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

Abstract

The present invention discloses a method, system, equipment and medium for monitoring and analyzing coking indicators based on a small coke oven. Initial coal blending ratio data and corresponding experimental adjustment data are obtained; the experimental process is controlled based on the initial coal blending ratio data and the corresponding experimental adjustment data, and the experimental process data and experimental result data are obtained in real time; comprehensive result data is generated based on the initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data; after conducting multiple experiments, the target coal blending ratio is determined based on the corresponding comprehensive result data of each experiment. The present invention sets the initial numerical value of the experiment, measures various data parameters in the process, and detects the characteristic parameters of the coke after the experiment. Based on the analysis and statistics of the result data, the target coal blending ratio is scientifically determined, and at the same time, it is ensured that the characteristic parameters of the coke under the coal blending ratio have a good correlation with the large coke oven.

Description

Technical Field

[0001] The present invention relates to the field of coke production, and in particular to a coking index monitoring and analysis method, system, computing device and computer storage medium based on a small coke oven. Background Art

[0002] The steel industry is an important basic industry of the national economy. However, with the strengthening of environmental awareness and the adjustment of energy structure, traditional coking technology can no longer meet the needs of modern steel production due to its heavy pollution and low production efficiency.

[0003] At the same time, market demands for coke quality are becoming increasingly stringent, requiring incoming clean coal to possess low ash, low sulfur, and excellent coking properties. This has led to a significant increase in production costs. To address this, steel companies are seeking ways to optimize coal blending ratios to reduce overall production costs while ensuring coke quality and environmental protection requirements. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a coking index monitoring and analysis method based on a small coke oven and a corresponding coking index monitoring and analysis system based on a small coke oven, a computing device and a computer storage medium.

[0005] According to one aspect of the present invention, a method for monitoring and analyzing coking indicators based on a small coke oven is provided, the method comprising:

[0006] Obtain initial coal blending ratio data and corresponding experimental adjustment data;

[0007] Control the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and obtain the experimental process data and experimental result data in real time;

[0008] Generate comprehensive result data based on initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data;

[0009] After conducting multiple experiments, the target coal blending ratio is determined based on the corresponding comprehensive result data of each experiment.

[0010] In the above solution, the obtaining of the initial coal blending ratio data and the corresponding experimental adjustment data further includes:

[0011] The initial coal blending ratio data is the mixing ratio of different coals preset by the user; the experimental adjustment data at least includes the coke oven temperature, the pressure inside the oven and the load pressure.

[0012] In the above scheme, the control of the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and the real-time acquisition of the experimental process data and the experimental result data further include:

[0013] Start the experiment based on the initial coal blending ratio data and the corresponding experimental adjustment data;

[0014] During the experiment, the operating parameters of the small coke oven with load were controlled based on the experimental adjustment data;

[0015] The experimental process is completed according to the operating parameters and the experimental process data is obtained in real time; wherein the experimental process data at least includes the temperature, pressure, oxygen content and poisonous gas data in the furnace.

[0016] In the above scheme, the control of the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and the real-time acquisition of the experimental process data and the experimental result data further include:

[0017] After the experiment, the experimental product is analyzed for its composition to determine the proportion of coke in the experimental product;

[0018] The coke yield is calculated based on the weight of the experimental raw materials and the weight of the coke in the experimental product;

[0019] Analyze the coke in the experimental product to determine the coke characteristic parameters; the coke characteristic parameters at least include the coke mechanical strength M25 and M10 and the coke hot strength index CRI and CSR;

[0020] The experimental result data are obtained by comprehensively considering the coke ratio, coke yield and coke characteristic parameters.

[0021] In the above scheme, after conducting multiple experiments, determining the target coal blending ratio based on the comprehensive result data corresponding to each experiment further includes:

[0022] Conduct multiple experiments by setting different initial coal blending ratio data and corresponding experimental adjustment data;

[0023] According to the comprehensive result data corresponding to each time, the target experimental data table is generated according to the changes in the initial coal blending ratio data and the corresponding experimental adjustment data;

[0024] According to user needs, the target coal blending ratio is determined from the target experimental data table.

[0025] In the above solution, the method further includes:

[0026] Establishing a toxic gas generation model based on deep learning and training the toxic gas generation model by constructing a training set to obtain a trained toxic gas generation model;

[0027] Obtain the initial coal blending ratio data of the current experiment and the corresponding experimental adjustment data, and collect the current release component data according to the sensors set at the preset positions;

[0028] Input the current initial coal blending ratio data, experimental adjustment data, and released component data into the trained toxic gas generation model to predict the type and generation time of toxic gases generated during the subsequent process of the current experiment and obtain prediction results;

[0029] Based on the prediction results, the safety devices corresponding to the small coke ovens are controlled to be opened or closed.

[0030] In the above solution, the method further comprises:

[0031] The poisonous gas generation model determines the difference between the predicted value and the true value through the mean square error loss function MSE during the training process. The mean square error loss function is

[0032]

[0033] in, The number of poisonous gas types; For the Sample data; For the The predicted value of sample data, For the The actual value of the sample data;

[0034] For each type of toxic gas, calculate the difference between the corresponding predicted value and the actual value, and determine the adjustment coefficient corresponding to each type of toxic gas ;in, For the Adjustment coefficient for each type of toxic gas;

[0035] The model correction coefficient is generated based on the adjustment coefficient, and the model is corrected to complete the model training. The model correction coefficient is

[0036]

[0037] in, and Respectively The average actual value and average predicted value of sample data of various types of toxic gases; is the learning rate.

[0038] According to another aspect of the present invention, a coking index monitoring and analysis system based on a small coke oven is provided, comprising: an initial data determination module, an experimental operation module, a data processing module and a target determination module; wherein,

[0039] The initial data determination module is used to obtain initial coal blending ratio data and corresponding experimental adjustment data;

[0040] The experimental operation module is used to control the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and obtain the experimental process data and experimental result data in real time;

[0041] The data processing module is used to generate comprehensive result data based on the initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data;

[0042] The target determination module is used to determine the target coal blending ratio based on the comprehensive result data corresponding to each experiment after performing multiple experiments.

[0043] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0044] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned method for monitoring and analyzing coking indicators based on a small coke oven.

[0045] According to another aspect of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned method for monitoring and analyzing coking indicators based on a small coke oven.

[0046] According to the technical solution provided by the present invention, initial coal blending ratio data and corresponding experimental adjustment data are obtained; the experimental process is controlled based on the initial coal blending ratio data and the corresponding experimental adjustment data, and the experimental process data and experimental result data are obtained in real time; comprehensive result data are generated based on the initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data; after conducting multiple experiments, the target coal blending ratio is determined based on the corresponding comprehensive result data of each experiment. Based on the technical solution provided by the present invention, by obtaining the initial coal blending ratio data and the corresponding experimental adjustment data, the initial operating parameters of the current experiment are determined, and the experimental process is controlled according to the experimental adjustment data to keep it within the preset reaction range, effectively reducing the risk of errors in the experimental results due to parameter changes, ensuring the stability of the experiment, and thus improving the accuracy of the experimental results; by analyzing the experimental products, the coke yield and the corresponding characteristic parameters are determined, and the actual quality of the output coke is accurately determined, which is helpful for the subsequent scientific selection of production conditions and coal blending ratio; based on multiple experiments of control variables, the experimental data corresponding to each experiment are obtained, and an experimental data table is comprehensively generated, thereby, based on user needs, the target coal blending ratio that meets their needs can be intuitively and clearly selected, and the production process under different subsequent needs can be better scientifically guided. In addition, by constructing a toxic gas generation model, the generation time and amount of toxic gases in the experimental process are accurately predicted, and the corresponding pollution treatment device is controlled to start operation in advance accordingly, which better ensures the safety of the experimental operation and reduces the environmental pollution ultimately generated by the experiment. At the same time, the generation and emission of pollutants in the actual production process are predicted and effective guidance is given.

[0047] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 A schematic flow chart of a method for monitoring and analyzing coking indicators based on a small coke oven according to one embodiment of the present invention is shown;

[0051] Figure 2A schematic flow chart of an experimental operation and data acquisition method based on a small coke oven according to one embodiment of the present invention is shown;

[0052] Figure 3 A schematic flow chart of a method for predicting the generation of toxic gases according to an embodiment of the present invention is shown;

[0053] Figure 4 A structural block diagram of a coking index monitoring and analysis system based on a small coke oven according to one embodiment of the present invention is shown;

[0054] Figure 5 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0055] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0056] Figure 1 A flow chart of a method for monitoring and analyzing coking indicators based on a small coke oven according to one embodiment of the present invention is shown. The method comprises the following steps:

[0057] Step S101: Acquire initial coal blending ratio data and corresponding experimental adjustment data.

[0058] Preferably, the initial coal blending ratio data is a user-preset mixing ratio of different coals; and the experimental adjustment data includes at least the coke oven temperature, the pressure inside the oven, and the load pressure, wherein the load pressure is the pressure applied to the experimental sample inside the oven.

[0059] Preferably, the initial coal blending ratio data also includes the weights corresponding to different coals and the overall weight of the sample.

[0060] Step S102: Control the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and obtain the experimental process data and experimental result data in real time.

[0061] Step S103: generating comprehensive result data according to the initial coal blending ratio data, the experimental adjustment data, the experimental process data and the experimental result data.

[0062] Preferably, the experimental result data at least includes the ingredients contained in the experimental product and the corresponding weights and proportions.

[0063] Step S104: After multiple experiments are performed, a target coal blending ratio is determined based on the comprehensive result data corresponding to each experiment.

[0064] Specifically, multiple experiments are conducted by setting different initial coal blending ratio data and corresponding experimental adjustment data;

[0065] According to the comprehensive result data corresponding to each time, the target experimental data table is generated according to the changes in the initial coal blending ratio data and the corresponding experimental adjustment data;

[0066] According to user needs, the target coal blending ratio is determined from the target experimental data table.

[0067] Preferably, each experiment is based on the control variable method, and different initial coal blending ratios or experimental adjustment data are set to complete the experiment; the experimental process data and experimental result data generated by each experiment are listed and sorted to generate a target experimental data table;

[0068] Users can determine the coal blending ratio that best meets their needs based on the required components and their proportions.

[0069] According to the coking index monitoring and analysis method based on a small coke oven provided in this embodiment, initial coal blending ratio data and corresponding experimental adjustment data are obtained; the experimental process is controlled based on the initial coal blending ratio data and the corresponding experimental adjustment data, and experimental process data and experimental result data are obtained in real time; comprehensive result data is generated based on the initial coal blending ratio data, experimental adjustment data, experimental process data, and experimental result data; after multiple experiments are conducted, the target coal blending ratio is determined based on the corresponding comprehensive result data of each experiment. According to the coking index monitoring and analysis method based on a small coke oven provided in this embodiment, the initial operating parameters of the current experiment are determined by obtaining the initial coal blending ratio data and the corresponding experimental adjustment data, and the experimental process is controlled according to the experimental adjustment data to keep it within a preset reaction range, effectively reducing the risk of error in the experimental results due to parameter changes, ensuring the stability of the experiment, and thereby improving the accuracy of the experimental results; based on multiple experiments of control variables, the experimental data corresponding to each experiment are obtained, and an experimental data table is comprehensively generated. Therefore, based on the user's needs, a target coal blending ratio that meets their needs can be intuitively and clearly selected, and better scientific guidance can be provided for subsequent production processes under different needs.

[0070] Figure 2 A schematic flow chart of an experimental operation and data acquisition method based on a small coke oven according to one embodiment of the present invention is shown;

[0071] like Figure 2 As shown, the method includes the following steps:

[0072] Step S201: starting an experiment based on the initial coal blending ratio data and the corresponding experimental adjustment data.

[0073] Step S202 : During the experiment, the operating parameters of the small loaded coke oven are controlled based on the experimental adjustment data.

[0074] Specifically, based on experimental data, the temperature and pressure inside the load-carrying small coke oven are controlled, and the coal charging and / or coke pushing mechanism is controlled.

[0075] Preferably, the coal cakes are heated by three-stage heating; the temperature and pressure in the furnace are collected using temperature sensors and pressure sensors, and based on the collected temperature and pressure data, the heating system is adjusted and controlled to ensure the stability of the pressure and temperature in the furnace.

[0076] Step S203: Complete the experiment process according to the operating parameters and obtain the experiment process data in real time.

[0077] Preferably, the experimental process data at least include temperature, pressure, oxygen content and poisonous gas data in the furnace.

[0078] Furthermore, toxic gas data may include toxic gas types and their corresponding concentrations. These toxic gas types may include at least hydrogen sulfide, ammonia, carbon monoxide, and benzene. Users can select and configure sensors to obtain data for other toxic gas types based on their needs, without limitation.

[0079] Step S204: After the experiment is completed, the experimental product is analyzed for components to obtain experimental result data.

[0080] Specifically, based on the component analysis of the experimental product, the proportion of coke in the experimental product is determined;

[0081] The coke yield is calculated based on the weight of the experimental raw materials and the weight of the coke in the experimental product;

[0082] Analyze the coke in the experimental product to determine the coke characteristic parameters; the coke characteristic parameters include at least the coke mechanical strength M25 and M10, and the coke hot strength index CRI (Coke Reactivity Index, coke reactivity) and CSR (Coke Strength Retention, post-reaction strength);

[0083] The experimental result data are obtained by comprehensively considering the coke ratio, coke yield and coke characteristic parameters.

[0084] Preferably, the total weight of the experimental product and the weight of the coke are obtained, and the coke ratio is obtained by the ratio of the coke weight to the total weight of the experimental product;

[0085] The mechanical strength of coke M25 and M10 can be measured using a coke mechanical strength measuring drum machine;

[0086] The drum test was performed after heating in a high-temperature reactor to obtain CRI and CSR data.

[0087] According to the above method, the experimental process can be controlled to keep it within the preset reaction range, effectively reducing the risk of errors in the experimental results due to parameter changes, ensuring the stability of the experiment, and thus improving the accuracy of the experimental results; by obtaining process data, the changes in individual parameters during the experiment can be effectively understood, the production process can be guided, and the pollutants that may be generated in the process can be understood to facilitate subsequent cleaning treatment; by analyzing the experimental products, the coke yield and the corresponding characteristic parameters can be determined, and the actual quality of the output coke can be accurately determined, which will help in the subsequent scientific selection of production conditions and coal blending ratios.

[0088] Figure 3 A schematic flow chart of a method for predicting the generation of toxic gases according to an embodiment of the present invention is shown;

[0089] like Figure 3 As shown, the method includes the following steps:

[0090] Step S301: Establish a toxic gas generation model based on deep learning and train the toxic gas generation model by constructing a training set to obtain a trained toxic gas generation model.

[0091] Specifically, a training set is constructed based on historically collected initial coal blending ratio data, experimental adjustment data, and experimental process data.

[0092] Preferably, the toxic gas generation model determines the difference between the predicted value and the true value through the mean square error loss function MSE during the training process, and the mean square error loss function is

[0093]

[0094] in, The number of poisonous gas types; For the Sample data; For the The predicted value of sample data, For the The actual value of the sample data;

[0095] For each type of toxic gas, calculate the difference between the corresponding predicted value and the actual value, and determine the adjustment coefficient corresponding to each type of toxic gas ;in, For the Adjustment coefficient for each type of toxic gas;

[0096] The model correction coefficient is generated based on the adjustment coefficient, and the model is corrected to complete the model training. The model correction coefficient is

[0097]

[0098] in, and Respectively The average actual value and average predicted value of sample data of various types of toxic gases; is the learning rate.

[0099] Step S302: acquiring the initial coal blending ratio data of the current experiment and the corresponding experimental adjustment data, and collecting the current released component data according to the sensor set at the preset position.

[0100] Specifically, the sensor can be selected according to needs to measure specific pollution components.

[0101] Step S303: input the current initial coal blending ratio data, experimental adjustment data and released component data into the trained poisonous gas generation model, predict the type and generation time of poisonous gas generated in the subsequent process of the current experiment, and obtain a prediction result.

[0102] Step S304: Based on the prediction result, the safety device corresponding to the small coke oven is controlled to be turned on or off.

[0103] Preferably, based on the prediction results, the safety device is opened in advance and closed later, and the pollution components are measured again using the sensor before closing. After confirming that the corresponding pollutants do not exist, the safety device is confirmed to be closed.

[0104] According to the above method, by constructing a toxic gas generation model, the time and amount of toxic gas generation during the experiment are accurately predicted, and the corresponding pollution treatment equipment is controlled to start operation in advance, which better ensures the safety of the experimental operation and reduces the environmental pollution ultimately caused by the experiment. At the same time, the generation and emission of pollutants in the actual production process are predicted, and effective guidance is given.

[0105] Figure 4 A structural block diagram of a coking index monitoring and analysis system based on a small coke oven according to one embodiment of the present invention is shown;

[0106] like Figure 4 As shown, the system includes: an initial data determination module 401, an experiment operation module 402, a data processing module 403 and a target determination module 404; wherein,

[0107] The initial data determination module 401 is used to obtain initial coal blending ratio data and corresponding experimental adjustment data.

[0108] Specifically, the initial data determination module 401 is further configured to:

[0109] The initial coal blending ratio data is the mixing ratio of different coals preset by the user; the experimental adjustment data at least includes the coke oven temperature, the pressure inside the oven and the load pressure.

[0110] The experiment operation module 402 is used to control the experiment process based on the initial coal blending ratio data and the corresponding experiment adjustment data, and to obtain the experiment process data and the experiment result data in real time.

[0111] Specifically, the experiment running module 402 is further used to:

[0112] Start the experiment based on the initial coal blending ratio data and the corresponding experimental adjustment data;

[0113] During the experiment, the operating parameters of the small coke oven with load were controlled based on the experimental adjustment data;

[0114] The experimental process is completed according to the operating parameters and the experimental process data is obtained in real time; wherein the experimental process data at least includes the temperature, pressure, oxygen content and poisonous gas data in the furnace.

[0115] Specifically, the experiment running module 402 is further used to:

[0116] After the experiment, the experimental product is analyzed for its composition to determine the proportion of coke in the experimental product;

[0117] The coke yield is calculated based on the weight of the experimental raw materials and the weight of the coke in the experimental product;

[0118] Analyze the coke in the experimental product to determine the coke characteristic parameters; the coke characteristic parameters at least include the coke mechanical strength M25 and M10 and the coke hot strength index CRI and CSR;

[0119] The experimental result data are obtained by comprehensively considering the coke ratio, coke yield and coke characteristic parameters.

[0120] Specifically, the experiment running module 402 is further used to:

[0121] Establish a toxic gas generation model based on deep learning and train the toxic gas generation model by constructing a training set to obtain a trained toxic gas generation model; (Construct a training set based on historically collected initial coal ratio data, experimental adjustment data, and experimental process data)

[0122] Obtain the initial coal blending ratio data of the current experiment and the corresponding experimental adjustment data, and collect the current release component data according to the sensors set at the preset positions;

[0123] Input the current initial coal blending ratio data, experimental adjustment data, and released component data into the trained toxic gas generation model to predict the type and generation time of toxic gases generated during the subsequent process of the current experiment and obtain prediction results;

[0124] Based on the prediction results, the safety devices corresponding to the small coke ovens are controlled to be opened or closed.

[0125] Preferably, the experiment running module 402 is further configured to:

[0126] The poisonous gas generation model determines the difference between the predicted value and the true value through the mean square error loss function MSE during the training process. The mean square error loss function is

[0127]

[0128] in, The number of poisonous gas types; For the Sample data; For the The predicted value of sample data, For the The actual value of the sample data;

[0129] For each type of toxic gas, calculate the difference between the corresponding predicted value and the actual value, and determine the adjustment coefficient corresponding to each type of toxic gas ;in, For the Adjustment coefficient for each type of toxic gas;

[0130] The model correction coefficient is generated based on the adjustment coefficient, and the model is corrected to complete the model training. The model correction coefficient is

[0131]

[0132] in, and Respectively The average actual value and average predicted value of sample data of various types of toxic gases; is the learning rate.

[0133] The data processing module 403 is used to generate comprehensive result data according to the initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data.

[0134] The target determination module 404 is used to determine the target coal blending ratio based on the comprehensive result data corresponding to each experiment after performing multiple experiments.

[0135] Specifically, the target determination model 404 is further used to:

[0136] Conduct multiple experiments by setting different initial coal blending ratio data and corresponding experimental adjustment data;

[0137] According to the comprehensive result data corresponding to each time, the target experimental data table is generated according to the changes in the initial coal blending ratio data and the corresponding experimental adjustment data;

[0138] According to user needs, the target coal blending ratio is determined from the target experimental data table.

[0139] The coking index monitoring and analysis system based on the small coke oven provided in this embodiment includes: an initial data determination module, an experimental operation module, a data processing module and a target determination module; wherein the initial data determination module is used to obtain initial coal blending ratio data and corresponding experimental adjustment data; the experimental operation module is used to control the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and obtain experimental process data and experimental result data in real time; the data processing module is used to generate comprehensive result data based on the initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data; the target determination module is used to determine the target coal blending ratio based on the corresponding comprehensive result data of each experiment after conducting multiple experiments. The coking index monitoring and analysis system based on the small coke oven provided by this embodiment obtains the initial coal ratio data and the corresponding experimental adjustment data to determine the initial operating parameters of the current experiment, and controls the experimental process according to the experimental adjustment data to keep it within the preset reaction range, effectively reducing the risk of experimental results errors due to parameter changes, ensuring the stability of the experiment, and thus improving the accuracy of the experimental results; by analyzing the experimental products, the coke yield and the corresponding characteristic parameters are determined, and the actual quality of the output coke is accurately determined, which is helpful for the subsequent scientific selection of production conditions and coal ratio; based on multiple experiments of control variables, the experimental data corresponding to each experiment are obtained, and an experimental data table is comprehensively generated. Therefore, based on user needs, the target coal ratio that meets their needs can be intuitively and clearly selected, and the subsequent production process under different needs can be better scientifically guided. In addition, by constructing a toxic gas generation model, the generation time and amount of toxic gases during the experiment are accurately predicted, and the corresponding pollution treatment device is controlled to start and operate in advance based on this, which better ensures the safety of the experimental operation and reduces the environmental pollution ultimately caused by the experiment. At the same time, the generation and emission of pollutants in the actual production process are predicted and effective guidance is provided.

[0140] The present invention also provides a non-volatile computer storage medium, which stores at least one executable instruction. The executable instruction can execute a coking index monitoring and analysis method based on a small coke oven in any of the above method embodiments.

[0141] Figure 5 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0142] like Figure 5 As shown, the computing device may include: a processor (processor) 502 , a communications interface (Communications Interface) 504 , a memory (memory) 506 , and a communication bus 508 .

[0143] in:

[0144] The processor 502 , the communication interface 504 , and the memory 506 communicate with each other via a communication bus 508 .

[0145] The communication interface 504 is used to communicate with other devices such as clients or other servers.

[0146] The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned embodiment of the coking index monitoring and analysis method based on a small coke oven.

[0147] Specifically, the program 510 may include program codes, which include computer operating instructions.

[0148] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in a computing device may be of the same type, such as one or more CPUs, or may be of different types, such as one or more CPUs and one or more ASICs.

[0149] The memory 506 is used to store the program 510. The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0150] Program 510 can specifically be used to cause processor 502 to execute a method for monitoring and analyzing coking indicators based on a small coke oven, as described in any of the above-described method embodiments. The specific implementation of each step in program 510 can be found in the corresponding descriptions of the corresponding steps and units in the above-described method for monitoring and analyzing coking indicators based on a small coke oven, and will not be repeated here. Those skilled in the art will clearly understand that, for ease and brevity of description, the specific operating processes of the devices and modules described above can refer to the corresponding process descriptions in the above-described method embodiments, and will not be repeated here.

[0151] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general-purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0152] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0153] Similarly, it should be understood that in order to streamline the present disclosure and aid understanding of one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims that follow the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the invention.

[0154] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0155] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0156] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in accordance with the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing a portion or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0157] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for monitoring and analyzing coking indicators based on a small coke oven, comprising: Obtain initial coal blending ratio data and corresponding experimental adjustment data; Based on the initial coal blending ratio data and the corresponding experimental adjustment data, the experimental process is controlled, and the experimental process data and experimental result data are obtained in real time; wherein, a toxic gas generation model based on deep learning is established and the toxic gas generation model is trained by constructing a training set to obtain a trained toxic gas generation model; wherein, the toxic gas generation model determines the difference between the predicted value and the actual value through the mean square error loss function MAE during the training process, and the mean square error loss function is in, The number of sample data for poisonous gases; For the Sample data; For the The predicted value of sample data, For the The actual value of the sample data; For each type of toxic gas, calculate the difference between the corresponding predicted value and the actual value, and determine the adjustment coefficient corresponding to each type of toxic gas ;in, For the Adjustment coefficient for each type of toxic gas; The model correction coefficient is generated based on the adjustment coefficient, and the model is corrected to complete the model training. The model correction coefficient is in, The number of poisonous gas types; and Respectively The average actual value and average predicted value of sample data of various types of toxic gases; is the learning rate; Obtain the initial coal blending ratio data of the current experiment and the corresponding experimental adjustment data, and collect the current release component data according to the sensors set at the preset positions; Input the current initial coal blending ratio data, experimental adjustment data, and released component data into the trained toxic gas generation model to predict the type and generation time of toxic gases generated during the subsequent process of the current experiment and obtain prediction results; Based on the prediction results, the safety devices corresponding to the small coke ovens are controlled to be turned on or off; Generate comprehensive result data based on initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data; After conducting multiple experiments, the target coal blending ratio is determined based on the corresponding comprehensive result data of each experiment.

2. The method according to claim 1, characterized in that The obtaining of the initial coal blending ratio data and the corresponding experimental adjustment data further includes: The initial coal blending ratio data is the mixing ratio of different coals preset by the user; the experimental adjustment data at least includes the coke oven temperature, the pressure inside the oven and the load pressure.

3. The method according to claim 1, characterized in that The controlling of the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and obtaining the experimental process data and the experimental result data in real time, further includes: Start the experiment based on the initial coal blending ratio data and the corresponding experimental adjustment data; During the experiment, the operating parameters of the small coke oven with load were controlled based on the experimental adjustment data; The experimental process is completed according to the operating parameters and the experimental process data is obtained in real time; wherein the experimental process data at least includes the temperature, pressure, oxygen content and poisonous gas data in the furnace.

4. The method according to claim 1, wherein The controlling of the experimental process based on the initial coal blending ratio data and the corresponding experimental adjustment data, and obtaining the experimental process data and the experimental result data in real time, further includes: After the experiment, the experimental product is analyzed for its composition to determine the proportion of coke in the experimental product; The coke yield is calculated based on the weight of the experimental raw materials and the weight of the coke in the experimental product; Analyze the coke in the experimental product to determine the coke characteristic parameters; the coke characteristic parameters at least include the coke mechanical strength M25 and M10 and the coke hot strength index CRI and CSR; The experimental result data are obtained by comprehensively considering the coke ratio, coke yield and coke characteristic parameters.

5. The method according to claim 1, wherein After conducting multiple experiments, determining the target coal blending ratio based on the comprehensive result data corresponding to each experiment further includes: Conduct multiple experiments by setting different initial coal blending ratio data and corresponding experimental adjustment data; According to the comprehensive result data corresponding to each time, the target experimental data table is generated according to the changes in the initial coal blending ratio data and the corresponding experimental adjustment data; According to user needs, the target coal blending ratio is determined from the target experimental data table.

6. A coking index monitoring and analysis system based on a small coke oven, comprising: Initial data determination module, experiment operation module, data processing module and target determination module; among them, The initial data determination module is used to obtain initial coal blending ratio data and corresponding experimental adjustment data; The experimental operation module is used to control the experimental process based on the initial coal ratio data and the corresponding experimental adjustment data, and obtain the experimental process data and experimental result data in real time; wherein, a poisonous gas generation model based on deep learning is established and the poisonous gas generation model is trained by constructing a training set to obtain a trained poisonous gas generation model; wherein, the poisonous gas generation model determines the difference between the predicted value and the actual value through the mean square error loss function MAE during the training process, and the mean square error loss function is in, The number of sample data for poisonous gases; For the Sample data; For the The predicted value of sample data, For the The actual value of the sample data; For each type of toxic gas, calculate the difference between the corresponding predicted value and the actual value, and determine the adjustment coefficient corresponding to each type of toxic gas ;in, For the Adjustment coefficient for each type of toxic gas; The model correction coefficient is generated based on the adjustment coefficient, and the model is corrected to complete the model training. The model correction coefficient is in, The number of poisonous gas types; and Respectively The average actual value and average predicted value of sample data of various types of toxic gases; is the learning rate; Obtain the initial coal blending ratio data of the current experiment and the corresponding experimental adjustment data, and collect the current release component data according to the sensors set at the preset positions; Input the current initial coal blending ratio data, experimental adjustment data, and released component data into the trained toxic gas generation model to predict the type and generation time of toxic gases generated during the subsequent process of the current experiment and obtain prediction results; Based on the prediction results, the safety devices corresponding to the small coke ovens are controlled to be turned on or off; The data processing module is used to generate comprehensive result data based on the initial coal blending ratio data, experimental adjustment data, experimental process data and experimental result data; The target determination module is used to determine the target coal blending ratio based on the comprehensive result data corresponding to each experiment after performing multiple experiments.

7. A computing device comprising: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the coking index monitoring and analysis method based on a small coke oven as described in any one of claims 1 to 5.

8. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the coking index monitoring and analysis method based on a small coke oven as described in any one of claims 1 to 5.

Images