The coal blending coking parameter optimization module is used to deploy the coal blending coking humidity control parameter optimization model, obtain the moisture information of the dehydrated coking wet coal to be analyzed and the current coal blending coking humidity control parameters in real time, and obtain the moisture information of the coal to be adjusted and the coal blending coking humidity control parameters to be adjusted; the moisture information of the coal to be adjusted, the coal blending coking humidity control parameters to be adjusted and the target coal moisture content are input into the coal blending coking humidity control parameter optimization model for analysis to obtain the optimized coal blending coking humidity control parameters, and the coal blending coking humidity control parameter optimization model includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer, which automatically adjusts and outputs the humidity control parameters most suitable for coal coking; the optimized coal blending coking humidity control parameters are used to adjust the coal commissioning process of the dehydrated coking wet coal to be analyzed in real time until the dehydrated coking wet coal to be analyzed meets the target coal moisture content.

[0012] The present invention has the following advantages: 1. The present invention realizes a comprehensive analysis of wet coal, including moisture and coal quality information, through the initial coal analysis model for coking with coal blending, thus providing accurate data support for subsequent moisture control operations; the moisture control parameter analysis model for coking with coal blending provides initial moisture control parameters through preprocessing and target value determination, which helps to adjust the moisture content of the coal to a state close to the optimal state; the moisture information of the dehydrated coking wet coal to be analyzed is acquired and analyzed in real time, and the moisture control parameter optimization model for coking with coal blending can dynamically adjust the moisture control parameters to ensure that the moisture content of the coal reaches the target value.

[0013] 2. The present invention reduces environmental problems caused by excessively high or low moisture content, such as dust pollution and energy waste, by precisely controlling the moisture content of coal. It realizes real-time monitoring and dynamic adjustment of the coal moisture control process by acquiring the moisture content information of the coal to be controlled and the exhaust gas intake of the coke oven in real time, thereby improving the flexibility and response speed of the moisture control process. It enables continuous learning and improvement through continuous data collection and model optimization to adapt to changes in the production process. It uses virtual models for simulation and efficiently evaluates the coke production and exhaust gas emissions under different target coal moisture contents, providing reliable reference data for actual operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is a schematic diagram of the structure of a coal blending coking control parameter optimization system used in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to enable persons skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0016] Embodiment 1, a method for optimizing coal blending coking control parameters, comprising: S1. Based on the initial coal analysis model for coal blending and coking and the wet coal to be coked, the coal information to be analyzed and the virtual model of the wet coal to be coked are obtained. The coal information to be analyzed includes the moisture information of the coal to be analyzed and the coal quality information of the coal to be analyzed. The initial coal analysis model for coal blending and coking includes a model construction layer, a volume analysis layer, a moisture determination layer and a result output layer, providing comprehensive coal quality and moisture information to optimize the coal blending and coking process; The wet coal to be coked is the coal to be prepared for coal blending and coking. The wet coal to be coked is placed on a conveyor belt for conveying and coking. The initial coal material analysis model for coal blending and coking in step S1 includes a model building layer, a volume analysis layer, a moisture measurement layer and a result output layer; The model building layer is used to scan the wet coal to be coked by using point cloud technology to obtain point cloud data of the wet coal to be coked; and to build a virtual model of the wet coal to be coked by using the point cloud data of the wet coal to be coked and the digital twin technology; The 3D laser scanning technology can be used to scan the wet coal for coking and establish a digital twin model. The digital twin technology can accurately simulate the process of coal blending and coking, realize high-precision 3D scanning of wet coal, and provide an accurate data basis for subsequent analysis. The volume analysis layer is used to perform volume analysis based on the virtual model of the wet coal to be coked, and obtain the coal quality information of the coal to be analyzed; The moisture determination layer is used to monitor the moisture content of the wet coal to be coked and obtain the moisture information of the coal to be analyzed; The result output layer is used to combine the coal quality information and the moisture information of the coal to be analyzed to obtain the coal information to be analyzed; The virtual model constructed through point cloud data and digital twin technology can accurately simulate the coal blending and coking process, improving the reliability and effectiveness of the simulation; the application of the volume analysis layer enables the detailed volume and quality information of the coal to be obtained from the virtual model, providing important reference data for coal blending; the implementation of the moisture determination layer realizes real-time monitoring of the moisture content of the coal, ensuring that the moisture control of the coal before coking meets the process requirements; S2. Input the coal information to be analyzed and the virtual model of the wet coal to be coked into the coal blending and coking moisture control parameter analysis model for analysis, and obtain the initial coal blending and coking moisture control parameters and the target coal moisture content; the coal blending and coking moisture control parameter analysis model includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer to ensure that the moisture content of the coal is adjusted to the optimal state, thereby optimizing the coking process; according to the initial coal blending and coking moisture control parameters, the wet coal to be coked is subjected to coal moisture adjustment operation to obtain the dehydrated wet coal to be analyzed; The coal blending coking debugging control parameter analysis model in step S2 includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer; The data preprocessing layer is used to preprocess the coal information to be analyzed to obtain preprocessed coal information; The target value determination layer is used to calculate the target moisture content of the coal according to the virtual model of the wet coal to be coked; The tail gas control layer is used to perform characteristic analysis based on the target coal moisture content and pre-treated coal information to obtain the initial coal blending coking coke oven tail gas intake volume, so as to reduce the moisture content of the wet coal to be coked to the target coal moisture content, and determine the initial coal blending coking humidity control parameters based on the initial coal blending coke oven tail gas intake volume; The result output layer is used to output the initial coal blending and coking humidity control parameters; The target value determination layer calculates the target moisture content of the coal and provides an accurate moisture control target for the coking process. The tail gas control layer accurately calculates the required coke oven tail gas intake according to the target moisture content and the pre-treated coal information, optimizing energy use and cost control. Through the adjustment of the tail gas control layer, it ensures that the moisture content in the coal can be reduced to the target content, improving the coking adaptability of the coal. The initial coal blending and coking humidity control parameters are automatically determined, reducing the interference of human factors and improving the consistency and repeatability of the humidity adjustment process. The precise control of the moisture content of the coal helps to improve the coking efficiency, and the quality of the coke is also guaranteed. The intake volume of the coke oven tail gas is optimized, the exhaust gas emission is reduced, and it plays a positive role in environmental protection. The coke oven tail gas is recycled from the exhaust gas generated during the previous coking, which helps to recycle resources and reduce tail gas emissions. The specific steps to determine the target coal moisture content include: According to the virtual model of wet coal to be coked, K target coal moisture content individuals W are constructed. k ; Each target coal moisture content individual W k The target coal moisture content to be optimized is included according to the virtual model of wet coal to be coked; the K target coal moisture content individuals W k Combine to obtain the target coal moisture content iteration population; set the maximum number of iterations; the maximum number of iterations is set by professional technicians according to actual conditions; when constructing the target coal moisture content individuals, the target coal moisture content to be optimized in each target coal moisture content individual is controlled to fluctuate within the set range, for example, 5-7%, and different target value iterations can be performed for different virtual models of wet coal to be coked, which is more targeted and universal; According to the target coal moisture content, iterate the target coal moisture content individuals W in the population k Perform simulation calculation to obtain the target coal moisture content individual W k The fitness Y k ; The specific steps of simulation calculation are: According to the virtual model of wet coal to be coked, simulation is performed. When the moisture content of the wet coal to be coked in the virtual model of wet coal to be coked reaches the target moisture content of the individual coal W k When the target coal moisture content to be optimized is , a simulated coal blending coking operation is performed to obtain the simulated coke yield M k And simulated exhaust gas volume Q k ; Using formula F k =W 1 *M k +W 2 * (1 / Q k ) to obtain the evaluation index F k , W1 and W 2 is the weight coefficient; the evaluation index F k As the target coal moisture content individual W k The fitness Y k ; W 1 and W 2 The value is set by professional technicians according to actual conditions; In the iteration process, a variety of technologies can be used to update the target coal moisture content iteration population to expand the possibility of the optimal solution, such as: selecting, recombining or mutating the target coal moisture content iteration population to construct a new target coal moisture content iteration population; When the maximum number of iterations is reached, the target coal moisture content individual W corresponding to the maximum fitness is output. k , which is the optimal target coal moisture content individual; the target coal moisture content to be optimized according to the virtual model of wet coal to be coked in the optimal target coal moisture content individual is used as the target coal moisture content; Through iterative calculation and fitness evaluation, the optimal target coal moisture content can be determined to provide an ideal raw material state for the coking process; simulation calculation predicts coke production and helps select individuals with moisture content that can maximize production; through simulation calculation of exhaust gas emissions, the environmental impact of different moisture contents on the coke production process can be evaluated; the evaluation index F k Comprehensive consideration of coke output and waste gas emissions helps to find the most cost-effective production conditions; by optimizing the moisture content of coal, coal resources can be used more effectively and waste can be reduced; selecting the optimal moisture content helps reduce energy consumption and environmental pollution, meeting the requirements of green production; The specific steps of training the coal blending coking commissioning control parameter analysis model include: Collect several groups of coke oven tail gas drying training samples; each group of coke oven tail gas drying training samples contains the volume of wet coal to be dried, the moisture content before drying and the target moisture content, and marks the coke oven tail gas content required for drying as the target value; combine several groups of coke oven tail gas drying training samples to obtain a coke oven tail gas drying training set; the coke oven tail gas drying training samples are collected from existing data; the BP neural network model can be used as the basic model of the coal blending coking debugging control parameter analysis model; Input the coke oven tail gas drying training set into the coal blending coking debugging control parameter analysis model for training with the target value as the target, and obtain the initial coal blending coking debugging control parameter analysis model; perform model verification on the initial coal blending coking debugging control parameter analysis model to obtain the initial coal blending coking debugging control parameter analysis model verification result; if the initial coal blending coking debugging control parameter analysis model verification result is passed, output the trained initial coal blending coking debugging control parameter analysis model as the coal blending coking debugging control parameter analysis model; otherwise, continue model training using the coke oven tail gas drying training set; By training the coal blending coking debugging control parameter analysis model and using the collected coke oven tail gas drying training samples, the coal drying process is precisely controlled and optimized, which not only improves the coke output and quality, reduces energy consumption and production costs, but also enhances the automation and intelligence level of production, and promotes the green and sustainable development of the coking industry. S3. Real-time acquisition of moisture information of the dehydrated coking wet coal to be analyzed and current coal blending and coking humidity control parameters, to obtain moisture information of the coal to be regulated and humidity control parameters of the coal blending and coking to be regulated; input the moisture information of the coal to be regulated, the coal blending and coking humidity control parameters to be regulated and the target coal moisture content into the coal blending and coking humidity control parameter optimization model for analysis, to obtain optimized coal blending and coking humidity control parameters, the coal blending and coking humidity control parameter optimization model includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer, and automatically adjusts and outputs the humidity control parameters most suitable for coal coking; the coal debugging process of the dehydrated coking wet coal to be analyzed is adjusted in real time using the optimized coal blending and coking humidity control parameters until the dehydrated coking wet coal to be analyzed meets the target coal moisture content; The coal blending and coking humidity control parameter optimization model in step S3 includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer; The data preprocessing layer is used to preprocess the moisture information of the coal material to be regulated and the humidity control parameters of the coal blending and coking to be regulated, and obtain the preprocessed moisture information of the coal material to be regulated and the preprocessed humidity control parameters of the coal blending and coking to be regulated; The feature prediction layer is used to perform prediction analysis based on the moisture information of the pre-processed coal to be regulated and the pre-processed coal blending and coking moisture control parameters to be regulated, and obtain the predicted target coal moisture content; The parameter optimization layer is used to compare the predicted target coal moisture content with the target coal moisture content. If the difference between the predicted target coal moisture content and the target coal moisture content is within the preset moisture difference threshold, the coal blending and coking humidity control parameters to be adjusted will continue to be used as the optimized coal blending and coking humidity control parameters; otherwise, the parameters are optimized according to the difference between the predicted target coal moisture content and the target coal moisture content to obtain the optimized coal blending and coking humidity control parameters; The result output layer is used to output the optimized coal blending and coking humidity control parameters; The specific steps of training the feature prediction layer in the coal blending and coking humidity control parameter optimization model include: Collect several groups of coal blending coking humidity control parameter prediction training samples, each group of coal blending coking humidity control parameter prediction training samples contains a group of target controlled coal moisture content, current coal moisture content and current coal blending coking humidity control parameters; use the target controlled coal moisture content as the prediction target value of each group of coal blending coking humidity control parameter prediction training samples; combine several groups of coal blending coking humidity control parameter prediction training samples to obtain a coal blending coking humidity control parameter prediction training set; Input the prediction training set of the humidity control parameter of the coking coal blending into the optimization model of the humidity control parameter of the coking coal blending to train the feature prediction layer and obtain the initial feature prediction layer; perform model evaluation on the initial feature prediction layer and obtain the model evaluation result of the initial feature prediction layer; if the model evaluation result of the initial feature prediction layer is passed, the initial feature prediction layer model is used as the feature prediction layer in the optimization model of the humidity control parameter of the coking coal blending; otherwise, continue to perform model training using the prediction training set of the humidity control parameter of the coking coal blending; Through real-time monitoring and prediction, real-time acquisition and analysis of moisture information of dehydrated coking wet coal and real-time adjustment of humidity control parameters are achieved to ensure that the moisture content of the coal meets the target requirements; the application of the feature prediction layer improves the prediction accuracy of changes in coal moisture content and provides reliable data support for parameter optimization; the parameter optimization layer automatically compares the prediction results with the target values ​​and optimizes the humidity control parameters, reducing manual operations and improving efficiency.

[0017] Example 2, a coal blending coking control parameter optimization system, see Figure 1 As shown, including: Coal blending and coking coal material determination module is used to deploy the initial coal material analysis model for coal blending and coking, and obtain the coal material information to be analyzed and the virtual model of the wet coal material to be coked based on the initial coal material analysis model for coal blending and coking and the wet coal material to be coked. The coal material information to be analyzed includes the moisture information and coal quality information of the coal material to be analyzed. The initial coal material analysis model for coal blending and coking includes a model construction layer, a volume analysis layer, a moisture determination layer and a result output layer, and provides comprehensive coal quality and moisture information to optimize the coal blending and coking process; The coal blending coking parameter output module is used to deploy the coal blending coking moisture control parameter analysis model, input the coal information to be analyzed and the virtual model of the wet coal to be coked into the coal blending coking moisture control parameter analysis model for analysis, and obtain the initial coal blending coking moisture control parameters and the target coal moisture content; the coal blending coking moisture control parameter analysis model includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer to ensure that the moisture content of the coal is adjusted to the optimal state, thereby optimizing the coking process; according to the initial coal blending coking moisture control parameters, the wet coal to be coked is subjected to coal moisture adjustment operation to obtain the dehydrated wet coal to be analyzed; The coal blending coking parameter optimization module is used to deploy the coal blending coking humidity control parameter optimization model, obtain the moisture information of the dehydrated coking wet coal to be analyzed and the current coal blending coking humidity control parameters in real time, and obtain the moisture information of the coal to be adjusted and the coal blending coking humidity control parameters to be adjusted; the moisture information of the coal to be adjusted, the coal blending coking humidity control parameters to be adjusted and the target coal moisture content are input into the coal blending coking humidity control parameter optimization model for analysis to obtain the optimized coal blending coking humidity control parameters, and the coal blending coking humidity control parameter optimization model includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer, which automatically adjusts and outputs the humidity control parameters most suitable for coal coking; the optimized coal blending coking humidity control parameters are used to adjust the coal commissioning process of the dehydrated coking wet coal to be analyzed in real time until the dehydrated coking wet coal to be analyzed meets the target coal moisture content.

[0018] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A method for optimizing coal blending coking control parameters, characterized in that: include: S1. Based on the initial coal analysis model for coal blending and coking and the wet coal to be coked, the coal information to be analyzed and the virtual model of the wet coal to be coked are obtained. The coal information to be analyzed includes the moisture information of the coal to be analyzed and the coal quality information of the coal to be analyzed. The initial coal analysis model for coal blending and coking includes a model construction layer, a volume analysis layer, a moisture determination layer and a result output layer, providing comprehensive coal quality and moisture information to optimize the coal blending and coking process; S2. Input the coal information to be analyzed and the virtual model of the wet coal to be coked into the coal blending and coking moisture control parameter analysis model for analysis, and obtain the initial coal blending and coking moisture control parameters and the target coal moisture content; the coal blending and coking moisture control parameter analysis model includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer to ensure that the moisture content of the coal is adjusted to the optimal state, thereby optimizing the coking process; according to the initial coal blending and coking moisture control parameters, the wet coal to be coked is subjected to coal moisture adjustment operation to obtain the dehydrated wet coal to be analyzed; S3. Real-time acquisition of moisture information of the dehydrated coking wet coal to be analyzed and current coal blending and coking humidity control parameters, to obtain moisture information of the coal to be adjusted and humidity control parameters of the coal blending and coking to be adjusted; input the moisture information of the coal to be adjusted, humidity control parameters of the coal blending and coking to be adjusted and target moisture content of the coal to be adjusted into the coal blending and coking humidity control parameter optimization model for analysis, to obtain optimized humidity control parameters of the coal blending and coking, the coal blending and coking humidity control parameter optimization model includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer, which automatically adjusts and outputs the humidity control parameters most suitable for coal coking; the coal commissioning process of the dehydrated coking wet coal to be analyzed is adjusted in real time using the optimized coal blending and coking humidity control parameters, until the dehydrated coking wet coal to be analyzed meets the target moisture content of the coal.

2. A method for optimizing coal blending coking control parameters according to claim 1, characterized in that: The initial coal material analysis model for coal blending and coking in step S1 includes a model building layer, a volume analysis layer, a moisture measurement layer and a result output layer; The model building layer is used to scan the transported wet coal to be coked using point cloud technology to obtain point cloud data of the wet coal to be coked; Use the point cloud data of wet coal to be coked and digital twin technology to build a virtual model of wet coal to be coked; The volume analysis layer is used to perform volume analysis based on the virtual model of the wet coal to be coked, and obtain the coal quality information of the coal to be analyzed; The moisture determination layer is used to monitor the moisture content of the wet coal to be coked and obtain the moisture information of the coal to be analyzed; The result output layer is used to combine the coal quality information and the moisture information of the coal to be analyzed to obtain the coal information to be analyzed.

3. A method for optimizing coal blending coking control parameters according to claim 2, characterized in that: The coal blending coking debugging control parameter analysis model in step S2 includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer; The data preprocessing layer is used to preprocess the coal information to be analyzed to obtain preprocessed coal information; The target value determination layer is used to calculate the target moisture content of the coal according to the virtual model of the wet coal to be coked; The tail gas control layer is used to perform characteristic analysis based on the target coal moisture content and pre-treated coal information to obtain the initial coal blending coking coke oven tail gas intake volume, so as to reduce the moisture content of the wet coal to be coked to the target coal moisture content, and determine the initial coal blending coking humidity control parameters based on the initial coal blending coke oven tail gas intake volume; The result output layer is used to output the initial coal blending and coking humidity control parameters.

4. A method for optimizing coal blending coking control parameters according to claim 3, characterized in that: The specific steps to determine the target coal moisture content include: According to the virtual model of wet coal to be coked, K target coal moisture content individuals W are constructed. k ; Each target coal moisture content individual W k The target coal moisture content to be optimized is included according to the virtual model of wet coal to be coked; the K target coal moisture content individuals W k Combine to obtain the target coal moisture content iterative population; set the maximum number of iterations; According to the target coal moisture content, iterate the target coal moisture content individuals W in the population k Perform simulation calculation to obtain the target coal moisture content individual W k The fitness Y k ; The specific steps of simulation calculation are: According to the virtual model of wet coal to be coked, simulation is performed. When the moisture content of the wet coal to be coked in the virtual model of wet coal to be coked reaches the target moisture content of the individual coal W k When the target coal moisture content to be optimized is , a simulated coal blending coking operation is performed to obtain the simulated coke yield M k And simulated exhaust gas volume Q k ; Using formula F k =W1*M k +W2*(1 / Q k ) to obtain the evaluation index F k , W1 and W2 are weight coefficients; the evaluation index F k As the target coal moisture content individual W k The fitness Y k ; When the maximum number of iterations is reached, the target coal moisture content individual W corresponding to the maximum fitness is output. k , which is the optimal target coal moisture content individual; the target coal moisture content to be optimized that is fitted according to the virtual model of the wet coal to be coked in the optimal target coal moisture content individual is used as the target coal moisture content.

5. A method for optimizing coal blending coking control parameters according to claim 4, characterized in that: The specific steps of training the coal blending coking commissioning control parameter analysis model include: Collect several groups of coke oven tail gas drying training samples; each group of coke oven tail gas drying training samples contains the volume of wet coal to be dried, the moisture content before drying and the target moisture content, and marks the coke oven tail gas content required for drying as the target value; combine several groups of coke oven tail gas drying training samples to obtain a coke oven tail gas drying training set; The coke oven exhaust gas drying training set is input into the coal blending coking debugging control parameter analysis model for training with the target value as the target, so as to obtain the initial coal blending coking debugging control parameter analysis model; the initial coal blending coking debugging control parameter analysis model is model verified to obtain the initial coal blending coking debugging control parameter analysis model verification result; if the initial coal blending coking debugging control parameter analysis model verification result is passed, the trained initial coal blending coking debugging control parameter analysis model is output as the coal blending coking debugging control parameter analysis model; otherwise, the model training is continued using the coke oven exhaust gas drying training set.

6. A method for optimizing coal blending coking control parameters according to claim 5, characterized in that: The coal blending and coking humidity control parameter optimization model in step S3 includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer; The data preprocessing layer is used to preprocess the moisture information of the coal material to be regulated and the humidity control parameters of the coal blending and coking to be regulated, and obtain the preprocessed moisture information of the coal material to be regulated and the preprocessed humidity control parameters of the coal blending and coking to be regulated; The feature prediction layer is used to perform prediction analysis based on the moisture information of the pre-processed coal to be regulated and the pre-processed coal blending and coking moisture control parameters to be regulated, and obtain the predicted target coal moisture content; The parameter optimization layer is used to compare the predicted target coal moisture content with the target coal moisture content. If the difference between the predicted target coal moisture content and the target coal moisture content is within the preset moisture difference threshold, the coal blending and coking humidity control parameters to be adjusted will continue to be used as the optimized coal blending and coking humidity control parameters; otherwise, the parameters are optimized according to the difference between the predicted target coal moisture content and the target coal moisture content to obtain the optimized coal blending and coking humidity control parameters; The result output layer is used to output the optimized coal blending and coking humidity control parameters.

7. A method for optimizing coal blending coking control parameters according to claim 6, characterized in that: The specific steps of training the feature prediction layer in the coal blending and coking humidity control parameter optimization model include: Collect several groups of coal blending coking humidity control parameter prediction training samples, each group of coal blending coking humidity control parameter prediction training samples contains a group of target controlled coal moisture content, current coal moisture content and current coal blending coking humidity control parameters; use the target controlled coal moisture content as the prediction target value of each group of coal blending coking humidity control parameter prediction training samples; combine several groups of coal blending coking humidity control parameter prediction training samples to obtain a coal blending coking humidity control parameter prediction training set; The training set of prediction of humidity control parameters for coking with coal blending is input into the optimization model of humidity control parameters for coking with coal blending to train the feature prediction layer and obtain the initial feature prediction layer; the model of the initial feature prediction layer is evaluated to obtain the model evaluation result of the initial feature prediction layer; if the model evaluation result of the initial feature prediction layer is passed, the initial feature prediction layer model is used as the feature prediction layer in the optimization model of humidity control parameters for coking with coal blending; otherwise, the model training is continued using the training set of prediction of humidity control parameters for coking with coal blending.

8. A coal blending coking control parameter optimization system, characterized in that: The system applies a method for optimizing coal blending coking control parameters as described in any one of claims 1 to 7, comprising: Coal blending and coking coal material determination module is used to deploy the initial coal material analysis model for coal blending and coking, and obtain the coal material information to be analyzed and the virtual model of the wet coal material to be coked based on the initial coal material analysis model for coal blending and coking and the wet coal material to be coked. The coal material information to be analyzed includes the moisture information and coal quality information of the coal material to be analyzed. The initial coal material analysis model for coal blending and coking includes a model construction layer, a volume analysis layer, a moisture determination layer and a result output layer, and provides comprehensive coal quality and moisture information to optimize the coal blending and coking process; The coal blending coking parameter output module is used to deploy the coal blending coking moisture control parameter analysis model, input the coal information to be analyzed and the virtual model of the wet coal to be coked into the coal blending coking moisture control parameter analysis model for analysis, and obtain the initial coal blending coking moisture control parameters and the target coal moisture content; the coal blending coking moisture control parameter analysis model includes a data preprocessing layer, a target value determination layer, an exhaust gas control layer and a result output layer to ensure that the moisture content of the coal is adjusted to the optimal state, thereby optimizing the coking process; according to the initial coal blending coking moisture control parameters, the wet coal to be coked is subjected to coal moisture adjustment operation to obtain the dehydrated wet coal to be analyzed; The coal blending coking parameter optimization module is used to deploy the coal blending coking humidity control parameter optimization model, obtain the moisture information of the dehydrated coking wet coal to be analyzed and the current coal blending coking humidity control parameters in real time, and obtain the moisture information of the coal to be adjusted and the coal blending coking humidity control parameters to be adjusted; the moisture information of the coal to be adjusted, the coal blending coking humidity control parameters to be adjusted and the target coal moisture content are input into the coal blending coking humidity control parameter optimization model for analysis to obtain the optimized coal blending coking humidity control parameters, and the coal blending coking humidity control parameter optimization model includes a data preprocessing layer, a feature prediction layer, a parameter optimization layer and a result output layer, which automatically adjusts and outputs the humidity control parameters most suitable for coal coking; the optimized coal blending coking humidity control parameters are used to adjust the coal commissioning process of the dehydrated coking wet coal to be analyzed in real time until the dehydrated coking wet coal to be analyzed meets the target coal moisture content.

Citation Information

Cited By

  • Coking index monitoring analysis method, system and equipment based on small coke oven and medium

    CN120044213A

  • Coking moisture control system based on atomization spraying

    CN120722853A