Adaptive management methods, devices and equipment for softening and dripping properties of sintered ore

Abstract

This invention provides an adaptive management method, apparatus, and equipment for the softening and dripping performance of sintered ore, relating to the field of softening and dripping performance management technology. It collects the current-time composition of sintering raw materials, the current-time ratio of sintering raw materials, and the current-time sintering process parameters, and calculates the theoretical composition of the sintered ore at the current time. It then calculates the theoretical value of the softening and dripping temperature of the sintered ore corresponding to the theoretical composition at the current time, inputs it into an accurate prediction model, and outputs the actual value of the softening and dripping temperature of the sintered ore at the current time. It determines the quantitative influence of the theoretical value of the softening and dripping temperature of the sintered ore at the current time and the current-time sintering process parameters on the actual value of the softening and dripping temperature of the sintered ore at the current time, adjusts the current-time sintering process parameters, and optimizes the softening and dripping temperature of the sintered ore. Compared with purely theoretical experimental methods, the actual value of the softening and dripping temperature of the sintered ore at the current time obtained by combining it with sintering process parameters is more accurate.

Description

Technical Field

[0001] This invention relates to the field of sinter softening drip performance management technology, and in particular to an adaptive management method, apparatus and equipment for sinter softening drip performance. Background Technology

[0002] The softening and dripping properties of sinter have a significant impact on blast furnace smelting, directly determining the stable operation of the high-temperature zone in the lower part of the blast furnace. These properties can only be obtained through specific experimental equipment, resulting in low data frequency and significant difficulty in data acquisition. When problems arise in sintering production, conducting sampling and experimental testing and analysis of the softening and dripping properties of sinter often takes a day or even several days, leading to direct economic losses of tens of thousands of tons of sinter.

[0003] Currently, most methods for optimizing sinter properties involve experimental mechanism studies and thermodynamic calculations. For example, based on mechanistic experimental research, the softening and dripping properties of sinter are improved; the MgO content of sinter that can optimize the softening and dripping properties is obtained through sintering cup experiments, sinter softening and dripping property testing, and blast furnace industrial tests; and the optimal sintering batching scheme is obtained by using thermodynamic calculations to determine the liquid phase quantity-temperature relationship corresponding to the sintering batching scheme, combined with melting characteristic test experiments.

[0004] However, the above methods are mostly based on theory or experimentation, and have a low degree of integration with actual on-site production, resulting in poor application value of the final data. Summary of the Invention

[0005] This invention provides an adaptive management method, apparatus, and equipment for the softening and dripping properties of sintered ore, which addresses the shortcomings of existing technologies where the integration between theoretical experiments and actual production is low, resulting in poor application value of the results data.

[0006] In a first aspect, the present invention provides an adaptive management method for the softening and dripping performance of sintered ore, comprising:

[0007] Collect the current sintering raw material composition, current sintering raw material ratio, and current sintering process parameters, and calculate the theoretical composition of the sintered ore at the current moment;

[0008] Based on thermodynamic theory, calculate the theoretical value of the softening and dripping temperature of the sinter at the current moment corresponding to the theoretical composition of the sinter at the current moment.

[0009] Input the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into the accurate prediction model, and output the actual value of the softening and dripping temperature of the sinter at the current moment. The accurate prediction model is constructed by integrating the mechanism and data.

[0010] The theoretical value of the softening and dripping temperature of the sinter at the current moment and the quantitative influence of the sintering process parameters at the current moment on the actual value of the softening and dripping temperature of the sinter at the current moment are determined, and the sintering process parameters at the current moment are adjusted to optimize the softening and dripping temperature of the sinter.

[0011] An adaptive management method for the softening and dripping performance of sintered ore provided by the present invention further includes:

[0012] Obtain the actual composition of the sinter at the previous moment before the current moment and the theoretical composition of the sinter at the previous moment, and predict the actual value of the softening and dripping temperature of the sinter at the previous moment through an accurate prediction model.

[0013] By comparing the actual composition of the sinter at the previous moment with the theoretical composition of the sinter at the previous moment, and combining the actual value of the softening and dripping temperature of the sinter at the previous moment with the accurate prediction model, the influence of composition deviation on the actual value of the softening and dripping temperature of the sinter is fed back, the raw material composition is adjusted, and the correction coefficient is calculated.

[0014] According to the adaptive management method for the softening and dripping performance of sintered ore provided by the present invention, before collecting the current sintering raw material composition, the current sintering raw material ratio, and the current sintering process parameters, the method further includes:

[0015] Determine the theoretical values ​​of the softening and dripping temperature of sintered ore, the sintering process parameters, and the actual values ​​of the softening and dripping temperature of sintered ore;

[0016] A prediction model is constructed by training the model using samples of theoretical values ​​of sintering melting and dripping temperature, sintering process parameters, and actual values ​​of sintering melting and dripping temperature.

[0017] According to the adaptive management method for the softening and dripping performance of sinter provided by the present invention, the step of determining the theoretical value sample of the softening and dripping temperature of sinter, the sintering process parameter sample, and the actual value sample of the softening and dripping temperature of sinter includes:

[0018] Collect historical data on softening and dripping experiments of sintered ore, historical sintered ore composition data, and historical sintering process parameters from steel enterprises;

[0019] By aligning with time indexes and integrating data frequencies, the collected historical sintering ore softening and dripping experimental data, historical sintering ore composition data, and historical sintering process parameters are matched to obtain samples of theoretical values ​​of sintering ore softening and dripping temperature, samples of sintering process parameters, and samples of actual values ​​of sintering ore softening and dripping temperature.

[0020] According to the adaptive management method for the softening and dripping performance of sintered ore provided by the present invention, after constructing the prediction model, the method further includes:

[0021] When the prediction accuracy of the prediction model exceeds a preset value, the prediction model is determined to be an accurate prediction model.

[0022] The accurate prediction model was analyzed to obtain the theoretical value of the sintering melting drip temperature and the ranking and trend of the influence of sintering process parameters on the sintering melting drip temperature.

[0023] An adaptive management method for the softening and dripping performance of sintered ore provided by the present invention further includes:

[0024] When the prediction accuracy of the prediction model does not exceed a preset value, the prediction model is determined to be an inaccurate prediction model.

[0025] By adding controllable sintering process parameters to the sintering process parameters, the accuracy of the inaccurate prediction model is improved, and the influence of uncontrollable parameters is fed back.

[0026] According to the adaptive management method for the softening and dripping properties of sintered ore provided by the present invention, after adjusting the sintering process parameters at the current moment, the method further includes:

[0027] Based on the aforementioned quantitative impact, feedback is provided to offer multi-faceted decision-making suggestions, providing data support for production review and enterprise optimization.

[0028] According to the present invention, an adaptive management method for the softening and dripping performance of sintered ore is provided, wherein the softening and dripping temperature of the sintered ore includes: softening start temperature, softening end temperature, melting start temperature, and dripping temperature.

[0029] Secondly, the present invention also provides an adaptive management device for the softening and dripping performance of sintered ore, comprising:

[0030] The data acquisition module is used to collect the current sintering raw material composition, the current sintering raw material ratio, and the current sintering process parameters, and to calculate the theoretical composition of the sintered ore at the current moment.

[0031] The calculation module is used to calculate the theoretical value of the softening and dripping temperature of the sinter at the current moment, corresponding to the theoretical composition of the sinter at the current moment, based on thermodynamic theory.

[0032] The prediction module is used to input the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into the accurate prediction model, and output the actual value of the softening and dripping temperature of the sinter at the current moment. The accurate prediction model is constructed by integrating the mechanism and data.

[0033] The optimization module is used to determine the theoretical value of the sintering melting dripping temperature at the current moment and the quantitative influence of the sintering process parameters at the current moment on the actual value of the sintering melting dripping temperature at the current moment, and to adjust the sintering process parameters at the current moment to optimize the sintering melting dripping temperature.

[0034] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the adaptive management method for the softening and dripping performance of sintered ore as described above.

[0035] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the adaptive management method for the softening and dripping performance of sintered ore as described above.

[0036] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the adaptive management method for the softening and dripping performance of sintered ore as described above.

[0037] This invention provides an adaptive management method, apparatus, and equipment for the softening and dripping performance of sintered ore. It collects the current-time composition of sintering raw materials, the current-time ratio of sintering raw materials, and the current-time sintering process parameters, and calculates the theoretical composition of the sintered ore at the current time. Based on thermodynamic theory, it calculates the theoretical value of the softening and dripping temperature of the sintered ore at the current time, corresponding to the theoretical composition. It inputs the theoretical value of the softening and dripping temperature of the sintered ore at the current time and the current-time sintering process parameters into an accurate prediction model, and outputs the actual value of the softening and dripping temperature of the sintered ore at the current time. The accurate prediction model is constructed by integrating the mechanism and data. It determines the quantitative influence of the theoretical value of the softening and dripping temperature of the sintered ore at the current time and the current-time sintering process parameters on the actual value of the softening and dripping temperature of the sintered ore at the current time, and adjusts the current-time sintering process parameters to optimize the softening and dripping temperature of the sintered ore. Compared with purely theoretical experimental methods, the actual value of the softening and dripping temperature of the sintered ore at the current time obtained by combining the theoretical value with the sintering process parameters and utilizing the accurate prediction model constructed by integrating the mechanism and data is more accurate, and the final result data has higher application value. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating the adaptive management method for the softening and dripping performance of sinter provided in this embodiment;

[0040] Figure 2This is a schematic diagram of the adaptive management device for the softening and dripping performance of sinter provided in this embodiment;

[0041] Figure 3 This is a schematic diagram of the structure of the electronic device provided in this embodiment. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0043] Figure 1 This is a flowchart illustrating the adaptive management method for the softening and dripping performance of sintered ore provided in this embodiment.

[0044] like Figure 1 As shown in the figure, the adaptive management method for the softening and dripping performance of sintered ore provided by the present invention mainly includes the following steps:

[0045] 101. Collect the current sintering raw material composition, current sintering raw material ratio, and current sintering process parameters, and calculate the theoretical composition of the sintered ore at the current moment.

[0046] In a specific implementation process, the softening and dripping properties of sintered ore significantly affect the stable operation of the blast furnace. Therefore, accurate data on the softening and dripping properties of sintered ore is needed to provide sound data support for enterprise decision-making. The moment when the softening and dripping properties of sintered ore need to be determined is defined as the current moment, which can be any moment. Data such as the composition of sintering raw materials, the proportion of sintering raw materials, and the sintering process parameters at the current moment can be collected through sensors, big data analytics, or system reading. Then, data calculations are performed on this data to obtain the theoretical composition of the sintered ore at the current moment.

[0047] 102. Based on thermodynamic theory, calculate the theoretical value of the softening and dripping temperature of the sinter at the current moment, corresponding to the theoretical composition of the sinter at the current moment.

[0048] The theoretical composition of the sinter at the current moment is input into the thermodynamic theoretical formula for calculation, yielding the corresponding theoretical value of the sinter's softening and dripping temperature at the current moment. A specific method could be:

[0049] Extract the liquid phase amount corresponding to the softening and dripping temperature of sinter at each historical moment, take the average of the liquid phase amounts at all historical moments, and when the liquid phase amount of the theoretical composition of sinter at the current moment reaches the average value, determine the corresponding thermodynamic calculation temperature as the theoretical value of the softening and dripping temperature of sinter.

[0050] 103. Input the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into the accurate prediction model, and output the actual value of the softening and dripping temperature of the sinter at the current moment. The accurate prediction model is constructed by integrating the mechanism and data.

[0051] Specifically, the process begins with constructing a predictive model, followed by calibration to obtain an accurate model. The model is constructed by collecting historical data on the softening and dripping of sintered ore from steel enterprises, including historical sintered ore composition data and historical sintering process parameters. This data is then matched using time index alignment and data frequency integration. Based on thermodynamic theory, the theoretical values ​​of the softening and dripping temperature of sintered ore corresponding to all historical sintered ore composition data are calculated. The softening and dripping temperature includes the softening start temperature, softening end temperature, melting start temperature, and dripping temperature. Samples of theoretical values, sintering process parameters, and actual values ​​of the softening and dripping temperature of sintered ore are obtained.

[0052] The model is then trained using samples of theoretical values ​​of sintering ore softening and dripping temperature, sintering process parameters, and actual values ​​of sintering ore softening and dripping temperature. The model is trained by collecting sintering process data from steel enterprises using big data technology and calculating the theoretical values ​​of sintering ore softening and dripping temperature based on thermodynamics and sintering ore composition. The data source is the entire sintering process data resource. The influence of sintering process parameters is incorporated into the sintering ore softening and dripping temperature prediction model, making it closely integrated with actual sintering production, resulting in high processing efficiency and strong real-time performance.

[0053] When the prediction accuracy of the prediction model exceeds the preset value, the prediction model is determined to be an accurate prediction model. The accurate prediction model is analyzed to obtain the ranking and trend of the influence of the theoretical value of the sintering melting drip temperature and sintering process parameters on the sintering melting drip temperature, which is used to summarize empirical patterns. When the prediction accuracy of the prediction model does not exceed the preset value, the prediction model is determined to be an inaccurate prediction model. Controllable sintering process parameters are added to the sintering process parameters to improve the accuracy of the inaccurate prediction model, and the uncontrollable parameters and their theoretical impact are fed back, providing suggestions for management to optimize the sintering process.

[0054] Among them, feedback on uncontrollable parameters and their theoretical impact provides management with suggestions for optimizing the sintering process. These suggestions include: when the uncontrollable parameter is the use of a new type of ore, if the theoretical composition of the sinter remains unchanged but the softening and dripping properties of the sinter change significantly after the change in the type of ore used as raw material, the assimilation temperature and liquid phase fluidity of the new ore should be tested. If the assimilation temperature is too high and / or the ore with poor liquid phase fluidity causes the softening and dripping properties of the sinter to deteriorate, the suggestion to reduce the proportion to control the softening and dripping temperature of the sinter should be fed back to the management system.

[0055] When the uncontrollable parameter is a large fluctuation in alkalinity deviation, it affects the formation of slag phase during the softening and dripping process of sintered ore. The suggestion to adjust the composition and content of the sintering flux to control the quality fluctuation of the sintering flux is fed back to the management system.

[0056] Accurate prediction models integrate metallurgical thermodynamics with data, achieving a fusion of mechanisms and data, enhancing the interpretability of the data model, and facilitating rapid understanding by field engineers. By closely combining model analysis results with actual field conditions, diverse decision-making suggestions are provided, offering data support for production review and enterprise optimization planning.

[0057] 104. Determine the theoretical value of the softening and dripping temperature of the sinter at the current moment and the quantitative influence of the sintering process parameters at the current moment on the actual value of the softening and dripping temperature of the sinter at the current moment, and adjust the sintering process parameters at the current moment to optimize the softening and dripping temperature of the sinter.

[0058] Specifically, the process for determining the quantitative impact is as follows: Based on an accurate prediction model, sample data is input into the accurate prediction model. A machine learning interpretable analysis algorithm is used to obtain the theoretical value of the sintering ore softening dripping temperature and the specific numerical impact of sintering process parameters on the model's expected value. The specific impact values ​​corresponding to the sintering process parameters are sorted, and the sintering process parameters whose impact on the sintering ore softening dripping temperature exceeds the preset value, along with their specific impact values, are obtained. The sintering process parameters are adjusted based on the magnitude of the impact values, while keeping other parameters input into the accurate prediction model unchanged, thereby optimizing the sintering ore softening dripping temperature.

[0059] By fully leveraging historical data from the sintering process, the analysis shifted from broad, trend-based summaries to precise, quantitative relationships, thus improving accuracy. During both the historical data modeling and actual production optimization phases, feedback and decision-making suggestions were provided from different perspectives based on model performance and analysis results, offering data support for optimizing the softening and dripping temperature of sintered ore, reviewing sintering production, and planning optimization strategies for steel enterprises.

[0060] Furthermore, based on the above embodiments, this embodiment also includes: obtaining the actual composition of the sinter at the previous moment and the theoretical composition of the sinter at the previous moment, and predicting the actual value of the softening and dripping temperature of the sinter at the previous moment through an accurate prediction model; comparing the actual composition of the sinter at the previous moment with the theoretical composition of the sinter at the previous moment, and combining the actual value of the softening and dripping temperature of the sinter at the previous moment with the accurate prediction model, feeding back the influence of composition deviation on the actual value of the softening and dripping temperature of the sinter, adjusting the raw material composition and calculating the correction coefficient.

[0061] Specifically, the method for adjusting the raw material composition and calculating the correction factor is as follows:

[0062] When the sinter has a TFe content of 0.5%, the theoretical TFe content and the actual TFe content of the sinter are the same. However, in actual production, fluctuations in raw materials and equipment can lead to differences between the theoretical and actual TFe contents of the sinter. To determine the theoretical and actual TFe contents of the sinter, a TFe correction factor for the raw materials is established. Based on the calculated proportions and composition, this correction factor is multiplied to obtain the adjusted theoretical TFe content of the sinter. As the theoretical and actual TFe contents of the sinter are continuously updated, the TFe correction factor is adjusted accordingly.

[0063] For example, if the theoretical TFe content of sinter is 56.5%, the corresponding actual TFe content of sinter is 56%. In this case, the TFe correction factor for the raw material is 1-(56.5-56) / 56.5. When calculating the theoretical TFe content of sinter again, the TFe correction factor for the raw material needs to be multiplied based on the calculation results of the proportions and components.

[0064] The specific method for quantifying the impact of sinter composition deviation on the sinter softening and dripping temperature at the previous moment is as follows:

[0065] Step 1: Calculate the liquid phase content of sinter corresponding to the theoretical composition of sinter including TFe content and the corresponding theoretical value of sinter softening dripping temperature, and obtain the specific numerical influence of the theoretical value of sinter softening dripping temperature on the expected value of the model.

[0066] Step 2: After determining the TFe deviation of the sinter, modify the TFe content in the theoretical composition of the sinter, calculate the liquid phase content of the sinter corresponding to the theoretical composition of the sinter including the modified TFe content, and the corresponding theoretical value of the sinter softening dripping temperature, and obtain the specific numerical influence of the theoretical value of the sinter softening dripping temperature on the expected value of the model (Influence2).

[0067] The third step is to compare Influence1 and Influence2 to determine the specific impact of the TFe content deviation in sinter on the softening and dripping temperature of sinter. The specific impact is then fed back to the terminal platform. The terminal platform receives instructions from engineers. If the engineer's instructions indicate that the TFe content deviation in sinter has a significant impact on the softening and dripping temperature of sinter, then a suggestion is made to organize and invest special resources to address the large TFe content deviation in sinter.

[0068] Based on the same general inventive concept, this invention also protects an adaptive management device for the softening and dripping performance of sintered ore. The adaptive management device for the softening and dripping performance of sintered ore described below and the adaptive management method for the softening and dripping performance of sintered ore described above can be referred to in correspondence with each other.

[0069] Figure 2 This is a schematic diagram of the adaptive management device for the softening and dripping performance of sintered ore provided in this embodiment.

[0070] like Figure 2 As shown in the figure, this embodiment provides an adaptive management device for the softening and dripping performance of sintered ore, comprising:

[0071] The data acquisition module 201 is used to acquire the current sintering raw material composition, the current sintering raw material ratio, and the current sintering process parameters, and to calculate the theoretical composition of the sintered ore at the current moment.

[0072] Calculation module 202 is used to calculate the theoretical value of the softening and dripping temperature of sinter at the current moment, corresponding to the theoretical composition of sinter at the current moment, based on thermodynamic theory.

[0073] The prediction module 203 is used to input the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into the accurate prediction model, and output the actual value of the softening and dripping temperature of the sinter at the current moment. The accurate prediction model is constructed by integrating the mechanism and data.

[0074] The optimization module 204 is used to determine the theoretical value of the softening and dripping temperature of the sinter at the current moment and the quantitative influence of the sintering process parameters at the current moment on the actual value of the softening and dripping temperature of the sinter at the current moment, and to adjust the sintering process parameters at the current moment to optimize the softening and dripping temperature of the sinter.

[0075] Figure 3 This is a schematic diagram of the structure of the electronic device provided in this embodiment.

[0076] like Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logic instructions in the memory 330 to execute an adaptive management method for the softening and dripping performance of sintered ore. This method includes: collecting the current composition of sintering raw materials, the current ratio of sintering raw materials, and the current sintering process parameters, and calculating the theoretical composition of the sintered ore at the current time; calculating the theoretical value of the softening and dripping temperature of the sintered ore at the current time corresponding to the theoretical composition of the sintered ore at the current time based on thermodynamic theory; inputting the theoretical value of the softening and dripping temperature of the sintered ore at the current time and the current sintering process parameters into an accurate prediction model, and outputting the actual value of the softening and dripping temperature of the sintered ore at the current time, wherein the accurate prediction model is constructed by integrating the mechanism and data; determining the quantitative influence of the theoretical value of the softening and dripping temperature of the sintered ore at the current time and the current sintering process parameters on the actual value of the softening and dripping temperature of the sintered ore at the current time, and adjusting the current sintering process parameters to optimize the softening and dripping temperature of the sintered ore.

[0077] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0078] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the adaptive management method for the softening and dripping performance of sintered ore provided by the above methods. The method includes: collecting the composition of sintering raw materials, the ratio of sintering raw materials, and the sintering process parameters at the current time, and calculating the theoretical composition of sintered ore at the current time; calculating the theoretical value of the softening and dripping temperature of sintered ore at the current time corresponding to the theoretical composition of sintered ore at the current time based on thermodynamic theory; inputting the theoretical value of the softening and dripping temperature of sintered ore at the current time and the sintering process parameters at the current time into an accurate prediction model, and outputting the actual value of the softening and dripping temperature of sintered ore at the current time, wherein the accurate prediction model is constructed by integrating mechanism and data; determining the quantitative influence of the theoretical value of the softening and dripping temperature of sintered ore at the current time and the sintering process parameters at the current time on the actual value of the softening and dripping temperature of sintered ore at the current time, and adjusting the sintering process parameters at the current time to optimize the softening and dripping temperature of sintered ore.

[0079] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements an adaptive management method for the softening and dripping performance of sinter provided by the methods described above. This method includes: collecting the composition of sintering raw materials, the ratio of sintering raw materials, and the sintering process parameters at the current moment, and calculating the theoretical composition of the sinter at the current moment; calculating the theoretical value of the softening and dripping temperature of the sinter at the current moment corresponding to the theoretical composition of the sinter at the current moment based on thermodynamic theory; inputting the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into an accurate prediction model, and outputting the actual value of the softening and dripping temperature of the sinter at the current moment, wherein the accurate prediction model is constructed by integrating mechanisms and data; determining the quantitative influence of the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment on the actual value of the softening and dripping temperature of the sinter at the current moment, and adjusting the sintering process parameters at the current moment to optimize the softening and dripping temperature of the sinter.

[0080] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An adaptive management method for the softening and dripping performance of sintered ore, characterized in that, include: Collect the current sintering raw material composition, current sintering raw material ratio, and current sintering process parameters, and calculate the theoretical composition of the sintered ore at the current moment; Based on thermodynamic theory, calculate the theoretical value of the softening and dripping temperature of the sinter at the current moment corresponding to the theoretical composition of the sinter at the current moment. Input the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into the accurate prediction model, and output the actual value of the softening and dripping temperature of the sinter at the current moment. The accurate prediction model is constructed by integrating the mechanism and data. The theoretical value of the softening and dripping temperature of the sinter at the current moment and the quantitative influence of the sintering process parameters at the current moment on the actual value of the softening and dripping temperature of the sinter at the current moment are determined, and the sintering process parameters at the current moment are adjusted to optimize the softening and dripping temperature of the sinter. Obtain the actual composition of the sinter at the previous moment before the current moment and the theoretical composition of the sinter at the previous moment, and predict the actual value of the softening and dripping temperature of the sinter at the previous moment through an accurate prediction model. By comparing the actual composition of the sinter at the previous moment with the theoretical composition of the sinter at the previous moment, and combining the actual value of the softening and dripping temperature of the sinter at the previous moment with the accurate prediction model, the influence of the composition deviation on the actual value of the softening and dripping temperature of the sinter is fed back, the raw material composition is adjusted and the correction coefficient is calculated. The specific method for adjusting the raw material composition and calculating the correction coefficient is as follows: when the sinter is TFe, determine the theoretical TFe content of the sinter and the corresponding actual TFe content of the sinter. Based on the theoretical TFe content of the sinter and the corresponding actual TFe content of the sinter, determine the TFe correction coefficient of the raw material. Based on the calculation results of the proportion and composition, multiply by the TFe correction coefficient of the raw material to obtain the adjusted theoretical TFe content of the sinter. Simultaneously, feedback is provided on the quantitative impact of sinter composition deviation on the sinter softening and dripping temperature at the previous moment: Step 1: Calculate the liquid phase content of sinter corresponding to the theoretical composition of sinter including TFe content and the corresponding theoretical value of sinter softening dripping temperature, and obtain the specific numerical influence of the theoretical value of sinter softening dripping temperature on the expected value of the model (Influence1). Step 2: After determining the TFe deviation of the sinter, modify the TFe content in the theoretical composition of the sinter, calculate the liquid phase content of the sinter corresponding to the theoretical composition of the sinter including the modified TFe content, and the corresponding theoretical value of the sinter softening dripping temperature, and obtain the specific numerical influence of the theoretical value of the sinter softening dripping temperature on the expected value of the model (Influence2). The third step is to compare Influence1 and Influence2 to determine the specific impact of the TFe content deviation in sinter on the softening and dripping temperature of sinter. The specific impact is then fed back to the terminal platform. The terminal platform receives instructions from engineers. If the engineer's instructions indicate that the TFe content deviation in sinter has a significant impact on the softening and dripping temperature of sinter, then a suggestion is made to organize and invest special resources to address the large TFe content deviation in sinter.

2. The adaptive management method for the softening and dripping performance of sintered ore according to claim 1, characterized in that, Before collecting the current sintering raw material composition, the current sintering raw material ratio, and the current sintering process parameters, the following steps are also included: Determine the theoretical values ​​of the softening and dripping temperature of sintered ore, the sintering process parameters, and the actual values ​​of the softening and dripping temperature of sintered ore; A prediction model is constructed by training the model using samples of theoretical values ​​of sintering melting and dripping temperature, sintering process parameters, and actual values ​​of sintering melting and dripping temperature.

3. The adaptive management method for the softening and dripping performance of sintered ore according to claim 2, characterized in that, The samples for determining the theoretical values ​​of the softening and dripping temperature of sintered ore, the samples of sintering process parameters, and the samples of the actual values ​​of the softening and dripping temperature of sintered ore include: Collect historical data on softening and dripping experiments of sintered ore, historical sintered ore composition data, and historical sintering process parameters from steel enterprises; By aligning with time indexes and integrating data frequencies, the collected historical sintering ore softening and dripping experimental data, historical sintering ore composition data, and historical sintering process parameters are matched to obtain samples of theoretical values ​​of sintering ore softening and dripping temperature, samples of sintering process parameters, and samples of actual values ​​of sintering ore softening and dripping temperature.

4. The adaptive management method for the softening and dripping performance of sintered ore according to claim 2, characterized in that, After constructing the prediction model, the following is also included: When the prediction accuracy of the prediction model exceeds a preset value, the prediction model is determined to be an accurate prediction model. The accurate prediction model was analyzed to obtain the theoretical value of the sintering melting drip temperature and the ranking and trend of the influence of sintering process parameters on the sintering melting drip temperature.

5. The adaptive management method for the softening and dripping performance of sintered ore according to claim 4, characterized in that, Also includes: When the prediction accuracy of the prediction model does not exceed a preset value, the prediction model is determined to be an inaccurate prediction model. By adding controllable sintering process parameters to the sintering process parameters, the accuracy of the inaccurate prediction model is improved, and the influence of uncontrollable parameters is fed back.

6. The adaptive management method for the softening and dripping performance of sintered ore according to any one of claims 1-5, characterized in that, After adjusting the sintering process parameters at the current moment, the method further includes: Based on the aforementioned quantitative impact, feedback is provided to offer multi-faceted decision-making suggestions, providing data support for production review and enterprise optimization.

7. The adaptive management method for the softening and dripping performance of sintered ore according to any one of claims 1-5, characterized in that, The softening and dripping temperatures of the sintered ore include: softening start temperature, softening end temperature, melting start temperature, and dripping temperature.

8. An adaptive management device for the softening and dripping performance of sintered ore, characterized in that, include: The data acquisition module is used to collect the current sintering raw material composition, the current sintering raw material ratio, and the current sintering process parameters, and to calculate the theoretical composition of the sintered ore at the current moment. The calculation module is used to calculate the theoretical value of the softening and dripping temperature of the sinter at the current moment, corresponding to the theoretical composition of the sinter at the current moment, based on thermodynamic theory. The prediction module is used to input the theoretical value of the softening and dripping temperature of the sinter at the current moment and the sintering process parameters at the current moment into the accurate prediction model, and output the actual value of the softening and dripping temperature of the sinter at the current moment. The accurate prediction model is constructed by integrating the mechanism and data. The optimization module is used to determine the theoretical value of the softening and dripping temperature of the sinter at the current moment and the quantitative influence of the sintering process parameters at the current moment on the actual value of the softening and dripping temperature of the sinter at the current moment, and to adjust the sintering process parameters at the current moment to optimize the softening and dripping temperature of the sinter. The adjustment module is used to obtain the actual composition of the sinter and the theoretical composition of the sinter at the previous moment before the current moment, and to predict the actual value of the softening and dripping temperature of the sinter at the previous moment through an accurate prediction model. By comparing the actual composition of the sinter at the previous moment with its theoretical composition, and combining the actual value of the sinter's softening and dripping temperature at the previous moment with the accurate prediction model, the influence of compositional deviation on the actual value of the sinter's softening and dripping temperature is fed back. The raw material composition is then adjusted, and a correction coefficient is calculated. The specific method for adjusting the raw material composition and calculating the correction coefficient is as follows: When the sinter is TFe, the theoretical TFe content and the corresponding actual TFe content of the sinter are determined. Using the theoretical TFe content and the corresponding actual TFe content, the raw material TFe correction coefficient is determined. Based on the calculation results of the proportions and composition, this is multiplied by the raw material TFe correction coefficient to obtain the adjusted theoretical TFe content of the sinter. Simultaneously, the quantitative influence of the sinter compositional deviation on the sinter's softening and dripping temperature at the previous moment is fed back. Step 1: Calculate the liquid phase content of sinter corresponding to the theoretical composition of sinter including TFe content and the corresponding theoretical value of sinter softening dripping temperature, and obtain the specific numerical influence of the theoretical value of sinter softening dripping temperature on the expected value of the model (Influence1). Step 2: After determining the TFe deviation in the sinter, modify the TFe content in the theoretical composition of the sinter, calculate the liquid phase content of the sinter corresponding to the theoretical composition of the sinter including the modified TFe content, and the corresponding theoretical value of the sinter softening dripping temperature. Obtain the specific numerical influence (Influence2) of the theoretical value of the sinter softening dripping temperature on the expected value of the model. Step 3: Compare Influence1 and Influence2 to determine the specific impact of the TFe content deviation in the sinter on the sinter softening dripping temperature. Feedback the specific impact to the terminal platform. The terminal platform receives engineer instructions. When the engineer instructions indicate that the TFe content deviation in the sinter has a significant impact on the sinter softening dripping temperature, a suggestion is made to organize and invest special resources to address the large TFe content deviation in the sinter.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the adaptive management method for the softening and dripping performance of sintered ore as described in any one of claims 1 to 7.

Images