Converter gas scheduling method, device, equipment, storage medium and product

Abstract

The invention relates to the technical field of energy scheduling, and discloses a converter gas scheduling method, device and equipment, a storage medium and a product, and the method comprises the steps: predicting the supply and demand information of converter gas in a preset time range based on the obtained converter gas information and production plan data; based on converter gas holder data in the supply and demand information and the converter gas information, establishing a capacity model and a mixed heat value change model of the gas holder, and determining state information of the gas holder under different scheduling strategies according to the capacity model and the mixed heat value change model; and solving an optimal scheduling scheme of the converter gas in a preset time range through a rolling optimization strategy by taking minimization of the total cost as an optimization target and combining preset constraint conditions and state information. A full-chain collaborative optimization framework of generation, buffering and consumption of converter gas is constructed, future cabinet position and heat value changes of the gas cabinet under different scheduling strategies can be predicted, and collaborative optimization scheduling of a converter gas system is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy scheduling, in particular to a converter gas scheduling method, device, equipment, storage medium and product. BACKGROUND

[0002] In a steel joint enterprise, the converter gas recovery system and the steel rolling heating furnace consumption system usually operate independently, although a converter gas tank with a buffering function can be used as a buffering adjustment unit for optimization control, but the traditional control strategy is based on the current state of the gas tank rather than prediction information, and the adjustment effect is limited, and due to the lack of accurate prediction and scheduling, the gas emission rate is high, and the heat energy cannot be fully utilized. SUMMARY

[0003] The main purpose of the present application is to provide a converter gas scheduling method, device, equipment, storage medium and product, which aims to solve the technical problems of lack of accurate prediction and scheduling in traditional control strategy, high gas emission rate and inability to fully utilize heat energy.

[0004] To achieve the above-mentioned purpose, the present application provides a converter gas scheduling method, which comprises: Based on the obtained converter gas information and production plan data, the supply and demand information of the converter gas in a preset time range is predicted; Based on the supply and demand information and the converter gas tank data in the converter gas information, a capacity model and a mixed heat value change model of the gas tank are established, and according to the capacity model and the mixed heat value change model, the state information of the gas tank under different scheduling strategies is determined; Taking the minimization of total cost as the optimization goal, combining the preset constraint condition and the state information, the optimal scheduling scheme of the converter gas in the preset time range is solved through a rolling optimization strategy.

[0005] Optionally, the converter gas information includes converter gas data and steel rolling heating furnace data, and the production plan data includes converter production plan data and steel rolling production plan data; The step of predicting the supply and demand information of the converter gas in a preset time range based on the obtained converter gas information and production plan data comprises: Determining the converter smelting stage of the converter gas and the working stage of the steel rolling heating furnace; Based on the converter smelting stage, the converter gas data and the converter production plan data, the converter gas production amount and the gas heat value of the converter in the preset time range are predicted; Based on the working stage, the steel rolling heating furnace data and the steel rolling production plan data, the converter gas demand amount and the heat value demand of the steel rolling heating furnace in the preset time range are predicted; According to the converter gas production, the gas calorific value, the converter gas demand and the calorific value demand, the supply and demand information of the converter gas is determined.

[0006] Optionally, the step of determining the converter smelting stage of the converter gas and the working stage of the steel rolling heating furnace comprises: Based on the oxygen lance signal in the converter gas data, the converter smelting stage of the current converter gas is determined. Based on the steel rolling production plan data, the working stage of the steel rolling heating furnace corresponding to the converter gas is determined.

[0007] Optionally, the preset time range comprises a first time range and a second time range, and the second preset time range is located after the first time range. The step of predicting the converter gas production and the gas calorific value of the converter in the preset time range based on the converter smelting stage, the converter gas data and the converter production plan data comprises: Based on the converter smelting stage, the first converter gas production and the initial gas calorific value of each converter in the first time range are predicted through the converter gas data. Based on the converter production plan data, the second converter gas production of each converter in the second time range is predicted through a template matching algorithm. The first converter gas production and the second converter gas production are weighted and fused to obtain a third converter gas production, and the converter gas production and the gas calorific value are determined according to the third converter gas production and the initial gas calorific value.

[0008] Optionally, the step of solving the optimal scheduling scheme of the converter gas in the preset time range by a rolling optimization strategy with the minimum total cost as the optimization target, combined with the preset constraint condition and the state information comprises: A target function with the minimum total cost as the target is constructed, and the target function comprises a dissipation penalty term, a calorific value quality penalty term and an operation stability penalty term. The constraint condition for the target function is set, and the constraint condition comprises a gas tank safe tank position constraint, a pipeline transportation capacity constraint, a calorific value matching constraint and an energy balance constraint. Based on the state information and the constraint condition, the target function is solved to obtain the optimal scheduling scheme of the corresponding control period. The first control instruction in the optimal scheduling scheme of each control period is issued to the bottom layer control equipment for execution, and the actual value after execution is collected in real time, and the deviation between the actual value and the supply and demand information is calculated. Based on the deviation, the state information of subsequent control cycles is adjusted, and the optimal scheduling scheme for the next control cycle is determined based on the state information.

[0009] Optionally, after the step of solving the optimal scheduling scheme for the converter gas within the preset time range, the method further includes: When equipment failure is detected or a severe imbalance between supply and demand is predicted, switch to an emergency control mode based on rule base control. In the emergency control mode, in response to the gas holder's inventory being greater than the gas holder's high-level threshold and the gas holder's mixed calorific value being greater than the calorific value requirement, the gas holder's output flow rate is increased. In response to the gas holder's inventory being less than the gas holder's low-level threshold and the predicted converter gas production at the next time point decreasing, the gas holder's output flow rate is reduced and backup fuel is activated.

[0010] Furthermore, to achieve the above objectives, this application also proposes a converter gas dispatching device, which includes: The information prediction module is used to predict the supply and demand information of converter gas within a preset time range based on the acquired converter gas information and production plan data. The information determination module is used to establish a capacity model and a mixed calorific value change model of the gas holder based on the supply and demand information and the converter gas holder data in the converter gas information, and to determine the state information of the gas holder under different scheduling strategies according to the capacity model and the mixed calorific value change model. The scheme determination module is used to solve the optimal scheduling scheme of the converter gas within the preset time range by taking the minimization of total cost as the optimization objective, combining preset constraints and the state information, and using a rolling optimization strategy.

[0011] In addition, to achieve the above objectives, this application also proposes a converter gas scheduling device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the converter gas scheduling method described above.

[0012] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the converter gas scheduling method described above.

[0013] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the converter gas scheduling method described above.

[0014] This application constructs a collaborative optimization framework for the entire chain of converter gas generation, buffering, and consumption. By systematically predicting future gas supply and demand and generating dispatch instructions based on the prediction results, it can proactively and forward-lookingly adjust the gas system's operating status, coordinating supply and demand. By establishing a dynamic model, it can predict future changes in the gas holder's position and calorific value under different dispatch strategies, thereby quantitatively assessing and proactively planning the gas holder's buffering capacity. This allows the dispatch system to utilize the gas holder's buffer space more accurately and safely, determining the optimal dispatch scheme. A rolling optimization strategy is adopted, re-predicting and optimizing based on the latest actual data in each control cycle. This means the dispatch scheme can continuously adapt to changes in the production process, promptly correcting deviations caused by prediction errors or external disturbances, achieving collaborative optimization dispatch of the converter gas system. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the converter gas dispatching method of this application; Figure 2 This is a schematic diagram of the configuration of pipeline instruments for converter gas prediction and intelligent dispatching in this application; Figure 3 This is a schematic diagram of the architecture of the converter gas dispatching system of this application; Figure 4 This is a flowchart illustrating the second embodiment of the converter gas dispatching method of this application; Figure 5 This is a flowchart illustrating the third embodiment of the converter gas dispatching method of this application; Figure 6 This is a schematic diagram of the data processing logic of the converter gas dispatching system in this application; Figure 7 This is a schematic diagram of the module structure of the converter gas dispatching device according to an embodiment of this application; Figure 8 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the converter gas scheduling method in this application embodiment.

[0018] Explanation of icon numbers: 1, 2, 3: Converter; 4, 8, 12, 20, 24: Variable frequency fans; 5, 9, 13: Gas detectors; 6, 10, 14: Switching station; 7, 11, 15, 17, 21, 25: Flow meter; 16, 19: Calorimeter; 18: Converter gas holder; 22, 26: Rolling mill workshop.

[0019] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] In integrated iron and steel enterprises, converter gas recovery systems and rolling mill heating furnace consumption systems typically operate independently, lacking coordinated optimization. Converter gas production is intermittent and fluctuates, while heating furnace demand is relatively continuous and stable. This supply-demand mismatch leads to gas venting or shortages. Although gas holders have buffering capabilities, traditional control strategies are based on current conditions rather than predictive information, resulting in limited adjustment effectiveness. Furthermore, due to the lack of precise forecasting and scheduling, the gas venting rate is high, and heat cannot be fully utilized.

[0023] Therefore, this application provides a converter gas scheduling method based on the prediction of gas recovery from multiple converters and the demand prediction of steel rolling heating furnaces, so as to achieve synergistic optimization of converter gas generation and steel rolling heating furnace consumption, improve gas utilization efficiency, and reduce venting rate.

[0024] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, data prediction, and program execution functions, such as a computer, or an electronic device capable of performing the above functions. The following description uses a smart gas dispatching system as an example to illustrate this embodiment and the subsequent embodiments.

[0025] Based on this, the embodiments of this application provide a converter gas scheduling method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the converter gas dispatching method of this application.

[0026] In this embodiment, the converter gas scheduling method includes: Step S10: Based on the acquired converter gas information and production plan data, predict the supply and demand information of converter gas within a preset time range.

[0027] It should be noted that converter gas information refers to real-time operational data related to converter gas production, storage, and consumption, including converter gas data, rolling mill heating furnace data, and converter gas holder data; production plan data refers to pre-established production arrangement information by enterprises, covering converter production plan data (such as smelting furnace batches, start-up time, steel grades and specifications, etc.) and rolling mill production plan data (such as rolling batches, heating furnace start-up and shutdown plans, output targets, etc.); the preset time range is a forecast period divided according to scheduling needs, which can include short-term (0-30 minutes) and medium-term (30 minutes to 24 hours) dimensions; supply and demand information refers to the supply (changes in converter gas production and calorific value) and demand (gas consumption and calorific value requirements of users such as rolling mill heating furnaces) of converter gas within the preset time range.

[0028] Specifically, before predicting the supply and demand information of converter gas within a preset time range, it is necessary to collect real-time signals of the flow rate, calorific value, CO content, O2 content, switching station status, oxygen lance height, and oxygen blowing status of each converter gas; simultaneously collect signals of gas consumption, calorific value demand, furnace temperature, and rolling rhythm of the steel rolling heating furnace; and monitor the position, inlet and outlet pressure, and temperature parameters of the converter gas holder; and obtain converter production plan and steel rolling production plan data from the production management system.

[0029] Understandably, after obtaining converter gas information and production plan data, the converter smelting stages (such as charging period, early blowing period, peak period, late blowing period, and tapping period) can be identified through process signals (such as oxygen lance signals) in the converter gas data. The heating furnace working stages (such as preheating period, heating period, and soaking period) can be identified based on the rolling plan. The time-series characteristics and intensity characteristics related to the gas generation and consumption patterns can be extracted to clarify the operating characteristics of different stages. Then, the prediction results of different time scales are weighted and fused through a multi-time-scale prediction model to generate a comprehensive prediction curve for gas supply and demand.

[0030] It should be understood that, based on converter oxygen lance signals, smelting stages, and production plans, a multi-timescale forecasting model can predict the future gas production and calorific value of each converter within a given time period. Based on the rolling schedule, steel grade specifications, and temperature curves of the steel rolling furnace, a demand forecasting algorithm can predict the gas demand and calorific value requirements for the corresponding future periods.

[0031] In one example, reference Figure 2 , Figure 2This is a schematic diagram of the pipeline instrumentation configuration for converter gas prediction and intelligent dispatching in this application. First, after converters 1, 2, and 3 produce gas during the smelting stage, it is transported by corresponding frequency converters 4, 8, and 12. During this transport, gas detectors 5, 9, and 13 collect real-time gas status data, while flow meters 7, 11, and 15 record the gas flow rate of a single converter. The flow of gas in each converter is controlled by switching stations 6, 10, and 14. After preliminary processing and data collection at this stage, the data is aggregated. The gas passes through a calorific value meter 16 to detect its initial calorific value and a flow meter 17 to record its total flow rate. It then enters a converter gas holder 18 for storage and buffering. The gas holder simultaneously records real-time position data. After storage, the gas passes through a calorific value meter 19 to detect its mixed calorific value, completing secondary data acquisition. The gas is then divided into two routes: one route is pressurized by a variable frequency fan 20 and metered by a flow meter 21 before being sent to the rolling mill workshop 22; the other route is pressurized by a variable frequency fan 24 and metered by a flow meter 25 before being sent to the rolling mill workshop 26, thus meeting the energy demand.

[0032] Step S20: Based on the supply and demand information and the converter gas holder data in the converter gas information, establish a capacity model and a mixed calorific value change model for the gas holder, and determine the state information of the gas holder under different scheduling strategies according to the capacity model and the mixed calorific value change model.

[0033] It should be noted that the converter gas holder data refers to real-time monitoring data during the operation of the gas holder, including the holder height, inlet and outlet gas flow rates, internal pressure and temperature, and initial calorific value of the gas inside the holder; the capacity model is a mathematical model describing the quantitative relationship between the gas storage volume inside the gas holder and physical parameters such as holder height, pressure, and temperature; the mixed calorific value change model is a model reflecting the dynamic changes in the calorific value of the mixed gas inside the gas holder with the calorific value of gas from different sources (each converter) and the input and output flow rates; the scheduling strategy refers to different operating schemes set to regulate the operation of the gas holder (such as different gas input / output flow rates and recovery rhythms); and the status information refers to key operating parameters such as the gas storage volume, real-time calorific value, pressure, and holder height inside the gas holder under a specific scheduling strategy.

[0034] Understandably, by combining the dynamic buffer model of the gas holder, the evolution of the mixed calorific value of the holder location and the interior under different scheduling strategies can be predicted, thereby assessing the system's buffering capacity. By integrating gas production and demand data, calorific value data, and real-time data such as the gas holder location, pressure, and temperature from the supply and demand information, and combining these with the gas holder's structural parameters (such as the holder volume coefficient and piston cross-sectional area), a capacity model is constructed to quantify the relationship between gas storage and physical parameters. Simultaneously, a mixed calorific value change model is constructed to calculate the real-time mixed calorific value within the holder. Subsequently, different scheduling strategies are set (such as adjusting the output flow rate to Q1 or Q2), and the strategy parameters are input into both models to simulate and calculate the gas storage, calorific value, and holder location at each time point under different strategies. Finally, the state information of the gas holder under different scheduling strategies is determined.

[0035] In one example, the gas holder's state equation can be represented by the dynamic changes in the gas holder's position. Dynamic changes in position:

[0036] in, Let t be the gas holder inventory at time t, which is a fixed value. The flow rate into the gas holder, The flow rate output to the heating furnace, and Adjustable accordingly. The amount of energy released can be used as an optimization objective.

[0037] The mixed calorific value model of the gas holder is represented by the dynamic change of the mixed calorific value inside the holder:

[0038] in, The mixed calorific value inside the gas holder. To determine the calorific value of the gas entering the gas holder, the following solution is obtained using the gas holder mixed calorific value model:

[0039] Since the calorific value of the output gas is equal to the current calorific value inside the cabinet. The output process does not change the average calorific value inside the cabinet, but only reduces the volume of gas inside. Therefore, the change in calorific value inside the cabinet depends only on the mixing of the input gas and the existing gas inside, and not directly on the output flow rate. The time interval is calculated by adding the calorific value of the input gas to the existing calorific value inside the cabinet, and then dividing by the total volume (the existing volume inside the cabinet plus the volume of the input gas). The combined calorific value.

[0040] Step S30: With minimizing the total cost as the optimization objective, and combining the preset constraints and the state information, the optimal scheduling scheme for the converter gas within the preset time range is solved through a rolling optimization strategy.

[0041] It should be noted that minimizing total cost refers to reducing the sum of all costs incurred during converter gas scheduling (including energy waste costs caused by gas venting, production efficiency losses due to calorific value mismatch, and maintenance costs caused by frequent equipment operation adjustments, etc.) to a minimum. The preset constraints are the limitations that ensure the safe and stable operation of the gas system, covering constraints such as gas holder safety position, pipeline transport capacity, calorific value matching, and energy balance. The rolling optimization strategy is a dynamic optimization method that divides the preset time range into multiple continuous control cycles. In each cycle, it solves for the local optimum based on the current state and prediction information, and continuously corrects the subsequent optimization process through real-time feedback. The optimal scheduling scheme is a set of scheduling instructions that satisfies all constraints and minimizes total cost, including instructions for generating gas holder inlet / outlet gas volume control, venting valve control strategies, and heating furnace fuel allocation suggestions.

[0042] In one example, reference Figure 3 , Figure 3 This is a schematic diagram of the converter gas dispatching system of this application. The converter gas dispatching system adopts a vertically layered architecture, consisting of the control execution layer, communication interface layer, data acquisition layer, data processing and prediction layer, optimization scheduling layer, and business application layer from bottom to top. Each layer supports and collaborates with the others. The control execution layer includes multiple execution systems, such as the gas recovery system, gas holder control system, gas venting control system, and heater fuel regulation system. The communication interface layer uses PLC / DCS, MES, and EMS system interfaces to achieve data interaction and command transmission between the control layer and the upper-level systems. The data acquisition layer relies on converter-side sensors, gas holder sensors, and heater-side sensors. The system includes an equipment and production planning system that collects on-site operational data and production planning information; a data processing and prediction layer that uses real-time computing, prediction algorithms, and rule engines to complete data cleaning, supply and demand forecasting, and anomaly prediction; an optimization and scheduling layer that uses multi-objective optimization, expert rule base, MPC, and other modules to solve for the optimal scheduling scheme; and an uppermost business application layer that presents the scheduling status and results to users through visual monitoring and scheduling instruction display, and performs performance analysis and early warning. The entire architecture realizes a closed loop of the entire process from on-site execution and data exchange to optimization decision-making and user display, supporting the intelligent scheduling and management of converter gas.

[0043] In this embodiment, a collaborative optimization framework for the entire chain of converter gas generation, buffering, and consumption is constructed. Through dynamic modeling of the gas holder and supply and demand prediction, the future position and calorific value changes of the gas holder under different scheduling strategies can be predicted. This enables quantitative evaluation and proactive planning of the buffering capacity of the gas holder, and determination of the optimal scheduling scheme, thus realizing the collaborative optimization scheduling of the converter gas system.

[0044] Reference Figure 4 ,Figure 4 This is a flowchart illustrating the second embodiment of the converter gas scheduling method of this application. Based on the first embodiment described above, a second embodiment of the converter gas scheduling method of this application is proposed. In the second embodiment, the converter gas information includes converter gas data and rolling mill heating furnace data, and the production plan data includes converter production plan data and rolling mill production plan data. Step S10 includes: Step S101: Determine the converter smelting stage of the converter gas and the working stage of the steel rolling heating furnace.

[0045] Furthermore, in order to achieve accurate and real-time determination of each stage of operation, and to quickly capture the dynamic changes in the converter smelting conditions and the production rhythm of the rolling mill heating furnace, ensuring that subsequent production and demand forecasts can be based on accurate stage divisions, step S101 may include: Based on the oxygen lance signal in the converter gas data, the converter smelting stage of the current converter gas is determined; based on the steel rolling production plan data, the working stage of the steel rolling heating furnace corresponding to the converter gas is determined.

[0046] It should be noted that the oxygen lance signal is the electrical signal of the oxygen lance's operating status (such as lowering for oxygen blowing, raising for stopping blowing, slag splashing for furnace protection, etc.) and related parameters (such as oxygen supply flow rate, oxygen pressure, lance position height) during the converter smelting process; the converter smelting stage refers to the different process stages of converter steelmaking, including the early blowing stage, the middle blowing stage, the late blowing stage, the tapping stage, and the furnace repair stage; the rolling mill production plan data is the pre-formulated production arrangement information of the rolling mill workshop, covering the heating furnace charging plan, heating rhythm, rolling batches, and furnace shutdown maintenance time; the rolling mill heating furnace working stage refers to the operating status stage of the heating furnace, including the heating period, the holding period, the waiting period, and the shutdown period.

[0047] Understandably, when determining the converter smelting stage based on oxygen lance signals, a mapping rule between oxygen lance signal characteristics and smelting stages can be established first. The industrial control system can then collect signals such as the oxygen lance's position, oxygen supply status, and operating commands in real time, matching the real-time signal characteristics with the mapping rule to automatically determine the current smelting stage of the converter. Similarly, when determining the heating furnace operating stage based on steel rolling production plan data, information such as time nodes, output targets, and furnace temperature settings in the production plan can be analyzed. Combined with the heating furnace's thermal characteristic curves, the plan data can be decomposed into the heating furnace operating status for each time period, thereby determining the operating stage of each heating furnace within a preset time range. For example, the planned full-load rolling period corresponds to the heating furnace holding period, and periods without rolling tasks correspond to the waiting period for materials.

[0048] Step S102: Based on the converter smelting stage, the converter gas data, and the converter production plan data, predict the converter gas production and calorific value within a preset time range.

[0049] It should be noted that the converter gas production refers to the total gas flow rate predicted within a preset time range during the converter smelting stage; the gas calorific value refers to the predicted total calorific value of the converter gas.

[0050] Furthermore, to integrate the predictive advantages of different time dimensions and significantly improve the comprehensiveness and accuracy of the overall prediction, the preset time range includes a first time range and a second time range, with the second preset time range located after the first time range. Step S102 may include: Based on the converter smelting stage, the first converter gas production and initial gas calorific value of each converter within a first time range are predicted using the converter gas data. Based on the converter production plan data, the second converter gas production of each converter within a second time range is predicted using a template matching algorithm. The first converter gas production and the second converter gas production are weighted and fused to obtain the third converter gas production. The converter gas production and gas calorific value are then determined based on the third converter gas production and the initial gas calorific value.

[0051] It should be noted that the first time range refers to the short-term forecast period (usually 0-30 minutes) starting from the current moment; the second time range is the medium-term forecast period (usually 30 minutes to 24 hours) following the first time range, covering the production rhythm of multiple subsequent smelting furnaces; the first converter gas production is the short-term gas production predicted based on real-time smelting stage and gas data, and the initial gas calorific value is the predicted value of the gas calorific value of each converter within the first time range; the second converter gas production is the medium-term gas production obtained by matching the production plan and historical templates; the third converter gas production is the comprehensive gas production calculated by weighting the first and second converter gas production by assigning different weights (dynamically adjusted according to the forecast accuracy).

[0052] Specifically, for the first time period, based on the determined converter smelting stage (such as the peak blowing period), real-time flow rate, oxygen supply intensity, furnace mouth pressure, and other features are extracted from the converter gas data. LSTM (Long Short Term Memory) and other time-series models are used to capture the dynamic changes in operating conditions, accurately predicting the first converter gas production and initial gas calorific value for each converter in the short term. For the second time period, information such as steel grade, furnace arrangement, and smelting cycle in the converter production plan data is analyzed. A template matching algorithm is used to retrieve typical gas production curves corresponding to similar production plans in history. The curve with the highest similarity is used as a benchmark to predict the second converter gas production for each converter in the medium to long term. Finally, weighting coefficients are set according to the historical prediction errors of the short- and medium-term prediction models. The two types of gas production data are fused using a weighted summation formula. Finally, the gas calorific value for the entire preset time period is calculated using converter gas production and initial gas calorific value techniques.

[0053] In one example, the predicted gas flow rate is:

[0054] in, The gas flow rates of each converter, based on a multi-model fusion prediction using LSTM and template matching, are as follows:

[0055] in, The gas flow rate predicted by LSTM. The predicted gas flow rate is matched to the template. Of course, to improve prediction accuracy, the prediction results from the physical model can also be incorporated, i.e.:

[0056] in, , and These are the corresponding weight coefficients. This is the gas flow rate predicted by the physical model.

[0057] Based on the gas flow rate and the initial gas calorific value of the i-th converter. The predicted calorific value of the gas can be obtained. :

[0058] Understandably, by dividing the time frame into short-term and medium-term time frames and adopting differentiated forecasting methods, the short-term forecast relies on real-time data and time-series models to accurately capture the fluctuations in the current smelting furnace conditions, ensuring the timeliness and accuracy of gas production and calorific value forecasts in the first time frame. The medium-term forecast, based on production plans and historical templates, can effectively grasp the production rhythm of subsequent furnaces, ensuring the trend and comprehensiveness of gas production forecasts in the second time frame.

[0059] Step S103: Based on the working stage, the data of the steel rolling heating furnace, and the steel rolling production plan data, predict the converter gas demand and calorific value demand of the steel rolling heating furnace within a preset time range.

[0060] It should be noted that the converter gas demand refers to the total predicted converter gas demand of the heating furnace within the preset time range to meet the billet heating process; the calorific value demand is the predicted calorific value required by the heating furnace to ensure thermal performance.

[0061] Understandably, predicting the converter gas demand and calorific value demand of steel rolling heating furnaces within a preset time range can involve analyzing steel rolling production plan data to determine the working phase sequence of each heating furnace within the preset time range; for different working phases, combining real-time parameters in the steel rolling heating furnace data, predicting the converter gas demand within a time period using a heating furnace gas demand prediction model; simultaneously, based on the thermal characteristics of the heating furnace (such as the need for high calorific value to ensure the heating rate during the heating period, and a higher tolerance for calorific value fluctuations during the holding period), and combined with the process requirements of each working phase, determining the calorific value demand range for each time period, and finally integrating them to form a converter gas demand curve and calorific value demand covering the preset time range.

[0062] In one example, the gas demand of furnace j at time t can be expressed as a mapping function based on thermal mechanisms, for example:

[0063] in, Indicates the rolling plan, Indicates the type of steel. Indicates the dimensions of the blank. The temperature curve, along with the gas demand of each heater at time t, allows us to obtain the predicted total demand.

[0064] The calorific value requirement can be represented by a correlation function based on process standards and thermal experience:

[0065] Among them, heating process requirements Including indicators such as heating rate and furnace temperature uniformity, steel grade characteristics It covers the thermal conductivity and phase transformation temperature of steel billets.

[0066] Step S104: Determine the supply and demand information of converter gas based on the converter gas production, the gas calorific value, the converter gas demand, and the calorific value demand.

[0067] It is understandable that supply and demand information can include both supply information and demand information. To determine the supply and demand information of converter gas, the amount of converter gas produced and the calorific value of the gas can be used as the supply information of converter gas, while the amount of converter gas demanded and the calorific value demanded can be used as the supply and demand information of converter gas.

[0068] In this embodiment, by distinguishing between the converter smelting stage and the rolling mill heating furnace operation stage to predict the gas production, calorific value and demand respectively, the operating characteristics of different production stages can be accurately matched, avoiding errors caused by general predictions, greatly improving the prediction accuracy of supply and demand information, providing a more reliable data foundation for the formulation of subsequent scheduling plans, and ensuring a high degree of fit between scheduling decisions and actual production needs.

[0069] Reference Figure 5 , Figure 5 This is a flowchart illustrating the third embodiment of the converter gas scheduling method of this application. Based on the above embodiments, a third embodiment of the converter gas scheduling method of this application is proposed. In the third embodiment, step S30 includes: Step S301: Construct an objective function with the goal of minimizing the total cost. The objective function includes a flare penalty term, a calorific value quality penalty term, and an operational stability penalty term.

[0070] It should be noted that the emission penalty is a quantitative representation of the losses such as energy waste and environmental costs caused by the emission of coal gas; the larger the emission, the higher the penalty value. The calorific value quality penalty is a quantitative description of the losses such as decreased production efficiency and product quality fluctuations caused by the deviation between the actual calorific value of the converter gas and the calorific value required by the heating furnace; the larger the deviation, the higher the penalty value. The operational stability penalty is a quantitative representation of the losses such as equipment wear and increased operation and maintenance costs caused by frequent adjustments to operating parameters such as the inlet and outlet flow rate of the gas holder and the valve opening; the larger the adjustment range, the higher the penalty value.

[0071] Specifically, in this embodiment, minimizing the total cost can be expressed as:

[0072] Where w1, w2, and w3 are weighting coefficients. This indicates a scattering penalty. The calorific value quality penalty is... The operational stability penalty term is represented as follows: . This represents the pipeline input error per unit time. This represents the pipeline output error per unit time.

[0073] Step S302: Set constraints for the objective function. The constraints include gas holder safety position constraints, pipeline transport capacity constraints, calorific value matching constraints, and energy balance constraints.

[0074] Understandably, the safety compartment constraint of the gas holder limits the storage capacity of the gas holder; the pipeline transport capacity constraint limits the flow rate of gas in the gas pipeline to prevent pipeline rupture or reduced transport efficiency due to excessive flow; the calorific value matching constraint limits the deviation between the actual calorific value of the converter gas and the calorific value required by the heating furnace to ensure the thermal stability of the heating furnace; and the energy balance constraint limits the conservation of energy input, output, and storage in the gas system to ensure a dynamic balance between supply and demand at the energy level.

[0075] Specifically, in this embodiment, the constraints are set with reference to the example below.

[0076] Safety constraints for gas holder operation:

[0077] in, and This indicates the upper and lower limits of the safety cabinet position constraints for the gas holder. This represents the maximum rate of change in the gas holder inventory.

[0078] Pipeline transport capacity constraints:

[0079] in, and This represents the extreme value of the intake flow rate set by the pipeline's transport capacity constraint. and This indicates the extreme value of the outlet flow rate set by the pipeline transport capacity constraint.

[0080] Heat value matching constraints:

[0081] in, This indicates that the calorific value matching constraint sets the maximum allowable deviation range of the calorific value.

[0082] Energy balance constraints:

[0083] By setting multi-dimensional constraints, a safe and feasible boundary is defined for the optimization solution of the objective function: the gas holder safety cabinet position constraint avoids mechanical failures caused by exceeding the cabinet position limit from the perspective of equipment safety, and extends the service life of the equipment; the pipeline transportation capacity constraint prevents pipeline overload operation and reduces the risk of safety accidents; the calorific value matching constraint ensures the stability of the heating furnace thermal process and avoids uneven heating of steel billets and decline in product quality due to calorific value fluctuations; the energy balance constraint ensures the dynamic conservation of supply and demand in the gas system and avoids system disorder caused by energy imbalance.

[0084] Step S303: Based on the state information and the constraints, solve the objective function to obtain the optimal scheduling scheme for the corresponding control period.

[0085] Step S304: The first control instruction in the optimal scheduling scheme of each control cycle is sent to the underlying control device for execution, and the actual value after execution is collected in real time, and the deviation between the actual value and the supply and demand information is calculated.

[0086] Step S305: Based on the deviation, adjust the state information of the subsequent control cycle, and determine the optimal scheduling scheme for the next control cycle based on the state information.

[0087] It should be noted that the underlying control equipment includes actuators such as variable frequency fans, switching stations, and venting valves; the actual value is the real operating data collected after the command is executed; the deviation is the difference between the actual value and the preset supply and demand information, which is used to dynamically correct subsequent optimization processes.

[0088] Specifically, based on the gas holder status information (such as real-time holder position and mixed calorific value) and preset constraints of the current control cycle, intelligent optimization algorithms such as Model Predictive Control (MPC) or Particle Swarm Optimization (PSO) are used to solve the objective function in the prediction time domain to obtain the optimal scheduling instruction sequence for the cycle (covering operating parameters for multiple future time steps). Simultaneously, only the first control instruction of the optimal instruction sequence (such as the gas holder outlet flow rate setpoint for the current cycle) is extracted and sent to the underlying control equipment for execution. At the same time, sensors collect real-time actual operating data after execution (such as actual outlet flow rate and holder position change), and calculate the deviation between the actual value and the previously predicted supply and demand information (such as predicted demand and predicted holder position change). The calculated deviation is substituted into the gas holder status model to dynamically adjust the initial state information for the next control cycle (such as correcting the predicted holder position). Based on the adjusted state information, the solution process is repeated to determine the optimal scheduling scheme for the next control cycle, forming a rolling optimization closed loop of solution, execution, feedback, and adjustment.

[0089] In one example, satisfying all the above constraints in each control cycle k, the following finite-time optimization problem is solved:

[0090] Where N is the prediction time domain length, , , w1, w2, and w3 are the weight coefficients of the objective function.

[0091] The optimal scheduling instruction sequence is sent to the underlying control equipment for execution. At the same time, the actual operation data after execution is collected in real time by sensors, and the deviation between the actual value and the predicted value is calculated. ,as follows:

[0092] in, This represents the actual value of the gas holder's inventory. This represents the predicted value of the gas holder inventory. This indicates the actual value of the predicted mixed calorific value of the gas inside the cabinet. This indicates the predicted mixed calorific value of the gas inside the cabinet.

[0093] The parameters used to correct subsequent prediction models are as follows:

[0094] Where K is the correction gain matrix. These are the prediction parameters for the (k+1)th control cycle. Let be the predicted parameter for the k-th control period. This represents the scheduling instruction for the k-th control cycle.

[0095] In one example, reference Figure 6 , Figure 6This is a schematic diagram of the data processing logic of the converter gas dispatching system of this application. The system is supported by a top-level smelting stage identification algorithm, a multi-timescale prediction algorithm, an adaptive learning algorithm, and a model predictive control (MPC) algorithm, which connect four functional modules downwards to form a collaborative closed loop. The operating condition prediction module includes real-time operating condition sensing, oxygen lance signal analysis, smelting stage identification, and fluctuation trend prediction functions. Relying on core algorithms such as the smelting stage identification algorithm, it completes real-time sensing, stage identification, and trend prediction of converter production conditions. The feedback correction module covers execution error monitoring, prediction deviation analysis, model parameter correction, and dispatching strategy optimization functions. Combined with the output of the operating condition prediction module, it achieves dynamic correction of model parameters and optimization adjustment of dispatching strategies through prediction deviation analysis and the linkage of the adaptive learning algorithm. The dispatching control module includes multi-objective optimization decision-making, MPC rolling optimization, and dispatching guidance. The command generation and control instruction issuance functions, based on the optimization results of the feedback correction module, utilize the Model Predictive Control (MPC) algorithm to complete multi-objective decision-making and rolling optimization, ultimately generating and issuing control instructions. The plan identification module, through production plan parsing, unit plan analysis, supply and demand matching identification, and risk point identification functions, completes the parsing of production plans and the early identification of supply, demand, and risks, and transmits the results to the scheduling control module. The modules interact through data links, and the core algorithms are embedded in the functional logic of each module, jointly constructing a full-process intelligent scheduling system to ensure the accuracy and adaptability of converter gas scheduling.

[0096] Furthermore, to set up emergency control modes for abnormal operating conditions such as equipment failure or severe supply-demand imbalance, and to pre-set clear emergency response rules, risks such as gas holder over-limit and calorific value deviating significantly from demand can be effectively prevented, ensuring the safe operation of the gas holder and downstream energy-consuming equipment, and improving the robustness and emergency response capabilities of the dispatching system. After step S30, the following may be included: When a device malfunction is detected or a severe imbalance between supply and demand is predicted, the system switches to an emergency control mode based on a rule base. In this emergency control mode, if the gas holder inventory is greater than the high threshold and the mixed calorific value of the gas holder is greater than the calorific value requirement, the gas holder output flow rate is increased. If the gas holder inventory is less than the low threshold and the predicted converter gas production at the next time point is reduced, the gas holder output flow rate is reduced and backup fuel is activated.

[0097] It should be noted that the emergency control mode is a special control method activated by the converter gas dispatching system when the conventional optimized control mode cannot cope with abnormal operating conditions. Its core relies on a preset rule base for rapid decision-making. The rule base is a set of fixed decision logics developed to address emergency scenarios such as equipment failure and supply-demand imbalance, integrating expert experience and process requirements. Equipment failure refers to abnormal operation of key equipment such as the converter, gas pipelines, sensors, and control valves (e.g., converter shutdown, valve jamming). Severe supply-demand imbalance refers to the difference between the predicted or actual converter gas production and the heating furnace demand exceeding a preset safety threshold. The high / low threshold of the gas holder is the upper and lower limits of the gas supply set to ensure the safe operation of the gas holder. Backup fuel is a preset alternative energy source, such as coke oven gas or natural gas, to cope with insufficient converter gas supply.

[0098] Specifically, in normal mode, optimized control is performed based on MPC; when a large fluctuation is predicted, the cabinet position is adjusted in advance and an early warning mode is entered; when equipment fails, the system switches to rule base control and enters emergency mode.

[0099] In one example, flow meters, calorific value analyzers, and composition analyzers were installed on the gas recovery pipelines of three converters; status sensors were added to the oxygen lance system; gas consumption monitoring devices were installed on two heaters; and gas holder position monitoring instruments were installed. All these components were connected to the production planning system via a data interface. Six months of historical operating data were collected to train a converter gas production prediction model and a heater demand prediction model.

[0100] In an example of a production day, at 08:00, the system predicted that from 10:00 to 12:00, both Converter 1 and Converter 2 would be in peak blowing conditions, with gas production reaching a peak of 65,000 Nm³ / h. However, the demand from the heating furnace was only 45,000 Nm³ / h, posing a risk of venting. At 08:15, the system optimization engine generated a scheduling plan, reducing the gas holder outlet flow in advance, lowering the holder level from 45% to 30%, reserving buffer space for peak gas production. Simultaneously, it suggested that the dispatcher arrange for the generator set to increase its load, thereby increasing gas consumption. From 10:00 to 12:00, the actual operation was largely consistent with the prediction; the gas holder effectively absorbed excess gas, increasing the holder level from 30% to 68%, with no venting occurring during this period. At 14:30, the system predicted that demand would decrease during the heating furnace roll change after 16:00, while converter gas production remained relatively stable. It generated a scheduling instruction to increase the holder level in advance, reserving gas for the night shift.

[0101] In an emergency response example, converter 3 prematurely terminated its blowing process due to equipment failure, resulting in a sudden decrease in gas production. The system immediately detected the anomaly, and at 15:20, the actual gas flow rate deviated from the predicted value by more than a threshold, triggering an early warning. At 15:21, the emergency dispatch module was activated, generating a response plan based on the rule base: prioritizing the gas supply to heater 2 (producing high value-added products), moderately reducing the gas ratio of heater 1, and initiating a small amount of coke oven gas supplementation. From 15:25 to 16:30, the system smoothly weathered the failure period, and heater production was unaffected.

[0102] In this embodiment, by comparing the deviation between predicted data and actual operating data in real time, a feedback correction mechanism is used to dynamically correct the prediction model, thereby improving the accuracy of subsequent predictions. Based on historical operating data and performance evaluation results, the prediction model parameters and optimized weight coefficients are updated periodically to achieve self-learning and continuous improvement of the system.

[0103] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the converter gas dispatching method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0104] This application also provides a converter gas dispatching device; please refer to [reference needed]. Figure 7 The converter gas dispatching device includes: The information prediction module 10 is used to predict the supply and demand information of converter gas within a preset time range based on the acquired converter gas information and production plan data. The information determination module 20 is used to establish a capacity model and a mixed calorific value change model of the gas holder based on the supply and demand information and the converter gas holder data in the converter gas information, and to determine the state information of the gas holder under different scheduling strategies according to the capacity model and the mixed calorific value change model. The scheme determination module 30 is used to solve the optimal scheduling scheme of the converter gas within the preset time range by taking the minimization of total cost as the optimization objective, combining preset constraints and the state information, and using a rolling optimization strategy.

[0105] The converter gas dispatching device provided in this application, employing the converter gas dispatching method in the above embodiments, can solve the technical problems of traditional control strategies lacking accurate prediction and dispatching, resulting in high gas venting rates and insufficient heat utilization. Compared with the prior art, the beneficial effects of the converter gas dispatching device provided in this application are the same as those of the converter gas dispatching method provided in the above embodiments, and other technical features in the converter gas dispatching device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0106] This application provides a converter gas scheduling device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the converter gas scheduling method in the above embodiment 1.

[0107] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing the converter gas dispatching equipment of the embodiments of this application. The converter gas dispatching equipment in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The converter gas dispatching equipment shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0108] like Figure 8 As shown, the converter gas dispatching equipment may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the converter gas dispatching equipment. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the converter gas dispatching equipment to communicate wirelessly or wiredly with other equipment to exchange data. Although the figure shows converter gas dispatching equipment with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0109] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0110] The converter gas dispatching equipment provided in this application, employing the converter gas dispatching method described in the above embodiments, can solve the technical problems of traditional control strategies lacking accurate prediction and dispatching, resulting in high gas venting rates and insufficient heat utilization. Compared with the prior art, the beneficial effects of the converter gas dispatching equipment provided in this application are the same as those of the converter gas dispatching method provided in the above embodiments, and other technical features of this converter gas dispatching equipment are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0111] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0112] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0113] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the converter gas scheduling method in the above embodiments.

[0114] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0115] The aforementioned computer-readable storage medium may be included in the converter gas dispatching equipment; or it may exist independently and not be assembled into the converter gas dispatching equipment.

[0116] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the converter gas scheduling equipment, cause the converter gas scheduling equipment to perform the converter gas scheduling method described above.

[0117] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0119] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0120] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described converter gas scheduling method. This solves the technical problems of traditional control strategies lacking accurate prediction and scheduling, resulting in high gas venting rates and insufficient heat utilization. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the converter gas scheduling method provided in the above embodiments, and will not be repeated here.

[0121] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the converter gas scheduling method described above.

[0122] The computer program product provided in this application can solve the technical problems of traditional control strategies lacking accurate prediction and scheduling, resulting in high gas venting rates and insufficient heat utilization. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the converter gas scheduling method provided in the above embodiments, and will not be repeated here.

[0123] The above description is only a part of the embodiments of this application and does not limit the scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included within the protection scope of this application.

Claims

1. A converter gas scheduling method, characterized in that, The converter gas scheduling method includes: Based on the acquired converter gas information and production plan data, predict the supply and demand information of converter gas within a preset time range; Based on the supply and demand information and the converter gas holder data in the converter gas information, a capacity model and a mixed calorific value change model of the gas holder are established, and the state information of the gas holder under different scheduling strategies is determined according to the capacity model and the mixed calorific value change model. With minimizing the total cost as the optimization objective, and combining preset constraints and the state information, the optimal scheduling scheme for the converter gas within the preset time range is solved through a rolling optimization strategy.

2. The converter gas dispatching method as described in claim 1, characterized in that, The converter gas information includes converter gas data and rolling mill heating furnace data; the production plan data includes converter production plan data and rolling mill production plan data. The step of predicting the supply and demand information of converter gas within a preset time range based on the acquired converter gas information and production plan data includes: Determine the converter smelting stage and the working stage of the steel rolling heating furnace for converter gas; Based on the converter smelting stage, the converter gas data, and the converter production plan data, the converter gas production and calorific value are predicted within a preset time range. Based on the aforementioned working stage, the data from the steel rolling heating furnace, and the steel rolling production plan data, the converter gas demand and calorific value demand of the steel rolling heating furnace within a preset time range are predicted. The supply and demand information of converter gas is determined based on the converter gas production, the gas calorific value, the converter gas demand, and the calorific value demand.

3. The converter gas scheduling method as described in claim 2, characterized in that, The steps for determining the converter smelting stage of the converter gas and the working stage of the steel rolling heating furnace include: Based on the oxygen lance signal in the converter gas data, the current converter smelting stage of the converter gas is determined. Based on the steel rolling production plan data, the operating stage of the steel rolling heating furnace corresponding to the converter gas is determined.

4. The converter gas dispatching method as described in claim 2, characterized in that, The preset time range includes a first time range and a second time range, wherein the second preset time range is located after the first time range; The step of predicting the converter gas production and calorific value within a preset time range based on the converter smelting stage, the converter gas data, and the converter production plan data includes: Based on the converter smelting stage, the first converter gas production and initial gas calorific value of each converter within the first time range are predicted using the converter gas data. Based on the converter production plan data, the second converter gas production of each converter within the second time range is predicted using a template matching algorithm. The first converter gas production rate and the second converter gas production rate are weighted and merged to obtain the third converter gas production rate. The converter gas production rate and the gas calorific value are determined based on the third converter gas production rate and the initial gas calorific value.

5. The converter gas dispatching method as described in claim 1, characterized in that, The step of finding the optimal scheduling scheme for the converter gas within a preset time range, with the goal of minimizing total cost and combining preset constraints and the state information, through a rolling optimization strategy, includes: Construct an objective function that aims to minimize the total cost, the objective function including an emission penalty term, a calorific value quality penalty term, and an operational stability penalty term; Set constraints for the objective function, including gas holder safety position constraints, pipeline transport capacity constraints, calorific value matching constraints, and energy balance constraints. Based on the state information and the constraints, the objective function is solved to obtain the optimal scheduling scheme for the corresponding control period; The first control instruction in the optimal scheduling scheme of each control cycle is sent to the underlying control device for execution, and the actual value after execution is collected in real time to calculate the deviation between the actual value and the supply and demand information. Based on the deviation, the state information of subsequent control cycles is adjusted, and the optimal scheduling scheme for the next control cycle is determined based on the state information.

6. The converter gas dispatching method according to any one of claims 1 to 5, characterized in that, After the step of solving the optimal scheduling scheme for the converter gas within the preset time range, the method further includes: When equipment failure is detected or a severe imbalance between supply and demand is predicted, switch to an emergency control mode based on rule base control. In the emergency control mode, in response to the gas holder's inventory being greater than the gas holder's high-level threshold and the gas holder's mixed calorific value being greater than the calorific value requirement, the gas holder's output flow rate is increased. In response to the gas holder's inventory being less than the gas holder's low-level threshold and the predicted converter gas production at the next time point decreasing, the gas holder's output flow rate is reduced and backup fuel is activated.

7. A converter gas dispatching device, characterized in that, The device includes: The information prediction module is used to predict the supply and demand information of converter gas within a preset time range based on the acquired converter gas information and production plan data. The information determination module is used to establish a capacity model and a mixed calorific value change model of the gas holder based on the supply and demand information and the converter gas holder data in the converter gas information, and to determine the state information of the gas holder under different scheduling strategies according to the capacity model and the mixed calorific value change model. The scheme determination module is used to solve the optimal scheduling scheme of the converter gas within the preset time range by taking the minimization of total cost as the optimization objective, combining preset constraints and the state information, and using a rolling optimization strategy.

8. A converter gas dispatching device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the converter gas scheduling method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the converter gas scheduling method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the converter gas scheduling method as described in any one of claims 1 to 6.

Images